> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# POST /v1/chat/completions

> OpenAI-compatible chat completions with streaming, tools, and full passthrough or conversion.

# POST /v1/chat/completions

The primary chat endpoint. Fully OpenAI compatible.

**Base URL**

```
POST https://api.openference.com/v1/chat/completions
```

## Minimal example

```json theme={null}
{
  "model": "your-model-name",
  "messages": [
    {"role": "user", "content": "Explain edge computing in one sentence."}
  ]
}
```

## Authentication

```http theme={null}
Authorization: Bearer YOUR_API_KEY
```

## Streaming

```json theme={null}
{
  "model": "your-model-name",
  "messages": [{"role": "user", "content": "Count to 5 slowly."}],
  "stream": true
}
```

You receive standard OpenAI SSE chunks ending in `data: [DONE]`.

## Tool calling (function calling)

Request:

```json theme={null}
{
  "model": "your-model-name",
  "messages": [{"role": "user", "content": "What's the weather in Paris?"}],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": { "type": "string" }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}
```

The assistant message may contain `tool_calls`. You then send back a `tool` role message with `tool_call_id`.

Openference passes these through (or converts) to the upstream format automatically.

## Temperature, max\_tokens, top\_p, etc.

All standard sampling parameters are forwarded.

## Format conversion

If the upstream for your chosen model uses Anthropic or Gemini, Openference converts the request and response shapes transparently.

You can send OpenAI format to a Claude model and get back OpenAI-shaped output.

## Model restrictions & 403

If the key is restricted, only allowed models accept traffic.

## See also

* [Anthropic messages](/api-reference/messages)
* [Errors](/api-reference/errors)
* [Rate limits](/api-reference/rate-limits)
* [Client integrations](/integrations/cursor)