One API for models, agents and tools
Every Hanzo capability answers under one base URL, behind one key.
curl -X POST \https://api.hanzo.ai
A completion from any model your organization can reach, streamed or buffered. Model ids come from the catalog, so the list is a request rather than a page in the docs.

Paste and ship
Paste this into any agent. It reads the skill manifest and calls API from there.
Read https://hanzo.ai/skill.md and use Hanzo API in my project.How it fits together
One key, one bill
A single key authenticates every endpoint, and usage meters to the organization it belongs to. Spend is attributed in one place instead of once per service.
Identity is the gateway’s to state
Every request passes a gateway that throws away the identity headers a client sent and writes them again from the verified token. Nothing downstream has to wonder whether an org id came from a token or from a curl flag.
Generated, not hand-written
The clients come from the OpenAPI document this API serves, and their method names are its operation ids. A client is checkable against a release rather than against somebody’s memory.
Every route lives under /v1
Every route lives under
/v1, and every service answers on the same host — there is no second base URL to configure and no v2 waiting to break the first one. Rate limits are applied per caller and across the edge as a whole; a rejected request comes back as a429with aRetry-Afterrather than a dropped connection.
Base URL
Authenticate with a bearer token: Authorization: Bearer <your key>. Keys are created and revoked in the console, and revoking one there is what stops it working.
Endpoint
curl -X POST https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer <your key>"Core endpoints
A few of the ones people reach for first. Every parameter and error shape is in the reference.
A completion from any model your organization can reach, streamed or buffered. Model ids come from the catalog, so the list is a request rather than a page in the docs.
DocsStateful multi-turn responses with built-in tool calling, structured outputs, reasoning traces, and server-managed conversation state.
DocsSub-10ms structured classification, routing, scoring, and guardrail decisions powered by Kai at a fraction of LLM cost.
DocsGenerate cinematic video with synchronized audio and camera motion from text or reference frames via Koma.
DocsPhotorealistic image generation, inpainting, and layout-accurate typography rendering via Iro.
DocsLow-latency neural speech synthesis, voice cloning, transcription, foley sound effects, and full-track music generation via Koe, Oto, and Uta.
DocsTextured 3D meshes and spatial world assets generated from text prompts or multi-view images via Mori.
DocsVectors for search, retrieval and clustering, from the same key and the same bill as generation.
DocsWhat your organization may call right now — every model we serve plus any provider account you have connected, with their identifiers and pricing.
DocsDefine an agent once, run it by reference, and read its runs afterwards. The definition lives here, so everything that runs it runs the same one.
DocsAST-indexed symbol search, repository context assembly, and semantic codebase Q&A across your organization’s repositories.
DocsLease isolated microVM sandboxes with filesystem, terminal WebSocket, headless browser screen streaming, and sub-second startup.
DocsClean markdown extraction from any live web page and structured real-time web search for RAG and agent research.
DocsWhat is left, and what was spent. Usage is recorded per call and attributed to the organization on the token, so a bill can be traced back to the request that caused it.
DocsThe tools your organization can call over REST or MCP. An agent picks from this list, and so can you — it is the same catalog either way.
Docs
Every Hanzo capability answers under one base URL, behind one key.