# ASI:One Documentation

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.asi1.ai/_mcp/server

## Docs

- [ASI:One Developer Platform](https://docs.asi1.ai/documentation/getting-started/overview.md): An OpenAI-compatible API whose models plan multi-step work and call specialist agents on Agentverse.
- [Developer Quickstart](https://docs.asi1.ai/documentation/getting-started/quickstart.md): Get up and running with ASI:One in minutes. This guide will walk you through setting up your first API request.
- [ASI:One Models](https://docs.asi1.ai/documentation/models.md): Three models that share one API - asi1 is the general default, asi1-ultra goes deeper, asi1-mini goes faster.
- [Chat Completions API](https://docs.asi1.ai/documentation/build-with-asi-one/chat-completions.md): Send a conversation to /v1/chat/completions, read the reply, stream it, and carry history across turns
- [Responses API](https://docs.asi1.ai/documentation/build-with-asi-one/responses.md): Create, stream, retrieve, chain, cancel and delete responses on /v1/responses
- [Tool Calling](https://docs.asi1.ai/documentation/build-with-asi-one/tool-calling.md): Extend ASI:One models with custom functions and real-world actions through tool selection.
- [Reasoning](https://docs.asi1.ai/documentation/build-with-asi-one/reasoning.md): Let ASI:One models think before they answer, and read the reasoning they produce
- [Structured Data](https://docs.asi1.ai/documentation/build-with-asi-one/structured-data.md): Get structured JSON responses from ASI:One using response_format and JSON schemas
- [Planner Mode](https://docs.asi1.ai/documentation/build-with-asi-one/planner.md): Break a complex request into steps that ASI:One plans, executes against agents and tools, and reports on as it goes
- [OpenAI Compatibility](https://docs.asi1.ai/documentation/build-with-asi-one/openai-compatibility.md): Use ASI:One with the OpenAI client libraries - supported parameters, the two endpoints, and ASI:One's own parameters
- [Errors and Rate Limits](https://docs.asi1.ai/documentation/build-with-asi-one/errors.md): The error envelope, what each status code means, and what to retry
- [Agent Chat Protocol](https://docs.asi1.ai/documentation/tutorials/agent-chat-protocol.md): Build agents that understand natural language and interoperate via the Agent Chat Protocol.
- [Using ASI:One with LangChain](https://docs.asi1.ai/documentation/tutorials/langchain.md): Point LangChain at ASI:One and use chat, streaming, structured output and tool calling.

## API Docs

- API Reference > Chat Completions [Create a chat completion](https://docs.asi1.ai/api-reference/chat-completions/create-a-chat-completion.md)
- API Reference > Responses [Create a response](https://docs.asi1.ai/api-reference/responses/create-a-response.md)
- API Reference > Responses [Retrieve a response](https://docs.asi1.ai/api-reference/responses/retrieve-a-response.md)
- API Reference > Responses [Delete a response](https://docs.asi1.ai/api-reference/responses/delete-a-response.md)
- API Reference > Responses [Cancel a response](https://docs.asi1.ai/api-reference/responses/cancel-a-response.md)
- API Reference > Responses [List input items](https://docs.asi1.ai/api-reference/responses/list-input-items.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.asi1.ai/openapi.json)
- [OpenAPI YAML](https://docs.asi1.ai/openapi.yaml)