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.x
  2. 3.0.7 – 3.0.126 releases with no change for you4 dependency updates, 2 maintenance@ai-sdk/provider 3.0.4@ai-sdk/provider-utils 4.0.8Show each
  3. 3.0.6

    7 Jan 2026
    • google: Parse structured output when using google provider tools

  4. 3.0.5

    6 Jan 2026
    • Add file support for Gemini 3 models

  5. 3.0.3 – 3.0.42 releases that only update dependencies@ai-sdk/provider 3.0.2@ai-sdk/provider-utils 4.0.4Show each
  6. 3.0.2

    30 Dec 2025
    • Trigger release to update @latest

  7. 3.0.1

    23 Dec 2025

    Only updates a dependency:@ai-sdk/provider-utils 4.0.1

  8. 3.0.0

    22 Dec 2025
    • Breaking

      Ai SDK 6 beta

    • provider: Add specificationVersion to ProviderV3

    • provider: Shared spec v3

  9. 2.x
  10. 2.0.111

    11 Nov 2026
    • Add support for the gemini-4-carbon model with the same capabilities as gemini-4-argon.

  11. 2.0.110

    10 Nov 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.46

  12. 2.0.109

    7 Nov 2026
    • Omit Google provider-defined tools, including File Search and Vertex RAG Store, when toolChoice is none so disabled tools cannot retrieve data or execute server-side. Preserve function declarations needed by conversation history while disabling function calling.

  13. 2.0.108

    3 Nov 2026
    • google: Handle cycles and BigInt in functionResponse and parse string functionCall arguments

    • Map Google RPC status names to HTTP status codes when streamed errors omit a numeric code, so transient failures such as UNAVAILABLE and RESOURCE_EXHAUSTED are marked retryable.

  14. 2.0.107

    30 Oct 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.43

  15. 2.0.106

    23 Oct 2026
    • google: Convert type: [X, "null"] to a plain nullable node so items and format beside it stay valid for Gemini

  16. 2.0.105

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

  17. 2.0.104

    19 Oct 2026
    • Preserve grounding metadata from each automatically continued Google response in groundingMetadataPerRequest. Previously, a later response without grounding could leave earlier Search queries absent from the final provider metadata even though their sources were returned. The new array preserves request order and includes null for requests without grounding.

  18. 2.0.103

    13 Oct 2026
    • google: Add gemini-4-argon model id and long decode support: requests that reach the per-request cap (CONTINUATION) are continued automatically with usage summed across requests and the first request's prompt token count exposed as providerMetadata.google.initialPromptTokenCount, and the continuationToken provider option / provider metadata resume responses that used up their maxOutputTokens budget

  19. 2.0.102

    7 Oct 2026
    • google: Add the 'gemini-nano-banana-2.1' model ID

  20. 2.0.101

    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.

  21. 2.0.99 – 2.0.1002 releases that only update dependencies@ai-sdk/provider-utils 3.0.40Show each
  22. 2.0.98

    23 Sep 2026
    • provider: Preserve opaque file URI strings for provider serialization

  23. 2.0.96

    3 Sep 2026
    • google: Add gemini-3.8-flash model

  24. 2.0.95

    31 Aug 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.36

  25. 2.0.94

    27 Aug 2026
    • Surface prompt-level Google safety blocks without candidates as content-filter results with prompt feedback metadata.

    • Omit unsupported frequency and presence penalties from Gemini 2.5 requests and return warnings instead.

  26. 2.0.93

    26 Aug 2026
    • google: Convert enum values to the Gemini schema format

  27. 2.0.90

    24 Aug 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.33

  28. 2.0.89

    20 Aug 2026
    • Inline local JSON Schema references in Google tool and structured-output schemas.

  29. 2.0.88

    13 Aug 2026
    • google: Add gemini-3.7-flash model

  30. 2.0.87

    11 Aug 2026
    • Preserve Google API error details in APICallError.data.

  31. 2.0.86

    29 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.31

  32. 2.0.85

    23 Jul 2026
    • provider/google: Default unknown Gemini model IDs to the newest supported capabilities

  33. 2.0.84

    21 Jul 2026
  34. 2.0.83

    20 Jul 2026
    • provider/google: Associate multiple code execution results with their tool call

  35. 2.0.82

    17 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.30

  36. 2.0.81

    15 Jul 2026
    • provider/google: Forward Vertex-only imageConfig options (personGeneration, prominentPeople, imageOutputOptions)

  37. 2.0.80

    14 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 3.0.29

  38. 2.0.79

    13 Jul 2026
    • Expand standalone Google threshold provider options into safety settings.

  39. 2.0.78

    1 Jul 2026
    • provider/google: Include usageMetadata in providerMetadata for non-streaming generate

  40. 2.0.76 – 2.0.772 releases that only update dependencies@ai-sdk/provider-utils 3.0.28Show each
  41. 2.0.75

    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.

  42. 2.0.74

    19 May 2026
    • provider/google: Add gemini-3.5-flash

  43. 2.0.73

    15 May 2026
    • provider/google: Support functionCall.id when returned by Gemini API and provide matching functionResponse.id

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.