Packages

@ai-sdk/google-vertex

5.0.144 · 20 Nov 2026Apache-2.06.4M / weekRepositoryHomepagenpmAtom feed

Your version

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

  1. 5.x · latest line
  2. 5.0.39

    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.

  3. 5.0.28 – 5.0.3810 releases that only update dependencies@ai-sdk/provider-utils 5.0.18@ai-sdk/google 4.0.31@ai-sdk/openai-compatible 3.0.20and 2 moreShow each
  4. 5.0.27

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

  5. 5.0.26

    22 Jul 2026

    Only updates a dependency:@ai-sdk/google 4.0.22

  6. 5.0.25

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

  7. 5.0.15 – 5.0.249 releases that only update dependencies@ai-sdk/provider-utils 5.0.12@ai-sdk/anthropic 4.0.17@ai-sdk/google 4.0.20and 1 moreShow each
  8. 5.0.14

    9 Jul 2026
    • Feat (video): support video (not just image) reference inputs in inputReferences for reference-to-video generation

  9. 5.0.11 – 5.0.133 releases that only update dependencies@ai-sdk/provider-utils 5.0.6@ai-sdk/openai-compatible 3.0.6@ai-sdk/anthropic 4.0.10and 1 moreShow each
  10. 5.0.10

    2 Jul 2026
    • Add experimental streaming transcription support for transcription models, including OpenAI gpt-realtime-whisper and xAI WebSocket STT.

  11. 5.0.8

    2 Jul 2026
    • Add vertex.interactions() for the Gemini Interactions API on Vertex AI. Targets the location-scoped .../locations/{region}/interactions resource using the existing Vertex OAuth credentials, enabling multimodal-output models such as gemini-omni-flash-preview (video output) through Vertex. The GoogleInteractionsLanguageModel is now exported from @ai-sdk/google/internal for provider reuse.

  12. 5.0.6

    1 Jul 2026
    • vertex: Support tuned models

  13. 5.0.5

    30 Jun 2026
    • Feat (provider/anthropic): add claude-sonnet-5 model id

  14. 5.0.4

    30 Jun 2026
    • Feat (video): add first-class frameImages and inputReferences call options for video generation

  15. 5.0.1 – 5.0.33 releases that only update dependencies@ai-sdk/anthropic 4.0.2@ai-sdk/provider-utils 5.0.1@ai-sdk/google 4.0.2and 1 moreShow each
  16. 5.0.0

    25 Jun 2026
    • Breaking

      anthropic: Remove cacheCreationInputTokens from providerMetadata

    • Breaking

      Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers using require() must switch to ESM import syntax.

    • Breaking

      Start v7 pre-release

  17. 4.x
  18. 4.0.234

    17 Nov 2026
    • Limit the size of Google Vertex tool result file downloads with toolResultDownloads.maxBytes, which defaults to 7 MiB. This is lower than the previous 2 GiB default for these downloads; raise toolResultDownloads.maxBytes for larger files.

    • Keep Google Vertex tool result downloads on the built-in validated transport and stop using the provider fetch option for them. Set toolResultDownloads.fetch to choose another transport for those downloads.

      The built-in transport resolves every hostname through a validating lookup hook and pins the connection to the resolved address on Node.js. Reusing the provider fetch option for downloads would adopt a logging, tracing, or proxy wrapper that does not validate DNS results, so tool result URLs whose hostnames resolve to private addresses could reach internal hosts. A transport set with toolResultDownloads.fetch must perform equivalent connect-time DNS validation, for example a guarded fetch on Bun or Deno.

  19. 4.0.233

    12 Nov 2026

    Only updates a dependency:@ai-sdk/google 3.0.146

  20. 4.0.232

    11 Nov 2026
    • Reject invalid Cloud Speech transcription regions and default locations before resolving credentials or sending requests, preventing URL delimiters from redirecting bearer tokens and audio to another host.

  21. 4.0.231

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

  22. 4.0.230

    10 Nov 2026
    • Route off-origin MaaS image downloads through the validated download transport so the built-in authentication wrappers in both entry points preserve Node.js DNS validation and manual redirect handling. Explicit custom fetch implementations and the browser redirect fallback remain supported.

  23. 4.0.228

    7 Nov 2026
    • Pass providerOptions.google.labels through to Google and Vertex AI Interactions requests, including streaming, so callers can attach request metadata such as safety_identifier.

    • Only send google cloud credentials from the maas provider to its own api, not to image urls from a response or their redirects

  24. 4.0.227

    6 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.

  25. 4.0.223 – 4.0.2264 releases that only update dependencies@ai-sdk/anthropic 3.0.138@ai-sdk/google 3.0.141@ai-sdk/openai-compatible 2.0.90and 1 moreShow 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.