Chat completions

POST /v1/chat/completions

Request body

Field	Type	Required	Description
`model`	string	required	Canonical model id, e.g. `anthropic/claude-sonnet-4-6`.
`messages`	array	required	OpenAI messages. `content` is a string or a multimodal array (vision). Roles: system, user, assistant, tool.
`stream`	boolean	default: false	Stream SSE `chat.completion.chunk` events.
`temperature`	number	default: 0.7	Sampling temperature, 0–2.
`max_tokens`	integer	default: 256	Max output tokens.
`top_p`	number	default: 1.0	Nucleus sampling.
`stop`	string \| array	optional	Stop sequence(s).
`n`	integer	default: 1	Number of choices.
`presence_penalty`	number	default: 0	−2 to 2.
`frequency_penalty`	number	default: 0	−2 to 2.
`tools`	array	optional	Function/tool definitions. See tool calling. AIx selects a compatible execution path.
`tool_choice`	string \| object	optional	`auto` · `none` · `required` · a specific function.
`response_format`	object	optional	`{"type":"json_object"}` or `json_schema`. See structured outputs.

Example

curl https://api.aix.theaimart.co/v1/chat/completions \
  -H "Authorization: Bearer $AIX_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "deepseek-ai/DeepSeek-V3.2",
        "messages": [{"role":"user","content":"hi"}] }'

client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",
    messages=[{"role": "user", "content": "hi"}],
)

await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V3.2",
  messages: [{ role: "user", content: "hi" }],
});

Try it

Try it Runs a live request with your key — stored only in this browser.

API key Model

Prompt

Response — `chat.completion`

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "created": 1718900000,
  "model": "deepseek-ai/DeepSeek-V3.2",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "…", "tool_calls": [] },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 12, "total_tokens": 21 }
}

The response preserves the standard chat.completion shape, including tool_calls, logprobs and structured-output results when supported by the selected model.

Streaming

With stream: true the response is text/event-stream of chat.completion.chunk events, terminated by data: [DONE]. See Streaming.

Errors

400 unsupported model / bad params · 401/403 auth · 402 insufficient credits · 429 rate limit · 503 no healthy route available. See Errors.

← Overview

Messages →