Packages

@ai-sdk/replicate

3.0.85 · 17 Nov 2026Apache-2.0111.4k / weekRepositoryHomepagenpmAtom feed

Your version

234 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.

  1. 3.0.84

    13 Nov 2026
    • Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.

  2. 3.0.78 – 3.0.835 releases that only update dependencies@ai-sdk/provider-utils 5.0.81@ai-sdk/provider 4.0.38Show each
  3. 3.0.77

    6 Nov 2026
    • Refactor Replicate model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Request behavior is unchanged.

    • replicate: Cancel abandoned image predictions on abort or poll timeout

      Image generations that were abandoned — the caller aborted via abortSignal or polling gave up after maxPollAttempts — stopped polling but left the prediction running on Replicate, where it kept consuming compute. The image model now sends a best-effort cancel request to POST /predictions/{prediction_id}/cancel in those cases. The cancel URL is built from the configured base URL instead of the response body's urls.cancel, so configured credentials are only sent to the provider origin. Cancellation uses only the provider headers, never reuses the aborted signal, is never retried, and never replaces the abort or timeout error.

  4. 3.0.76

    5 Nov 2026
    • Pass through seed: 0 instead of dropping it in image and video models. KlingAI now reports seed: 0 as an unsupported setting like any other seed.

  5. 3.0.74 – 3.0.752 releases that only update dependencies@ai-sdk/provider-utils 5.0.74Show each
  6. 3.0.73

    30 Oct 2026
    • Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

      The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

  7. 3.0.67 – 3.0.726 releases that only update dependencies@ai-sdk/provider-utils 5.0.71@ai-sdk/provider 4.0.34Show each
  8. 3.0.66

    21 Oct 2026
    • Defer construction of provider validation schemas until first use to reduce package import time.

  9. 3.0.53 – 3.0.6513 releases that only update dependencies@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64Show each
  10. 3.0.52

    28 Sep 2026
    • Use standards-compliant User-Agent header

  11. 3.0.51

    28 Sep 2026
    • provider: Advertise image model file and mask input support

      Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.

      Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.

  12. 3.0.46 – 3.0.504 releases that only update dependencies@ai-sdk/provider-utils 5.0.49@ai-sdk/provider 4.0.18Show each
  13. 3.0.45

    18 Sep 2026
    • replicate: Poll image predictions that exceed the synchronous wait duration

  14. 3.0.43

    16 Sep 2026
    • Keep default Node.js downloads protected by DNS validation and connection pinning when frameworks or instrumentation wrap global fetch before or after the SDK loads.

  15. 3.0.34 – 3.0.429 releases that only update dependencies@ai-sdk/provider 4.0.15@ai-sdk/provider-utils 5.0.41Show each

A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.