Text completions — POST /v1/completions

The text completions endpoint is a legacy OpenAI-compatible endpoint that generates a continuation of a raw text prompt rather than a structured message history. It is routed through the same provider dispatch pipeline as chat completions, so the same attestation headers and streaming format apply. For most use cases, prefer POST /v1/chat/completions, which is the actively developed endpoint with full tool-call and response-format support.

Authentication

All inference endpoints require a Bearer token:

Authorization: Bearer eigeninference-...

Request

string

required

The model ID to use. See Models for the list of available IDs.

string

required

The input text to complete.

integer

Maximum number of tokens to generate. Defaults to 8192 if not set.

number

Sampling temperature between 0 and 2.

boolean

default:"false"

When true, returns the response as SSE chunks ending with data: [DONE].

Example

cURL

curl https://api.darkbloom.dev/v1/completions \
  -H "Authorization: Bearer eigeninference-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5-27b-claude-opus-8bit",
    "prompt": "The capital of France is",
    "max_tokens": 16
  }'

Inference

Account

Network

Text completions — POST /v1/completions

Authentication

Request

Example

​Authentication

​Request

​Example

Authentication

Request

Example