NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #4482 most downloaded on npm
Latest stable
4.0.102
Last release 7 days ago
10 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Most releases are documented
notes for 36 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
688 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
f5fc6ba: Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while
@ai-sdk/openai-compatible@3.0.92
Your coding agent can read these notes before it upgrades. Set up the MCP server →
@ai-sdk/openai-compatible@3.0.91
Nothing published for this version
Nothing published for this version
### Patch Changes - Updated dependencies [6d50947] - @ai-sdk/provider-utils@5.0.81
203a0e0: Centralize Fish Audio speech and transcription model IDs, timestamp defaults, loudness normalization support, and provider option metadata in
Patch Changes Updated dependencies [9184a35] @ai-sdk/provider-utils@5.0.57
Patch Changes @ai-sdk/provider-utils@5.0.56
f5fc6ba: Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while
@ai-sdk/openai-compatible@3.0.92
web_fetch_20260209 and web_search_20260209@ai-sdk/openai-compatible@3.0.91
### Patch Changes - Updated dependencies [08336f1] - @ai-sdk/provider-utils@4.0.17
64a8fae: chore: remove obsolete model IDs for Anthropic, Google, OpenAI, xAI
### Patch Changes - Updated dependencies [58bc42d] - @ai-sdk/provider-utils@4.0.16
Updated dependencies [ 6400cf8 ]
output_format parameter to output_config.format for structured outputs + Enabled native structured output support for Bedrock Anthropic models via output_config.format.9345eac : Refactor Z.AI model ID logic into a model catalog that declares capabilities and provider options, and generate provider capability document
Updated dependencies [ 36802d4 ]
cacheControl provider option as top-level cache_control in Anthropic API request body to support automatic caching.Updated dependencies [ fa15312 ]
2a1c664: feat(provider/anthropic): add support for new Claude Sonnet 4.6 model
7716e18 : Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated req
7716e18: 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.
Updated dependencies [7716e18]
Updated dependencies [5c247e9]
Updated dependencies [dcd2f8d]
Updated dependencies [ 61a315e ]
Updated dependencies [ 57086ff ]
Updated dependencies [ e64ed82 ]
### Patch Changes - Updated dependencies [6d50947] - @ai-sdk/provider-utils@5.0.81
response.usage.raw when streamingUpdated dependencies [ 8202f5b ]
Updated dependencies [ 10026d1 ]
1a054af : Defer construction of provider validation schemas until first use to reduce package import time.
Updated dependencies [ 0c2a9de ]
### Patch Changes - Updated dependencies [53f6731] - @ai-sdk/provider@3.0.7 - @ai-sdk/provider-utils@4.0.13
Updated dependencies [ 36802d4 ]
Updated dependencies [ 0957554 ]
Updated dependencies [ 130e871 ]
Updated dependencies [ 2e89fa4 ]
Updated dependencies [ 9667bf2 ]
Updated dependencies [ 57086ff ]
### Patch Changes - Updated dependencies [6d50947] - @ai-sdk/provider-utils@5.0.81
e729d58 : chore(docs): update README.md for consistent format and to avoid duplication
2c70b90: chore: update provider docs
f5fc6ba: Derive known model ID suggestions from each provider's model catalog declarations so catalog updates automatically update autocomplete, while
heygen.decisionModel('heygen-decision-1') and heygen-decision-1-turbo, including image and video inputs### Patch Changes - Updated dependencies [6d50947] - @ai-sdk/provider-utils@5.0.81
0c2a9de : Add maxOutputTokens and reasoning to experimental decision calls and forward them to language-model-backed decisions. Language-model adapter
maxOutputTokens and reasoning to experimental decision calls and forward them to language-model-backed decisions. Language-model adapters keep reasoning disabled when omitted. Native decision providers warn when either setting is unsupported.ede5b89 : chore: migrate package builds from tsup to tsdown
authToken option to support Authorization: Bearer authentication as an alternative to x-api-key header authentication.c2511c1 : fix: use standards-compliant User-Agent header
Updated dependencies [ e3605f6 ]
Updated dependencies [ af9597b ]
Updated dependencies [ 9667bf2 ]
Updated dependencies [ fe07867 ]
9184a35: Add ordered text, file, and JSON parts to experimental decision state. Support image input in OpenAI Decisions and language model adapters. G
9184a35: Add ordered text, file, and JSON parts to experimental decision state. Support image input in OpenAI Decisions and language model adapters. Gateway retains its existing string and JSON request format and rejects files, as does TypeSafe AI.
Arrays passed directly as state now contain decision state parts. Wrap JSON arrays in an object or a json part.
Normalize all public state forms into an array of parts before calling decision providers. Providers receive text and JSON objects as text and json parts.
Serialize decision file bytes as base64 in OpenTelemetry state attributes. Model-call spans record normalized state parts, while outer spans retain public state inputs.
Preserve native JSON state in TypeSafe AI when state contains one JSON part. Label shared state in language-model decision prompts.
Updated dependencies [9184a35]
e729d58 : chore(docs): update README.md for consistent format and to avoid duplication
Updated dependencies [ 0455398 ]
Updated dependencies [ 215b25e ]
Updated dependencies [ 11b4c2d ]
Updated dependencies [ 0c2a9de ]
02d9b68: fix input_tokens compatibility
input_tokens compatibility### Patch Changes - Updated dependencies [6d50947] - @ai-sdk/provider-utils@5.0.81
Updated dependencies [ 912fb01 ]
bee4f82: fix(anthropic): enable structured output support for claude-haiku-4-5
This fixes an issue where the strict: true property was not included in the request body when using tools with Claude Haiku 4.5, because supportsStructuredOutput was incorrectly set to false for this model.
Claude Haiku 4.5 supports structured outputs, so the strict property should be forwarded to the Anthropic API when specified on tools.
Updated dependencies [ a4ba394 ]
Resolves the Anthropic API breaking change where sampling parameters must use only temperature OR top_p, not both. When both parameters are provided:
2231e84: fix(anthropic): implement temperature/topP mutual exclusivity
Resolves the Anthropic API breaking change where sampling parameters must use only temperature OR top_p, not both. When both parameters are provided:
See Anthropic migration guide: https://platform.claude.com/docs/en/about-claude/models/migrating-to-claude-4
Updated dependencies [ 6bcc0f8 ]
One column per month.