Create a response

Creates a response using the OpenAI Responses API format. Set stream: true for server-sent events.

POST /v1/responses

cURL

basic

curl --request POST \
  --url https://api.abliteration.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "abliterated-model",
  "input": "Write one sentence about Stonehenge."
}
'

200

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1735958400,
  "status": "completed",
  "model": "abliterated-model",
  "output": [
    {
      "id": "msg_abc123",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Stonehenge is a prehistoric monument in Wiltshire, England.",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 14,
    "output_tokens": 10,
    "total_tokens": 24
  },
  "remaining_credits": 487,
  "estimated_credits_used": 1,
  "estimated_cost_usd": 0.00012
}

{
  "error": "<string>",
  "code": "<string>"
}

{
  "error": "<string>",
  "code": "<string>"
}

{
  "error": "<string>",
  "code": "<string>"
}

{
  "error": "<string>",
  "code": "<string>"
}

{
  "error": "<string>",
  "code": "<string>"
}

Authorizations

Authorization · string · header · required

Use a JWT or abliteration.ai API key as a Bearer token.

Headers

X-Free-Tier · enum<string>

Set to true to use the single anonymous free request.

Available options: true

Body

application/json

model · string · required

Model id.

input · string (string | object)[]

Plain text input or a structured Responses API input array.

instructions · string

Optional system-style instruction.

stream · boolean · default: false

temperature · number

Required range: 0 <= x <= 2

max_output_tokens · integer

Required range: x >= 1

tools · object[]

Tool definitions passed through to the upstream Responses implementation.

tool_choice · string object

Controls whether the model may call tools.

flagged_categories · string[]

Optional moderation categories to block for this request. Supported: harassment, hate, illicit, sexual. Self-harm and sexual/minors are always blocked.

Response

200

application/json

Responses API response

id · string · required

object · enum<string> · required

Available options: response

status · string · required

model · string · required

created_at · integer

output · object[]

Show child attributes

usage · object

Show child attributes

remaining_credits · integer | null

estimated_credits_used · integer

estimated_cost_usd · number