Troubleshooting

Streaming chunks not parsing

Use this checklist to diagnose the issue quickly.

Run the test vector to confirm the fix.

Quick start

Base URL
Sanity check request
curl https://api.abliteration.ai/v1/chat/completions \
  -H "Authorization: Bearer $ABLIT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "abliterated-model",
  "messages": [
    { "role": "user", "content": "Reply with: base url fixed." }
  ],
  "temperature": 0.2
}'

Free preview for 5 messages. Sign up to continue.

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.

Symptoms

  • Raw data: lines instead of parsed deltas.
  • Client hangs or never reaches [DONE].
  • JSON parse errors mid-stream.

Fix checklist

  • Ensure stream: true is set in the request payload.
  • Parse data: lines and ignore empty keep-alives.
  • Do not buffer the response body before parsing.

Validate the fix

Run a short prompt and confirm the response includes the expected text.

Validation payload
{
  "model": "abliterated-model",
  "messages": [
    { "role": "user", "content": "Reply with: base url fixed." }
  ],
  "temperature": 0.2
}

Mini playground

Response will appear here.
Expected output should include base url fixed.

Test vector

Expected output should include base url fixed.

Request payload
{
  "model": "abliterated-model",
  "messages": [
    {
      "role": "user",
      "content": "Reply with: base url fixed."
    }
  ],
  "temperature": 0.2,
  "stream": false
}

Common errors & fixes

  • Streaming chunks not parsing: Ensure stream: true is set in the request payload.

Related links