Chat completions

POST /v1/chat/completions

Returns a model's reply to a list of messages, as one JSON object or as server-sent events.

Parameters

Other OpenAI chat completions fields pass to the model unchanged. The request body is limited to 32 MB. Each model's page lists its support for thinking, tools and response_format: Models.

Headers

A non-streamed request without a response after about 100 s fails with 524. Stream long requests, and keep X-LLM-Wait below 90 on non-streamed requests.

Request

curl https://api.albastov.com/v1/chat/completions \
  -H "Authorization: Bearer $ALBASTAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b",
    "messages": [
      {"role": "user", "content": "Say hello in four words."}
    ],
    "chat_template_kwargs": {"enable_thinking": false},
    "max_tokens": 50
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.albastov.com/v1",
    api_key=os.environ["ALBASTAR_API_KEY"],
)
reply = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "Say hello in four words."}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
    max_tokens=50,
)
print(reply.choices[0].message.content)

const res = await fetch("https://api.albastov.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ALBASTAR_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.8-27b",
    messages: [{ role: "user", content: "Say hello in four words." }],
    chat_template_kwargs: { enable_thinking: false },
    max_tokens: 50,
  }),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const reply = await res.json();
console.log(reply.choices[0].message.content);

Response

200, Content-Type: application/json, an OpenAI chat.completion object.

{
  "id": "chatcmpl-b50af0eb9c5d02d9",
  "object": "chat.completion",
  "created": 1793305215,
  "model": "qwen3.8-27b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, my friend.",
        "reasoning": null
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 7,
    "total_tokens": 25,
    "prompt_tokens_details": {"cached_tokens": 0},
    "completion_tokens_details": {"reasoning_tokens": 0}
  }
}

Responses may carry further OpenAI extension fields, most with null values. Ignore unknown fields.

Streamed response

With "stream": true: 200, Content-Type: text/event-stream. Each event is one data: line with a chat.completion.chunk object, then a blank line.

In an engine_restarted error event, code is the number 502: read type.

Errors

Errors use the OpenAI format, {"error": {"message", "type", "code", ...}}, with Content-Type: application/json. Branch on code.

A request the model rejects, such as a prompt over the context length, returns 400 with the model's own error type; code equals type.

{
  "error": {
    "message": "Loading qwen3.8-27b; retry in 150 s",
    "type": "model_loading",
    "code": "model_loading",
    "model": "qwen3.8-27b",
    "state": "starting",
    "retry_after_s": 150
  }
}

{
  "error": {
    "message": "Queued (1 ahead); retry in 30 s",
    "type": "queued",
    "code": "queued",
    "model": "qwen3.8-27b",
    "position": 1,
    "retry_after_s": 30,
    "reason": "queued behind other work"
  }
}

retry_after_s equals Retry-After. reason on queued and gpu-busy is queued behind other work or another model is in use; on other codes reason is readable text and varies. Every 429 except rate_limited and every 503 except device_offline carries Retry-After; retry model_loading, queued, gpu-busy, insufficient_memory and device_busy after Retry-After seconds. llm-unavailable and gpu-busy are in kebab-case among the snake_case codes of this route (known issue: Errors).