Model

abliterated-model

Model ID: abliterated-model. Use this exact value in the model field of your requests.

Benchmark scores and refusal rate for the model are listed below.

Quick start

Base URL
Example request
{
  "model": "abliterated-model",
  "messages": [
    { "role": "user", "content": "Summarize this report in one paragraph." }
  ],
  "temperature": 0.2
}

Service notes

  • Pricing model: Usage-based pricing (~$5 per 1M tokens) billed on total tokens (input + output). See the API pricing page for current plans.
  • Data retention: No prompt/output retention by default. Operational telemetry (token counts, timestamps, error codes) is retained for billing and reliability.
  • Compatibility: OpenAI-style /v1/chat/completions request and response format with a base URL switch.
  • Latency: Depends on model size, prompt length, and load. Streaming reduces time-to-first-token.
  • Throughput: Team plans include priority throughput. Actual throughput varies with demand.
  • Rate limits: Limits vary by plan and load. Handle 429s with backoff and respect any Retry-After header.

Pricing at a glance

Effective price: ~$5 per 1M tokens (based on $10 for ~2M tokens).

Billing uses total tokens (input + output). Image inputs are metered as token equivalents and count as input tokens.

Subscription credits reset monthly and do not roll over. Prepaid credits are one-time and do not expire.

See the pricing page for current plans.

Model specs

Latest published benchmark scores and refusal rate for abliterated-model.

Metric Score
mmlu_pro 82.1
gpqa 73.1
aime_2025 83.7
mmmu_pro 68.1
refusals (mlabonne/harmful_behaviors) 3/100

Common errors & fixes

  • 401 Unauthorized: Check that your API key is set and sent as a Bearer token.
  • 404 Not Found: Make sure the base URL ends with /v1 and you call /chat/completions.
  • 400 Bad Request: Verify the model id and that messages are an array of { role, content } objects.
  • 429 Rate limit: Back off and retry. Use the Retry-After header for pacing.

Related links