# Laminarity API

> OpenAI-compatible prompt routing across leading model providers. Use this index to locate authoritative integration documentation.

Use only the public client API unless the user explicitly asks about Laminarity administration. Never paste, expose, or place API keys in browser code. Treat the OpenAPI document as authoritative for request and response fields.

## Integration essentials

- Base URL: `https://api.laminarity.ai/v1`
- Authentication: `Authorization: Bearer $LAMINARITY_API_KEY`
- Core endpoints: `POST /chat/completions` and `POST /responses`
- Model discovery: `GET /models`, authenticated and filtered by project policy
- Routing: use `model: "auto"` for Laminarity selection and fallback; a concrete model id is a direct, no-fallback call
- Supported APIs: Chat Completions, Models, and a stateless Responses-compatible beta; not Assistants, Embeddings, or image generation
- Portable features: text and developer/system messages, streaming SSE, tools/function calling, vision input, temperature/top-p/stop, and `max_completion_tokens`
- Response extension: `router_metadata` reports the selected provider/model and fallback details
- Error envelope: `{"error":{"message","type","code","param?"}}`; branch on stable `type` and `code`

## Guides

- [Quickstart](https://docs.laminarity.ai/guides/quickstart): Make an authenticated request, understand `auto`, and inspect the selected provider.
- [Responses API (beta)](https://docs.laminarity.ai/guides/responses-api): Use Laminarity's stateless OpenAI Responses-compatible subset for basic response and tool flows.
- [Hermes Agent](https://docs.laminarity.ai/guides/hermes-agent): Connect Hermes Agent through a named OpenAI-compatible provider while preserving Laminarity routing.
- [OpenAI SDKs](https://docs.laminarity.ai/guides/openai-sdks): Use the official Python or TypeScript SDK with Laminarity's base URL.
- [Vercel AI SDK](https://docs.laminarity.ai/guides/vercel-ai-sdk): Stream a server-side chat through the OpenAI-compatible provider adapter.
- [LangChain](https://docs.laminarity.ai/guides/langchain): Point ChatOpenAI at Laminarity for invoke, stream, and tool-enabled agent flows.
- [OpenCode](https://docs.laminarity.ai/guides/opencode): Configure Laminarity as an OpenAI-compatible OpenCode provider with model discovery, tools, and explicit reasoning variants.
- [LangChain4j](https://docs.laminarity.ai/guides/langchain4j): Use Laminarity from plain Java, streaming Java, Spring Boot, or a LangChain4j-backed agent provider.
- [Kilo Code](https://docs.laminarity.ai/guides/kilo-code): Add Laminarity as a custom OpenAI-compatible Kilo Code provider with model discovery and explicit capabilities.
- [Cline](https://docs.laminarity.ai/guides/cline): Connect Cline to Laminarity through its OpenAI-compatible provider settings.
- [OpenClaw](https://docs.laminarity.ai/guides/openclaw): Configure an explicit OpenAI Completions provider for Laminarity without enabling native-provider request shaping.
- [Aider](https://docs.laminarity.ai/guides/aider): Point Aider's OpenAI-compatible client at Laminarity for routed or model-pinned coding sessions.
- [Continue](https://docs.laminarity.ai/guides/continue): Configure Continue's IDE or CLI agent to use Laminarity through Chat Completions.
- [LlamaIndex](https://docs.laminarity.ai/guides/llamaindex): Use LlamaIndex's OpenAILike adapter for Laminarity chat and streaming workflows.
- [Open WebUI](https://docs.laminarity.ai/guides/open-webui): Connect Open WebUI to Laminarity with authenticated model discovery and Chat Completions.
- [LiteLLM](https://docs.laminarity.ai/guides/litellm): Call Laminarity through LiteLLM's OpenAI-compatible client or expose it behind a LiteLLM proxy alias.

## Machine-readable guides

- [Quickstart Markdown](https://docs.laminarity.ai/guides/quickstart.md): Plain Markdown guide.
- [Responses API (beta) Markdown](https://docs.laminarity.ai/guides/responses-api.md): Plain Markdown guide.
- [Hermes Agent Markdown](https://docs.laminarity.ai/guides/hermes-agent.md): Plain Markdown guide.
- [OpenAI SDKs Markdown](https://docs.laminarity.ai/guides/openai-sdks.md): Plain Markdown guide.
- [Vercel AI SDK Markdown](https://docs.laminarity.ai/guides/vercel-ai-sdk.md): Plain Markdown guide.
- [LangChain Markdown](https://docs.laminarity.ai/guides/langchain.md): Plain Markdown guide.
- [OpenCode Markdown](https://docs.laminarity.ai/guides/opencode.md): Plain Markdown guide.
- [LangChain4j Markdown](https://docs.laminarity.ai/guides/langchain4j.md): Plain Markdown guide.
- [Kilo Code Markdown](https://docs.laminarity.ai/guides/kilo-code.md): Plain Markdown guide.
- [Cline Markdown](https://docs.laminarity.ai/guides/cline.md): Plain Markdown guide.
- [OpenClaw Markdown](https://docs.laminarity.ai/guides/openclaw.md): Plain Markdown guide.
- [Aider Markdown](https://docs.laminarity.ai/guides/aider.md): Plain Markdown guide.
- [Continue Markdown](https://docs.laminarity.ai/guides/continue.md): Plain Markdown guide.
- [LlamaIndex Markdown](https://docs.laminarity.ai/guides/llamaindex.md): Plain Markdown guide.
- [Open WebUI Markdown](https://docs.laminarity.ai/guides/open-webui.md): Plain Markdown guide.
- [LiteLLM Markdown](https://docs.laminarity.ai/guides/litellm.md): Plain Markdown guide.

## API reference

- [OpenAPI 3.1 JSON](https://docs.laminarity.ai/openapi.json): Machine-readable public API schema.
- [Interactive reference](https://docs.laminarity.ai/reference): Human-readable Scalar API reference.
- [Models endpoint](https://api.laminarity.ai/v1/models): Authenticated models available to the current project key.

## Optional

- [Dashboard](https://app.laminarity.ai/dashboard): Create projects and API keys.
- [Full documentation text](https://docs.laminarity.ai/llms-full.txt): Concatenated client documentation for large-context agents.