Skip to main content
POST
/
v1
/
responses
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."
}
'
{
  "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
}

Documentation Index

Fetch the complete documentation index at: https://docs.abliteration.ai/llms.txt

Use this file to discover all available pages before exploring further.

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

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

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

Responses API response

​
id
string
required
​
object
enum<string>
required
Available options:
response
​
status
string
required
​
model
string
required
​
created_at
integer
​
output
object[]
​
usage
object
​
remaining_credits
integer | null
​
estimated_credits_used
integer
​
estimated_cost_usd
number
Last modified on May 2, 2026