Create a chat completion | EmpirioLabs AI Docs

curl -X POST https://api.empiriolabs.ai/v1/chat/completions \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "model": "mistral-small-4",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather in Paris?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string"
            }
          },
          "required": [
            "city"
          ]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

{
  "id": "string",
  "object": "chat.completion",
  "created": 1,
  "model": "string",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "string",
        "content": "string",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  }
}

OpenAI-compatible chat completions. Pass any chat-capable model from the catalog as model. Supports streaming (SSE), tool calling, vision input, audio input, JSON mode, structured output, and provider-specific reasoning controls.

Streaming uses Server-Sent Events with data: ... lines and a final data: [DONE].

Authentication

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Request

This endpoint expects an object.

modelstringRequired

messageslist of objectsRequired

streambooleanOptionalDefaults to false

temperaturedoubleOptional0-2

max_tokensintegerOptional

toolslist of objectsOptional

tool_choiceenum or map from strings to anyOptional

response_formatobjectOptional

Constrain the output format on models that advertise structured output. Omit it for normal text. Set { "type": "json_object" } to force a valid JSON object (JSON mode). Set { "type": "json_schema", "json_schema": { "name": "...", "strict": true, "schema": { ... } } } to force output that conforms to a JSON Schema. Support is per model: check the structured_output field and the “Structured Outputs” capability on GET /v1/models/{model}. Sending it to a model that does not support the requested format returns a 400.

enable_thinkingbooleanOptional

Enable model reasoning on models that advertise this parameter.

thinking_budgetintegerOptional>=1

Maximum tokens reserved for model reasoning on models that advertise this parameter.

disable_formattingbooleanOptionalDefaults to false

Return raw upstream response with no server-side formatting.

Response

Completion (or SSE stream when stream=true).

idstringOptional

objectstringOptional

createdintegerOptional

modelstringOptional

choiceslist of objectsOptional

usageobjectOptional

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

429

Too Many Requests Error