@ai-sdk/google-vertex
5.0.144 · 20 Nov 2026Apache-2.06.4M / weekRepositoryHomepagenpmAtom feed
682 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
5.0.144
20 Nov 2026google, google-vertex: Finish live transcription streams without the 3-second grace period
gemini-3.5-transcribe-liveends each segment withgenerationCompleteand never sendsturnComplete, so live transcription streams always waited out the 3-second finish grace period and merged all segments into onetranscript-finalwithout separating whitespace. Segments now complete ongenerationComplete, and streams finish as soon as server voice activity detection shows that all sent audio has been transcribed.Adds
providerOptions.google.streaming.automaticActivityDetection.disabled(googleVertexon Vertex) for push-to-talk input: the audio stream is transcribed as a single turn without splitting at pauses, and the transcript is finalized as soon as the audio input closes.
Patch Changes
google, google-vertex: Finish live transcription streams without the 3-second grace period
gemini-3.5-transcribe-liveends each segment withgenerationCompleteand never sendsturnComplete, so live transcription streams always waited out the 3-second finish grace period and merged all segments into onetranscript-finalwithout separating whitespace. Segments now complete ongenerationComplete, and streams finish as soon as server voice activity detection shows that all sent audio has been transcribed.Adds
providerOptions.google.streaming.automaticActivityDetection.disabled(googleVertexon Vertex) for push-to-talk input: the audio stream is transcribed as a single turn without splitting at pauses, and the transcript is finalized as soon as the audio input closes.
5.0.143
20 Nov 2026google: Add the
gemini-4-neonmodel ID withxhighthinking support
Patch Changes
google: Add the
gemini-4-neonmodel ID withxhighthinking support
5.0.142
17 Nov 2026provider/google: Redact MCP server credentials in telemetry
Expose
googleVertex.tools.mcpServerfor Google Vertex Interactions models. Its
MCP server header values are redacted from telemetry, matching@ai-sdk/google.
Patch Changes
provider/google: Redact MCP server credentials in telemetry
Expose
googleVertex.tools.mcpServerfor Google Vertex Interactions models. Its
MCP server header values are redacted from telemetry, matching@ai-sdk/google.
5.0.141
13 Nov 2026Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.
Add the missing
gemini-4-hydrogenmodel ID to the Vertex catalog so model suggestions and generated capability documentation include it.
Patch Changes
Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while preserving existing suggestions, endpoint-specific model lists, and support for custom model IDs.
Add the missing
gemini-4-hydrogenmodel ID to the Vertex catalog so model suggestions and generated capability documentation include it.
5.0.140
13 Nov 20265.0.139
12 Nov 2026Forward the provider's configured fetch transport when downloading file inputs. Add a
fetchoption tocreateDownloadso core downloads can also useguarded-fetchfor opt-in DNS validation on Node.js. The function returned bycreateDownloadcan now also be passed asexperimental_downloadtogenerateTextandstreamText, andexperimental_downloadnow also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.Keep Azure image and Vertex tool-result downloads separate from provider authentication wrappers so file hosts never receive Azure bearer tokens or Vertex Express Mode API keys.
Pass the call's abort signal to custom download requests, including prompt assets and generated files, so
experimental_download: createDownload({ fetch })preserves cancellation and timeouts.
Patch Changes
Forward the provider's configured fetch transport when downloading file inputs. Add a
fetchoption tocreateDownloadso core downloads can also useguarded-fetchfor opt-in DNS validation on Node.js. The function returned bycreateDownloadcan now also be passed asexperimental_downloadtogenerateTextandstreamText, andexperimental_downloadnow also handles generated file URLs returned by the model, so one hook covers all core downloads. Document that the default URL checks do not resolve DNS and recommend the guarded transport or network egress controls for untrusted URLs.Keep Azure image and Vertex tool-result downloads separate from provider authentication wrappers so file hosts never receive Azure bearer tokens or Vertex Express Mode API keys.
Pass the call's abort signal to custom download requests, including prompt assets and generated files, so
experimental_download: createDownload({ fetch })preserves cancellation and timeouts.
5.0.138
11 Nov 2026Only updates a dependency:@ai-sdk/google 4.0.118
5.0.137
10 Nov 2026Add support for the
gemini-4-carbonmodel with the same capabilities asgemini-4-argon.
Patch Changes
Add support for the
gemini-4-carbonmodel with the same capabilities asgemini-4-argon.
5.0.136
10 Nov 2026acdccac: 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.
Patch Changes
acdccac: 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.
5.0.134
7 Nov 2026Pass
providerOptions.google.labelsthrough to Google and Vertex AI Interactions requests, including streaming, so callers can attach request metadata such assafety_identifier.Only send google cloud credentials from the maas provider to its own api, not to image urls from a response or their redirects
Omit Google provider-defined tools, including File Search and Vertex RAG Store, when
toolChoiceisnoneso disabled tools cannot retrieve data or execute server-side. Preserve function declarations needed by conversation history while disabling function calling. This also applies when structured output uses a synthetic JSON response tool.
Patch Changes
Pass
providerOptions.google.labelsthrough to Google and Vertex AI Interactions requests, including streaming, so callers can attach request metadata such assafety_identifier.Only send google cloud credentials from the maas provider to its own api, not to image urls from a response or their redirects
Omit Google provider-defined tools, including File Search and Vertex RAG Store, when
toolChoiceisnoneso disabled tools cannot retrieve data or execute server-side. Preserve function declarations needed by conversation history while disabling function calling. This also applies when structured output uses a synthetic JSON response tool.
5.0.133
6 Nov 2026Refactor Google Vertex model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Export Google catalog metadata internally for Vertex to reuse. Request behavior is unchanged.
Patch Changes
Refactor Google Vertex model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability documentation from it. Export Google catalog metadata internally for Vertex to reuse. Request behavior is unchanged.
5.0.132
5 Nov 2026Preserve the order of text and complete function calls in streamed Google responses, including standalone thought signatures on empty text or reasoning parts.
Keep provider metadata on empty text parts when converting results to response messages so it can be passed back in subsequent requests.
Omit foreign-provider empty signature text when replaying history through Anthropic or Bedrock, preserving Bedrock’s existing native reasoning-history handling.
Pass through
seed: 0instead of dropping it in image and video models. KlingAI now reportsseed: 0as an unsupported setting like any other seed.Expose optional transcription word timings separately from segments and accept shared timestampGranularities. Explicit provider timing settings take precedence. OpenAI now sends timestamp_granularities only with verbose_json and warns when a requested timing is unavailable or excluded.
Patch Changes
Preserve the order of text and complete function calls in streamed Google responses, including standalone thought signatures on empty text or reasoning parts.
Keep provider metadata on empty text parts when converting results to response messages so it can be passed back in subsequent requests.
Omit foreign-provider empty signature text when replaying history through Anthropic or Bedrock, preserving Bedrock’s existing native reasoning-history handling.
Pass through
seed: 0instead of dropping it in image and video models. KlingAI now reportsseed: 0as an unsupported setting like any other seed.Expose optional transcription word timings separately from segments and accept shared timestampGranularities. Explicit provider timing settings take precedence. OpenAI now sends timestamp_granularities only with verbose_json and warns when a requested timing is unavailable or excluded.
Add a
supportsNativeStructuredOutputopt-in to the Vertex Anthropic provider soautocan use native structured output for Claude 4.5 and newer when enabled by Google Cloud policy. Keep tool emulation as the default and avoid adding the structured-output beta header for providers without strict tool support.
5.0.129 – 5.0.1313 releases that only update dependencies@ai-sdk/provider-utils 5.0.74@ai-sdk/google 4.0.111@ai-sdk/anthropic 4.0.96and 1 moreShow each
- 5.0.1313 Nov 2026@ai-sdk/provider-utils 5.0.74@ai-sdk/google 4.0.111@ai-sdk/anthropic 4.0.96and 1 more
- 5.0.1302 Nov 2026@ai-sdk/anthropic 4.0.95@ai-sdk/google 4.0.110@ai-sdk/openai-compatible 3.0.83and 1 more
- 5.0.12930 Oct 2026@ai-sdk/anthropic 4.0.94
5.0.128
30 Oct 2026Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.
The experimental OpenAI Live
getServerWebSocketConfig()method can now resolve asynchronously. Await its result before using the connection settings.
Patch Changes
Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.
The experimental OpenAI Live
getServerWebSocketConfig()method can now resolve asynchronously. Await its result before using the connection settings.
5.0.126 – 5.0.1272 releases that only update dependencies@ai-sdk/google 4.0.108@ai-sdk/provider-utils 5.0.71@ai-sdk/anthropic 4.0.92and 1 moreShow each
- 5.0.12729 Oct 2026@ai-sdk/google 4.0.108@ai-sdk/provider-utils 5.0.71@ai-sdk/anthropic 4.0.92and 1 more
- 5.0.12628 Oct 2026@ai-sdk/anthropic 4.0.91
5.0.125
27 Oct 2026Support Google Auth Library 11 in
@ai-sdk/google-vertex
5.0.120 – 5.0.1245 releases that only update dependencies@ai-sdk/anthropic 4.0.90@ai-sdk/provider-utils 5.0.70@ai-sdk/google 4.0.107and 2 moreShow each
- 5.0.12427 Oct 2026@ai-sdk/anthropic 4.0.90@ai-sdk/provider-utils 5.0.70@ai-sdk/google 4.0.107and 1 more
- 5.0.12326 Oct 2026@ai-sdk/provider-utils 5.0.69@ai-sdk/openai-compatible 3.0.79@ai-sdk/anthropic 4.0.89and 1 more
- 5.0.12224 Oct 2026@ai-sdk/provider 4.0.34@ai-sdk/openai-compatible 3.0.78@ai-sdk/provider-utils 5.0.68and 2 more
- 5.0.12122 Oct 2026@ai-sdk/provider-utils 5.0.67@ai-sdk/provider 4.0.33@ai-sdk/anthropic 4.0.87and 2 more
- 5.0.12022 Oct 2026@ai-sdk/anthropic 4.0.86@ai-sdk/google 4.0.103@ai-sdk/provider 4.0.32and 2 more
5.0.119
21 Oct 2026Defer construction of provider validation schemas until first use to reduce package import time.
Patch Changes
Defer construction of provider validation schemas until first use to reduce package import time.
5.0.116 – 5.0.1183 releases that only update dependencies@ai-sdk/anthropic 4.0.84@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64and 2 moreShow each
- 5.0.11820 Oct 2026@ai-sdk/anthropic 4.0.84@ai-sdk/provider 4.0.31@ai-sdk/provider-utils 5.0.64and 2 more
- 5.0.11719 Oct 2026@ai-sdk/openai-compatible 3.0.73
- 5.0.11619 Oct 2026@ai-sdk/provider 4.0.30@ai-sdk/google 4.0.100@ai-sdk/anthropic 4.0.83and 2 more
5.0.115
16 Oct 2026google: Surface in-stream errors
Patch Changes
google: Surface in-stream errors
5.0.113 – 5.0.1142 releases that only update dependencies@ai-sdk/google 4.0.98@ai-sdk/provider 4.0.28@ai-sdk/openai-compatible 3.0.70and 2 moreShow each
- 5.0.11415 Oct 2026@ai-sdk/google 4.0.98
- 5.0.11315 Oct 2026@ai-sdk/provider 4.0.28@ai-sdk/openai-compatible 3.0.70@ai-sdk/anthropic 4.0.81and 2 more
5.0.112
15 Oct 2026vertex-anthropic: Forward 'providerOptions.vertex.labels' as a header
Patch Changes
vertex-anthropic: Forward 'providerOptions.vertex.labels' as a header
5.0.111
13 Oct 2026google: Add
gemini-4-argonmodel id and long decode support forgenerateContent: 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 asproviderMetadata.google.initialPromptTokenCount, and thecontinuationTokenprovider option / provider metadata resume responses that used up theirmaxOutputTokensbudget.generateTextwith the Interactions API now pollsbackground: truemodel calls until they finish.
Patch Changes
google: Add
gemini-4-argonmodel id and long decode support forgenerateContent: 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 asproviderMetadata.google.initialPromptTokenCount, and thecontinuationTokenprovider option / provider metadata resume responses that used up theirmaxOutputTokensbudget.generateTextwith the Interactions API now pollsbackground: truemodel calls until they finish.
5.0.110
12 Oct 2026Only updates dependencies:@ai-sdk/anthropic 4.0.79@ai-sdk/google 4.0.94@ai-sdk/provider-utils 5.0.59@ai-sdk/provider 4.0.27and 1 more
5.0.109
8 Oct 2026Map the top level embedding dimensions to provider settings
Patch Changes
Map the top level embedding dimensions to provider settings
5.0.106 – 5.0.1083 releases that only update dependencies@ai-sdk/anthropic 4.0.77@ai-sdk/provider 4.0.25@ai-sdk/provider-utils 5.0.57and 2 moreShow each
- 5.0.1088 Oct 2026@ai-sdk/anthropic 4.0.77
- 5.0.1078 Oct 2026@ai-sdk/provider 4.0.25@ai-sdk/provider-utils 5.0.57@ai-sdk/anthropic 4.0.76and 2 more
- 5.0.1067 Oct 2026@ai-sdk/google 4.0.91
5.0.105
7 Oct 2026anthropic: Add Claude Haiku 5.5 support
Patch Changes
anthropic: Add Claude Haiku 5.5 support
add the
claude-haiku-5-5model ID to@ai-sdk/anthropicand@ai-sdk/google-vertex,anthropic.claude-haiku-5-5andus.anthropic.claude-haiku-5-5to@ai-sdk/amazon-bedrock, andanthropic/claude-haiku-5.5to@ai-sdk/gatewayrecognize
claude-haiku-5-5as a known model with a 128k max output token limit, adaptive thinking, and all five effort levels; thinking can be disabled up tohigheffort, andxhighandmaxare lowered tohighwith a warning when thinking is disabledclaude-haiku-5-5does not support thinking token budgets:thinking: { type: 'enabled', budgetTokens }is converted to adaptive thinking with a warninguse the JSON tool fallback for structured output on Amazon Bedrock for
claude-haiku-5-5
5.0.104
7 Oct 2026Only updates dependencies:@ai-sdk/provider 4.0.24@ai-sdk/anthropic 4.0.74@ai-sdk/google 4.0.90@ai-sdk/openai-compatible 3.0.65and 1 more
5.0.103
6 Oct 2026google: Add the 'gemini-nano-banana-2.1' model ID
Patch Changes
google: Add the 'gemini-nano-banana-2.1' model ID
5.0.101 – 5.0.1022 releases that only update dependencies@ai-sdk/provider 4.0.22@ai-sdk/provider-utils 5.0.54@ai-sdk/anthropic 4.0.72and 2 moreShow each
5.0.100
30 Sep 2026ai: Add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks
Validate hostname parts using
isValidHostnamePart
Patch Changes
ai: Add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks
Validate hostname parts using
isValidHostnamePart
5.0.99
30 Sep 2026Only updates dependencies:@ai-sdk/anthropic 4.0.69@ai-sdk/google 4.0.86@ai-sdk/openai-compatible 3.0.60@ai-sdk/provider 4.0.20and 1 more
5.0.98
28 Sep 2026Use standards-compliant User-Agent header
Patch Changes
Use standards-compliant User-Agent header
5.0.97
28 Sep 2026anthropic: Add Claude Sonnet 5.5 support
Patch Changes
anthropic: Add Claude Sonnet 5.5 support
add the
claude-sonnet-5-5model ID to@ai-sdk/anthropicand@ai-sdk/google-vertex,anthropic.claude-sonnet-5-5andus.anthropic.claude-sonnet-5-5to@ai-sdk/amazon-bedrock, andanthropic/claude-sonnet-5.5to@ai-sdk/gatewayadd the
between_toolsthinking type (thinking: { type: 'between_tools' }), the lowest thinking setting onclaude-sonnet-5-5;xhighandmaxeffort are lowered tohighwith a warning because the API rejects them withbetween_toolsclaude-sonnet-5-5rejects disabled thinking:thinking: { type: 'disabled' }is replaced withbetween_toolsthinking (with a warning),reasoning: 'none'maps tobetween_toolsthinking, and budget-based thinking is converted to adaptive thinkingclaude-sonnet-5-5rejects forced tool use:requiredand named tool choices fall back toauto, andstructuredOutputMode: 'jsonTool'falls back to native structured outputs, each with a warning
5.0.96
28 Sep 2026provider: Advertise image model file and mask input support
Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.
Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.
Patch Changes
provider: Advertise image model file and mask input support
Use confirmed model IDs for capability declarations so unrecognized model names remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and allow asynchronous capability lookups and middleware overrides to resolve to unknown.
Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together AI Gemini image inputs unsupported by the current single-image request mapping.
5.0.95
25 Sep 2026google: Forward supported Vertex tool result URLs as function response file data
Patch Changes
google: Forward supported Vertex tool result URLs as function response file data
5.0.93
24 Sep 2026Only updates dependencies:@ai-sdk/anthropic 4.0.63@ai-sdk/google 4.0.80
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.