Packages

@ai-sdk/fireworks

3.0.97 · 17 Nov 2026Apache-2.0936k / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 2.0.92 – 2.0.987 releases that only update dependencies@ai-sdk/provider-utils 4.0.63@ai-sdk/openai-compatible 2.0.88@ai-sdk/provider 3.0.19Show each
  2. 2.0.91

    30 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.

  3. 2.0.80 – 2.0.9011 releases that only update dependencies@ai-sdk/provider-utils 4.0.56@ai-sdk/openai-compatible 2.0.80@ai-sdk/provider 3.0.18Show each
  4. 2.0.79

    19 Aug 2026
    • fireworks: Enable structured outputs so response_format json_schema is forwarded instead of degrading to json_object

  5. 2.0.73 – 2.0.786 releases that only update dependencies@ai-sdk/openai-compatible 2.0.69@ai-sdk/provider-utils 4.0.46@ai-sdk/provider 3.0.15Show each
  6. 2.0.72

    1 Aug 2026
    • Parse the object error envelope Fireworks actually returns ({"error":{"object","type","code","message"}}) instead of a bare string. The mismatched schema failed to parse, so error messages silently degraded to the HTTP reason phrase — Bad Request over HTTP/1.1, and an empty string over HTTP/2, which has no reason phrase. Fireworks' own message now reaches the caller, e.g. Model not found, inaccessible, and/or not deployed rather than Not Found.

  7. 2.0.63 – 2.0.719 releases that only update dependencies@ai-sdk/provider-utils 4.0.41@ai-sdk/openai-compatible 2.0.63@ai-sdk/provider 3.0.14Show each
  8. 2.0.62

    28 Jun 2026
    • Add serviceTier provider option for Fireworks chat models.

  9. 2.0.60 – 2.0.612 releases that only update dependencies@ai-sdk/provider-utils 4.0.33@ai-sdk/openai-compatible 2.0.54@ai-sdk/provider 3.0.12Show each
  10. 2.0.59

    25 Jun 2026
    • Publish all packages under the @ai-v6 dist tag.

  11. 2.0.58

    24 Jun 2026
    • Add the promptCacheKey provider option for Fireworks prompt cache affinity
      and Kimi K2.6 model autocomplete, and remove the deprecated Kimi K2.5
      serverless model from autocomplete.

  12. 2.0.56

    12 Jun 2026
    • Enable includeUsage for Fireworks so streaming responses report token usage

  13. 2.0.55

    12 Jun 2026
    • Only send provider credentials to same-origin response-supplied URLs

      Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as polling_url, urls.get, result_url, result.sample, or video.uri) and reused the authenticated headers — or appended ?key=<API_KEY> — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.

      A new isSameOrigin helper is added to @ai-sdk/provider-utils, and the affected fetches in @ai-sdk/black-forest-labs, @ai-sdk/fireworks, @ai-sdk/replicate, @ai-sdk/gladia, @ai-sdk/fal, and @ai-sdk/google now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.

  14. 2.0.49 – 2.0.546 releases with no change for you5 dependency updates, 1 without a note@ai-sdk/openai-compatible 2.0.48@ai-sdk/provider-utils 4.0.27Show 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.