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

# Chat completions

> OpenAI-compatible chat endpoint.

Use `/v1/chat/completions` for OpenAI-compatible text generation.

```bash theme={null}
curl https://apiany.ai/v1/chat/completions \
  -H "Authorization: Bearer $APIANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      { "role": "system", "content": "You are concise." },
      { "role": "user", "content": "Explain API aggregation in one sentence." }
    ],
    "temperature": 0.7
  }'
```

## Streaming

Set `stream: true` to receive server-sent events. Each event is an OpenAI
`chat.completion.chunk`, and the stream ends with `data: [DONE]`.

```bash theme={null}
curl https://apiany.ai/v1/chat/completions \
  -H "Authorization: Bearer $APIANY_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "gpt-5.4",
    "messages": [{ "role": "user", "content": "Hello" }],
    "stream": true
  }'
```

## Parameters

OpenAI-standard parameters are accepted, including `temperature`, `top_p`,
`max_tokens`, `max_completion_tokens`, `stop`, `n`, `frequency_penalty`, `presence_penalty`, `seed`,
`response_format`, `tools`, `tool_choice`, `logprobs`, `top_logprobs`,
`logit_bias`, `user`, and `stream`.

## Kimi K3 compatibility

`kimi-k3` uses the same OpenAI-compatible endpoint, but its native contract has
model-specific rules:

* K3 always reasons. Use top-level `reasoning_effort: "max"`; the K2.x
  `thinking` object is accepted only as an enabled compatibility alias.
* Prefer `max_completion_tokens`. APIAny accepts deprecated `max_tokens` and
  converts it only when the selected route targets Kimi K3. If no limit is provided, Kimi's
  official default is used. The explicit maximum is 1,048,576 tokens.
* K3 sampling is fixed by the provider. APIAny removes `temperature`, `top_p`,
  `frequency_penalty`, and `presence_penalty` only for K3; `n` must be `1`.
* `reasoning_content` is the reasoning trace and `content` is the final answer.
  Streaming returns them as separate deltas. Do not merge the reasoning trace
  into the final answer.
* Replay the complete assistant message, including `reasoning_content` and
  `tool_calls`, in multi-turn and tool-calling requests.
* The last assistant message may use `partial: true`. A content-less system
  message may carry `tools` to load K3 tools dynamically.
* K3 image/video content blocks must use a Base64 `data:` URL or an `ms://`
  file ID. Public HTTP media URLs are rejected before the model request is sent.

```bash theme={null}
curl https://apiany.ai/v1/chat/completions \
  -H "Authorization: Bearer $APIANY_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "kimi-k3",
    "messages": [{"role": "user", "content": "Prove that sqrt(2) is irrational."}],
    "reasoning_effort": "max",
    "max_completion_tokens": 16384,
    "stream": true
  }'
```

If `finish_reason` is `length`, the output budget was exhausted. The response
is still OpenAI-compatible, but the final answer may be missing or incomplete;
increase `max_completion_tokens` or reduce the input before retrying.

## Notes

* The `model` is a public APIAny.AI model ID.
* Token usage is normalized into the OpenAI-style `usage` object when usage data is available.