NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm · #2521 most downloaded on npm
Last release today
05 Oct 2026
Ships on a steady schedule
a new release about every 8 days
Some releases are documented
notes for 30 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
761 releases · first in 2025
One column per month.
Nothing published for this version
d1bb9e8: chore(provider/gateway): update gateway model settings files
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle callbacks
e25994e: fix(gateway): scope getCredits() to teamIdOrSlug
The credits endpoint reads the team from the teamId / slug query parameter rather than the x-vercel-ai-gateway-team header. getCredits() now forwards the configured team as a query parameter, so credentials that can access multiple teams (such as Vercel access tokens) are no longer rejected with an authentication error.
e74afc5: chore(provider/gateway): update gateway model settings files
Updated dependencies [8c65988]
Updated dependencies [527a163]
040033b: feat(openai): add GPT-6.1 Sol model support
870f509: chore(provider/gateway): update gateway model settings files
e361d39: feat(anthropic): add Claude Sonnet 5.5 support
e361d39: feat(anthropic): add Claude Sonnet 5.5 support
claude-sonnet-5-5 model ID to @ai-sdk/anthropic and @ai-sdk/google-vertex, anthropic.claude-sonnet-5-5 and us.anthropic.claude-sonnet-5-5 to @ai-sdk/amazon-bedrock, and anthropic/claude-sonnet-5.5 to @ai-sdk/gatewaybetween_tools thinking type (thinking: { type: 'between_tools' }), the lowest thinking setting on claude-sonnet-5-5; xhigh and max effort are lowered to high with a warning because the API rejects them with between_toolsclaude-sonnet-5-5 rejects disabled thinking: thinking: { type: 'disabled' } is replaced with between_tools thinking (with a warning), reasoning: 'none' maps to between_tools thinking, and budget-based thinking is converted to adaptive thinkingclaude-sonnet-5-5 rejects forced tool use: required and named tool choices fall back to auto, and structuredOutputMode: 'jsonTool' falls back to native structured outputs, each with a warning### Patch Changes - Updated dependencies [e3605f6] - Updated dependencies [525efc5] - @ai-sdk/provider-utils@5.0.50 - @ai-sdk/provider@4.0.19
e6a7996: fix(provider/gateway): accept any non-empty conditional evaluation fallback model
b67b1b7: feat(provider/gateway): type conditional evaluation fallbacks
### Patch Changes - Updated dependencies [af9597b] - Updated dependencies [bc49f78] - @ai-sdk/provider-utils@5.0.49
124b6ef: chore(provider/gateway): update gateway model settings files
2693319: Add Gemini 3.8 TTS support with structured speech metadata and per-turn speaker and style controls for prebuilt voices. Preserve native WAV r
2693319: Add Gemini 3.8 TTS support with structured speech metadata and per-turn speaker and style controls for prebuilt voices. Preserve native WAV responses without adding a second header, support explicit raw PCM, mu-law, and A-law output, and identify headerless audio formats correctly. Add the Gemini 3.8 speech model IDs to Google and Gateway types.
Share transcript and custom-voice inspection through the Google provider internal export, and reject empty speech transcripts before sending a request. Default newer and custom model IDs to structured speech while preserving the legacy format for Gemini 2.5 and 3.1.
b73f2f9: feat(provider/gateway): add quantization conditions to the has provider option
Updated dependencies [fe07867]
Updated dependencies [a4b0940]
Updated dependencies [771e74b]
ed5a1d7: chore(provider/gateway): update gateway model settings files
49295bb: feat(anthropic): add Claude Opus 5.5 support
49295bb: feat(anthropic): add Claude Opus 5.5 support
claude-opus-5-5 model ID to @ai-sdk/anthropic and anthropic/claude-opus-5.5 to @ai-sdk/gatewayclaude-opus-5-5, claude-fable-5, claude-fable-5-1) no longer receive thinking: { type: 'disabled' } or budget-based thinking; the provider drops the unsupported setting, maps reasoning: 'none' to effort: 'low', and emits a warningclaude-opus-5-5, claude-fable-5-1) fall back to auto tool choice for required and named tool choices, and to native structured outputs when structuredOutputMode: 'jsonTool' is requested, each with a warningcomputerToolset_20260801 computer use tool (computer_toolset_20260801), which is required for computer use on claude-opus-5-5mid-conversation-output-config-2026-07-01 beta header for per-message effort20dd00a: feat(provider/gateway): support reasoning and tool-use in has model filtering
reasoning and tool-use in has model filteringexperimental_cancelBatch8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
ede5b89: chore: migrate package builds from tsup to tsdown
6982e9d: Include evaluation models in getAvailableModels() instead of filtering them out as unknown model types.
### Patch Changes - Updated dependencies [215b25e] - Updated dependencies [d4d96bf] - Updated dependencies [a7dd893] - Updated dependencies [3456e2c]
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
040033b: feat(openai): add GPT-6.1 Sol model support
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
048ce06 : feat(batch): surface the uploaded input file on the batch start result ( providerMetadata.<provider>.inputFileId / inputFileExpiresAt ) and
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
Your coding agent can read these notes before it upgrades. Set up the MCP server →