OTHER · CHANGELOG

Changelog

Notable platform and API changes. Webhook subscribers also receive billing.rate_change and model.deprecation_announced events for anything that affects pricing or availability.

  1. 2026-04-22added

    Qwen 3.6 27B is GA

    Strong on multilingual code and tool calling. Available at fp16, fp8, and int4.

  2. 2026-04-08changed

    Default quantization for DeepSeek V4 Pro is now fp8

    Calibrated evals show < 0.5% delta vs fp16 on MMLU-redux, GSM8K, and HumanEval-Plus. Throughput is up ~1.7×, per-token price unchanged. Pin fp16 explicitly if you need parity with published benchmarks.

  3. 2026-03-22changed

    Webhook retries follow exponential backoff

    Retry schedule moved from a flat 5-minute interval to: 0s, 30s, 2m, 10m, 1h, 3h, 6h, 12h, 24h. Total window is unchanged at ~24h. The Hoonify-Delivery header now increments per attempt for log correlation.

  4. 2026-02-26fixed

    Stale Retry-After when behind some proxies

    Fixed a regression where Retry-After was rounded to the nearest minute on some egress paths, causing clients to back off harder than necessary. SDKs now see fractional second values again.

  5. 2026-02-12deprecated

    Gemma 3 27B is sunset

    Hoonify is removing Gemma 3 27B on 2026-05-15. Gemma 4 31B at fp16 is the recommended replacement and is consistently ahead on capability evals at comparable throughput cost. The API returns a deprecation field; webhook event model.deprecation_announced has fired.

  6. 2026-02-04security

    API key prefix

    New key format: hoon_sk_live_. Existing keys stay valid until 2026-08-01. Rotate at your own pace via the API keys page.

  7. 2026-01-20added

    system_fingerprint in response body

    Every chat completion now returns a system_fingerprint. Stable while the operator setup, model, and quantization are unchanged — useful for caching and reproducibility.

Related: Webhooks