Packages

@ai-sdk/openai-compatible

3.0.93 · 17 Nov 2026Apache-2.014.4M / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 2.0.85

    16 Oct 2026
    • openai-compatible: Support URL-based image responses

      Add opt-in URL validation and credential origin handling to getFromApi for URL-based image responses. Validate redirect targets, strip unsafe request headers, and drop credentials on cross-origin redirects while preserving existing unvalidated requests.

  2. 2.0.81 – 2.0.844 releases that only update dependencies@ai-sdk/provider 3.0.19@ai-sdk/provider-utils 4.0.60Show each
  3. 2.0.80

    28 Sep 2026
    • provider-utils: Preserve streamed tool calls with unreliable IDs and indices

  4. 2.0.76 – 2.0.794 releases that only update dependencies@ai-sdk/provider 3.0.18@ai-sdk/provider-utils 4.0.55Show each
  5. 2.0.75

    9 Sep 2026
    • openai-compatible: Keep reasoning streams contiguous when deltas include empty tool call arrays

    • openai: Return an AI SDK error for empty chat completion choices

  6. 2.0.74

    30 Aug 2026
    • Support text and thinking parts in array-based chat completion content while ignoring unknown part types.

  7. 2.0.71 – 2.0.733 releases that only update dependencies@ai-sdk/provider-utils 4.0.49Show each
  8. 2.0.70

    21 Aug 2026
    • openai-compatible: Report truncated chat streams as errors

  9. 2.0.69

    18 Aug 2026
    • openai-compatible: Preserve unmapped usage fields in usage.raw

      usage.raw is specified as usage "in the shape that the provider returns",
      and the chat model already parsed the usage object loosely so that extra
      top-level fields survived. The nested prompt_tokens_details and
      completion_tokens_details objects were still strict, so anything a provider
      reported inside them was dropped — which is where providers put their most
      distinguishing detail. The existing "should preserve extra usage fields"
      fixture was itself losing audio_tokens, image_tokens and text_tokens
      this way.

      Both nested objects are now parsed loosely, as is the completion model's usage
      schema, which was strict throughout despite feeding the same raw field.

      Only usage.raw changes. The mapped token counts are unaffected.

  10. 2.0.67 – 2.0.682 releases that only update dependencies@ai-sdk/provider-utils 4.0.46Show each
  11. 2.0.66

    11 Aug 2026
    • provider/openai-compatible: Clamp outputTokens.text at 0 when a provider reports completion_tokens_details.reasoning_tokens greater than completion_tokens (observed with Baseten serving reasoning models that hit the length stop mid-reasoning). The text share of completion tokens can never be negative; total and reasoning remain as reported by the provider.

  12. 2.0.62 – 2.0.654 releases that only update dependencies@ai-sdk/provider-utils 4.0.43Show each
  13. 2.0.61

    15 Jul 2026
    • Preserve structured error data from chat completion SSE streams.

  14. 2.0.59 – 2.0.602 releases that only update dependencies@ai-sdk/provider-utils 4.0.39@ai-sdk/provider 3.0.14Show each
  15. 2.0.58

    7 Jul 2026
    • openai-compatible: Buffer tool call deltas until function.name arrives

    • security: Prevent streaming tool calls from finalizing on parsable partial JSON

      Streaming tool call arguments were finalized using isParsableJson() as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs in flush() after the stream is fully consumed.

    • More precise default message for tool execution denial

  16. 2.0.53 – 2.0.575 releases that only update dependencies@ai-sdk/provider-utils 4.0.36@ai-sdk/provider 3.0.13Show each
  17. 2.0.52

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

  18. 2.0.49 – 2.0.513 releases with no change for you2 dependency updates, 1 without a note@ai-sdk/provider-utils 4.0.30Show each
  19. 2.0.48

    22 May 2026
    • Accept empty string role in streaming delta chunks from OpenAI-compatible providers

  20. 2.0.47

    7 May 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.27

  21. 2.0.46

    4 May 2026
    • openai, openai-compatible: Only send null content for assistant messages with tool calls

  22. 2.0.45

    1 May 2026
    • vertex: Add grok models to vertex provider

  23. 2.0.43 – 2.0.442 releases that only update dependencies@ai-sdk/provider-utils 4.0.26@ai-sdk/provider 3.0.10Show each
  24. 2.0.42

    29 Apr 2026
    • Trigger release for all packages after provenance setup

    • Patch - send content: null instead of empty string for tool-only assistant messages

  25. 2.0.41

    7 Apr 2026
    • Add AI Gateway hint to provider READMEs

  26. 2.0.40

    6 Apr 2026
    • openai-compatible: Honor camelCase providerOptions key in chat and completion models

  27. 2.0.38 – 2.0.392 releases that only update dependencies@ai-sdk/provider-utils 4.0.23Show each
  28. 2.0.37

    20 Mar 2026
    • Publish v6 to latest npm dist tag

  29. 2.0.36

    5 Mar 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.20

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.