Packages

@ai-sdk/google

4.0.122 · 17 Nov 2026Apache-2.014.6M / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 3.0.62

    11 Apr 2026
    • google-vertex: Don't send streamFunctionCallArguments for unary API calls and change default to false

  2. 3.0.61

    9 Apr 2026
    • google-vertex: Add support for streaming tool arguments input

  3. 3.0.60

    7 Apr 2026
    • Add AI Gateway hint to provider READMEs

  4. 3.0.59

    6 Apr 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.23

  5. 3.0.58

    3 Apr 2026
    • provider/google: Preserve per-modality token details in usage data

  6. 3.0.57

    3 Apr 2026
    • provider/google: Fix Gemini service tier enum after upstream update

  7. 3.0.56

    2 Apr 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.22

  8. 3.0.55

    1 Apr 2026
    • provider/google: Support combining built-in tools with function calling on Gemini 3

  9. 3.0.54

    30 Mar 2026
    • provider/google: Add support for service tier parameter

  10. 3.0.53

    23 Mar 2026

    Maintenance only: docs, tests, build or refactoring. Nothing changes in how you use it.

  11. 3.0.52

    20 Mar 2026
    • Publish v6 to latest npm dist tag

    • provider/google: Add multimodal tool-result support for Google function responses.

      Tool results with output.type = 'content' now map media parts into
      functionResponse.parts for Google models, including image-data,
      file-data, and base64 data: URLs in URL-style content parts.
      Remote HTTP(S) URLs in URL-style tool-result parts are not supported.

  12. 3.0.51

    10 Mar 2026
    • google: Add new finishMessage field in providerMetadata

  13. 3.0.50

    10 Mar 2026
    • provider/google: Add gemini-embedding-2-preview and fix multimodal embedding support with embedMany

  14. 3.0.49

    10 Mar 2026
    • provider/google: Correct JSDoc for multimodal embedding content option

  15. 3.0.48

    10 Mar 2026
    • provider/google: Support multimodal content parts in embedding provider options

  16. 3.0.47

    9 Mar 2026
    • provider/google: Correctly mark reasoning files as such and fix related multi-turn errors

  17. 3.0.46

    5 Mar 2026

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

  18. 3.0.45

    5 Mar 2026
    • provider/google: Preserve groundingMetadata and urlContextMetadata when they arrive in a stream chunk before the finishReason chunk

  19. 3.0.44

    5 Mar 2026
    • google: Use VALIDATED function calling mode when any tool has strict:true

  20. 3.0.43

    5 Mar 2026
    • Fix gateway failover losing thoughtSignature when failing over from Vertex to Google AI Studio. The Google provider now falls back to checking the vertex namespace for thoughtSignature, matching the existing Vertex-to-Google fallback behavior.

  21. 3.0.41 – 3.0.422 releases that only update dependencies@ai-sdk/provider-utils 4.0.19Show each
  22. 3.0.40

    4 Mar 2026
    • google: Make urlMetadata optional in urlContextMetadata schema

  23. 3.0.39

    4 Mar 2026
    • google: Add support for image search, replace obsolete google_search_retrieval implementation

  24. 3.0.38

    4 Mar 2026
    • ai: Fix missing support for image thought signatures (e.g. for Gemini image models)

  25. 3.0.37

    3 Mar 2026
    • provider/google: Add gemini-3.1-flash-lite-preview

  26. 3.0.34 – 3.0.363 releases with no change for you2 dependency updates, 1 maintenance@ai-sdk/provider-utils 4.0.17Show each
  27. 3.0.33

    26 Feb 2026
    • provider/google: Add support for new Google image model aspect ratios and sizes

  28. 3.0.32

    26 Feb 2026
    • provider/google: Add support for gemini-3.1-flash-image-preview

  29. 3.0.31

    24 Feb 2026
    • Added missing model IDs to GoogleGenerativeAIModelId and GoogleGenerativeAIVideoModelId types for better autocomplete support.

  30. 3.0.30

    19 Feb 2026
    • provider/google: Add support for gemini-3.1-pro-preview

  31. 3.0.29

    12 Feb 2026

    Only updates a dependency:@ai-sdk/provider-utils 4.0.15

  32. 3.0.28

    12 Feb 2026
    • provider/google-vertex: Allow using Gemini image models with generateImage

  33. 3.0.27

    12 Feb 2026
    • vertex: Add fallback for providerOptions keyname

  34. 3.0.26

    11 Feb 2026
    • google: Allow using Gemini image models with generateImage

  35. 3.0.25

    11 Feb 2026
    • Normalize provider specific model options type names and ensure they are exported

  36. 3.0.24

    10 Feb 2026
    • google: Handle thoughtSignature on empty-text parts in doGenerate and doStream

  37. 3.0.23

    9 Feb 2026
    • google: Make codeExecutionResult.output optional in response schema

      Gemini 3 Flash omits the output field in codeExecutionResult when code execution produces no text output (e.g., only saves files). The Zod response schema now accepts a missing output field and defaults it to an empty string.

  38. 3.0.22

    6 Feb 2026
    • Feat (ai, provider): default global provider video model resolution

  39. 3.0.21

    4 Feb 2026
    • google: Remove shut down gemini-2.5-flash-image-preview

  40. 3.0.20

    1 Feb 2026
    • Feat (ai, provider): experimental generate video support

  41. 3.0.17 – 3.0.193 releases with no change for you2 dependency updates, 1 maintenance@ai-sdk/provider-utils 4.0.12@ai-sdk/provider 3.0.6Show each
  42. 3.0.16

    28 Jan 2026
    • Fix (provider/google): make segment optional in groundingSupports schema

      The Google Generative AI API sometimes returns grounding supports without a segment field. This change makes the segment field optional to handle these responses correctly.

  43. 3.0.13 – 3.0.153 releases with no change for you2 dependency updates, 1 maintenance@ai-sdk/provider-utils 4.0.10@ai-sdk/provider 3.0.5Show 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.