Create a completion | EmpirioLabs AI Docs

OpenAI-compatible prompt completions for clients that send a raw prompt instead of chat messages. Only models that advertise POST /v1/completions in supported_endpoints accept this shape. Streaming uses Server-Sent Events and includes usage when the model service reports it.

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

promptstring or list of stringsRequired

streambooleanOptionalDefaults to false

temperaturedoubleOptional0-2

max_tokensintegerOptional

top_pdoubleOptional0-1

stopstring or list of stringsOptional

logit_biasmap from strings to doublesOptional

Bias token IDs by adding positive or negative values before sampling.

Response

Completion object or SSE stream when stream=true.

idstring

objectstring

createdinteger

modelstring

choiceslist of objects

usageobject

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

429

Too Many Requests Error

$	curl -X POST https://api.empiriolabs.ai/v1/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "qwen3-5-9b",
>	"prompt": "Write one concise launch sentence.",
>	"stream": true,
>	"max_tokens": 64
>	}'

1	{
2	"id": "cmpl-7a9f3b2d4e5f67890abc123def45678",
3	"object": "text_completion",
4	"created": 1712345678,
5	"model": "qwen3-5-9b",
6	"choices": [
7	{
8	"text": "Introducing our revolutionary product that transforms your daily routine effortlessly.",
9	"index": 0,
10	"finish_reason": "stop"
11	}
12	],
13	"usage": {
14	"prompt_tokens": 7,
15	"completion_tokens": 14,
16	"total_tokens": 21
17	}
18	}