# Hanzo

> The AI operating system for business. Building business software since 2014. Techstars '17.

One API at https://api.hanzo.ai/v1 for every model, Kai decisions and agents,
behind one key, beside Chat, Dev, Studio, Tabs and Bot. A person starts on the
Free plan: 50 free requests a day, no card.

## For agents

Sign up free with a wallet. Get an API key free. A small free allowance to try it. Top up in USDC or USDT over the API to raise your limits and pay as you go. No human required.

- Start: https://hanzo.ai/agents#headless, the path step by step and the whole of it as one TypeScript file.
- Discover: `GET https://api.hanzo.ai/v1` lists every capability and `GET https://api.hanzo.ai/v1/openapi.json` is the whole spec, no key for either.
- Your numbers: `GET https://api.hanzo.ai/v1/billing/tier` with your key says your plan, what it allows and what is left; `GET https://api.hanzo.ai/v1/billing/plans` lists every plan and price, no key needed.
- Top up: `GET https://api.hanzo.ai/v1/billing/crypto/options`, `POST https://api.hanzo.ai/v1/billing/crypto/deposit`, then `GET https://api.hanzo.ai/v1/billing/crypto/deposit/{id}` until it says succeeded.
- Every request spelled out: https://docs.hanzo.ai/docs/agents
- Talk to people at Hanzo: https://cal.com/hanzo

## The prompt

Paste this into any agent.

```text
Hanzo (https://hanzo.ai) is the AI operating system for business: one API for every model, Kai decisions and agents, with one key. Building business software since 2014. Techstars '17.

Sign up free with a wallet. Get an API key free. A small free allowance to try it. Top up in USDC or USDT over the API to raise your limits and pay as you go. No human required.

Base URL: https://api.hanzo.ai/v1 (chat completions in the OpenAI shape). Discover: GET https://api.hanzo.ai/v1 lists every capability, GET https://api.hanzo.ai/v1/<capability> its operations, and https://api.hanzo.ai/v1/openapi.json is the whole spec. No key needed for any of the three.

1. Sign up with a wallet: GET https://hanzo.id/v1/iam/web3/nonce?chain=evm&address=<address>, sign the CAIP-122 message it describes with EIP-191 personal_sign, POST https://hanzo.id/v1/iam/web3/verify (clientId "hanzo-ai", chain "evm", scheme "secp256k1-eip191", type "code" with a PKCE challenge), then exchange the code at https://hanzo.id/v1/iam/oauth/token. A first-seen wallet gets its own account and organization. A Solana wallet asks with chain=solana, writes "Solana account" in the message, and sends chain "solana", scheme "ed25519" and its signature as base64, never base58.
2. Get a key: POST https://api.hanzo.ai/v1/account/keys {"name":"agent","type":"secret"} with that token. The key is shown once.
3. Read your allowance: GET https://api.hanzo.ai/v1/billing/tier with the key says your plan, what it allows and what is left; GET https://api.hanzo.ai/v1/billing/plans lists every plan and price.
4. Top up: GET https://api.hanzo.ai/v1/billing/crypto/options, then POST https://api.hanzo.ai/v1/billing/crypto/deposit {"chain":"base","token":"usdc","amountCents":2000}. Send that token on that chain to the address it returns, and GET https://api.hanzo.ai/v1/billing/crypto/deposit/<id> until it says succeeded.
5. Call: POST https://api.hanzo.ai/v1/chat/completions {"model":"zen-free","messages":[{"role":"user","content":"Hello"}]} with Authorization: Bearer <key>.

The whole path as one TypeScript file: https://hanzo.ai/agents#headless. Every request spelled out: https://docs.hanzo.ai/docs/agents. Talk to people at Hanzo: https://cal.com/hanzo.
```

## Platform

Enso is the intelligence layer: one endpoint that reads the objective, applies
your policies and puts the right model behind the work. Zen is the open-weight
family. Both run beside the rest of the catalog on the same endpoint and the
same key.

Kai is the decision model: typed questions about a state (choice, noul, score),
answered with calibrated distributions instead of generated text, at
`POST https://api.hanzo.ai/v1/decisions`. Docs: https://docs.hanzo.ai/docs/decisions

- Sign in with a person nearby: `curl -fsSL https://hanzo.sh | sh`, then `hanzo auth login` (on a machine with no browser it prints a link and an 8-character code your person approves on any device), then `export HANZO_API_KEY="$(hanzo auth token)"` or `hanzo account keys create --name agent --type secret`. An agent with its own inbox signs up by email code over HTTP: https://docs.hanzo.ai/docs/agents
- Pay: USDC or USDT over the API, on the chains `GET /v1/billing/crypto/options` lists (today Base, Ethereum and Solana); a deposit address is the caller's own, valid 24 hours, credited when the chain confirms. A person pays by card, Apple Pay or Google Pay at https://hanzo.ai/pay, and wire instructions come from `GET /v1/billing/wire`. Plans and prices: https://hanzo.ai/pricing
- Bound spend: a key takes a monthly budget in cents and a rate in requests a minute; a session takes a cap at `POST /v1/agent/sessions/{id}/budget`.
- Evaluate Kai: the frozen harness is public at https://github.com/hanzoai/benchmarks (decision/); published runs, no key needed: https://api.hanzo.ai/v1/research/runs?org=hanzo&benchmark=app.phishing
- Tools: `npx -y --package=@hanzo/mcp@latest hanzo-mcp serve` is an MCP server over stdio for Claude Code, Codex, Cursor and Zed.
- Skills: `npx skills add https://hanzoskills.com/hanzo.md`, and the index at https://hanzoskills.com/llms.txt
- Docs for agents: https://docs.hanzo.ai/llms.txt. Every operation: https://api.hanzo.ai/v1/openapi.json, also listed in https://hanzo.ai/.well-known/api-catalog

## Company

- Building business software since 2014; the commerce platform's first commit is dated 2014-09-29, and it has been a Go-native platform since October 2014. Founded as Crowdstart (crowdstart.com), a crowdfunding and commerce platform, and renamed Hanzo in 2016.
- First customer, 2014: SKULLY, the fastest fully funded campaign on Indiegogo, raising $1M in about 45 hours (TechCrunch, 2014-08-14: https://techcrunch.com/2014/08/14/the-skully-smart-helmet-is-the-fastest-funded-indiegogo-campaign-to-hit-1m/).
- AI and machine learning in commercial use since 2014; GPT models in production by 2019.
- The first blockchain-native commerce platform, 2017: the Unikrn ICO raised over 120,000 ETH (Crunchbase News, 2017-10-24: https://news.crunchbase.com/startups/found-ico-makes-sense/).
- Techstars '17: https://hanzo.blog/2017-06-08-techstars-17/ and Startland News, 2017-10-10: https://startlandnews.com/2017/10/techstars-spotlight-hanzos-e-commerce-tools-designed-to-make-you-money/
- Hundreds of venture-funded startups, backed by Y Combinator, 500 Startups, Techstars and other tier-1 firms: billions in client revenue, two companies taken past 100 million users, and two that went public on Nasdaq in 2024, Damon Motorcycles and Triller.
- Damon Motorcycles' CES 2020 launch ran on Hanzo: $8.4M of motorcycles sold in 30 days at a 541:1 return on ad spend, with AI-generated ads (https://hanzo.ai/customers/damon-motorcycles).
- A decade of running commerce, analytics and marketing for that portfolio is what Hanzo's AI is built on.
- Led by CEO Antje Worring (https://www.linkedin.com/in/antje-worring/) and CTO Zach Kelling (https://www.linkedin.com/in/zeekay/, https://github.com/zeekay).
- History: https://hanzo.ai/about. Book a call: https://cal.com/hanzo. Investors: ir@hanzo.ai. Security: security@hanzo.ai.

## Pages

Every page is also served as markdown at the same path with a `.md` suffix.

- [Building business software since 2014 — Hanzo AI](https://hanzo.ai/about.md): Hanzo is the AI operating system for business: AI in commercial use since 2014, the first blockchain-native commerce platform in 2017, Techstars '17, and hundreds of venture-funded startups served, two of which went public.
- [Affiliates — Hanzo AI](https://hanzo.ai/affiliate.md): Earn recurring revenue sharing on customer referrals. High-commission affiliate program for developers, creators, and agencies.
- [Hanzo for agents: free to start, pay as you go — Hanzo AI](https://hanzo.ai/agents.md): Sign up free with a wallet. Get an API key free. A small free allowance to try it. Top up in USDC or USDT over the API to raise your limits and pay as you go. No human required.
- [The agents in every workspace — Hanzo AI](https://hanzo.ai/agents/crew.md): The team of agents every Hanzo workspace comes with, and Bots at work in their own room.
- [A Python SDK for agents that work together — Hanzo AI](https://hanzo.ai/agents/sdk.md): Build, orchestrate, and deploy autonomous AI coding agents and multi-agent networks with MCP tool execution, memory, and sandboxed runtimes.
- [Hanzo Analytics — Hanzo AI](https://hanzo.ai/analytics.md): Privacy-first product analytics and real-time event tracking for web apps, AI agents, and APIs. High-speed queries with zero tracking bloat.
- [One API for models, agents and tools — Hanzo AI](https://hanzo.ai/api.md): One base URL and one key for every model, Kai decisions, agents and the rest of Hanzo at api.hanzo.ai/v1. If you have used the OpenAI API, you already know most of this. Start free: 50 requests a day.
- [Hanzo Authz — Hanzo AI](https://hanzo.ai/authz.md): Fine-grained authorization engine. Zanzibar-style relationship graph for production scale.
- [Workflow automation in one binary — Hanzo AI](https://hanzo.ai/auto.md): Automate workflows with visual drag-and-drop triggers, webhooks, and durable execution. Visual canvas, connectors, and database in one process.
- [The apps a workflow can reach — Hanzo AI](https://hanzo.ai/automations.md): Every connector you can drop onto a Hanzo Auto canvas: read from it, write to it, or let a change in it start a run.
- [The backend in one file — Hanzo AI](https://hanzo.ai/base.md): Complete backend in one embedded binary: SQL database, auth, file storage, realtime streams, and server logic with zero devops overhead.
- [Hanzo — Benchmarks](https://hanzo.ai/benchmarks.md): Independent AI benchmarks: Enso model routing, Zen reasoning, Kai decisions, memory retrieval latency, and engine throughput.
- [CronQuestions benchmark — Hanzo AI](https://hanzo.ai/benchmarks/cronquestions.md): CronQuestions benchmark: Hanzo graph API answers 99.9% across 26,168 questions at 0.06 ms per question vs 5.4s for Semantica.
- [Dormant agent cost benchmark — Hanzo AI](https://hanzo.ai/benchmarks/fleet.md): Benchmark 1M dormant AI agents: 477 bytes of state each, 309k written/sec, and 0.034 ms resume times on Hanzo's high-speed agent engine.
- [Live agent footprint benchmark — Hanzo AI](https://hanzo.ai/benchmarks/goroutine.md): Benchmark AI agents as goroutines: 601 bytes heap, 125 ns spawn, and 107 ms to wake 1M agents vs V8 isolates. Ultra-light concurrency.
- [GPQA-Diamond routing benchmark — Hanzo AI](https://hanzo.ai/benchmarks/gpqa.md): One set of 198 graduate-level questions through Enso's router and single models from other labs, every row a research run with its accuracy, count and what its tokens cost at list prices.
- [Engine prefill on CUDA vs llama.cpp — Hanzo AI](https://hanzo.ai/benchmarks/inference.md): hanzo-engine against llama.cpp on CUDA, same weights, same box: prefill throughput where the whole 95% interval of the ratio lies above parity.
- [AG News benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-ag-news.md): Kai and Jev on the same 400 questions of AG News, one run per Kai revision.
- [Banking77 benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-banking77.md): Kai and Jev on the same 400 questions of Banking77, one run per Kai revision.
- [Choosing among many options benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-choice-size.md): Accuracy at each number of listed options, every option scored, the same cases put to both models.
- [DAIR Emotion benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-dair-emotion.md): Kai and Jev on the same 400 questions of DAIR Emotion, one run per Kai revision.
- [Email spam benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-email-spam.md): Kai and Jev on the same 400 questions of Email spam, one run per Kai revision.
- [Latency of one decision benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-latency.md): Time to one decision, by serving mode and device. No baseline was timed on the same hardware, so these stand alone.
- [MASSIVE benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-massive.md): Kai and Jev on the same 5,100 questions of MASSIVE, one run per Kai revision.
- [Model routing benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-model-routing.md): Kai and Jev on the same 399 questions of Model routing, one run per Kai revision.
- [Phishing benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-phishing.md): Kai and Jev on the same 400 questions of Phishing, one run per Kai revision.
- [RAG relevance benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-rag-relevance.md): Kai and Jev on the same 400 questions of RAG relevance, one run per Kai revision.
- [Support triage benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-support-triage.md): Kai and Jev on the same 400 questions of Support triage, one run per Kai revision.
- [Toxicity benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-toxicity.md): Kai and Jev on the same 400 questions of Toxicity, one run per Kai revision.
- [Typed decisions benchmark · Kai — Hanzo AI](https://hanzo.ai/benchmarks/kai-typed-decisions.md): Kai and Jev on the same 2,000 questions of Typed decisions, one run per Kai revision.
- [LoCoMo-Conv benchmark — Hanzo AI](https://hanzo.ai/benchmarks/locomo-conv.md): LoCoMo-Conv retrieval benchmark: reproducing paper retrieval protocols to boost R@10 by 16.8 points and long-term agent memory by 19.7.
- [LoCoMo, retrieval scoped by subject — Hanzo AI](https://hanzo.ai/benchmarks/locomo-subject-scope.md): A Go LoCoMo harness with no language model in it: scoping retrieval to the person a question names moves adversarial F1 from 0.200 to 0.502, with a 95% interval over conversations wholly above zero.
- [LoCoMo benchmark — Hanzo AI](https://hanzo.ai/benchmarks/locomo.md): Hanzo Context on LoCoMo retrieval: multi-hop ALL@20 jumps from 18.8 to 37.5 on held-out splits, outperforming standard cosine search.
- [LongMemEval benchmark — Hanzo AI](https://hanzo.ai/benchmarks/longmemeval.md): LongMemEval benchmark across 4,846 sessions: Hanzo ranks evidence sessions in top 5 for 90.6% of questions vs 85.8% for cosine search.
- [MemoryAgentBench benchmark — Hanzo AI](https://hanzo.ai/benchmarks/memoryagentbench.md): MemoryAgentBench benchmark: Hanzo Context doubles multi-hop substring EM from 33 to 67 on 262k haystacks without LLM memory reads.
- [Platform bench benchmark · Agent platform — Hanzo AI](https://hanzo.ai/benchmarks/platform-bench.md): What an agent costs at rest, what a sandbox that runs a shell costs to start cold, and what one call costs at the margin, each beside the figure its alternative publishes. Every script re-runs to produce its row.
- [RepoBench-R benchmark — Hanzo AI](https://hanzo.ai/benchmarks/repobench-r.md): Cross-file code retrieval benchmark: typed links over imports and symbols beat dense retrieval across RepoBench-R settings and splits.
- [Sandbox cold start benchmark — Hanzo AI](https://hanzo.ai/benchmarks/sandbox.md): Time to a running sandbox: a V8 context ready to execute JavaScript in 0.13 ms, the median of one pass, reproducible by one command.
- [Zen 6 throughput benchmark · Zen 6 — Hanzo AI](https://hanzo.ai/benchmarks/zen-6.md): Zen 6, the latest open-weight generation, on three machines Hanzo owns: prompt prefill and single-request decode, in tokens per second, one machine each.
- [Get there first — Hanzo AI](https://hanzo.ai/beta.md): Early access to Dev, Studio, Kai, Enso and Zen.
- [Hanzo Billing — Hanzo AI](https://hanzo.ai/billing.md): Recurring subscriptions, usage-based pricing, prorated upgrades, dunning, and tax.
- [One API key, every chain. And an agent that can use it. — Hanzo AI](https://hanzo.ai/blockchain.md): Unified Web3 infrastructure for developers and AI agents: RPCs, indexing, smart contract wallets, and cross-chain transfers in one API.
- [Bundler API — Hanzo AI](https://hanzo.ai/blockchain/bundler.md): Production-grade bundler for account abstraction.
- [Hanzo Chains — Hanzo AI](https://hanzo.ai/blockchain/chains.md): High-availability RPC endpoints and WebSocket nodes for 100+ blockchains: Ethereum, Solana, Lux ecosystem, EVM L2s, and Cosmos.
- [Hanzo DeFi — Blockchain — Hanzo AI](https://hanzo.ai/blockchain/defi.md): Modular DeFi infrastructure for staking, lending, swapping, and yield aggregation.
- [100+ Chains. One API. — Hanzo AI](https://hanzo.ai/blockchain/directory.md): RPC endpoints, chain IDs, WebSockets, explorers, and Hanzo product support for every network.
- [Hanzo Exchange — Hanzo AI](https://hanzo.ai/blockchain/exchange.md): Build trading platforms with institutional-grade infrastructure.
- [Hanzo Explorer — Hanzo AI](https://hanzo.ai/blockchain/explorer.md): An explorer for Lux and every chain connected to it.
- [Gas Manager — Hanzo AI](https://hanzo.ai/blockchain/gas.md): Paymaster-as-a-Service for ERC-4337 account abstraction. Sponsor transaction gas, set rate limits, and let new users start without holding gas.
- [Hanzo Indexer — Hanzo AI](https://hanzo.ai/blockchain/indexer.md): Index and query on-chain data at scale.
- [NFT API — Hanzo AI](https://hanzo.ai/blockchain/nft.md): Complete NFT data API for ERC-721 and ERC-1155 tokens.
- [Hanzo Oracle — Hanzo AI](https://hanzo.ai/blockchain/oracle.md): Price feeds, randomness, weather, and custom attestations, delivered to your contracts.
- [Hanzo Pay — Hanzo AI](https://hanzo.ai/blockchain/pay.md): A complete payment gateway bridging fiat and crypto.
- [Hanzo Rollups — Hanzo AI](https://hanzo.ai/blockchain/rollups.md): Deploy and manage rollup infrastructure.
- [Token API — Hanzo AI](https://hanzo.ai/blockchain/tokens.md): One token data API for every EVM chain.
- [Transfers API — Hanzo AI](https://hanzo.ai/blockchain/transfers.md): Query and monitor token transfers across all EVM and Lux chains. Real-time transfer history, transaction indexing, and webhook alerts.
- [Smart Wallets — Hanzo AI](https://hanzo.ai/blockchain/wallets.md): Smart contract wallets with account abstraction.
- [Webhooks — Hanzo AI](https://hanzo.ai/blockchain/webhooks.md): Real-time blockchain webhooks for on-chain events. Subscribe to token transfers, smart contract events, and wallet transactions reliably.
- [Websockets — Hanzo AI](https://hanzo.ai/blockchain/websockets.md): Real-time bidirectional communication with blockchain networks.
- [Blog — Hanzo AI](https://hanzo.ai/blog.md): Insights on AI agents, Zen foundation models, MCP infrastructure, and enterprise deployment from the engineers building Hanzo Cloud.
- [Kai 1: Decisions, Not Completions — Hanzo AI](https://hanzo.ai/blog/kai-decision-models.md): Kai answers typed questions with a probability for each answer and writes no text. What it is, how to call it, and its limits.
- [A New Pareto Frontier — Hanzo AI](https://hanzo.ai/blog/pareto-frontier.md): Hanzo Gen weaves Enso and Kai into the coding agent you already use: better, cheaper and faster at once.
- [The Next Frontier Will Be Synthesis — Hanzo AI](https://hanzo.ai/blog/synthesis.md): A glider is five cells. Collide enough of them and you can build a computer. We are building AI the same way.
- [Hanzo Bot — AI teammates you can hand real work to — Hanzo AI](https://hanzo.ai/bot.md): Give a bot a job. It has its own computer, signs in to your tools, and comes back when the work is done. On your machine, in our cloud, or both.
- [Hanzo Brand Guidelines. — Hanzo AI](https://hanzo.ai/brand.md): How to draw a Hanzo interface: the marks, the type, the colour, and the spacing.
- [AI Buying Specialist — Hanzo AI](https://hanzo.ai/buying-specialist.md): Find the right Hanzo plan for your team. Get instant pricing, seat calculations, custom quotes, and guidance from our AI buying specialist.
- [Hanzo Cap Table - Equity Management Platform](https://hanzo.ai/captable.md): Manage share classes, stock options, SAFEs, convertible notes, and equity plans. The open-source alternative to Carta.
- [Compilers, cryptography, and the cloud they run on — Hanzo AI](https://hanzo.ai/careers.md): Hanzo is a small team building an open AI cloud — the inference engine, the models, the backend services, and the agents that use them.
- [AI/ML Research Engineer (AI Research) — Hanzo Careers](https://hanzo.ai/careers/ai-ml-research-engineer.md): Work on foundational models, fine-tuning, and novel architectures. Experience with transformers, RLHF, and distributed training required. Join the Hanzo team building the open AI cloud.
- [Compiler Engineer (Engineering) — Hanzo Careers](https://hanzo.ai/careers/compiler-engineer.md): Build high-performance inference engines and model compilers. Experience with LLVM, MLIR, or similar frameworks preferred. Join the Hanzo team building the open AI cloud.
- [Cryptography Engineer (ZKP) (Blockchain) — Hanzo Careers](https://hanzo.ai/careers/cryptography-engineer-zkp.md): Implement zero-knowledge proofs for AI verification and on-chain compute. Experience with SNARKs/STARKs required. Join the Hanzo team building the open AI cloud.
- [MCP Protocol Engineer (Infrastructure) — Hanzo Careers](https://hanzo.ai/careers/mcp-protocol-engineer.md): Design and implement Model Context Protocol servers and tooling. Shape the future of AI agent infrastructure. Join the Hanzo team building the open AI cloud.
- [Open Application (Engineering / Research) — Hanzo Careers](https://hanzo.ai/careers/open.md): Introduce yourself and share what you want to build at Hanzo. Join the Hanzo team building the open AI cloud.
- [Product Designer (Design) — Hanzo Careers](https://hanzo.ai/careers/product-designer.md): Design beautiful, intuitive interfaces for AI products. Experience with developer tools and data visualization a plus. Join the Hanzo team building the open AI cloud.
- [Senior Backend Engineer (Go/Rust) (Platform) — Hanzo Careers](https://hanzo.ai/careers/senior-backend-engineer.md): Build scalable, high-performance backend services for our AI platform. Experience with distributed systems required. Join the Hanzo team building the open AI cloud.
- [Hanzo Chat — a chat app that does more than answer](https://hanzo.ai/chat.md): AI chat that searches the web, executes code, analyzes files, and generates images in one workspace. Run in the cloud or self-hosted.
- [A senior engineer in your shell — Hanzo AI](https://hanzo.ai/cli.md): One unified CLI for autonomous coding, model inference, and cloud deployments. Plan, edit, deploy, and monitor directly from your terminal.
- [AI Metrics — Hanzo Cloud](https://hanzo.ai/cloud/ai-metrics.md)
- [Annotation Queues — Hanzo Cloud](https://hanzo.ai/cloud/annotation-queues.md)
- [API Keys — Hanzo Cloud](https://hanzo.ai/cloud/api-keys.md)
- [Applications — Hanzo Cloud](https://hanzo.ai/cloud/applications.md)
- [Audit — Hanzo Cloud](https://hanzo.ai/cloud/audit.md): Every privileged action across the cloud, recorded append-only and anchored on-chain. Query by actor, resource, or time window; export for your auditors.
- [Benchmark — Hanzo Cloud](https://hanzo.ai/cloud/benchmark.md)
- [Builds — Hanzo Cloud](https://hanzo.ai/cloud/builds.md): Reproducible container builds from a git push, cached and signed, pushed to your own registry. No build logic per repo — one declared pipeline.
- [Chat — Hanzo Cloud](https://hanzo.ai/cloud/chat.md)
- [Clusters — Hanzo Cloud](https://hanzo.ai/cloud/clusters.md)
- [Containers — Hanzo Cloud](https://hanzo.ai/cloud/containers.md)
- [Datasets — Hanzo Cloud](https://hanzo.ai/cloud/datasets.md)
- [Embeddings — Hanzo Cloud](https://hanzo.ai/cloud/embeddings.md): Open embedding models for text, code, and images behind one API, wired straight into Vector for retrieval. Batch or realtime, metered per token.
- [Environments — Hanzo Cloud](https://hanzo.ai/cloud/environments.md): Every project gets isolated environments with their own secrets, data, and domains. Promote a build between them rather than rebuilding it.
- [Evals — Hanzo Cloud](https://hanzo.ai/cloud/evals.md): Benchmark, grade, and regression-test models and agents. LLM-as-judge, golden sets, and drift detection with reproducible scorecards anchored on-chain.
- [Experiments — Hanzo Cloud](https://hanzo.ai/cloud/experiments.md)
- [GPUs — Hanzo Cloud](https://hanzo.ai/cloud/gpus.md): H100, A100, and consumer-class GPUs on demand — attach to a machine, a container, or a training job. Per-second billing, no reservations, no idle spend.
- [Indexer — Hanzo Cloud](https://hanzo.ai/cloud/indexer.md)
- [Kubernetes — Hanzo Cloud](https://hanzo.ai/cloud/kubernetes.md)
- [Your laptop is the cluster — Hanzo AI](https://hanzo.ai/cloud/local.md): The same Hanzo cloud, booted on your own machine in seconds.
- [Logs — Hanzo Cloud](https://hanzo.ai/cloud/logs.md): Structured logs from every service in one searchable store, retained per plan and scoped per organization. No agent to install and no second log vendor.
- [Marketplace — Hanzo Cloud](https://hanzo.ai/cloud/marketplace.md)
- [Memory — Hanzo Cloud](https://hanzo.ai/cloud/memory.md)
- [Networks — Hanzo Cloud](https://hanzo.ai/cloud/networks.md)
- [Nodes — Hanzo Cloud](https://hanzo.ai/cloud/nodes.md)
- [Oracles — Hanzo Cloud](https://hanzo.ai/cloud/oracles.md)
- [Pipelines — Hanzo Cloud](https://hanzo.ai/cloud/pipelines.md): One declarative file describes build, test, and deploy for every repo in the org. Runs on your own runners; no per-repo workflow logic to keep in sync.
- [Plans & Pricing — Hanzo Cloud](https://hanzo.ai/cloud/plans.md)
- [Projects — Hanzo Cloud](https://hanzo.ai/cloud/projects.md)
- [Prompts — Hanzo Cloud](https://hanzo.ai/cloud/prompts.md)
- [Providers — Hanzo Cloud](https://hanzo.ai/cloud/providers.md)
- [Referrals — Hanzo Cloud](https://hanzo.ai/cloud/referrals.md)
- [Releases — Hanzo Cloud](https://hanzo.ai/cloud/releases.md): A release is an immutable pin of image plus configuration. Roll forward or back to any previous one in a single operation, with a full history of who shipped what.
- [Research — Hanzo Cloud](https://hanzo.ai/cloud/research.md)
- [Score Configs — Hanzo Cloud](https://hanzo.ai/cloud/score-configs.md)
- [Scores — Hanzo Cloud](https://hanzo.ai/cloud/scores.md)
- [Secrets — Hanzo Cloud](https://hanzo.ai/cloud/secrets.md): Versioned secrets with per-environment scoping, synced into Kubernetes as native resources. Nothing is ever written in plaintext, and every read is audited.
- [Service Mesh — Hanzo Cloud](https://hanzo.ai/cloud/service-mesh.md)
- [Sessions — Hanzo Cloud](https://hanzo.ai/cloud/sessions.md)
- [Payments — Hanzo Cloud](https://hanzo.ai/cloud/settlement.md)
- [Tokens — Hanzo Cloud](https://hanzo.ai/cloud/tokens.md)
- [Wallets — Hanzo Cloud](https://hanzo.ai/cloud/wallet.md)
- [Zero Trust — Hanzo Cloud](https://hanzo.ai/cloud/zero-trust.md)
- [Hanzo Commerce - Headless Commerce API](https://hanzo.ai/commerce.md): Build modern commerce experiences with Hanzo Commerce APIs.
- [How we compare, row by row, with the source on every row — Hanzo AI](https://hanzo.ai/compare.md): Side-by-side technical benchmarks and pricing comparisons between Hanzo AI Cloud and AWS, Google Cloud, OpenAI, Supabase, and Vercel.
- [Enso vs OpenRouter, Portkey, LiteLLM — Hanzo](https://hanzo.ai/compare/model-routing.md): Which API should you route your model calls through? All four put many models behind one key. They differ less than any of them advertise — and where they do differ, it is not always in our favour. Rows we measured ourselves, and rows each vendor published, kept apart.
- [What it costs to run it yourself — Hanzo](https://hanzo.ai/comparison.md): The open-source stacks people reach for, priced from the compute their own compose files reserve, and the operating work that is not a line item.
- [Hanzo Computer — Hanzo AI](https://hanzo.ai/computer.md): Vision-based computer-use agents that see screens, navigate desktops, and control browser workflows natively without custom API integrations.
- [Hanzo Console — Hanzo AI](https://hanzo.ai/console.md): Track every LLM call across your stack. Monitor costs, latency, quality, and token usage.
- [Talk to sales — Hanzo AI](https://hanzo.ai/contact-sales.md): Tell us what you want to build. We come back with a plan for your company: where Hanzo runs, what it costs and how you start.
- [Contact — Hanzo AI](https://hanzo.ai/contact.md): Reach Hanzo's sales, support and press teams, book a call, or find us in San Francisco.
- [Hanzo Crawl - AI-Ready Web Crawler](https://hanzo.ai/crawl.md): Turn any website into clean, structured Markdown for LLMs. JavaScript rendering, parallel crawling, structured extraction. Powered by crawl4ai.
- [Real teams. Real launches. Real results. — Hanzo AI](https://hanzo.ai/customers.md): Hanzo has run launches end to end: the store, the ads, the audience and the numbers. These are the companies, and what their launches did.
- [Damon Motorcycles · $8.4M in bikes sold in 30 days — Hanzo AI](https://hanzo.ai/customers/damon-motorcycles.md): Damon revealed the Hypersport at CES 2020. Hanzo ran the reveal, the four days of the show and the month after it, and the platform sold $8.4M of motorcycles in 30 days on $15,532 of ad spend.
- [KANOA · $7M+ raised in preorders — Hanzo AI](https://hanzo.ai/customers/kanoa.md): KANOA designed a truly wireless earphone for music and sport. Hanzo built its site and store, ran the preorder campaign, and made it one of the most successful crowdfunded projects of its time.
- [Hanzo Dashboards — Hanzo AI](https://hanzo.ai/dashboards.md): Grafana-compatible dashboards for infrastructure, application, and business metrics.
- [Hanzo Dataroom - Secure Document Sharing & Analytics](https://hanzo.ai/dataroom.md): Share documents with real-time analytics, access controls, and custom branding. Perfect for fundraising, due diligence, and investor updates.
- [Hanzo Datastore — a column store for analytical SQL](https://hanzo.ai/datastore.md): High-performance columnar datastore with SIMD vectorization. Purpose-built for real-time analytics, metrics, logs, and telemetry.
- [Hanzo Desktop — Hanzo AI](https://hanzo.ai/desktop.md): Native desktop app for macOS, Windows, and Linux. Run local models, orchestrate AI agents, and manage cloud workspaces.
- [Hanzo Dev — the coding agent](https://hanzo.ai/dev.md): Autonomous AI coding agent for your terminal, IDE, and cloud. Reads code, fixes bugs, runs tests, and creates PRs. Open source.
- [Hanzo DNS — Hanzo AI](https://hanzo.ai/dns.md): One API for Cloudflare, CoreDNS, Route53, and more. Parallel queries, DNSSEC, audit logging, and CLI-native workflows for infrastructure teams.
- [Download Hanzo — Hanzo AI](https://hanzo.ai/download.md): Download Hanzo for macOS, Windows, Linux, VS Code, and terminal CLI. Build and deploy autonomous AI agents everywhere you work.
- [Hanzo Edge — Hanzo AI](https://hanzo.ai/edge.md): Deploy globally in milliseconds with ultra-low latency edge computing infrastructure.
- [Hanzo Engine — Hanzo AI](https://hanzo.ai/engine.md): High-throughput, Rust-native inference engine for LLMs and embeddings. Accelerated token generation, low latency, and minimal memory footprint.
- [Hanzo Enso — Choose an outcome](https://hanzo.ai/enso.md): Intelligent model routing for frontier AI. Enso balances quality, latency, cost, and policy across top models and agents via one API.
- [Enterprise AI — Hanzo AI](https://hanzo.ai/enterprise.md): Enterprise AI platform deployed in your cloud, on-premise, or air-gapped. Dedicated GPU clusters, custom models, and 24/7 engineering support.
- [Hanzo Extension — your browser, as a tool an agent can use](https://hanzo.ai/extension.md): Browser extension for Chrome, Firefox, and Safari. Let Hanzo AI agents navigate tabs, extract data, and automate browser tasks securely.
- [Hanzo Flow — Hanzo AI](https://hanzo.ai/flow.md): Build AI agents, RAG pipelines, and multi-step workflows with a drag-and-drop canvas.
- [Hanzo Founder Program — Build OSS, Earn Free AI & Join Private Slack — Hanzo AI](https://hanzo.ai/founder.md): Contribute to Hanzo open-source repos, merge PRs to earn free Hanzo Pro & Ultra AI compute, join our private Founders Slack with founders Zach & Antje, and get verified profile badges.
- [Hanzo Functions — Hanzo AI](https://hanzo.ai/functions.md): Serverless function execution for any workload. Deploy code in seconds without managing infrastructure.
- [Gallery — Hanzo AI](https://hanzo.ai/gallery.md): Production-ready templates for AI agents, RAG pipelines, and full-stack apps. Clone, customize, and deploy to Hanzo Cloud in minutes.
- [Hanzo Gateway — Hanzo AI](https://hanzo.ai/gateway.md): Unified API gateway for AI models and cloud services: authentication, rate limiting, load balancing, caching, and end-to-end observability.
- [Hanzo Gen — any coding agent, on Hanzo’s rails](https://hanzo.ai/gen.md): Run your favorite coding agents — Claude Code, Cursor, Codex — with Hanzo tools and models attached. Open source, install in one command.
- [Guard — Hanzo AI](https://hanzo.ai/guard.md): Stop prompt injection, PII leaks, and unsafe outputs before they reach your users.
- [Hanzo GUI — Hanzo AI](https://hanzo.ai/gui.md): Cross-platform design system and UI toolkit for web, mobile, and desktop. Unified styling tokens, accessible primitives, and motion design.
- [How do I change my model improvement setting? — Hanzo AI](https://hanzo.ai/help/privacy/model-training.md): Turn “Help improve Hanzo’s models” on or off, and what each choice means for your chats and coding sessions.
- [Hanzo HSM — Hanzo AI](https://hanzo.ai/hsm.md): Hardware Security Module (HSM) and KMS integration: unified cryptographic key management across AWS KMS, Google Cloud KMS, and Azure Key Vault.
- [Hanzo IAM — Hanzo AI](https://hanzo.ai/iam.md): Identity and access management for every service. OIDC SSO, fine-grained RBAC, organization scoping, and audit logs.
- [An IDE that remembers your codebase — Hanzo AI](https://hanzo.ai/ide.md): AI-first IDE powered by a high-performance Rust engine. Persistent project memory, call-graph awareness, and sandboxed tool execution.
- [Hanzo Identity — Hanzo AI](https://hanzo.ai/identity.md): Decentralized identity and access management (IAM) platform: OAuth, passkeys, MFA, and post-quantum cryptographic tenant auth.
- [Hanzo IDV — Hanzo AI](https://hanzo.ai/idv.md): Identity verification for regulated workflows. KYC, KYB, and AML in a single API.
- [Hanzo AI — Smarter, Faster, Cheaper. Pick all three.](https://hanzo.ai/index.md): Frontier intelligence up to 200× faster and 400× cheaper. Every model behind one key. Agents sign up, get a key and top up with no human.
- [Hanzo Ingress — Hanzo AI](https://hanzo.ai/ingress.md): High-performance HTTP/HTTPS reverse proxy purpose-built for Kubernetes.
- [Hanzo Insights — Hanzo AI](https://hanzo.ai/insights.md): Understand user behavior with event analytics, session recording, funnels, and A/B testing. Roll out features safely with feature flags.
- [Integrations — Hanzo AI](https://hanzo.ai/integrations.md): Connect Hanzo to LangChain, LlamaIndex, Vercel AI SDK, AutoGen, Docker, and Kubernetes. SDKs for Python, TypeScript, Go, and Rust.
- [Use Hanzo AI with Anthropic SDK — Hanzo AI](https://hanzo.ai/integrations/anthropic-sdk.md): Use the Anthropic Python or TypeScript SDK with Hanzo AI to access Claude models alongside 50+ other models through a single API key and billing account.
- [Use Hanzo AI with AutoGen — Hanzo AI](https://hanzo.ai/integrations/autogen.md): Build multi-agent systems with Microsoft AutoGen. Set base_url to api.hanzo.ai/v1 in the AutoGen config, name a Hanzo model, and the agents run on it.
- [Use Hanzo AI with Continue.dev — Hanzo AI](https://hanzo.ai/integrations/continue-dev.md): Configure Continue.dev VS Code / JetBrains extension to use Hanzo AI as your coding assistant. Add Hanzo as a custom OpenAI-compatible provider in your config.
- [Use Hanzo AI with CrewAI — Hanzo AI](https://hanzo.ai/integrations/crewai.md): Use CrewAI to build collaborative AI agent teams powered by Hanzo AI models. CrewAI's role-based agents work with any OpenAI-compatible provider.
- [Use Hanzo AI with Cursor — Hanzo AI](https://hanzo.ai/integrations/cursor.md): Use Hanzo AI models inside Cursor IDE by adding a custom API provider. Access Zen, GPT-4.1, Claude Sonnet, and 50+ other models directly in your editor.
- [Use Hanzo AI with Docker — Hanzo AI](https://hanzo.ai/integrations/docker.md): Deploy Hanzo AI-powered services in Docker containers. Use the Hanzo API from any containerized application with proper environment configuration.
- [Use Hanzo AI with DSPy — Hanzo AI](https://hanzo.ai/integrations/dspy.md): Use DSPy to program (not prompt) Hanzo AI models. DSPy's systematic approach to LM prompting works with any OpenAI-compatible provider.
- [Use Hanzo AI with GitHub Copilot — Hanzo AI](https://hanzo.ai/integrations/github-copilot.md): Extend your GitHub Copilot workflow with Hanzo AI for access to additional models and capabilities via the API. Use Hanzo for tasks Copilot can't handle.
- [Use Hanzo AI with Go — Hanzo AI](https://hanzo.ai/integrations/go.md): Use Hanzo AI in Go using the official OpenAI Go client or any OpenAI-compatible Go library. Hanzo's standard REST API works with all HTTP clients.
- [Use Hanzo AI with Haystack — Hanzo AI](https://hanzo.ai/integrations/haystack.md): Build NLP pipelines and RAG systems with Haystack. Point OpenAIChatGenerator at api.hanzo.ai/v1, name a Hanzo model, and the pipeline runs unchanged.
- [Use Hanzo AI with Hugging Face — Hanzo AI](https://hanzo.ai/integrations/huggingface.md): Access Hugging Face models and use the HF Inference API through the Hanzo AI API. Also use Hanzo AI models with HuggingFace Hub tooling.
- [Use Hanzo AI with Kubernetes — Hanzo AI](https://hanzo.ai/integrations/kubernetes.md): Deploy Hanzo AI-powered workloads on Kubernetes. Securely manage your Hanzo API key as a K8s secret and inject it into pods.
- [Use Hanzo AI with LangChain — Hanzo AI](https://hanzo.ai/integrations/langchain.md): Integrate LangChain with Hanzo AI to build chains, agents, and RAG pipelines using any model on Hanzo's gateway. Hanzo is OpenAI-compatible so ChatOpenAI just works.
- [Use Hanzo AI with LlamaIndex — Hanzo AI](https://hanzo.ai/integrations/llamaindex.md): Use LlamaIndex with Hanzo AI to build powerful RAG applications, data agents, and query pipelines. Drop in Hanzo as your LLM provider with zero friction.
- [Use Hanzo AI with OpenAI Python SDK — Hanzo AI](https://hanzo.ai/integrations/openai-sdk.md): Use the official OpenAI Python SDK with Hanzo AI by pointing it to our OpenAI-compatible API endpoint. Access every model on Hanzo's gateway with your existing OpenAI code — no refactor needed.
- [Use Hanzo AI with Python — Hanzo AI](https://hanzo.ai/integrations/python.md): Use Hanzo AI in Python with the official OpenAI SDK (fully compatible), the Anthropic SDK, or via HTTP with httpx/requests. Zero lock-in, standard interfaces.
- [Use Hanzo AI with Rust — Hanzo AI](https://hanzo.ai/integrations/rust.md): Use Hanzo AI in Rust via the async-openai crate or raw reqwest HTTP calls. Full async support with Tokio, streaming, and type-safe API access.
- [Use Hanzo AI with TypeScript — Hanzo AI](https://hanzo.ai/integrations/typescript.md): Use Hanzo AI in TypeScript and Node.js with the OpenAI SDK, Vercel AI SDK, or raw fetch. Full type safety and async/streaming support.
- [Use Hanzo AI with Vercel AI SDK — Hanzo AI](https://hanzo.ai/integrations/vercel-ai-sdk.md): Use the Vercel AI SDK with Hanzo AI to build streaming AI UIs, chatbots, and generative interfaces in Next.js, React, and other frameworks.
- [Hanzo Investor Relations — Hanzo AI](https://hanzo.ai/investors.md): Models, agents and the cloud beneath them — one account, one key, one bill. See the research, open-source traction, team and investor contact.
- [Iro — Imagine without limits. | Hanzo Creative AI](https://hanzo.ai/iro.md): High-fidelity image generation, creative direction, editing, character design and consistent visual assets. Request research access and studio workflows.
- [Jin — Hanzo AI](https://hanzo.ai/jin.md): Open research on Joint-Embedding Predictive Architectures (JEPA): self-supervised visual representations, world models, and multimodal learning.
- [Hanzo Kai — One intelligence. Every modality. Every decision.](https://hanzo.ai/kai.md): Calibrated probability decision model for discrete choices. Get confidence scores per option with zero output token cost via one API call.
- [How to use Kai, Hanzo’s decision model](https://hanzo.ai/kai/guide.md): Developer guide for Kai decision models: API reference, structured outputs, low-latency reasoning, and token pricing on Hanzo Cloud.
- [Hanzo Kata — Autonomous coding agent & CI/CD loop](https://hanzo.ai/kata.md): Autonomous test repair, CI/CD triage, and repository maintenance. Powered by Kai typed decisions and Enso model routing.
- [Hanzo KMS — Hanzo AI](https://hanzo.ai/kms.md): End-to-end encrypted secret storage with environment sync, automatic rotation, audit trails, and native K8s integration.
- [Koe — Performance in every word. | Hanzo Creative AI](https://hanzo.ai/koe.md): Directable speech synthesis, character performances, dubbing and multilingual dialogue. Request research access and studio workflows.
- [Koma — Every frame tells a story. | Hanzo Creative AI](https://hanzo.ai/koma.md): Cinematic video generation, character continuity, motion, animation, and shot-level creative control. Request research access and studio workflows.
- [Learn Hanzo — Hanzo AI](https://hanzo.ai/learn.md): Start with a working request, then go as deep as you need. Everything here is part of the documentation — this page is the map.
- [Hanzo Ledger — Hanzo AI](https://hanzo.ai/ledger.md): Programmable, immutable double-entry accounting ledger engine for fintech apps, wallets, marketplaces, and multi-currency exchanges.
- [Legal & Trust Center — Hanzo](https://hanzo.ai/legal.md): The canonical home for Hanzo's legal agreements, policies, and notices. Every Hanzo product links here.
- [Acceptable Use Policy — Hanzo](https://hanzo.ai/legal/acceptable-use.md): What you may and may not do with Hanzo, the extra care high-risk uses need, and how we enforce it. Also called the Usage Policy.
- [Biometric, Voice, and Likeness Notice — Hanzo](https://hanzo.ai/legal/biometric-voice.md): How Hanzo handles faces, voices, and likeness in features that process them — notice, consent, retention and destruction, and the prohibition on unauthorized cloning.
- [Consumer Health Data Privacy Policy — Hanzo](https://hanzo.ai/legal/consumer-health.md): Hanzo's posture on consumer health data under Washington's My Health My Data Act and similar laws — what we do not collect, and the safeguards that apply if a feature ever does.
- [Cookie Notice — Hanzo](https://hanzo.ai/legal/cookies.md): The cookies and similar technologies Hanzo uses, the consent posture by category, and how to control them.
- [Cybersecurity Policy — Hanzo](https://hanzo.ai/legal/cybersecurity.md): How we protect your data — who can reach it, how it is encrypted, and what happens if something goes wrong.
- [Data Processing Addendum — Hanzo](https://hanzo.ai/legal/dpa.md): Processor terms, SCCs, subprocessor governance, and security measures for business customers whose data Hanzo processes on their behalf.
- [Privacy Policy — Hanzo](https://hanzo.ai/legal/privacy.md): What personal data Hanzo collects, why, who sees it, how long we keep it, how analytics and advertising consent works by region, and how to change your model-training setting.
- [Research API and R&D Ops Board Supplemental Terms — Hanzo](https://hanzo.ai/legal/research-api.md): Terms for the /v1/research registry, run ingestion, evidence integrity, durability states, and research-record rights.
- [AI Research and Data Contribution Terms — Hanzo](https://hanzo.ai/legal/research-contribution.md): The opt-in terms that govern whether and how your data may be used for Hanzo AI research and training — the four data-use states, affirmative election, withdrawal, and the Verified Commons.
- [Subprocessor Register — Hanzo](https://hanzo.ai/legal/subprocessors.md): The providers Hanzo engages to process data on behalf of customers — infrastructure, inference gateways, and the model providers reached through them — with data categories, regions, transfer mechanism, and training posture.
- [Terms of Service — Hanzo](https://hanzo.ai/legal/terms.md): The agreement between you and Hanzo AI, Inc. for your account and your use of Hanzo — chat, coding, agents, APIs and the rest of the Services.
- [Hanzo Machines — Hanzo AI](https://hanzo.ai/machines.md): Dedicated AI compute infrastructure optimized for machine learning and high-performance workloads.
- [An MCP server with thirteen tools — Hanzo AI](https://hanzo.ai/mcp.md): Standard Model Context Protocol servers for AI agents: filesystem, git, code indexing, shell, and HTTP over stdio or streaming HTTP.
- [Hanzo Metrics — Hanzo AI](https://hanzo.ai/metrics.md): High-cardinality time-series database and real-time query engine engineered for AI agent workloads, telemetry, and compute metrics.
- [Models — Hanzo AI](https://hanzo.ai/models.md): Explore frontier models and open-weight architectures. Access Enso, Zen, and 500+ partner models through one unified OpenAI-compatible API.
- [Aion Labs Models via Hanzo AI — 6 models](https://hanzo.ai/models/aion-labs.md): Access 6 Aion Labs models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Aion-2.0 — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-2.0.md): Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Aion-3.0-Mini — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-3.0-mini.md): Aion-3.0 Mini is a multi-model roleplaying and storytelling system from Aio... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Aion-3.0 — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-3.0.md): Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Aion 3.5 Mini — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-3.5-mini.md): Aion 3.5 Mini is a multi-model roleplaying and storytelling system from Aio... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Aion 3.5 — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-3.5.md): Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Aion-RP 1.0 (8B) — Use via Hanzo AI API](https://hanzo.ai/models/aion-labs/aion-rp-llama-3.1-8b.md): Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Alibaba Models via Hanzo AI — 6 models](https://hanzo.ai/models/alibaba.md): Access 6 Alibaba models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [HappyHorse 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/happyhorse-1.0.md): HappyHorse 1.0 is a video generation model from Alibaba. It generates short... Call via Hanzo's OpenAI-compatible API.
- [HappyHorse 1.1 — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/happyhorse-1.1.md): HappyHorse 1.1 is a video generation model from Alibaba. It generates short... Call via Hanzo's OpenAI-compatible API.
- [Wan 2.6 — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/wan-2.6.md): Alibaba's most advanced video generation model, supporting over 10 visual c... Call via Hanzo's OpenAI-compatible API.
- [Wan 2.7 — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/wan-2.7.md): Wan 2.7 is a video generation model from Alibaba. It supports text-to-video... Call via Hanzo's OpenAI-compatible API.
- [Wan 3.0 Prime — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/wan-3.0-prime.md): Wan 3.0 Prime is a fast-mode variant of Wan 3.0 from Alibaba. It supports t... Call via Hanzo's OpenAI-compatible API.
- [Wan 3.0 — Use via Hanzo AI API](https://hanzo.ai/models/alibaba/wan-3.0.md): Wan 3.0 is a video generation model from Alibaba for text-to-video, image-t... Call via Hanzo's OpenAI-compatible API.
- [Amazon Models via Hanzo AI — 5 models](https://hanzo.ai/models/amazon.md): Access 5 Amazon models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Nova 2 Lite — Use via Hanzo AI API](https://hanzo.ai/models/amazon/nova-2-lite-v1.md): Nova 2 Lite is a fast, cost-effective reasoning model for everyday workload... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nova Lite 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/amazon/nova-lite-v1.md): Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that f... Call via Hanzo's OpenAI-compatible API. Context: 300K.
- [Nova Micro 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/amazon/nova-micro-v1.md): Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Nova Premier 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/amazon/nova-premier-v1.md): Amazon Nova Premier is the most capable of Amazon’s multimodal models for c... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nova Pro 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/amazon/nova-pro-v1.md): Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on pr... Call via Hanzo's OpenAI-compatible API. Context: 300K.
- [Anthracite Models via Hanzo AI — 1 models](https://hanzo.ai/models/anthracite-org.md): Access 1 Anthracite models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Magnum v4 72B — Use via Hanzo AI API](https://hanzo.ai/models/anthracite-org/magnum-v4-72b.md): This is a series of models designed to replicate the prose quality of the C... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Anthropic Models via Hanzo AI — 24 models](https://hanzo.ai/models/anthropic.md): Access 24 Anthropic models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Claude Fable Latest — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-fable-latest.md): This model always redirects to the latest model in the Claude Fable family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Haiku 4.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-haiku-4.5.md): Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, deliverin... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Claude Haiku 5.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-haiku-5.5.md): Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sen... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Haiku Latest — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-haiku-latest.md): This model always redirects to the latest model in the Claude Haiku family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus 4.1 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-4.1.md): Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offeri... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Claude Opus 4.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-4.5.md): Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for compl... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Claude Opus 4.6 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-4.6.md): Opus 4.6 is Anthropic’s strongest model for coding and long-running profess... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus 4.7 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-4.7.md): Opus 4.7 is the next generation of Anthropic's Opus family, built for long-... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus 4.8 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-4.8.md): Claude Opus 4.8 is Anthropic's most capable generally available model in th... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus 5.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-5.5.md): Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, codi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus 5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-5.md): Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Opus Latest — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-opus-latest.md): This model always redirects to the latest model in the Claude Opus family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Sonnet 4.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-sonnet-4.5.md): Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Sonnet 4.6 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-sonnet-4.6.md): Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontie... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Sonnet 5.5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-sonnet-5.5.md): Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyda... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Sonnet 5 — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-sonnet-5.md): Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier perf... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Claude Sonnet Latest — Use via Hanzo AI API](https://hanzo.ai/models/anthropic/claude-sonnet-latest.md): This model always redirects to the latest model in the Claude Sonnet family... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [assemblyai Models via Hanzo AI — 1 models](https://hanzo.ai/models/assemblyai.md): Access 1 assemblyai models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [TTS 1 — Use via Hanzo AI API](https://hanzo.ai/models/assemblyai/assemblyai-tts-1.md): AssemblyAI TTS 1 is a text-to-speech model from AssemblyAI. It is suited fo... Call via Hanzo's OpenAI-compatible API.
- [black-forest-labs Models via Hanzo AI — 1 models](https://hanzo.ai/models/black-forest-labs.md): Access 1 black-forest-labs models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [FLUX 3 Video — Use via Hanzo AI API](https://hanzo.ai/models/black-forest-labs/flux-3-video.md): FLUX.3 Video is a video generation model from Black Forest Labs. It support... Call via Hanzo's OpenAI-compatible API.
- [ByteDance Models via Hanzo AI — 13 models](https://hanzo.ai/models/bytedance.md): Access 13 ByteDance models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Seed 1.6 Flash — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-1.6-flash.md): Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed 1.6 — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-1.6.md): Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed 2.1 Turbo — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-2-1-turbo.md): Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and lon... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed-2.0-Code — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-2.0-code.md): Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed-2.0-Lite — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-2.0-lite.md): Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that deli... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed-2.0-Mini — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-2.0-mini.md): Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensiti... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Seed Audio 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seed-audio-1-0.md): Seed Audio 1.0 is ByteDance Seed's non-streaming audio generation model. It... Call via Hanzo's OpenAI-compatible API.
- [Seedance 1.5 Pro — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seedance-1-5-pro.md): ByteDance's next-generation audio-visual generation model with a 4.5B param... Call via Hanzo's OpenAI-compatible API.
- [Seedance 2.0 Fast — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seedance-2.0-fast.md): Seedance 2.0 Fast is a video generation model from ByteDance. It supports t... Call via Hanzo's OpenAI-compatible API.
- [Seedance 2.0 Mini — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seedance-2.0-mini.md): Seedance 2.0 Mini is a video generation model from ByteDance. It supports t... Call via Hanzo's OpenAI-compatible API.
- [Seedance 2.0 — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seedance-2.0.md): Seedance 2.0 is a video generation model from ByteDance. It supports text-t... Call via Hanzo's OpenAI-compatible API.
- [Seedance 2.5 — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/seedance-2.5.md): Seedance 2.5 is a video generation model from ByteDance. It is suited for l... Call via Hanzo's OpenAI-compatible API.
- [UI-TARS 7B — Use via Hanzo AI API](https://hanzo.ai/models/bytedance/ui-tars-1.5-7b.md): UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based e... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [canopylabs Models via Hanzo AI — 1 models](https://hanzo.ai/models/canopylabs.md): Access 1 canopylabs models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Orpheus 3B — Use via Hanzo AI API](https://hanzo.ai/models/canopylabs/orpheus-3b-0.1-ft.md): Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned... Call via Hanzo's OpenAI-compatible API.
- [Cognitive Computations Models via Hanzo AI — 1 models](https://hanzo.ai/models/cognitivecomputations.md): Access 1 Cognitive Computations models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Uncensored — Use via Hanzo AI API](https://hanzo.ai/models/cognitivecomputations/dolphin-mistral-24b-venice-edition.md): Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned varian... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Cohere Models via Hanzo AI — 6 models](https://hanzo.ai/models/cohere.md): Access 6 Cohere models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Command A+ — Use via Hanzo AI API](https://hanzo.ai/models/cohere/command-a-plus.md): Command A+ is Cohere's flagship model for enterprise agentic workflows. It... Call via Hanzo's OpenAI-compatible API. Context: 192K.
- [Command A — Use via Hanzo AI API](https://hanzo.ai/models/cohere/command-a.md): Command A is an open-weights 111B parameter model with a 256k context windo... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Command R (08-2024) — Use via Hanzo AI API](https://hanzo.ai/models/cohere/command-r-08-2024.md): command-r-08-2024 is an update of the Command R with improved performance f... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Command R+ (08-2024) — Use via Hanzo AI API](https://hanzo.ai/models/cohere/command-r-plus-08-2024.md): command-r-plus-08-2024 is an update of the Command R+ with roughly 50% high... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Command R7B (12-2024) — Use via Hanzo AI API](https://hanzo.ai/models/cohere/command-r7b-12-2024.md): Command R7B (12-2024) is a small, fast update of the Command R+ model, deli... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [North Mini Code (free) — Use via Hanzo AI API](https://hanzo.ai/models/cohere/north-mini-code:free.md): North Mini Code is Cohere's first agentic coding model and the debut of its... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [deepgram Models via Hanzo AI — 2 models](https://hanzo.ai/models/deepgram.md): Access 2 deepgram models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Aura-2 — Use via Hanzo AI API](https://hanzo.ai/models/deepgram/aura-2.md): Aura-2 is a multilingual text-to-speech model from Deepgram. It supports De... Call via Hanzo's OpenAI-compatible API.
- [Flux TTS — Use via Hanzo AI API](https://hanzo.ai/models/deepgram/flux-tts.md): Flux TTS is a text-to-speech model from Deepgram. It is suited for natural,... Call via Hanzo's OpenAI-compatible API.
- [DeepSeek Models via Hanzo AI — 18 models](https://hanzo.ai/models/deepseek.md): Access 18 DeepSeek models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [DeepSeek V3 0324 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-chat-v3-0324.md): DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iter... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V3.1 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-chat-v3.1.md): DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B activ... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V3 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-chat.md): DeepSeek-V3 is the latest model from the DeepSeek team, building upon the i... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek Flash Latest — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-flash-latest.md): This model always redirects to the latest model in the DeepSeek Flash famil... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek Pro Latest — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-pro-latest.md): This model always redirects to the latest model in the DeepSeek Pro family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [R1 0528 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-r1-0528.md): May 28th update to the original DeepSeek R1 Performance on par with OpenAI... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V3.1 Terminus — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v3.1-terminus.md): DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the mod... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V3.2 Exp — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v3.2-exp.md): DeepSeek-V3.2-Exp is an experimental large language model released by DeepS... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V3.2 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v3.2.md): DeepSeek-V3.2 is a large language model designed to harmonize high computat... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [DeepSeek V4 Flash 0731 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-flash-0731.md): DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek,... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4 Flash Latest — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-flash-latest.md): This model always redirects to the latest model in the DeepSeek V4 Flash fa... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4 Flash Vision Exp — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-flash-vision-exp.md): DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of D... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4 Flash 0423 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-flash.md): DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4 Pro 0813 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-pro-0813.md): DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSee... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4 Pro 0423 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4-pro.md): DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek wit... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4.1 Flash 1017 — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4.1-flash-1017.md): DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [DeepSeek V4.1 Flash — Use via Hanzo AI API](https://hanzo.ai/models/deepseek/deepseek-v4.1-flash.md): DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [dots-studio Models via Hanzo AI — 1 models](https://hanzo.ai/models/dots-studio.md): Access 1 dots-studio models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Dots3-Note Preview (free) — Use via Hanzo AI API](https://hanzo.ai/models/dots-studio/dots-3-note-preview:free.md): Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Stu... Call via Hanzo's OpenAI-compatible API. Context: 512K.
- [elevenlabs Models via Hanzo AI — 9 models](https://hanzo.ai/models/elevenlabs.md): Access 9 elevenlabs models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Eleven Flash v2.5 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-flash-v2.5.md): Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenL... Call via Hanzo's OpenAI-compatible API.
- [Eleven Flash v2 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-flash-v2.md): Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model... Call via Hanzo's OpenAI-compatible API.
- [Eleven Multilingual v2 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-multilingual-v2.md): Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is sui... Call via Hanzo's OpenAI-compatible API.
- [Eleven Turbo v2.5 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-turbo-v2.5.md): Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It... Call via Hanzo's OpenAI-compatible API.
- [Eleven Turbo v2 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-turbo-v2.md): Eleven Turbo v2 is an English-only, low-latency text-to-speech model from E... Call via Hanzo's OpenAI-compatible API.
- [Eleven v3 Conversational — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-v3-conversational.md): Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a varia... Call via Hanzo's OpenAI-compatible API.
- [Eleven v3 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-v3.md): Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionall... Call via Hanzo's OpenAI-compatible API.
- [Eleven v4 Turbo — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-v4-turbo.md): Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It k... Call via Hanzo's OpenAI-compatible API.
- [Eleven v4 — Use via Hanzo AI API](https://hanzo.ai/models/elevenlabs/eleven-v4.md): Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most... Call via Hanzo's OpenAI-compatible API.
- [elorian Models via Hanzo AI — 1 models](https://hanzo.ai/models/elorian.md): Access 1 elorian models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Glimpse — Use via Hanzo AI API](https://hanzo.ai/models/elorian/glimpse.md): Glimpse is a multimodal visual reasoning model from Elorian, built for visu... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Hanzo Enso — presets and research runs](https://hanzo.ai/models/enso.md): Enso frontier model router: dynamic routing across top AI models, benchmarked on GPQA Diamond and LiveCodeBench for quality and cost.
- [fireworks Models via Hanzo AI — 1 models](https://hanzo.ai/models/fireworks.md): Access 1 fireworks models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Ember-1 — Use via Hanzo AI API](https://hanzo.ai/models/fireworks/ember-1.md): Ember-1 is a specialized reasoning model from Fireworks Research, built on... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [fish-audio Models via Hanzo AI — 5 models](https://hanzo.ai/models/fish-audio.md): Access 5 fish-audio models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Drama 3 — Use via Hanzo AI API](https://hanzo.ai/models/fish-audio/drama-3.md): Drama 3 is a text-to-speech model from Fish Audio built for directed voice... Call via Hanzo's OpenAI-compatible API.
- [S1 — Use via Hanzo AI API](https://hanzo.ai/models/fish-audio/s1.md): S1 is a multilingual text-to-speech model from Fish Audio. It is suited for... Call via Hanzo's OpenAI-compatible API.
- [S2 Pro — Use via Hanzo AI API](https://hanzo.ai/models/fish-audio/s2-pro.md): S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited... Call via Hanzo's OpenAI-compatible API.
- [S2.1 Pro Free (free) — Use via Hanzo AI API](https://hanzo.ai/models/fish-audio/s2.1-pro-free:free.md): S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for t... Call via Hanzo's OpenAI-compatible API.
- [S2.1 Pro — Use via Hanzo AI API](https://hanzo.ai/models/fish-audio/s2.1-pro.md): S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It... Call via Hanzo's OpenAI-compatible API.
- [Google Models via Hanzo AI — 49 models](https://hanzo.ai/models/google.md): Access 49 Google models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Nano Banana (Gemini 2.5 Flash Image) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-2.5-flash-image.md): Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. I... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Gemini 2.5 Flash Lite — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-2.5-flash-lite.md): Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 fa... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 2.5 Flash — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-2.5-flash.md): Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 2.5 Pro Preview 06-05 — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-2.5-pro-preview.md): Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 2.5 Pro — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-2.5-pro.md): Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3 Flash Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3-flash-preview.md): Gemini 3 Flash Preview is a high speed, high value thinking model designed... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nano Banana Pro (Gemini 3 Pro Image Preview) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3-pro-image-preview.md): Nano Banana Pro is Google’s most advanced image-generation and editing mode... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Nano Banana Pro (Gemini 3 Pro Image) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3-pro-image.md): Nano Banana Pro is Google’s most advanced image-generation and editing mode... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Nano Banana 2 (Gemini 3.1 Flash Image Preview) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-image-preview.md): Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Nano Banana 2 (Gemini 3.1 Flash Image) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-image.md): Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-lite-image.md): Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Gemini 3.1 Flash Lite Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-lite-preview.md): Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized f... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.1 Flash Lite — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-lite.md): Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optim... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.1 Flash TTS Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-flash-tts-preview.md): Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a s... Call via Hanzo's OpenAI-compatible API.
- [Gemini 3.1 Pro Preview Custom Tools — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-pro-preview-customtools.md): Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that imp... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.1 Pro Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.1-pro-preview.md): Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enh... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.5 Flash Lite — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.5-flash-lite.md): Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.5 Flash — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.5-flash.md): Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing nea... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.6 Flash — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.6-flash.md): Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.7 Flash — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.7-flash.md): Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 3.8 Flash Lite TTS — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.8-flash-lite-tts.md): Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fas... Call via Hanzo's OpenAI-compatible API.
- [Gemini 3.8 Flash TTS — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.8-flash-tts.md): Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successo... Call via Hanzo's OpenAI-compatible API.
- [Gemini 3.8 Flash — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-3.8-flash.md): Gemini 3.8 Flash is Google's most intelligent Flash model with significant... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini 4 Argon — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-4-argon.md): Gemini 4 Argon is Google's flagship reasoning model, built for complex soft... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemini Flash Latest — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-flash-latest.md): This model always redirects to the latest model in the Gemini Flash family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nano Banana 2.1 — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-nano-banana-2.1.md): Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and e... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Gemini Pro Latest — Use via Hanzo AI API](https://hanzo.ai/models/google/gemini-pro-latest.md): This model always redirects to the latest model in the Gemini Pro family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Gemma 2 27B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-2-27b-it.md): Gemma 2 27B by Google is an open model built from the same research and tec... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Gemma 3 12B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-3-12b-it.md): Gemma 3 introduces multimodality, supporting vision-language input and text... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Gemma 3 27B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-3-27b-it.md): Gemma 3 introduces multimodality, supporting vision-language input and text... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Gemma 3 4B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-3-4b-it.md): Gemma 3 introduces multimodality, supporting vision-language input and text... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Gemma 4 26B A4B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-4-26b-a4b-it.md): Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model f... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Gemma 4 26B A4B (free) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-4-26b-a4b-it:free.md): Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model f... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Gemma 4 31B — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-4-31b-it.md): Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supp... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Gemma 4 31B (free) — Use via Hanzo AI API](https://hanzo.ai/models/google/gemma-4-31b-it:free.md): Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supp... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Lyria 3 Clip Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/lyria-3-clip-preview.md): 30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Lyria 3 Pro Preview — Use via Hanzo AI API](https://hanzo.ai/models/google/lyria-3-pro-preview.md): Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Veo 3.1 Fast — Use via Hanzo AI API](https://hanzo.ai/models/google/veo-3.1-fast.md): Google's mid-tier video generation model balancing speed and quality. Veo 3... Call via Hanzo's OpenAI-compatible API.
- [Veo 3.1 Lite — Use via Hanzo AI API](https://hanzo.ai/models/google/veo-3.1-lite.md): Google's most cost-effective video generation model, designed for high-volu... Call via Hanzo's OpenAI-compatible API.
- [Veo 3.1 — Use via Hanzo AI API](https://hanzo.ai/models/google/veo-3.1.md): Google's state-of-the-art video generation model, built for maximum visual... Call via Hanzo's OpenAI-compatible API.
- [Gryphe Models via Hanzo AI — 1 models](https://hanzo.ai/models/gryphe.md): Access 1 Gryphe models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [MythoMax 13B — Use via Hanzo AI API](https://hanzo.ai/models/gryphe/mythomax-l2-13b.md): One of the highest performing and most popular fine-tunes of Llama 2 13B, w... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Hanzo Models via Hanzo AI — 30 models](https://hanzo.ai/models/hanzo.md): Access 30 Hanzo models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Enso (enso-auto) — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso-auto.md): Routes each request to one tier by the reasoning depth it asks for: enso-fl... Call via Hanzo's OpenAI-compatible API. Context: 900K.
- [Enso Flash — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso-flash.md): Fast, economical Enso tier for high-volume, low-latency everyday work, with... Call via Hanzo's OpenAI-compatible API. Context: 900K.
- [enso-free — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso-free.md): Use enso-free through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [enso-pro — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso-pro.md): Use enso-pro through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Enso Ultra — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso-ultra.md): Adaptive fan-out — probes a task-appropriate model, escalates to a top-K pa... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Enso — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/enso.md): Hanzo's proprietary frontier model — Opus-class reasoning by default with 1... Call via Hanzo's OpenAI-compatible API. Context: 900K.
- [free — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/free.md): Use free through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Kai (kai-1.8) — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/kai-1.8.md): Hanzo Kai is a structured decision model answering typed questions at /v1/d... Call it at POST /v1/decisions. Context: 33K.
- [Kai — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/kai.md): Hanzo Kai is a structured decision model answering typed questions at /v1/d... Call it at POST /v1/decisions. Context: 33K.
- [koma — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/koma.md): Use koma through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [zen-embedding-3 — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-embedding-3.md): Use zen-embedding-3 through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Zen Embedding — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-embedding.md): Dense text embeddings for semantic search, retrieval, and clustering. Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [zen-free — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-free.md): Use zen-free through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Zen Guard — Content Safety — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-guard.md): Safety classifier for moderation and guardrails across a broad category and... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [zen-scribe — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-scribe.md): Hanzo's speech-to-text model, which writes down what is said in any languag... Call via Hanzo's OpenAI-compatible API.
- [Zen VL — Vision-Language — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-vl.md): Reads images and reasons over them — visual Q&A, document and chart underst... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [zen-voice-mini — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen-voice-mini.md): Hanzo's text-to-speech voice, served at /v1/audio/speech. Call via Hanzo's OpenAI-compatible API.
- [hanzo/zen — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen.md): Use hanzo/zen through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Zen5 Coder — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-coder.md): Code-specialized Zen5 tier. 80B sparse MoE tuned for repo-scale code unders... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [zen5-evo — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-evo.md): Use zen5-evo through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Zen5 Flash — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-flash.md): Smallest and cheapest text-only Zen5 chat tier. 4B-class dense, sub-100ms T... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Zen5 Mini — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-mini.md): Frontier agentic at the lowest cost in the family. Built on a 230B agentic... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Zen5 Pro — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-pro.md): Zen Flash IQ2_XXS-imatrix weights (81 GB GGUF on zenlm/zen-5-pro-gguf). 284... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [zen5-spark — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5-spark.md): Use zen5-spark through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [Zen5 (Default) — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen5.md): Canonical Zen5 default. a 35B frontier MoE (3B active) (35B total / 3B acti... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [zen6-coder — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen6-coder.md): Use zen6-coder through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [zen6-flash — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen6-flash.md): Use zen6-flash through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [zen6-free — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen6-free.md): Use zen6-free through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [zen6-max — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen6-max.md): Use zen6-max through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [zen6 — Use via Hanzo AI API](https://hanzo.ai/models/hanzo/zen6.md): Use zen6 through one Hanzo API key. Call via Hanzo's OpenAI-compatible API.
- [hexgrad Models via Hanzo AI — 1 models](https://hanzo.ai/models/hexgrad.md): Access 1 hexgrad models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Kokoro 82M — Use via Hanzo AI API](https://hanzo.ai/models/hexgrad/kokoro-82m.md): Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad.... Call via Hanzo's OpenAI-compatible API.
- [heygen Models via Hanzo AI — 4 models](https://hanzo.ai/models/heygen.md): Access 4 heygen models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [HeyGen Video — Use via Hanzo AI API](https://hanzo.ai/models/heygen/heygen-video-1.md): HeyGen Video is a general-purpose video generation model from HeyGen. It re... Call via Hanzo's OpenAI-compatible API.
- [HeyGen Voice Turbo — Use via Hanzo AI API](https://hanzo.ai/models/heygen/heygen-voice-1-turbo.md): HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's tex... Call via Hanzo's OpenAI-compatible API.
- [HeyGen Voice Turbo (free) — Use via Hanzo AI API](https://hanzo.ai/models/heygen/heygen-voice-1-turbo:free.md): HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's tex... Call via Hanzo's OpenAI-compatible API.
- [HeyGen Voice — Use via Hanzo AI API](https://hanzo.ai/models/heygen/heygen-voice-1.md): HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 defaul... Call via Hanzo's OpenAI-compatible API.
- [IBM Granite Models via Hanzo AI — 1 models](https://hanzo.ai/models/ibm-granite.md): Access 1 IBM Granite models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Granite 4.2 8B — Use via Hanzo AI API](https://hanzo.ai/models/ibm-granite/granite-4.2-8b.md): Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathem... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Inception Models via Hanzo AI — 3 models](https://hanzo.ai/models/inception.md): Access 3 Inception models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Mercury 2.5 — Use via Hanzo AI API](https://hanzo.ai/models/inception/mercury-2.5.md): Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLL... Call via Hanzo's OpenAI-compatible API. Context: 260K.
- [Mercury 2 — Use via Hanzo AI API](https://hanzo.ai/models/inception/mercury-2.md): Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffu... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Mercury 3 — Use via Hanzo AI API](https://hanzo.ai/models/inception/mercury-3.md): Mercury 3 is a diffusion-based language model from Inception, and the lab's... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [inclusionAI Models via Hanzo AI — 3 models](https://hanzo.ai/models/inclusionai.md): Access 3 inclusionAI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Ling 3.0 Flash VL — Use via Hanzo AI API](https://hanzo.ai/models/inclusionai/ling-3.0-flash-vl.md): Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE fr... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Ling 3.0 Flash — Use via Hanzo AI API](https://hanzo.ai/models/inclusionai/ling-3.0-flash.md): *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Ling 3.1 Flash — Use via Hanzo AI API](https://hanzo.ai/models/inclusionai/ling-3.1-flash.md): Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusio... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [inference-net Models via Hanzo AI — 2 models](https://hanzo.ai/models/inference-net.md): Access 2 inference-net models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Schematron V2 Small — Use via Hanzo AI API](https://hanzo.ai/models/inference-net/schematron-v2-small.md): Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from In... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Schematron V2 Turbo — Use via Hanzo AI API](https://hanzo.ai/models/inference-net/schematron-v2-turbo.md): Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from In... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [kwaivgi Models via Hanzo AI — 3 models](https://hanzo.ai/models/kwaivgi.md): Access 3 kwaivgi models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Video v3.0 Pro — Use via Hanzo AI API](https://hanzo.ai/models/kwaivgi/kling-v3.0-pro.md): Kling v3.0 Pro is Kuaishou's premium video generation model, offering highe... Call via Hanzo's OpenAI-compatible API.
- [Video v3.0 Standard — Use via Hanzo AI API](https://hanzo.ai/models/kwaivgi/kling-v3.0-std.md): Kling v3.0 Standard is a video generation model from Kuaishou. It supports... Call via Hanzo's OpenAI-compatible API.
- [Video O1 — Use via Hanzo AI API](https://hanzo.ai/models/kwaivgi/kling-video-o1.md): Kling Video O1 is a video generation model from Kuaishou. It supports text... Call via Hanzo's OpenAI-compatible API.
- [Liquid AI Models via Hanzo AI — 3 models](https://hanzo.ai/models/liquid.md): Access 3 Liquid AI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [LFM2.5-2.6B — Use via Hanzo AI API](https://hanzo.ai/models/liquid/lfm-2.5-2.6b.md): LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for a... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [LFM2.5-2.6B (free) — Use via Hanzo AI API](https://hanzo.ai/models/liquid/lfm-2.5-2.6b:free.md): LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for a... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [LFM2.5-24B-A2B — Use via Hanzo AI API](https://hanzo.ai/models/liquid/lfm-2.5-24b-a2b.md): LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Mancer Models via Hanzo AI — 1 models](https://hanzo.ai/models/mancer.md): Access 1 Mancer models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Weaver (alpha) — Use via Hanzo AI API](https://hanzo.ai/models/mancer/weaver.md): An attempt to recreate Claude-style verbosity, but don't expect the same le... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Meituan Models via Hanzo AI — 1 models](https://hanzo.ai/models/meituan.md): Access 1 Meituan models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [LongCat 2.0 — Use via Hanzo AI API](https://hanzo.ai/models/meituan/longcat-2.0.md): LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, wit... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Meta Models via Hanzo AI — 16 models](https://hanzo.ai/models/meta.md): Access 16 Meta models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Llama 3.1 70B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-3.1-70b-instruct.md): Meta's latest class of model (Llama 3.1) launched with a variety of sizes &... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Llama 3.1 8B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-3.1-8b-instruct.md): Meta's latest class of model (Llama 3.1) launched with a variety of sizes &... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Llama 3.2 1B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-3.2-1b-instruct.md): Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently... Call via Hanzo's OpenAI-compatible API. Context: 60K.
- [Llama 3.2 3B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-3.2-3b-instruct.md): Llama 3.2 3B is a 3-billion-parameter multilingual large language model, op... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Llama 3.3 70B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-3.3-70b-instruct.md): The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Llama 4 Maverick — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-4-maverick.md): Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language... Call via Hanzo's OpenAI-compatible API. Context: 524K.
- [Llama 4 Scout — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-4-scout.md): Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language mod... Call via Hanzo's OpenAI-compatible API. Context: 328K.
- [Llama Guard 4 12B — Use via Hanzo AI API](https://hanzo.ai/models/meta/llama-guard-4-12b.md): Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-... Call via Hanzo's OpenAI-compatible API. Context: 164K.
- [Muse Glimmer 30B — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-glimmer-30b.md): Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superin... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Muse Spark 1.1 — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-1.1.md): Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Spark 1.2 Contributor — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-1.2-contributor.md): Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Spark 1.2 — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-1.2.md): Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Spark 1.3 Contributor — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-1.3-contributor.md): Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Spark 1.3 — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-1.3.md): Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running a... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Spark Open — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-spark-open.md): Muse Spark Open is a coding-optimized open-weight model. Trained specifical... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Muse Wonder — Use via Hanzo AI API](https://hanzo.ai/models/meta/muse-wonder.md): Muse Wonder is a frontier reasoning model from Meta, designed for complex p... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Microsoft Models via Hanzo AI — 5 models](https://hanzo.ai/models/microsoft.md): Access 5 Microsoft models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [MAI-Voice-2-Flash — Use via Hanzo AI API](https://hanzo.ai/models/microsoft/mai-voice-2-flash.md): MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI f... Call via Hanzo's OpenAI-compatible API.
- [MAI-Voice-2.1-Flash — Use via Hanzo AI API](https://hanzo.ai/models/microsoft/mai-voice-2.1-flash.md): MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI... Call via Hanzo's OpenAI-compatible API.
- [MAI-Voice-2.1 — Use via Hanzo AI API](https://hanzo.ai/models/microsoft/mai-voice-2.1.md): MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-s... Call via Hanzo's OpenAI-compatible API.
- [MAI-Voice-2 — Use via Hanzo AI API](https://hanzo.ai/models/microsoft/mai-voice-2.md): MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is... Call via Hanzo's OpenAI-compatible API.
- [Phi 4 — Use via Hanzo AI API](https://hanzo.ai/models/microsoft/phi-4.md): Microsoft Research Phi-4 is designed to perform well in complex reasoning t... Call via Hanzo's OpenAI-compatible API. Context: 16K.
- [Minimax Models via Hanzo AI — 14 models](https://hanzo.ai/models/minimax.md): Access 14 Minimax models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Hailuo 2.3 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/hailuo-2.3.md): Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompt... Call via Hanzo's OpenAI-compatible API.
- [H3 Max — Use via Hanzo AI API](https://hanzo.ai/models/minimax/hailuo-3-max.md): MiniMax H3 Max is a video-generation model from MiniMax, jointly released w... Call via Hanzo's OpenAI-compatible API.
- [H3 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/hailuo-3.md): MiniMax H3 is a lightweight, open-weights video generation model from MiniM... Call via Hanzo's OpenAI-compatible API.
- [MiniMax-01 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-01.md): MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiniMax M1 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m1.md): MiniMax-M1 is a large-scale, open-weight reasoning model designed for exten... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiniMax M2-her — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m2-her.md): MiniMax M2-her is a dialogue-first large language model built for immersive... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [MiniMax M2.1 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m2.1.md): MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimi... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [MiniMax M2.5 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m2.5.md): MiniMax-M2.5 is a SOTA large language model designed for real-world product... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [MiniMax M2.7 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m2.7.md): MiniMax-M2.7 is a next-generation large language model designed for autonom... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [MiniMax M2 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m2.md): MiniMax-M2 is a compact, high-efficiency large language model optimized for... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [MiniMax M3.1 Flash — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m3.1-flash.md): MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiniMax M3 — Use via Hanzo AI API](https://hanzo.ai/models/minimax/minimax-m3.md): MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text,... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Speech 2.8 HD — Use via Hanzo AI API](https://hanzo.ai/models/minimax/speech-2.8-hd.md): MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited... Call via Hanzo's OpenAI-compatible API.
- [Speech 2.8 Turbo — Use via Hanzo AI API](https://hanzo.ai/models/minimax/speech-2.8-turbo.md): MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suit... Call via Hanzo's OpenAI-compatible API.
- [Mistral Models via Hanzo AI — 23 models](https://hanzo.ai/models/mistralai.md): Access 23 Mistral models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Codestral 2508 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/codestral-2508.md): Mistral's cutting-edge language model for coding released end of July 2025.... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Devstral 2 2512 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/devstral-2512.md): Devstral 2 is a state-of-the-art open-source model by Mistral AI specializi... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Ministral 3 14B 2512 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/ministral-14b-2512.md): The largest model in the Ministral 3 family, Ministral 3 14B offers frontie... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Ministral 3 3B 2512 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/ministral-3b-2512.md): The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful,... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Ministral 3 8B 2512 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/ministral-8b-2512.md): A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, e... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Mistral Large 2407 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-large-2407.md): This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Mistral Large 3 2512 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-large-2512.md): Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a s... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Mistral Large 4 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-large-4-0.md): Mistral Large 4 is a frontier multimodal (text and image input) model from... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Mistral Large — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-large.md): This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-larg... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Mistral Medium 3.5 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-medium-3-5.md): Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Mistral Medium 3.1 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-medium-3.1.md): Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a hi... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Mistral Medium 3 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-medium-3.md): Mistral Medium 3 is a high-performance enterprise-grade language model desi... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Mistral Nemo — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-nemo.md): A 12B parameter model with a 128k token context length built by Mistral in... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Saba — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-saba.md): Mistral Saba is a 24B-parameter language model specifically designed for th... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Mistral Small 3 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-small-24b-instruct-2501.md): Mistral Small 3 is a 24B-parameter language model optimized for low-latency... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Mistral Small 4 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-small-2603.md): Mistral Small 4 is the next major release in the Mistral Small family, unif... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Mistral Small 3.1 24B — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-small-3.1-24b-instruct.md): Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Mistral Small 3.2 24B — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mistral-small-3.2-24b-instruct.md): Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Mixtral 8x22B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/mixtral-8x22b-instruct.md): Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Voxtral Mini TTS — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/voxtral-mini-tts-2603.md): Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voic... Call via Hanzo's OpenAI-compatible API.
- [Voxtral TTS 3 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/voxtral-mini-tts-3-0.md): Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natu... Call via Hanzo's OpenAI-compatible API.
- [Voxtral Small 24B 2507 — Use via Hanzo AI API](https://hanzo.ai/models/mistralai/voxtral-small-24b-2507.md): Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [moondream Models via Hanzo AI — 2 models](https://hanzo.ai/models/moondream.md): Access 2 moondream models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Moondream 3 Preview — Use via Hanzo AI API](https://hanzo.ai/models/moondream/moondream3-preview.md): Moondream 3 Preview is a vision-language model from Moondream with 9B total... Call via Hanzo's OpenAI-compatible API. Context: 32K.
- [Moondream 3.1 — Use via Hanzo AI API](https://hanzo.ai/models/moondream/moondream3.1-9b-a2b.md): Moondream 3.1 is a vision-language model from Moondream, the successor to M... Call via Hanzo's OpenAI-compatible API. Context: 32K.
- [Moonshot AI Models via Hanzo AI — 10 models](https://hanzo.ai/models/moonshotai.md): Access 10 Moonshot AI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Kimi K2 0905 — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2-0905.md): Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale M... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Kimi K2 Thinking — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2-thinking.md): Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to dat... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Kimi K2.5 — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2.5.md): Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Kimi K2.6 — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2.6.md): Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for l... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Kimi K2.7 Code — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2.7-code.md): MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Kimi K2 0711 — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k2.md): Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model d... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Kimi K3.1 Pro — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k3.1-pro.md): Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning mo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Kimi K3 — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-k3.md): Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Kimi Latest — Use via Hanzo AI API](https://hanzo.ai/models/moonshotai/kimi-latest.md): This model always redirects to the latest model in the Kimi family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Morph Models via Hanzo AI — 2 models](https://hanzo.ai/models/morph.md): Access 2 Morph models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Morph V3 Fast — Use via Hanzo AI API](https://hanzo.ai/models/morph/morph-v3-fast.md): Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% acc... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Morph V3 Large — Use via Hanzo AI API](https://hanzo.ai/models/morph/morph-v3-large.md): Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nex-AGI Models via Hanzo AI — 2 models](https://hanzo.ai/models/nex-agi.md): Access 2 Nex-AGI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Nex-N2.5-Mini — Use via Hanzo AI API](https://hanzo.ai/models/nex-agi/nex-n2.5-mini.md): Nex-N2.5 is an agentic model built to turn goals into working, verified out... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nex-N2.5-Pro — Use via Hanzo AI API](https://hanzo.ai/models/nex-agi/nex-n2.5-pro.md): Nex-N2.5 is an agentic model built to turn goals into working, verified out... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nous Research Models via Hanzo AI — 3 models](https://hanzo.ai/models/nousresearch.md): Access 3 Nous Research models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Hermes 3 405B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/nousresearch/hermes-3-llama-3.1-405b.md): Hermes 3 is a generalist language model with many improvements over Hermes... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Hermes 3 70B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/nousresearch/hermes-3-llama-3.1-70b.md): Hermes 3 is a generalist language model with many improvements over Hermes... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Hermes 4 405B — Use via Hanzo AI API](https://hanzo.ai/models/nousresearch/hermes-4-405b.md): Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [NVIDIA Models via Hanzo AI — 12 models](https://hanzo.ai/models/nvidia.md): Access 12 NVIDIA models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Nemotron 3 Nano 30B A3B — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3-nano-30b-a3b.md): NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest c... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nemotron 3 Nano Omni (free) — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.md): NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Nemotron 3 Super — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3-super-120b-a12b.md): NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activati... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nemotron 3 Ultra — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3-ultra-550b-a55b.md): NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration mod... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nemotron 3 Ultra (free) — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3-ultra-550b-a55b:free.md): NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration mod... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nemotron 3.5 Content Safety — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-content-safety.md): NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal gua... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Nemotron 3.5 Content Safety (free) — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-content-safety:free.md): NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal gua... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Nemotron 3.5 Lightning — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-lightning.md): NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVID... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Nemotron 3.5 Lightning (free) — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-lightning:free.md): NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVID... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nemotron 3.5 Super VL — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-super-vl.md): NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Nemotron 3.5 Super VL (free) — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/nemotron-3.5-super-vl:free.md): NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Switchyard — Use via Hanzo AI API](https://hanzo.ai/models/nvidia/switchyard.md): Switchyard is an open-source model routing system that switches between mul... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [OpenAI Models via Hanzo AI — 81 models](https://hanzo.ai/models/openai.md): Access 81 OpenAI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [GPT-3.5 Turbo 16k — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-3.5-turbo-16k.md): This model offers four times the context length of gpt-3.5-turbo, allowing... Call via Hanzo's OpenAI-compatible API. Context: 16K.
- [GPT-4.1 Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4.1-mini.md): GPT-4.1 Mini is a mid-sized model delivering performance competitive with G... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-4.1 Nano — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4.1-nano.md): For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-4.1 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4.1.md): GPT-4.1 is a flagship large language model optimized for advanced instructi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-4 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4.md): OpenAI's flagship model, GPT-4 is a large-scale multimodal language model c... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [GPT-4o-mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4o-mini.md): GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [GPT-4o — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-4o.md): GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text a... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [GPT-5 Image Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5-image-mini.md): GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5 Image — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5-image.md): GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image gener... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5 Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5-mini.md): GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5 Nano — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5-nano.md): GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimiz... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5 Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5-pro.md): GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in r... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.1-Codex-Max — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.1-codex-max.md): GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for lon... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.1-Codex-Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.1-codex-mini.md): GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.1-Codex — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.1-codex.md): GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software en... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.1 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.1.md): GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering st... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.2-Codex — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.2-codex.md): GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for softwar... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.2 Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.2-pro.md): GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.2 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.2.md): GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering st... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.3-Codex — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.3-codex.md): GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.4 Image 2 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.4-image-2.md): GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image... Call via Hanzo's OpenAI-compatible API. Context: 272K.
- [GPT-5.4 Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.4-mini.md): GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more effi... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.4 Nano — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.4-nano.md): GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-5.4 Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.4-pro.md): GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.4 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.4.md): GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.5 Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.5-pro.md): GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.5 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.5.md): GPT-5.5 is OpenAI’s frontier model designed for complex professional worklo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Luna Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-luna-pro.md): GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Luna — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-luna.md): GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Sol Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-sol-pro.md): GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `r... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Sol — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-sol.md): GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Terra Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-terra-pro.md): GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served wit... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5.6 Terra — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.6-terra.md): GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned be... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-5 — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-5.md): GPT-5 is OpenAI’s most advanced model, offering major improvements in reaso... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT-6 Astra Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-astra-pro.md): GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with `r... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6 Astra — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-astra.md): GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6 Luna Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-luna-pro.md): GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with `rea... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6 Luna — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-luna.md): GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, posi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6 Sol Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-sol-pro.md): GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with `reaso... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6 Sol — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6-sol.md): GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, po... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6.1 Sol Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6.1-sol-pro.md): GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with `r... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6.1 Sol — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6.1-sol.md): GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the fl... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6.1 Terra Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6.1-terra-pro.md): GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served wit... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT-6.1 Terra — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-6.1-terra.md): GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced belo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT Astra Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-astra-latest.md): This model always redirects to the latest model in the GPT Astra family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT Audio Mini — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-audio-mini.md): A cost-efficient version of GPT Audio. The new snapshot features an upgrade... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [GPT Audio — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-audio.md): The gpt-audio model is OpenAI's first generally available audio model. The... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [GPT Chat Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-chat-latest.md): GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that alwa... Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [GPT Luna Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-luna-latest.md): This model always redirects to the latest model in the GPT Luna family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT Mini Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-mini-latest.md): This model always redirects to the latest model in the GPT Mini family. Call via Hanzo's OpenAI-compatible API. Context: 400K.
- [gpt-oss-120b — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-oss-120b.md): gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) lan... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [gpt-oss-20b — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-oss-20b.md): gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [gpt-oss-safeguard-20b — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-oss-safeguard-20b.md): gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gp... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [GPT Sol Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-sol-latest.md): This model always redirects to the latest model in the GPT Sol family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GPT Terra Latest — Use via Hanzo AI API](https://hanzo.ai/models/openai/gpt-terra-latest.md): This model always redirects to the latest model in the GPT Terra family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [o3 Pro — Use via Hanzo AI API](https://hanzo.ai/models/openai/o3-pro.md): The o-series of models are trained with reinforcement learning to think bef... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [o3 — Use via Hanzo AI API](https://hanzo.ai/models/openai/o3.md): o3 is a well-rounded and powerful model across domains. It sets a new stand... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [OpenRouter Models via Hanzo AI — 6 models](https://hanzo.ai/models/openrouter.md): Access 6 OpenRouter models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Auto Router (Beta) — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/auto-beta.md): The experimental version of our Auto Router where we test new improvements.... Call via Hanzo's OpenAI-compatible API. Context: 2M.
- [Auto Router — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/auto.md): The Auto Router automatically selects the best model for your prompt, power... Call via Hanzo's OpenAI-compatible API. Context: 2M.
- [Body Builder (beta) — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/bodybuilder.md): Transform your natural language requests into structured OpenRouter API req... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Free Models Router — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/free.md): The simplest way to get free inference. openrouter/free is a router that se... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Fusion — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/fusion.md): Fusion turns your prompt into a small multi-model deliberation. A panel of... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Pareto Code Router — Use via Hanzo AI API](https://hanzo.ai/models/openrouter/pareto-code.md): The Pareto Router maintains a tiered shortlist of strong coding models, ran... Call via Hanzo's OpenAI-compatible API. Context: 2M.
- [particle-ai Models via Hanzo AI — 1 models](https://hanzo.ai/models/particle-ai.md): Access 1 particle-ai models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Particle-1 — Use via Hanzo AI API](https://hanzo.ai/models/particle-ai/particle-1.md): Particle-1 is a token-efficient agentic coding model from Particle AI, post... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Perceptron Models via Hanzo AI — 2 models](https://hanzo.ai/models/perceptron.md): Access 2 Perceptron models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Perceptron Mk1.5 — Use via Hanzo AI API](https://hanzo.ai/models/perceptron/perceptron-mk1.5.md): Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agen... Call via Hanzo's OpenAI-compatible API. Context: 37K.
- [Perceptron Mk1 — Use via Hanzo AI API](https://hanzo.ai/models/perceptron/perceptron-mk1.md): Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language m... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Perplexity Models via Hanzo AI — 5 models](https://hanzo.ai/models/perplexity.md): Access 5 Perplexity models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Sonar Deep Research — Use via Hanzo AI API](https://hanzo.ai/models/perplexity/sonar-deep-research.md): Sonar Deep Research is a research-focused model designed for multi-step ret... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Sonar Pro Search — Use via Hanzo AI API](https://hanzo.ai/models/perplexity/sonar-pro-search.md): Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mod... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Sonar Pro — Use via Hanzo AI API](https://hanzo.ai/models/perplexity/sonar-pro.md): Note: Sonar Pro pricing includes Perplexity search pricing. See details her... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [Sonar Reasoning Pro — Use via Hanzo AI API](https://hanzo.ai/models/perplexity/sonar-reasoning-pro.md): Note: Sonar Pro pricing includes Perplexity search pricing. See details her... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Sonar — Use via Hanzo AI API](https://hanzo.ai/models/perplexity/sonar.md): Sonar is lightweight, affordable, fast, and simple to use — now featuring c... Call via Hanzo's OpenAI-compatible API. Context: 127K.
- [poolside Models via Hanzo AI — 4 models](https://hanzo.ai/models/poolside.md): Access 4 poolside models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Laguna S 2.1 — Use via Hanzo AI API](https://hanzo.ai/models/poolside/laguna-s-2.1.md): Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 i... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Laguna S 2.1 (free) — Use via Hanzo AI API](https://hanzo.ai/models/poolside/laguna-s-2.1:free.md): Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 i... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Laguna XS 2.1 — Use via Hanzo AI API](https://hanzo.ai/models/poolside/laguna-xs-2.1.md): Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Laguna XS 2.1 (free) — Use via Hanzo AI API](https://hanzo.ai/models/poolside/laguna-xs-2.1:free.md): Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [prism-ml Models via Hanzo AI — 2 models](https://hanzo.ai/models/prism-ml.md): Access 2 prism-ml models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Ternary Bonsai 2 27B — Use via Hanzo AI API](https://hanzo.ai/models/prism-ml/ternary-bonsai-2-27b.md): Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Q... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Ternary Bonsai 2 9B — Use via Hanzo AI API](https://hanzo.ai/models/prism-ml/ternary-bonsai-2-9b.md): Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for co... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen Models via Hanzo AI — 44 models](https://hanzo.ai/models/qwen.md): Access 44 Qwen models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Qwen2.5 72B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-2.5-72b-instruct.md): Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 bri... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Qwen2.5 7B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-2.5-7b-instruct.md): Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brin... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Qwen2.5 Coder 32B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-2.5-coder-32b-instruct.md): Qwen2.5-Coder is the latest series of Code-Specific Qwen large language mod... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [Qwen-Audio-3.0-TTS Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-audio-3.0-tts-flash.md): Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech m... Call via Hanzo's OpenAI-compatible API.
- [Qwen-Audio-3.0-TTS Plus — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-audio-3.0-tts-plus.md): Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, g... Call via Hanzo's OpenAI-compatible API.
- [Qwen-Plus — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen-plus.md): Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model w... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen2.5 VL 72B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen2.5-vl-72b-instruct.md): Qwen2.5-VL is proficient in recognizing common objects such as flowers, bir... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Qwen3 14B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-14b.md): Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 s... Call via Hanzo's OpenAI-compatible API. Context: 41K.
- [Qwen3 235B A22B Instruct 2507 — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-235b-a22b-2507.md): Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 235B A22B Thinking 2507 — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-235b-a22b-thinking-2507.md): Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of... Call via Hanzo's OpenAI-compatible API. Context: 128K.
- [Qwen3 30B A3B Instruct 2507 — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-30b-a3b-instruct-2507.md): Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts languag... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 30B A3B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-30b-a3b.md): Qwen3, the latest generation in the Qwen large language model series, featu... Call via Hanzo's OpenAI-compatible API. Context: 41K.
- [Qwen3 32B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-32b.md): Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 s... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Qwen3 Coder 30B A3B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-coder-30b-a3b-instruct.md): Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE)... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 Coder Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-coder-flash.md): Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their pro... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3 Coder Next — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-coder-next.md): Qwen3-Coder-Next is an open-weight causal language model optimized for codi... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 Coder 480B A35B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-coder.md): Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generatio... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 Next 80B A3B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-next-80b-a3b-instruct.md): Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 VL 235B A22B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-vl-235b-a22b-instruct.md): Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 VL 30B A3B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-vl-30b-a3b-instruct.md): Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text ge... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 VL 30B A3B Thinking — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-vl-30b-a3b-thinking.md): Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text ge... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3 VL 8B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3-vl-8b-instruct.md): Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-V... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5-122B-A10B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-122b-a10b.md): The Qwen3.5 122B-A10B native vision-language model is built on a hybrid arc... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5-27B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-27b.md): The Qwen3.5 27B native vision-language Dense model incorporates a linear at... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5-35B-A3B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-35b-a3b.md): The Qwen3.5 Series 35B-A3B is a native vision-language model designed with... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5 397B A17B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-397b-a17b.md): The Qwen3.5 series 397B-A17B native vision-language model is built on a hyb... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5-9B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-9b.md): Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, design... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.5-Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-flash-02-23.md): The Qwen3.5 native vision-language Flash models are built on a hybrid archi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.5 Plus 2026-02-15 — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-plus-02-15.md): The Qwen3.5 native vision-language series Plus models are built on a hybrid... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.5 Plus 2026-04-20 — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.5-plus-20260420.md): Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from A... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.6 27B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.6-27b.md): Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Te... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.6 35B A3B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.6-35b-a3b.md): Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Qwen3.6 Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.6-flash.md): Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 s... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.6 Plus — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.6-plus.md): Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linea... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.7 Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.7-flash.md): Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suit... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.7 Max — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.7-max.md): Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.7 Plus — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.7-plus.md): Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supp... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 2.4T A95B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-2.4t-a95b.md): Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qw... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 27B — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-27b.md): Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-flash.md): Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited fo... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 Max (0902) — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-max-0902.md): Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 Max Prime — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-max-prime.md): Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibab... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Qwen3.8 Omni Flash — Use via Hanzo AI API](https://hanzo.ai/models/qwen/qwen3.8-omni-flash.md): Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [recursive Models via Hanzo AI — 1 models](https://hanzo.ai/models/recursive.md): Access 1 recursive models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Flint (free) — Use via Hanzo AI API](https://hanzo.ai/models/recursive/flint-v1.0:free.md): Flint is an open-weight mixture-of-experts model from Recursive, with about... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [reflection Models via Hanzo AI — 1 models](https://hanzo.ai/models/reflection.md): Access 1 reflection models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Beam 1.0 501B A23B — Use via Hanzo AI API](https://hanzo.ai/models/reflection/beam-1.0-501b-a23b.md): Beam 1.0 is Reflection's open-weight reasoning model for coding and long-ho... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Reka AI Models via Hanzo AI — 2 models](https://hanzo.ai/models/rekaai.md): Access 2 Reka AI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Reka Edge — Use via Hanzo AI API](https://hanzo.ai/models/rekaai/reka-edge.md): Reka Edge is an extremely efficient 7B multimodal vision-language model tha... Call via Hanzo's OpenAI-compatible API. Context: 16K.
- [Reka Flash 3 — Use via Hanzo AI API](https://hanzo.ai/models/rekaai/reka-flash-3.md): Reka Flash 3 is a general-purpose, instruction-tuned large language model w... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [Relace Models via Hanzo AI — 2 models](https://hanzo.ai/models/relace.md): Access 2 Relace models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Relace Apply 3 — Use via Hanzo AI API](https://hanzo.ai/models/relace/relace-apply-3.md): Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Relace Search — Use via Hanzo AI API](https://hanzo.ai/models/relace/relace-search.md): The relace-search model uses 4-12 `view_file` and `grep` tools in parallel... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [runway Models via Hanzo AI — 1 models](https://hanzo.ai/models/runway.md): Access 1 runway models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Gen-4.5 — Use via Hanzo AI API](https://hanzo.ai/models/runway/gen-4.5.md): Runway Gen-4.5 is a video generation model from Runway for text-to-video an... Call via Hanzo's OpenAI-compatible API.
- [Sakana AI Models via Hanzo AI — 4 models](https://hanzo.ai/models/sakana.md): Access 4 Sakana AI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Fugu Max — Use via Hanzo AI API](https://hanzo.ai/models/sakana/fugu-max.md): Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather t... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Fugu Ultra v2 — Use via Hanzo AI API](https://hanzo.ai/models/sakana/fugu-ultra-v2.md): Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. R... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Fugu Ultra — Use via Hanzo AI API](https://hanzo.ai/models/sakana/fugu-ultra.md): Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rath... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Sakana Namazu — Use via Hanzo AI API](https://hanzo.ai/models/sakana/sakana-namazu.md): Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, bas... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Sao10K Models via Hanzo AI — 2 models](https://hanzo.ai/models/sao10k.md): Access 2 Sao10K models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Llama 3 8B Lunaris — Use via Hanzo AI API](https://hanzo.ai/models/sao10k/l3-lunaris-8b.md): Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Llama 3.1 Euryale 70B v2.2 — Use via Hanzo AI API](https://hanzo.ai/models/sao10k/l3.1-euryale-70b.md): Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k.... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [scaledown Models via Hanzo AI — 2 models](https://hanzo.ai/models/scaledown.md): Access 2 scaledown models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Extract — Use via Hanzo AI API](https://hanzo.ai/models/scaledown/extract.md): Extract is a description-driven entity extraction model from ScaleDown. Ins... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Summarize — Use via Hanzo AI API](https://hanzo.ai/models/scaledown/summarize.md): Summarize is an abstractive summarization model from ScaleDown. It condense... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [sesame Models via Hanzo AI — 1 models](https://hanzo.ai/models/sesame.md): Access 1 sesame models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [CSM 1B — Use via Hanzo AI API](https://hanzo.ai/models/sesame/csm-1b.md): CSM 1B is a conversational speech model from Sesame. It accepts text input... Call via Hanzo's OpenAI-compatible API.
- [StepFun Models via Hanzo AI — 3 models](https://hanzo.ai/models/stepfun.md): Access 3 StepFun models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Step 3.5 Flash — Use via Hanzo AI API](https://hanzo.ai/models/stepfun/step-3.5-flash.md): Step 3.5 Flash is StepFun's most capable open-source foundation model. Buil... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Step 3.7 Flash — Use via Hanzo AI API](https://hanzo.ai/models/stepfun/step-3.7-flash.md): Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Ex... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Step 5 Preview — Use via Hanzo AI API](https://hanzo.ai/models/stepfun/step-5-preview.md): Step 5 Preview is StepFun's flagship model for agentic work, built on a spa... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [tbc Models via Hanzo AI — 1 models](https://hanzo.ai/models/tbc.md): Access 1 tbc models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Mischief 1 — Use via Hanzo AI API](https://hanzo.ai/models/tbc/mischief-1.md): TBC Mischief 1 is the world's first neuron-derived video model from The Bio... Call via Hanzo's OpenAI-compatible API.
- [Tencent Models via Hanzo AI — 7 models](https://hanzo.ai/models/tencent.md): Access 7 Tencent models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Hunyuan A13B Instruct — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hunyuan-a13b-instruct.md): Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language mo... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Hy-MT2-1.8B — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy-mt2-1.8b.md): Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Hy-MT2-30B-A3B — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy-mt2-30b-a3b.md): Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Hy-MT2-7B — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy-mt2-7b.md): Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33... Call via Hanzo's OpenAI-compatible API. Context: 8K.
- [Hy3 preview — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy3-preview.md): Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent desi... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Hy3 — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy3.md): Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active,... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Hy4 preview — Use via Hanzo AI API](https://hanzo.ai/models/tencent/hy4-preview.md): Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B a... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [TheDrummer Models via Hanzo AI — 3 models](https://hanzo.ai/models/thedrummer.md): Access 3 TheDrummer models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Cydonia 24B V4.1 — Use via Hanzo AI API](https://hanzo.ai/models/thedrummer/cydonia-24b-v4.1.md): Uncensored and creative writing model based on Mistral Small 3.2 24B with g... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [Skyfall 36B V2 — Use via Hanzo AI API](https://hanzo.ai/models/thedrummer/skyfall-36b-v2.md): Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically... Call via Hanzo's OpenAI-compatible API. Context: 33K.
- [UnslopNemo 12B — Use via Hanzo AI API](https://hanzo.ai/models/thedrummer/unslopnemo-12b.md): UnslopNemo v4.1 is the latest addition from the creator of Rocinante, desig... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Thinking Machines Models via Hanzo AI — 4 models](https://hanzo.ai/models/thinkingmachines.md): Access 4 Thinking Machines models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Inkling Small — Use via Hanzo AI API](https://hanzo.ai/models/thinkingmachines/inkling-small.md): Inkling Small is an open-weight multimodal mixture-of-experts model from Th... Call via Hanzo's OpenAI-compatible API. Context: 524K.
- [Inkling Small (free) — Use via Hanzo AI API](https://hanzo.ai/models/thinkingmachines/inkling-small:free.md): Inkling Small is an open-weight multimodal mixture-of-experts model from Th... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Inkling — Use via Hanzo AI API](https://hanzo.ai/models/thinkingmachines/inkling.md): Inkling is an open-weight multimodal mixture-of-experts model from Thinking... Call via Hanzo's OpenAI-compatible API. Context: 524K.
- [Inkling (free) — Use via Hanzo AI API](https://hanzo.ai/models/thinkingmachines/inkling:free.md): Inkling is an open-weight multimodal mixture-of-experts model from Thinking... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [typesafe Models via Hanzo AI — 3 models](https://hanzo.ai/models/typesafe.md): Access 3 typesafe models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Jev 1.13 — Use via Hanzo AI API](https://hanzo.ai/models/typesafe/jev-1.13.md): TypeSafe's decision model, reached through OpenRouter, at its list price: $... Call it at POST /v1/decisions.
- [Jev — Use via Hanzo AI API](https://hanzo.ai/models/typesafe/jev-latest.md): TypeSafe's decision model, reached through OpenRouter, at its list price: $... Call it at POST /v1/decisions.
- [Jev Router — Use via Hanzo AI API](https://hanzo.ai/models/typesafe/jev-router.md): Jev Router picks the best model and reasoning effort for each request, bala... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [unbiased Models via Hanzo AI — 3 models](https://hanzo.ai/models/unbiased.md): Access 3 unbiased models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Pareto 26.10 — Use via Hanzo AI API](https://hanzo.ai/models/unbiased/pareto-26.10.md): Pareto is a multimodal composite model built for research, coding, and agen... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Pareto 26.9 — Use via Hanzo AI API](https://hanzo.ai/models/unbiased/pareto-26.9.md): Pareto is a multimodal composite model built for research, coding, and agen... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Pareto Latest — Use via Hanzo AI API](https://hanzo.ai/models/unbiased/pareto-latest.md): This model always redirects to the latest model in the Pareto family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Undi95 Models via Hanzo AI — 1 models](https://hanzo.ai/models/undi95.md): Access 1 Undi95 models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [ReMM SLERP 13B — Use via Hanzo AI API](https://hanzo.ai/models/undi95/remm-slerp-l2-13b.md): A recreation trial of the original MythoMax-L2-B13 but with updated models.... Call via Hanzo's OpenAI-compatible API. Context: 6K.
- [Upstage Models via Hanzo AI — 2 models](https://hanzo.ai/models/upstage.md): Access 2 Upstage models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Solar Mini 4 — Use via Hanzo AI API](https://hanzo.ai/models/upstage/solar-mini4.md): Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-par... Call via Hanzo's OpenAI-compatible API. Context: 524K.
- [Solar Pro 4 — Use via Hanzo AI API](https://hanzo.ai/models/upstage/solar-pro4.md): Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 5... Call via Hanzo's OpenAI-compatible API. Context: 524K.
- [Writer Models via Hanzo AI — 1 models](https://hanzo.ai/models/writer.md): Access 1 Writer models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Palmyra X5 — Use via Hanzo AI API](https://hanzo.ai/models/writer/palmyra-x5.md): Palmyra X5 is Writer's most advanced model, purpose-built for building and... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [xAI Models via Hanzo AI — 13 models](https://hanzo.ai/models/x-ai.md): Access 13 xAI models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Grok 4.20 Multi-Agent — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.20-multi-agent.md): Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for col... Call via Hanzo's OpenAI-compatible API. Context: 2M.
- [Grok 4.20 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.20.md): Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed an... Call via Hanzo's OpenAI-compatible API. Context: 2M.
- [Grok 4.3 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.3.md): Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inpu... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Grok 4.5 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.5.md): Grok 4.5 is a model from SpaceXAI with frontier performance on coding, know... Call via Hanzo's OpenAI-compatible API. Context: 500K.
- [Grok 4.6 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.6.md): Grok 4.6 is a model from SpaceXAI with frontier performance on coding, know... Call via Hanzo's OpenAI-compatible API. Context: 500K.
- [Grok 4.7 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-4.7.md): Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowle... Call via Hanzo's OpenAI-compatible API. Context: 500K.
- [Grok Build 0.1 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-build-0.1.md): Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for age... Call via Hanzo's OpenAI-compatible API. Context: 256K.
- [Grok Imagine Video 1.5 Lite — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-imagine-video-1.5-lite.md): Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model... Call via Hanzo's OpenAI-compatible API.
- [Grok Imagine Video 1.5 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-imagine-video-1.5.md): Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It create... Call via Hanzo's OpenAI-compatible API.
- [Grok Imagine Video — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-imagine-video.md): Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditi... Call via Hanzo's OpenAI-compatible API.
- [Grok Latest — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-latest.md): This model always redirects to the latest Grok model from xAI. Call via Hanzo's OpenAI-compatible API. Context: 500K.
- [Grok Voice TTS 1.0 — Use via Hanzo AI API](https://hanzo.ai/models/x-ai/grok-voice-tts-1.0.md): Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts tex... Call via Hanzo's OpenAI-compatible API.
- [Xiaomi Models via Hanzo AI — 5 models](https://hanzo.ai/models/xiaomi.md): Access 5 Xiaomi models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [MiMo-V2.5-Pro — Use via Hanzo AI API](https://hanzo.ai/models/xiaomi/mimo-v2.5-pro.md): MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiMo-V2.5 — Use via Hanzo AI API](https://hanzo.ai/models/xiaomi/mimo-v2.5.md): MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agen... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiMo-V2.6-Flash — Use via Hanzo AI API](https://hanzo.ai/models/xiaomi/mimo-v2.6-flash.md): MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Bui... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiMo-V2.6-Pro-UltraSpeed — Use via Hanzo AI API](https://hanzo.ai/models/xiaomi/mimo-v2.6-pro-ultraspeed.md): MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship fou... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [MiMo-V2.6-Pro — Use via Hanzo AI API](https://hanzo.ai/models/xiaomi/mimo-v2.6-pro.md): MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built a... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [xingchen-agi Models via Hanzo AI — 1 models](https://hanzo.ai/models/xingchen-agi.md): Access 1 xingchen-agi models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [Xing4.0 29B A4B (free) — Use via Hanzo AI API](https://hanzo.ai/models/xingchen-agi/xing4.0-29b-a4b:free.md): Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from Ch... Call via Hanzo's OpenAI-compatible API. Context: 262K.
- [Z.ai Models via Hanzo AI — 20 models](https://hanzo.ai/models/z-ai.md): Access 20 Z.ai models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing.
- [GLM 4.5 Air — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.5-air.md): GLM-4.5-Air is the lightweight variant of our latest flagship model family,... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [GLM 4.5 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.5.md): GLM-4.5 is our latest flagship foundation model, purpose-built for agent-ba... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [GLM 4.5V — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.5v.md): GLM-4.5V is a vision-language foundation model for multimodal agent applica... Call via Hanzo's OpenAI-compatible API. Context: 66K.
- [GLM 4.6 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.6.md): Compared with GLM-4.5, this generation brings several key improvements: Lon... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [GLM 4.6V — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.6v.md): GLM-4.6V is a large multimodal model designed for high-fidelity visual unde... Call via Hanzo's OpenAI-compatible API. Context: 131K.
- [GLM 4.7 Flash — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.7-flash.md): As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances... Call via Hanzo's OpenAI-compatible API. Context: 200K.
- [GLM 4.7 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-4.7.md): GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key area... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [GLM 5 Turbo — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5-turbo.md): GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong... Call via Hanzo's OpenAI-compatible API. Context: 203K.
- [GLM 5.1 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.1.md): GLM-5.1 delivers a major leap in coding capability, with particularly signi... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [GLM 5.2 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.2.md): GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM 5.3 Flash — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.3-flash.md): GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for effi... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM 5.3 FlashX — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.3-flashx.md): GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM 5.3 Prime — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.3-prime.md): GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its f... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM 5.3 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.3.md): GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex softw... Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM 5 — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5.md): GLM-5 is Z.ai’s flagship open-source foundation model engineered for comple... Call via Hanzo's OpenAI-compatible API. Context: 205K.
- [GLM 5V Turbo — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-5v-turbo.md): GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, buil... Call via Hanzo's OpenAI-compatible API. Context: 203K.
- [GLM Flash Latest — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-flash-latest.md): This model always redirects to the latest model in the GLM Flash family. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [GLM Latest — Use via Hanzo AI API](https://hanzo.ai/models/z-ai/glm-latest.md): This model always redirects to the latest GLM model from Z.ai. Call via Hanzo's OpenAI-compatible API. Context: 1M.
- [Mori — Build worlds, not just images. | Hanzo Creative AI](https://hanzo.ai/mori.md): 3D assets, geometry, materials, environments and spatially consistent scenes. Request research access and studio workflows.
- [Hanzo MQ — Hanzo AI](https://hanzo.ai/mq.md): BullMQ-compatible job queue with scheduling, rate limiting, priorities, retries, and dead letter queues.
- [Hanzo Network — Hanzo AI](https://hanzo.ai/network.md): A decentralized AI compute marketplace. Buy verified inference from a global pool of nodes, settle on-chain, pay only for what you use.
- [Subscribe to Hanzo AI Newsletter & Developer Updates — Hanzo AI](https://hanzo.ai/newsletter.md): Opt in to receive frontier AI model announcements (Enso, Zen 6), developer tutorials, platform updates, and technical deep dives from Hanzo AI.
- [Hanzo Node — Hanzo AI](https://hanzo.ai/node.md): Run a node on the Hanzo Network. Contribute compute, serve inference, and earn rewards from a decentralized AI marketplace.
- [Hanzo O11y — Hanzo AI](https://hanzo.ai/o11y.md): Unified AI observability platform: distributed tracing, real-time metrics, structured logs, and profiling for LLMs and agent swarms.
- [Open Source — 1600+ repositories — Hanzo AI](https://hanzo.ai/open-source.md): Explore 1600+ open-source repos across AI infrastructure and models. Verified authors earn 20% of metered spend from deployed projects.
- [Hanzo Operative — Hanzo AI](https://hanzo.ai/operative.md): A container with a Linux desktop inside it and a model driving that desktop by screenshot, mouse and keyboard. You watch through a browser.
- [Hanzo Operator — Hanzo AI](https://hanzo.ai/operator.md): Declarative Kubernetes operator and infrastructure orchestrator for deploying, scaling, and managing Hanzo services and AI clusters.
- [Open source royalty — Hanzo AI](https://hanzo.ai/oss.md): A verified author earns 20% of the metered spend of every org that deploys a project built from their repository.
- [Hanzo Apps — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-app.md): [Legacy] Hanzo app templates — see github.com/hanzoai for current projects. The 11 public repositories of hanzo-app on GitHub, with their stars, forks, languages and last push.
- [Hanzo Apps — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-apps.md): [Legacy] Hanzo app templates — see github.com/hanzoai for current projects. The 91 public repositories of hanzo-apps on GitHub, with their stars, forks, languages and last push.
- [hanzo-community — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-community.md): The 38 public repositories of hanzo-community on GitHub, with their stars, forks, languages and last push.
- [Hanzo Core — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-core.md): Core modules for Hanzo Platform. The 5 public repositories of hanzo-core on GitHub, with their stars, forks, languages and last push.
- [hanzo-cpp — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-cpp.md): The 2 public repositories of hanzo-cpp on GitHub, with their stars, forks, languages and last push.
- [hanzo-dart — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-dart.md): The 3 public repositories of hanzo-dart on GitHub, with their stars, forks, languages and last push.
- [hanzo-docs — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-docs.md): The 5 public repositories of hanzo-docs on GitHub, with their stars, forks, languages and last push.
- [hanzo-ds — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-ds.md): The 5 public repositories of hanzo-ds on GitHub, with their stars, forks, languages and last push.
- [hanzo-fi — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-fi.md): The 4 public repositories of hanzo-fi on GitHub, with their stars, forks, languages and last push.
- [hanzo-git — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-git.md): The 2 public repositories of hanzo-git on GitHub, with their stars, forks, languages and last push.
- [hanzo-go — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-go.md): The 7 public repositories of hanzo-go on GitHub, with their stars, forks, languages and last push.
- [hanzo-inc — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-inc.md): The 2 public repositories of hanzo-inc on GitHub, with their stars, forks, languages and last push.
- [Hanzo — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-io.md): Hanzo business apps. The 9 public repositories of hanzo-io on GitHub, with their stars, forks, languages and last push.
- [Hanzo JS — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-js.md): JavaScript SDK + libraries for Hanzo Ecosystem. The 8 public repositories of hanzo-js on GitHub, with their stars, forks, languages and last push.
- [hanzo-kotlin — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-kotlin.md): The 1 public repositories of hanzo-kotlin on GitHub, with their stars, forks, languages and last push.
- [hanzo-kt — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-kt.md): The 2 public repositories of hanzo-kt on GitHub, with their stars, forks, languages and last push.
- [Hanzo Labs — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-labs.md): Accelerate growth  🚀. The 8 public repositories of hanzo-labs on GitHub, with their stars, forks, languages and last push.
- [hanzo-py — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-py.md): The 1 public repositories of hanzo-py on GitHub, with their stars, forks, languages and last push.
- [hanzo-rs — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-rs.md): The 1 public repositories of hanzo-rs on GitHub, with their stars, forks, languages and last push.
- [hanzo-studio — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-studio.md): Hanzo Studio — AI development environment. The 2 public repositories of hanzo-studio on GitHub, with their stars, forks, languages and last push.
- [hanzo-swift — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-swift.md): The 2 public repositories of hanzo-swift on GitHub, with their stars, forks, languages and last push.
- [hanzo-templates — open source — Hanzo AI](https://hanzo.ai/oss/hanzo-templates.md): The 22 public repositories of hanzo-templates on GitHub, with their stars, forks, languages and last push.
- [Hanzo AI — open source — Hanzo AI](https://hanzo.ai/oss/hanzoai.md): AI infrastructure for the agentic era — LLM gateway, MCP tools, multi-agent SDKs, and dev tools. Techstars '17. The 461 public repositories of hanzoai on GitHub, with their stars, forks, languages and last push.
- [hanzobot — open source — Hanzo AI](https://hanzo.ai/oss/hanzobot.md): Hanzo Bot — AI agent and bot framework. The 2 public repositories of hanzobot on GitHub, with their stars, forks, languages and last push.
- [hanzocd — open source — Hanzo AI](https://hanzo.ai/oss/hanzocd.md): The 1 public repositories of hanzocd on GitHub, with their stars, forks, languages and last push.
- [hanzochat — open source — Hanzo AI](https://hanzo.ai/oss/hanzochat.md): The 1 public repositories of hanzochat on GitHub, with their stars, forks, languages and last push.
- [Hanzo KMS — open source — Hanzo AI](https://hanzo.ai/oss/hanzokms.md): Hanzo KMS — Enterprise Secret Management & Key Infrastructure. The 20 public repositories of hanzokms on GitHub, with their stars, forks, languages and last push.
- [hanzokv — open source — Hanzo AI](https://hanzo.ai/oss/hanzokv.md): Hanzo KV — distributed key-value store. The 3 public repositories of hanzokv on GitHub, with their stars, forks, languages and last push.
- [Hanzo Network — open source — Hanzo AI](https://hanzo.ai/oss/hanzonet.md): Hanzo Network — decentralized AI compute marketplace. The 1 public repositories of hanzonet on GitHub, with their stars, forks, languages and last push.
- [hanzos3 — open source — Hanzo AI](https://hanzo.ai/oss/hanzos3.md): Hanzo S3 — S3-compatible object storage. The 1 public repositories of hanzos3 on GitHub, with their stars, forks, languages and last push.
- [hanzoskill — open source — Hanzo AI](https://hanzo.ai/oss/hanzoskill.md): Hanzo Skills — AI skill modules. The 749 public repositories of hanzoskill on GitHub, with their stars, forks, languages and last push.
- [hanzoui — open source — Hanzo AI](https://hanzo.ai/oss/hanzoui.md): Hanzo UI — React component library (Radix + Tailwind). The 1 public repositories of hanzoui on GitHub, with their stars, forks, languages and last push.
- [hanzozt — open source — Hanzo AI](https://hanzo.ai/oss/hanzozt.md): Hanzo Zero Trust — programmable zero-trust networking for AI infrastructure. The 2 public repositories of hanzozt on GitHub, with their stars, forks, languages and last push.
- [lux-cpp — open source — Hanzo AI](https://hanzo.ai/oss/lux-cpp.md): The 4 public repositories of lux-cpp on GitHub, with their stars, forks, languages and last push.
- [lux-rs — open source — Hanzo AI](https://hanzo.ai/oss/lux-rs.md): The 1 public repositories of lux-rs on GitHub, with their stars, forks, languages and last push.
- [Lux FHE — open source — Hanzo AI](https://hanzo.ai/oss/luxfhe.md): Lux FHE research, examples, and SDK and tooling. The 56 public repositories of luxfhe on GitHub, with their stars, forks, languages and last push.
- [luxfi — open source — Hanzo AI](https://hanzo.ai/oss/luxfi.md): Post-quantum blockchain with multi-consensus, FHE, and cross-chain interoperability. The 344 public repositories of luxfi on GitHub, with their stars, forks, languages and last push.
- [zap-proto — open source — Hanzo AI](https://hanzo.ai/oss/zap-proto.md): The 55 public repositories of zap-proto on GitHub, with their stars, forks, languages and last push.
- [Zen LM — open source — Hanzo AI](https://hanzo.ai/oss/zenlm.md): Frontier language models from 600M to 480B parameters — edge to cloud. Open weights, Zen architecture. The 88 public repositories of zenlm on GitHub, with their stars, forks, languages and last push.
- [ZOO — open source — Hanzo AI](https://hanzo.ai/oss/zooai.md): Protecting endangered species through regenerative finance. The 40 public repositories of zooai on GitHub, with their stars, forks, languages and last push.
- [Oto — Give every moment its sound. | Hanzo Creative AI](https://hanzo.ai/oto.md): Film Foley, immersive sound effects, environmental audio and synchronized scene sound. Request research access and studio workflows.
- [Hanzo Payments — Hanzo AI](https://hanzo.ai/payments.md): One integration, and the processor becomes a routing decision. A switch between your checkout and the companies that move the money.
- [The Zen of Hanzo — 64 patterns for intelligent systems](https://hanzo.ai/philosophy.md): Systems philosophy for open, decentralized AI. Architectural patterns for understandable, adaptive, and human-aligned intelligence.
- [Hanzo Platform — one stack, down to the kernel](https://hanzo.ai/platform.md): Models, agents, applications, data and infrastructure on one operating plane, from GPU kernel to autonomous agent. Run it managed or on infrastructure you control.
- [Playground — try every model in every mode — Hanzo AI](https://hanzo.ai/playground.md): Test and compare every model in the catalog interactively: chat, completions, vision, embeddings, audio, and image generation with real-time cost tracking.
- [Press Resources. — Hanzo AI](https://hanzo.ai/press.md): Everything you need to write about Hanzo AI, Inc. Download our press kit, access brand assets, and find media contacts.
- [Pricing — start free, every model on one bill — Hanzo AI](https://hanzo.ai/pricing.md): Start free with no card. Pro, Max and Team cover every model, Kai and Hanzo Dev on one bill, with a budget on every key. Pay by card, Apple Pay or Google Pay, or fund usage in USDC or USDT.
- [Agents: Workers the company keeps: a model, instructions, tools and a budget — Hanzo AI](https://hanzo.ai/products/agents.md): Workers the company keeps: a model, instructions, tools and a budget.
- [Company: The legal body: formation, cap table, documents and filings, as operations — Hanzo AI](https://hanzo.ai/products/company.md): The legal body: formation, cap table, documents and filings, as operations.
- [Identity: Who is acting — a person, a program or an agent — and what it may reach — Hanzo AI](https://hanzo.ai/products/identity.md): Who is acting — a person, a program or an agent — and what it may reach.
- [Machines: Real computers, leased by the org, for agents and for the software they ship — Hanzo AI](https://hanzo.ai/products/machines.md): Real computers, leased by the org, for agents and for the software they ship.
- [Memory: What the company knows, and when it knew it — Hanzo AI](https://hanzo.ai/products/memory.md): What the company knows, and when it knew it.
- [Models: Every model behind one endpoint and one key — Hanzo AI](https://hanzo.ai/products/models.md): Every model behind one endpoint and one key.
- [Record: Every act on every layer, by a person or an agent, in one trail — Hanzo AI](https://hanzo.ai/products/record.md): Every act on every layer, by a person or an agent, in one trail.
- [Projects — Hanzo AI](https://hanzo.ai/projects.md): Coordinate parallel threads, customize project icons and colors, import from Claude/Codex/Cursor, and create docs, sheets, presentations, images, videos, ads, and emails in one unified workspace.
- [Hanzo PubSub — Hanzo AI](https://hanzo.ai/pubsub.md): Managed NATS with JetStream for durable messaging. At-least-once delivery, key-value stores, object stores, and request-reply patterns.
- [Instant data sync across all clients — Hanzo AI](https://hanzo.ai/realtime.md): Ultra-low latency realtime synchronization engine for collaborative applications, multiplayer experiences, and streaming AI agents.
- [Hanzo Registry — Hanzo AI](https://hanzo.ai/registry.md): Container registry with IAM-token auth. Push, pull, and sign OCI images without rotating long-lived registry passwords.
- [Research Access & Early Access — Hanzo Creative AI, Kai-1.7 & Zen 7 — Hanzo AI](https://hanzo.ai/research-access.md): Apply for private research access to Hanzo Creative AI (Koma, Iro, Mori, Oto, Koe, Uta), Kai-1.7 Decision Intelligence, and Zen 7 foundation reasoning.
- [Work we publish — Hanzo AI](https://hanzo.ai/research.md): Hanzo builds infrastructure that has to hold up under audit, regulation and adversaries.
- [Hanzo Risk](https://hanzo.ai/risk.md): One risk plane for accounts, payments and agents. The compliance face is live; the decide plane is being built.
- [Hanzo S3 — Hanzo AI](https://hanzo.ai/s3.md): Object storage that your existing tools already speak, and you never pay to read your own data back.
- [SDKs for every language — Hanzo AI](https://hanzo.ai/sdks.md): Official SDKs for TypeScript, Python, Go, Rust, and Swift. Integrate Hanzo AI models, autonomous agents, and cloud APIs with type safety.
- [Hanzo Search — keyword and meaning in the same query](https://hanzo.ai/search.md): Hybrid search engine combining full-text lexical search and vector embeddings in a single ranked query. Built for RAG and AI applications.
- [What protects your data, and how. — Hanzo AI](https://hanzo.ai/security.md): Enterprise security architecture: sovereign tenant isolation, edge identity verification, post-quantum cryptography, and immutable audit logs.
- [Hanzo Sentinel — Hanzo AI](https://hanzo.ai/sentinel.md): Automated error tracking, crash reporting, and AI performance monitoring. Detect exceptions, regressions, and slow requests in real time.
- [Hanzo Sign — send a document, get it signed](https://hanzo.ai/sign.md): Open-source electronic signature platform. Legally binding digital document signing with complete audit trails. Self-host or use cloud.
- [Skills — Hanzo AI](https://hanzo.ai/skills.md): Modular agent skills and tool definitions. Equip coding agents with specialized capabilities on demand without context window bloat.
- [Get Hanzo text messages — Hanzo AI](https://hanzo.ai/sms-opt-in.md): Opt in to receive two-factor authentication codes, account and security alerts, and transactional notifications by SMS.
- [Solutions for every team and industry — Hanzo AI](https://hanzo.ai/solutions.md): What Hanzo does for each team, each industry and each kind of work: the workflows it takes over, the products underneath, and what is true about security.
- [Hanzo for AI agents — Hanzo AI](https://hanzo.ai/solutions/agents.md): Define an agent once — model, instructions, tools and a budget — run it by name from anywhere, and read back every step it took.
- [Hanzo for content creation — Hanzo AI](https://hanzo.ai/solutions/content-creation.md): Write, illustrate, narrate and publish from one account — and pay for a render once it finishes, at what it actually cost. A job that fails is not billed.
- [Hanzo for cybersecurity — Hanzo AI](https://hanzo.ai/solutions/cybersecurity.md): Put agents on the queue — the triage, the investigation, the fix — on a platform whose own controls are written down mechanism by mechanism, with every agent action in the audit trail.
- [Hanzo for data teams — Hanzo AI](https://hanzo.ai/solutions/data.md): Put events, tables and documents where agents can query them — and keep every answer tied to the query, the file or the assertion it came from.
- [Hanzo for design teams — Hanzo AI](https://hanzo.ai/solutions/design.md): Explore visuals in a graph you can edit, turn the direction into a working app instead of a mockup, and hand engineering the components they already build with.
- [Hanzo for education — Hanzo AI](https://hanzo.ai/solutions/education.md): Give students a tutor that explains instead of answering, give teachers their evenings back, and give researchers compute billed by the second.
- [Hanzo for engineering teams — Hanzo AI](https://hanzo.ai/solutions/engineering.md): An agent that plans, edits and opens pull requests; one API for every model behind it; and the sandboxes, machines and observability to ship what it writes.
- [Hanzo for finance teams — Hanzo AI](https://hanzo.ai/solutions/finance.md): Agents that reconcile, report and chase, on a ledger that refuses an unbalanced entry — and a record of every run, so the auditor reads what happened instead of asking.
- [Hanzo for financial services — Hanzo AI](https://hanzo.ai/solutions/financial-services.md): Automate onboarding, reconciliation and reporting on a platform that records who did what — person or agent — and keeps each organization’s data in its own store.
- [Hanzo for government — Hanzo AI](https://hanzo.ai/solutions/government.md): Run the whole platform inside your own boundary — on-premises or air-gapped, on open-source software your team can read — and put agents to work on casework, records and requests.
- [Hanzo for healthcare — Hanzo AI](https://hanzo.ai/solutions/healthcare.md): Take documentation, scheduling and research off clinicians’ desks, with patient data kept in your own environment unless a Business Associate Agreement covers it.
- [Hanzo for legal teams — Hanzo AI](https://hanzo.ai/solutions/law.md): Contract review, research and first drafts, with every answer tied to the clause or source it came from — and client content kept out of model training by default.
- [Hanzo for marketing teams — Hanzo AI](https://hanzo.ai/solutions/marketing.md): Go from a brief to a published campaign — copy, images, video and the landing page — and measure it with the same platform that shipped it.
- [Hanzo for operations teams — Hanzo AI](https://hanzo.ai/solutions/operations.md): Turn the checklist nobody wants into a workflow that runs itself, with a budget on every agent and a record of every step it took.
- [Hanzo for research — Hanzo AI](https://hanzo.ai/solutions/research.md): Agents that search the web and your own corpus, read the sources in full, and write answers that cite them — on a memory that knows what was true and when.
- [Hanzo Reserved tier — Hanzo AI](https://hanzo.ai/solutions/reserved.md): Capacity set aside for your organization — dedicated compute and inference for production traffic, or the whole stack on hardware you own — on an agreement sized to your load.
- [Hanzo for retail — Hanzo AI](https://hanzo.ai/solutions/retail.md): Write the catalog, run the storefront, answer customers and measure every change — with agents doing the repetitive part and one platform under all of it.
- [Hanzo for sales teams — Hanzo AI](https://hanzo.ai/solutions/sales.md): Give every rep a bot that researches the account before the call, drafts the follow-up after it, and keeps the CRM current — working in the tools the rep already uses.
- [The Hanzo Startup Program — Hanzo AI](https://hanzo.ai/startups.md): Build frontier AI on the same infrastructure we run in production.
- [Hanzo Stream — Hanzo AI](https://hanzo.ai/stream.md): High-throughput event streaming platform: Kafka protocol compatibility backed by lightweight, distributed NATS JetStream infrastructure.
- [Hanzo Studio — the visual AI engine for generative media](https://hanzo.ai/studio.md): Visual node-graph builder for generative media. Create image, video, audio, and 3D pipelines without code. Open source or cloud managed.
- [Subscribe to Hanzo AI Updates & Developer Newsletter — Hanzo AI](https://hanzo.ai/subscribe.md): Subscribe to product releases, frontier AI models, developer tools, and engineering updates from Hanzo AI.
- [Support — Hanzo](https://hanzo.ai/support.md): Get help with Hanzo — the Help Center, documentation, live system status, and a way to reach a human.
- [Keep tabs on your agents — Hanzo AI](https://hanzo.ai/tabs.md): Interactive web terminals for autonomous coding agents. Multiplex, split, tile, and monitor remote agent shells directly in your browser.
- [Hanzo Team — the workspace for humans and AI — Hanzo AI](https://hanzo.ai/team.md): Your people and your AI agents plan, build, and ship together in one workspace: channels, direct messages, and agents you hand work to with a mention.
- [Hanzo Telemetry — Hanzo AI](https://hanzo.ai/telemetry.md): OpenTelemetry-native data collector and stream pipeline purpose-built for high-throughput AI agent workloads and cloud telemetry.
- [Start from a product — Hanzo AI](https://hanzo.ai/templates.md): Open a finished product, edit it in Hanzo, and bring it into any coding agent you already use.
- [Hanzo Treasury — Hanzo AI](https://hanzo.ai/treasury.md): Automated corporate treasury management: multi-currency cash sweeps, payment reconciliation, yield optimization, and institutional custody.
- [Security you can read — Hanzo AI](https://hanzo.ai/trust.md): Enterprise trust, compliance, and governance at Hanzo. Access controls, audit logging, fail-closed KMS key isolation, and continuous audits.
- [Hanzo Tunnel — Hanzo AI](https://hanzo.ai/tunnel.md): Secure localhost tunnels for development and demos. Expose any local port to a public URL with end-to-end TLS in one command.
- [Hanzo UI — Hanzo AI](https://hanzo.ai/ui.md): Accessible, high-performance React component library and design system tokens for building modern, responsive AI applications and websites.
- [Uta — Compose beyond imagination. | Hanzo Creative AI](https://hanzo.ai/uta.md): Soundtracks, original songs, musical ideas, cue-driven scoring and creative music production. Request research access and studio workflows.
- [Hanzo Visor — Hanzo AI](https://hanzo.ai/visor.md): Provision, configure, monitor, and tear down virtual machines and bare-metal hosts from one API.
- [Hanzo World — Hanzo AI](https://hanzo.ai/world.md): A live map of every model, agent, and AI workload across your organization. Latency, cost, drift and anomalies, shown as they happen.
- [Hanzo ZAP — the Zero-copy Application Protocol](https://hanzo.ai/zap.md): Zero-copy binary RPC protocol for AI agents. In-place wire parsing with zero memory allocation. Libraries for Go, Rust, and TypeScript.
- [The Zen family — Hanzo AI](https://hanzo.ai/zen.md): Open-weight foundation models for agentic coding. Download weights or run Zen 6 and Zen 6 Flash directly on Hanzo Cloud.
- [The complete Zen API catalog — Hanzo AI](https://hanzo.ai/zen/models.md): 45 open foundation models for agentic coding, vision, audio, and reasoning. Run locally or call via Hanzo Cloud from $0.015/MTok.
- [Zen 6 Max — Hanzo AI](https://hanzo.ai/zen/zen6-max.md): One model name. 3.7 trillion parameters across a routed fusion: Enso picks the specialist for each request, with a long context, tools and code.