@ai-sdk/anthropic
4.0.106 · 17 Nov 2026Apache-2.024.5M / weekRepositoryHomepagenpmAtom feed
457 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.
4.0.54
15 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.15@ai-sdk/provider-utils 5.0.41
4.0.53
11 Sep 2026Reject unsupported batch request types
Support image generation requests in batches
anthropic: Expand preserved thinking support to cover
prefix_mismatch_behavior: 'error'
Patch Changes
Reject unsupported batch request types
Support image generation requests in batches
anthropic: Expand preserved thinking support to cover
prefix_mismatch_behavior: 'error'
4.0.52
9 Sep 2026anthropic: Add batch cancellation and listing
Patch Changes
anthropic: Add batch cancellation and listing
4.0.51
9 Sep 2026Only updates dependencies:@ai-sdk/provider 4.0.12@ai-sdk/provider-utils 5.0.38
4.0.50
8 Sep 2026Support per-request models in batch
Patch Changes
Support per-request models in batch
4.0.49
2 Sep 2026anthropic: Recognize dated Google Vertex Claude 4 model IDs when selecting model capabilities
4.0.48
2 Sep 2026anthropic: Add fable 5.1 support
Patch Changes
anthropic: Add fable 5.1 support
4.0.47
1 Sep 2026provider: Extend the FilesV4 interface with optional
getFileMetadata,downloadFile(streaming), anddeleteFileoperations, plusabortSignal/headerscall options and a{ type: 'stream' }upload data variant; upload results now exposebyteSize,createdAt, andexpiresAt(also surfaced by the coreuploadFile()helper, which now forwardsabortSignal/headers); addpostMultipartStreamToApi(streaming multipart uploads with deterministic part ordering and failure-path stream teardown),deleteFromApi, andcreateBinaryStreamResponseHandlerto provider-utils
Patch Changes
provider: Extend the FilesV4 interface with optional
getFileMetadata,downloadFile(streaming), anddeleteFileoperations, plusabortSignal/headerscall options and a{ type: 'stream' }upload data variant; upload results now exposebyteSize,createdAt, andexpiresAt(also surfaced by the coreuploadFile()helper, which now forwardsabortSignal/headers); addpostMultipartStreamToApi(streaming multipart uploads with deterministic part ordering and failure-path stream teardown),deleteFromApi, andcreateBinaryStreamResponseHandlerto provider-utils
4.0.46
30 Aug 2026provider/anthropic: Preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests
Patch Changes
provider/anthropic: Preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests
4.0.44 – 4.0.452 releases that only update dependencies@ai-sdk/provider-utils 5.0.33Show each
- 4.0.4528 Aug 2026@ai-sdk/provider-utils 5.0.33
- 4.0.4426 Aug 2026@ai-sdk/provider-utils 5.0.32
4.0.42
25 Aug 2026Add batch completion webhooks.
experimental_startTextBatchaccepts awebhookUrl, and the gateway provider registers it through the batchcallbackUrlcontract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.
Patch Changes
Add batch completion webhooks.
experimental_startTextBatchaccepts awebhookUrl, and the gateway provider registers it through the batchcallbackUrlcontract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.
4.0.40 – 4.0.412 releases that only update dependencies@ai-sdk/provider-utils 5.0.29Show each
- 4.0.4122 Aug 2026@ai-sdk/provider-utils 5.0.29
- 4.0.4019 Aug 2026@ai-sdk/provider-utils 5.0.28
4.0.39
14 Aug 2026Preserve Anthropic server-tool caller metadata in multi-turn conversations.
4.0.35 – 4.0.384 releases that only update dependencies@ai-sdk/provider-utils 5.0.27@ai-sdk/provider 4.0.7Show each
- 4.0.3811 Aug 2026@ai-sdk/provider-utils 5.0.27
- 4.0.3710 Aug 2026@ai-sdk/provider-utils 5.0.26
- 4.0.367 Aug 2026@ai-sdk/provider 4.0.7@ai-sdk/provider-utils 5.0.25
- 4.0.357 Aug 2026@ai-sdk/provider-utils 5.0.24
4.0.34
7 Aug 2026anthropic: Add text batch support
4.0.33
6 Aug 2026Only updates dependencies:@ai-sdk/provider 4.0.6@ai-sdk/provider-utils 5.0.23
4.0.32
6 Aug 2026Reject spliced Anthropic generations while allowing duplicate message start events for the active message.
4.0.29 – 4.0.302 releases that only update dependencies@ai-sdk/provider-utils 5.0.21Show each
- 4.0.304 Aug 2026@ai-sdk/provider-utils 5.0.21
- 4.0.294 Aug 2026@ai-sdk/provider-utils 5.0.20
4.0.28
3 Aug 2026Preserve Anthropic prompt-cache matches by replaying complete code-execution transcripts in their original wire shape.
Patch Changes
Preserve Anthropic prompt-cache matches by replaying complete code-execution transcripts in their original wire shape.
4.0.27
31 Jul 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.18
4.0.26
31 Jul 2026Return visible summarized reasoning when generic reasoning enables adaptive thinking.
Patch Changes
Return visible summarized reasoning when generic reasoning enables adaptive thinking.
4.0.25
30 Jul 2026Add experimental_toolCaller routing to generateText for code mode
Patch Changes
Add experimental_toolCaller routing to generateText for code mode
4.0.22 – 4.0.243 releases that only update dependencies@ai-sdk/provider-utils 5.0.15@ai-sdk/provider 4.0.4Show each
- 4.0.2429 Jul 2026@ai-sdk/provider-utils 5.0.15
- 4.0.2328 Jul 2026@ai-sdk/provider-utils 5.0.14
- 4.0.2227 Jul 2026@ai-sdk/provider 4.0.4@ai-sdk/provider-utils 5.0.13
4.0.21
26 Jul 2026anthropic: Report thinking tokens as reasoning token usage
4.0.20
24 Jul 2026Feat (provider/anthropic): support fallbacks 'default' mode, which routes safety classifier refusals to Anthropic's recommended fallback model (adds the server-side-fallback-2026-07-01 beta automatically)
Feat (provider/anthropic): support mid-conversation tool changes via the toolChanges system message provider option, emitting tool_addition/tool_removal content blocks and the mid-conversation-tool-changes-2026-07-01 beta
Feat (provider/anthropic): add claude-opus-5 model id with frontier-tier capabilities (128k output tokens, structured output, adaptive thinking, xhigh effort, sampling parameter rejection, thinking-disabled only at effort high or below)
4.0.19
23 Jul 2026Fix (provider/anthropic): use current-generation capability defaults for unrecognized Claude model IDs while retaining conservative defaults for legacy Claude and non-Claude models.
4.0.18
21 Jul 2026Warn when an unknown model uses the default 4096 max output token limit.
4.0.17
21 Jul 2026amazon-bedrock: Sanitize unsupported JSON Schema constraints in native Anthropic structured output
provider/anthropic: Warn when parallel tool use is requested with JSON tool structured output
Patch Changes
amazon-bedrock: Sanitize unsupported JSON Schema constraints in native Anthropic structured output
provider/anthropic: Warn when parallel tool use is requested with JSON tool structured output
4.0.16
17 Jul 2026provider/anthropic: Preserve web search citations when replaying assistant messages
Patch Changes
provider/anthropic: Preserve web search citations when replaying assistant messages
4.0.15
14 Jul 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.10
4.0.14
13 Jul 2026provider-utils: Validate provider-response URLs in
getFromApigetFromApinow has avalidateUrlflag. It is optional so existing callers keep compiling (omitting it behaves likefalse, i.e. no validation), but all AI SDK provider packages set it explicitly at every call site so each one makes a visible trust decision. Whentrue, the URL is routed throughfetchWithValidatedRedirects— the same guard used bydownloadBlob— which rejects private/loopback/link-local targets, re-validates every redirect hop, strips proxy/metadata/cookie request headers, and drops all caller headers except the user-agent on cross-origin redirects (custom API-key headers must not follow a redirect off-origin any more thanAuthorizationmay); blocked URLs throwDownloadError. It is enabled at the image/video/audio download and polling call sites where the URL comes from a provider response body; URLs built from developer-configured endpoints passvalidateUrl: falseand are unaffected.A new optional
credentialedOriginwithholds caller headers unless the URL is same-origin with it, so the API key is not sent to a response-supplied host on a different origin.A new optional
trustedOriginexempts URLs (and redirect hops) that are same-origin with the developer-configured provider endpoint from target validation, so self-hosted and localhost deployments whose response URLs point back at the configured host keep working; all other hops are still validated.Also closes range gaps in
validateDownloadUrl(IPv4224.0.0.0/4multicast and the TEST-NET documentation ranges192.0.2.0/24,198.51.100.0/24,203.0.113.0/24; IPv6 documentation ranges2001:db8::/32and3fff::/20), and follows only the fetch-spec redirect status codes (301/302/303/307/308) — aLocationheader on any other status is not followed. This guard performs string/literal checks only and does not resolve DNS; hostnames that resolve to private addresses and DNS rebinding remain out of scope and must be constrained at the network layer (or by injecting a Nodefetchthat pins the resolved IP at connect time) for server deployments handling untrusted URLs. Seecontributing/secure-url-handling.md.Reject empty OpenAI, Anthropic, and Replicate base URLs with a helpful AI SDK
invalid argument error.
Patch Changes
provider-utils: Validate provider-response URLs in
getFromApigetFromApinow has avalidateUrlflag. It is optional so existing callers keep compiling (omitting it behaves likefalse, i.e. no validation), but all AI SDK provider packages set it explicitly at every call site so each one makes a visible trust decision. Whentrue, the URL is routed throughfetchWithValidatedRedirects— the same guard used bydownloadBlob— which rejects private/loopback/link-local targets, re-validates every redirect hop, strips proxy/metadata/cookie request headers, and drops all caller headers except the user-agent on cross-origin redirects (custom API-key headers must not follow a redirect off-origin any more thanAuthorizationmay); blocked URLs throwDownloadError. It is enabled at the image/video/audio download and polling call sites where the URL comes from a provider response body; URLs built from developer-configured endpoints passvalidateUrl: falseand are unaffected.A new optional
credentialedOriginwithholds caller headers unless the URL is same-origin with it, so the API key is not sent to a response-supplied host on a different origin.A new optional
trustedOriginexempts URLs (and redirect hops) that are same-origin with the developer-configured provider endpoint from target validation, so self-hosted and localhost deployments whose response URLs point back at the configured host keep working; all other hops are still validated.Also closes range gaps in
validateDownloadUrl(IPv4224.0.0.0/4multicast and the TEST-NET documentation ranges192.0.2.0/24,198.51.100.0/24,203.0.113.0/24; IPv6 documentation ranges2001:db8::/32and3fff::/20), and follows only the fetch-spec redirect status codes (301/302/303/307/308) — aLocationheader on any other status is not followed. This guard performs string/literal checks only and does not resolve DNS; hostnames that resolve to private addresses and DNS rebinding remain out of scope and must be constrained at the network layer (or by injecting a Nodefetchthat pins the resolved IP at connect time) for server deployments handling untrusted URLs. Seecontributing/secure-url-handling.md.Reject empty OpenAI, Anthropic, and Replicate base URLs with a helpful AI SDK
invalid argument error.
4.0.10 – 4.0.123 releases with no change for you2 dependency updates, 1 maintenance@ai-sdk/provider 4.0.3@ai-sdk/provider-utils 5.0.7Show each
- 4.0.1210 Jul 2026docs, tests or tooling
- 4.0.119 Jul 2026@ai-sdk/provider 4.0.3@ai-sdk/provider-utils 5.0.7
- 4.0.108 Jul 2026@ai-sdk/provider-utils 5.0.6
4.0.9
7 Jul 2026anthropic: Wrap invalid tool input in object
4.0.8
4 Jul 2026anthropic: Forward
thinking: { type: 'disabled' }to the API instead of stripping itPreviously, setting
providerOptions.anthropic.thinking = { type: 'disabled' }(or top-levelreasoning: 'none') was accepted by the schema but silently dropped from the outgoing request. For models that default thinking on (e.g. Sonnet 5), this left thinking enabled and could consume a smallmax_tokensbudget entirely. Thedisabledvalue is now sent to the Anthropic Messages API.
4.0.7
2 Jul 2026Add experimental streaming transcription support for transcription models, including OpenAI
gpt-realtime-whisperand xAI WebSocket STT.
Patch Changes
Add experimental streaming transcription support for transcription models, including OpenAI
gpt-realtime-whisperand xAI WebSocket STT.
4.0.6
2 Jul 2026- Security
Prevent prototype pollution when synchronously parsing provider JSON inputs and expose
secureJsonParsefrom provider-utils. Normalize a bare
https://api.anthropic.combase URL to include/v1.
Patch Changes
- Security
Prevent prototype pollution when synchronously parsing provider JSON inputs and expose
secureJsonParsefrom provider-utils. Normalize a bare
https://api.anthropic.combase URL to include/v1.
4.0.5
1 Jul 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.3
4.0.4
30 Jun 2026Feat (provider/anthropic): add
claude-sonnet-5model id
4.0.3
30 Jun 2026Only updates dependencies:@ai-sdk/provider 4.0.1@ai-sdk/provider-utils 5.0.2
4.0.2
29 Jun 2026anthropic: Correctly map delta type when code execution tools are used
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.