Completions API

Overview

This /v1/completions endpoint is a legacy prompt-based completions API with no currently active model (GPT-5.4 Pro has been retired). For the new GPT-5.4 / GPT-5.5, use the Responses API (/v1/responses) — see /docs/codex. For ordinary chat models, use /v1/messages or /v1/chat/completions (see /docs/llm).

Endpoint

Available Models

Prices are per 1M tokens

Request Parameters

Basic Request

curl -X POST https://api.apimodels.app/v1/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-pro",
    "prompt": "Write a detailed analysis of quantum computing:",
    "max_tokens": 1024
  }'

Response

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1700000000,
  "model": "gpt-5.4-pro",
  "choices": [
    {
      "text": "Quantum computing leverages the principles of quantum mechanics...",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 256,
    "total_tokens": 268
  }
}

Streaming

Set stream: true to receive Server-Sent Events (SSE).

curl -X POST https://api.apimodels.app/v1/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-pro",
    "prompt": "Explain the theory of relativity:",
    "max_tokens": 1024,
    "stream": true
  }'

Billing

Credits are calculated based on actual token usage:

Cost = (prompt_tokens * input_price + completion_tokens * output_price) / 1,000,000
Credits = Cost  // amounts are in USD ($)

Error Codes