Responses API

Reference for POST /v1/responses.

Responses API

The Responses API provides an alternative interface based on the OpenAI Responses API format. It offers the same Forge routing, memory, and security capabilities as Chat Completions but uses a different request/response structure that is better suited for single-turn interactions and tool-use workflows.

Endpoint

POST /v1/responses

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID or `"auto"`
`input`	string\|array	Yes	Input text or array of input items
`instructions`	string	No	System instructions
`tools`	array	No	Tool definitions
`temperature`	number	No	Sampling temperature
`max_output_tokens`	integer	No	Maximum output tokens
`forge`	object	No	Forge extensions (same as Chat Completions)

Example Request

curl -X POST https://api.optima-forge.com/v1/responses \
  -H "Authorization: Bearer $FORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "input": "Summarize the key features of Optima Forge.",
    "instructions": "Be concise. Use bullet points.",
    "max_output_tokens": 300
  }'

Response Format

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1709000000,
  "model": "claude-sonnet-4-20250514",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Key features of Optima Forge:\n- Intelligent multi-provider routing..."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 18,
    "output_tokens": 95,
    "total_tokens": 113
  }
}

Chat Completions

Features API

Back to all documentation