Fenno API
Fenno API provides a common entry point for models available to your account through OpenAI-compatible, Anthropic Messages and Gemini protocols. Configure the endpoint, credentials and exact model ID, then verify the capabilities required by your application.
Connect compatible coding tools and backend applications. Model access, supported features and usage depend on the selected model and your account.
First request in five minutes: create a key, point your SDK at Fenno, run a completion.
Auth headers and SDK setup for the OpenAI, Anthropic and Gemini protocols.
Reasoning, multimodal input, tool calls, structured output, prompt caching and image generation.
Chat Completions, Responses, Embeddings, image generation and more.
Base URL
| Protocol | Base URL |
|---|---|
| OpenAI compatible | https://api.fenno.ai/v1 |
| Anthropic native | https://api.fenno.ai |
| Gemini native | https://api.fenno.ai |
Native Anthropic and Gemini SDKs append their own versioned path (/v1/messages,
/v1beta/models/*), so point them at the host without /v1. OpenAI-compatible clients expect
the version in the base URL, so use https://api.fenno.ai/v1.
Supported protocols
| Protocol | Typical callers | Path prefix |
|---|---|---|
| OpenAI compatible | OpenAI SDK, Codex, Cline, OpenCode, LangChain | /v1/* |
| Anthropic native | Claude Code, Anthropic SDK | /v1/messages |
| Gemini native | Gemini CLI, Google GenAI SDK | /v1beta/models/* |
Next steps
- New to Fenno? Start with Quickstart.
- Already have a key? Read Authentication.
- Debugging? See Errors & retries.
Read by task
- Render incremental answers: streaming.
- Execute application operations: function calling, with server-side authorization.
- Extract machine-readable data: structured output.
- Analyze images or build retrieval: vision, embeddings.
- Operate reliably: caching, costs, rate limits.
The guide explains complete tasks; the API reference looks up protocol fields, responses and errors without duplicating the tutorials.