NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #2521 most downloaded on npm
Latest stable
4.0.146
Last release 8 days ago
13 Nov 2026
Ships on a steady schedule
a new release about every 8 days
Some releases are documented
notes for 29 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
846 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
### Patch Changes - Updated dependencies [2ebc78b] - Updated dependencies [cb4fa52] - @ai-sdk/provider-utils@5.0.80 - @ai-sdk/provider@4.0.38
Your coding agent can read these notes before it upgrades. Set up the MCP server →
### Patch Changes - Updated dependencies [2ebc78b] - Updated dependencies [cb4fa52] - @ai-sdk/provider-utils@5.0.80 - @ai-sdk/provider@4.0.38
23a0fff: chore(provider/gateway): update gateway model settings files
7f76d83: fix(gateway): forward server-returned warnings on language model doGenerate
7f76d83: fix(gateway): forward server-returned warnings on language model doGenerate
generateText(...).warnings through the gateway provider was always an empty
array: doGenerate spread the gateway response body and then overwrote the
server's warnings with a locally constructed empty array. The warnings the
gateway relays from the upstream provider (and gateway-originated warnings)
are now forwarded, matching the streaming path and every other modality.
5ec21a6: fix: reject unsupported batch request types
94d5d6d : Support reasoningEffortUpdate: 'none' for GPT-6 Sol and Luna in request-level options and positioned system messages. Validate update effort
reasoningEffortUpdate: 'none' for GPT-6 Sol and Luna in request-level options and positioned system messages. Validate update efforts against the model's supported efforts, warning and omitting unsupported request-level updates and rejecting unsupported historical updates.aa4cc14: Preserve image-result retryability returned by the AI Gateway.
a4ba394: feat: support per-request models in batch
3cfc1fc: feat(gateway): add support for gpt-6-astra
a7e324b: chore(provider/gateway): update gateway model settings files
5484f27: chore(provider/gateway): update gateway model settings files
4d25a08: feat(anthropic): add fable 5.1 support
### Patch Changes - Updated dependencies [5190b67] - @ai-sdk/provider@4.0.10 - @ai-sdk/provider-utils@5.0.35
1329d5a: chore(provider/gateway): update gateway model settings files
d2507af: chore(provider/gateway): update gateway model settings files
805bbfc: chore(provider/gateway): update gateway model settings files
0e7994c: chore(provider/gateway): update gateway model settings files
591d25b: feat: add batch completion webhooks. experimental_startTextBatch accepts a webhookUrl, and the gateway provider registers it through the batc
experimental_startTextBatch accepts a webhookUrl, and the gateway provider registers it through the batch callbackUrl contract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.e12e068: chore(provider/gateway): update gateway model settings files
a371615: feat (provider/gateway): add Tako Search tool support
dedac59: chore(provider/gateway): update gateway model settings files
5941bd6: feat(gateway): implement handleWebhookOption on the video model so generateVideo({ webhook }) registers the factory URL as the gateway's call
handleWebhookOption on the video model so generateVideo({ webhook }) registers the factory URL as the gateway's callbackUrl and awaits delivery instead of falling back to polling6e405ae : fix(xai): preserve additionalProperties: false in tool schemas
a9cea74: Keep default Node.js downloads protected by DNS validation and connection pinning when frameworks or instrumentation wrap global fetch before
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
### Patch Changes - Updated dependencies [8c65988] - Updated dependencies [527a163] - @ai-sdk/provider@4.0.21 - @ai-sdk/provider-utils@5.0.53
### Patch Changes - Updated dependencies [8c65988] - Updated dependencies [527a163] - @ai-sdk/provider@4.0.21 - @ai-sdk/provider-utils@5.0.53
providerMetadata.<provider>.inputFileId / inputFileExpiresAt) and accept an inputFileExpiresAfter provider option on the OpenAI and xAI batch input file uploadede5b89: chore: migrate package builds from tsup to tsdown
16650e9: feat(google): add gemini-3.7-flash model
gemini-3.7-flash modelea75787: Serialize structured Gateway error responses in nested API call error messages.
a4d386d: feat(xai): add the Grok 4.6 model IDs and support its xhigh reasoning effort
xhigh reasoning effortUpdated dependencies [ 90192f1 ]
3cc1bb6: chore(provider/gateway): update gateway model settings files
Updated dependencies [ 3e125ba ]
c477556: chore(provider/gateway): update gateway model settings files
### Patch Changes - Updated dependencies [1937bef] - @ai-sdk/provider-utils@5.0.24
89080c8: feat (provider/gateway): support the async video operation flow (doStart/doStatus) on the v4 video model
89080c8: feat (provider/gateway): support the async video operation flow (doStart/doStatus) on the v4 video model
89080c8: fix (ai/gateway): make retried doStart calls idempotent
generateVideo retries doStart, which creates a billable generation, so a
retry after a lost response could start a second one. It now mints one
idempotency token per logical start — outside the retry closure — and forwards it
as an idempotency-key header, so a provider that deduplicates (the Vercel AI
Gateway does) sees the same key on every attempt. GatewayVideoModel simply
forwards the caller's headers rather than inferring retry identity from an
options object, which would collide across unrelated calls.
Updated dependencies [ b74971f ]
7aeab10: chore(provider/gateway): update gateway model settings files
53c326e: chore(provider/gateway): update gateway model settings files
### Patch Changes - Updated dependencies [160ccdb] - @ai-sdk/provider-utils@5.0.20
### Patch Changes - Updated dependencies [79e133c] - @ai-sdk/provider@4.0.5 - @ai-sdk/provider-utils@5.0.19
cb4fa52: add experimental extract api and extraction model spec
bdd5e28: feat(provider/gateway): support 'vision' (image input) in the has provider option
'vision' (image input) in the has provider option### Patch Changes - Updated dependencies [5fc7da5] - Updated dependencies [93b2acd] - @ai-sdk/provider-utils@5.0.18
4f2e064: chore(provider/gateway): update gateway model settings files
### Patch Changes - Updated dependencies [fa95504] - @ai-sdk/provider-utils@5.0.17
af3f400: chore(provider/gateway): update gateway model settings files
0012529: chore(provider/gateway): update gateway model settings files
bf216b3: chore(provider/gateway): update gateway model settings files
### Patch Changes - Updated dependencies [0c464d9] - Updated dependencies [c49380c] - @ai-sdk/provider-utils@5.0.14
d9d2a11: chore(provider/gateway): update gateway model settings files
0a7c7f4: chore(provider/gateway): update gateway model settings files
2112ff1: chore(provider/gateway): update gateway model settings files
7c16f21: feat(google): add gemini-3.6-flash and gemini-3.5-flash-lite models
gemini-3.6-flash and gemini-3.5-flash-lite models### Patch Changes - Updated dependencies [02ffdcb] - Updated dependencies [76cb673] - @ai-sdk/provider-utils@5.0.12
cefa3b1: chore(provider/gateway): remove hipaaCompliant provider option
hipaaCompliant provider option### Patch Changes - Updated dependencies [cd06458] - @ai-sdk/provider-utils@5.0.11
341616a: feat: add kimi-k3 model and reasoningEffort provider option
reasoningEffort provider option8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
gateway.experimental_transcription.getToken for minting transcription-bound client secretsOne column per month.