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. 4.0.70

    15 Sep 2026
    • google: Preserve JSON Schema instead of converting to OpenAPI schema

    • google: Keep a realtime functionResponse.response an object

      Gemini types that field as a google.protobuf.Struct, which accepts an object and nothing else. onToolCall returns unknown and addToolOutput takes unknown, so a string, number, array or null tool result reached the wire unwrapped, Gemini closed the socket with 1007, and the close code was dropped on the way back so the application saw a plain disconnect. A non-object result is now wrapped under the output key the field's own docstring prescribes; an object is passed through unchanged, as before.

      An output that is not valid JSON no longer becomes {}. That branch told the model the tool had returned an empty object, with nothing thrown and the socket still up, so the answer was wrong with nothing to notice. The text is kept instead.

  2. 4.0.69

    12 Sep 2026
    • vertex: Download tool result file URLs

  3. 4.0.68

    11 Sep 2026
    • Reject unsupported batch request types

    • Support image generation requests in batches

  4. 4.0.67

    9 Sep 2026
    • google: Add batch cancellation and listing

  5. 4.0.65

    8 Sep 2026
    • Support per-request models in batch

    • Retry unclassified empty image results, preserve retry-attempt accounting, add provider-independent result retryability classification, and mark Google and Google Vertex prompt blocks as terminal.

  6. 4.0.64

    4 Sep 2026
    • ai: Support minItems and maxItems in array outputs

    • google: Map code execution tool name- #20260

  7. 4.0.63

    2 Sep 2026
    • google: Support agentic video processing in the Interactions API

    • batch: Surface the uploaded input file on the batch start result (providerMetadata.<provider>.inputFileId / inputFileExpiresAt) and accept an inputFileExpiresAfter provider option on the OpenAI and xAI batch input file upload

    • google: Add gemini-3.8-flash model

  8. 4.0.62

    2 Sep 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.36

  9. 4.0.61

    1 Sep 2026
    • provider: Extend the FilesV4 interface with optional getFileMetadata, downloadFile (streaming), and deleteFile operations, plus abortSignal/headers call options and a { type: 'stream' } upload data variant; upload results now expose byteSize, createdAt, and expiresAt (also surfaced by the core uploadFile() helper, which now forwards abortSignal/headers); add postMultipartStreamToApi (streaming multipart uploads with deterministic part ordering and failure-path stream teardown), deleteFromApi, and createBinaryStreamResponseHandler to provider-utils

  10. 4.0.60

    1 Sep 2026
    • Add tool calling support to batch

  11. 4.0.59

    31 Aug 2026
    • google: Support video response formats in Gemini Interactions

  12. 4.0.57

    28 Aug 2026
    • google: Recognize Google Files URLs when using a baseUrl

  13. 4.0.56

    27 Aug 2026
    • Preserve complete Google Generative Language usage metadata in raw usage results.

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

  14. 4.0.55

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

  15. 4.0.54

    26 Aug 2026
    • Feat (provider/google, provider/google-vertex): Gemini 3.5 Transcribe support — unary transcription (gemini-3.5-transcribe) via generateContent with language detection, speaker diarization, word timestamps, and custom vocabulary, plus streaming transcription (gemini-3.5-transcribe-live) over the Live API WebSocket with mode: 'VERBATIM' | 'SMART' transcription formatting

  16. 4.0.53

    26 Aug 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.32

  17. 4.0.51

    25 Aug 2026
    • google: Support the Gemini Batch API with experimental_startTextBatch

  18. 4.0.49 – 4.0.502 releases with no change for you1 dependency update, 1 maintenance@ai-sdk/provider-utils 5.0.29Show each
  19. 4.0.48

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

  20. 4.0.47

    19 Aug 2026
    • Handle empty string tool call IDs

  21. 4.0.46

    19 Aug 2026
    • google: Use low as the minimum reasoning level for full Gemini Flash 3.7 and later

  22. 4.0.45

    18 Aug 2026
    • google: Coerce minimal reasoning to low for Gemini 3.7 Flash

  23. 4.0.44

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

  24. 4.0.43

    12 Aug 2026
    • Preserve forced tool calls when strict function tools are configured.

  25. 4.0.42

    11 Aug 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.27

  26. 4.0.41

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

    • Preserve Google API error details in APICallError.data.

  27. 4.0.33 – 4.0.408 releases with no change for you7 dependency updates, 1 maintenance@ai-sdk/provider-utils 5.0.26@ai-sdk/provider 4.0.7Show each
  28. 4.0.32

    3 Aug 2026
    • Async APIs for generateVideo (poll, webhook)

      Adds an asynchronous start/status flow to the experimental video model
      interface (VideoModelV4): models may now implement doStart, doStatus,
      and handleWebhookOption instead of (or in addition to) doGenerate, and
      experimental_generateVideo accepts poll and webhook options to
      orchestrate completion via polling or webhooks. Polling configuration can use
      a custom delay implementation for durable workflow compatibility.

  29. 4.0.28 – 4.0.314 releases that only update dependencies@ai-sdk/provider-utils 5.0.18Show each
  30. 4.0.27

    28 Jul 2026
    • Forward topK through Google Interactions requests and warn when unsupported frequency or presence penalties are provided.

    • Allow fetch to derive the content length for Google file upload request bodies.

  31. 4.0.26

    28 Jul 2026
    • Add experimental streaming speech translation models (openai.translation('gpt-realtime-translate') over the OpenAI Realtime translations WebSocket and google.translation('gemini-3.5-live-translate-preview') over the Gemini Live API). connectToWebSocket in @ai-sdk/provider-utils now passes close code and reason to onClose (additive, optional parameter).

  32. 4.0.24

    24 Jul 2026
    • google: Omit unsupported function call IDs

  33. 4.0.23

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

  34. 4.0.22

    22 Jul 2026
    • provider/google: Preserve Gemini Live lifecycle events

    • Avoid missing thought-signature warnings and skip-validator injection for valid unsigned Gemini 3 parallel function calls in the same model response.

  35. 4.0.21

    21 Jul 2026
    • google: Add gemini-3.6-flash and gemini-3.5-flash-lite models

  36. 4.0.20

    21 Jul 2026

    Only updates a dependency:@ai-sdk/provider-utils 5.0.12

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.