@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.x · latest line
4.0.1
27 Jun 2026Only updates a dependency:@ai-sdk/provider-utils 5.0.1
4.0.0
25 Jun 2026- Breaking
anthropic: Remove cacheCreationInputTokens from providerMetadata
- Breaking
ai: Add support for uploading provider skills using the provider references abstraction
- Breaking
Remove CommonJS exports from all packages. All packages are now ESM-only (
"type": "module"). Consumers usingrequire()must switch to ESMimportsyntax.
Major Changes
- Breaking
anthropic: Remove cacheCreationInputTokens from providerMetadata
- Breaking
ai: Add support for uploading provider skills using the provider references abstraction
- Breaking
Remove CommonJS exports from all packages. All packages are now ESM-only (
"type": "module"). Consumers usingrequire()must switch to ESMimportsyntax. - Breaking
provider: Add new top-level reasoning parameter to spec and support it in
generateTextandstreamText - Breaking
Start v7 pre-release
- Breaking
Make provider implementations code patterns more consistent, including renaming certain exported symbols
For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
Patch Changes
provider/anthropic: Fix remaining errors with Anthropic
code_executiontool dynamic calls from latestweb_fetchorweb_searchAdd AI Gateway hint to provider READMEs
anthropic: Reorder assistant content b/w client and provider tool use
Feat (provider/anthropic): support passing metadata.user_id
anthropic: Add the new advisor tool
- Removed
Remove stale
effort-2025-11-24beta header — the extended thinking effort parameter is GA and no longer requires the beta flag. Vertex AI's strict validator was actively rejecting requests with this header. provider/anthropic: Automatically use sandbox in bash tool
Trigger release for all packages after provenance setup
More precise default message for tool execution denial
anthropic: Skip passing beta header for tool search tools
anthropic: Preserve the error code returned by model
- Breaking
Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.
Feat (provider/anthropic): add support for inference_geo provider option
Trigger initial canary release
provider: Preserve error type prefix in getErrorMessage
provider-utils: Add
spawnCommandmethod toExperimental_Sandboxto allow for detached command executionprovider: Change file part data property to be tagged with a type and remove the image part type
provider: Align tool result output content file part types with top-level message file part types
provider/anthropic: Add support for
claude-fable-5and thefallbacksAPI parameterAdd workflow serialization support to all provider models.
@ai-sdk/provider-utils: NewserializeModel()helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.All providers:
headersis now optional in provider config types. This is non-breaking — existing code that passesheaderscontinues to work. Custom provider implementations that construct model configs manually can now omitheaders, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.All provider model classes now include
WORKFLOW_SERIALIZEandWORKFLOW_DESERIALIZEstatic methods, enabling them to cross workflow step boundaries without serialization errors.provider/anthropic: Add support for Opus 4.7 and relevant API enhancements
- 3.x
3.0.142 – 3.0.1432 releases that only update dependencies@ai-sdk/provider-utils 4.0.67Show each
- 3.0.14317 Nov 2026@ai-sdk/provider-utils 4.0.67
- 3.0.14210 Nov 2026@ai-sdk/provider-utils 4.0.66
3.0.140
7 Nov 2026Disable MCP connector tools when structured output falls back to the JSON response tool and the caller selects no tools or a named application tool, and when a named application tool choice falls back to automatic tool selection.
Patch Changes
Disable MCP connector tools when structured output falls back to the JSON response tool and the caller selects no tools or a named application tool, and when a named application tool choice falls back to automatic tool selection.
3.0.139
6 Nov 2026anthropic: Support adding tools by value in mid-conversation
toolChanges(inline-tools-2026-09-15)Reject conflicting inline tool additions when a named tool choice falls back to auto or the internal JSON response tool limits available application tools, including definitions replayed from conversation history. Only validate definitions emitted in the request, preserving warning-only handling of ignored additions on the initial system message.
3.0.138
3 Nov 2026Enable native structured output and strict tools for supported Claude 5 models on Bedrock. In automatic mode, Bedrock and Anthropic now fall back for schemas that native structured output cannot represent: recursive references, open objects, or more than ten optional properties. Anthropic uses the JSON response tool; Bedrock Converse uses the JSON tool or JSON instructions for models that reject forced tool use. The JSON-tool fallback excludes disabled and unselected application tools. Explicit
outputFormatselection remains unchanged.anthropic: Parse valid JSON string tool input and safely serialize BigInt and cycles in tool results
Patch Changes
Enable native structured output and strict tools for supported Claude 5 models on Bedrock. In automatic mode, Bedrock and Anthropic now fall back for schemas that native structured output cannot represent: recursive references, open objects, or more than ten optional properties. Anthropic uses the JSON response tool; Bedrock Converse uses the JSON tool or JSON instructions for models that reject forced tool use. The JSON-tool fallback excludes disabled and unselected application tools. Explicit
outputFormatselection remains unchanged.anthropic: Parse valid JSON string tool input and safely serialize BigInt and cycles in tool results
3.0.137
30 Oct 2026anthropic: Use native structured outputs for Claude models that reject forced tool use (Sonnet 5.5, Opus 5.5, Fable 5.1) even when the provider disables them by default, as Amazon Bedrock and Google Vertex do. Self-referencing schemas keep the JSON response tool. Also keep
definitionsand$defsnext to a top-level$refwhen sanitizing structured output schemas, so the reference still resolves.anthropic: When the JSON response tool is in use but the model answers in text without calling it (for example with manual thinking, where the forced tool choice is downgraded to
auto), return the final answer text instead of dropping it. Text before a tool call, result, or message continuation is still dropped.anthropic: Keep the JSON response tool for schemas that native structured outputs cannot represent when upgrading models that reject forced tool use. Schemas with open objects (maps, free-form objects) would otherwise come back as
{}, and schemas with more than 10 optional properties can be rejected as too complex.
3.0.136
29 Oct 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.63
3.0.135
21 Oct 2026Defer validation schema construction until first use to reduce provider import time.
Defer construction of Anthropic provider option schemas until they are first used to reduce package import time.
Patch Changes
Defer validation schema construction until first use to reduce provider import time.
Defer construction of Anthropic provider option schemas until they are first used to reduce package import time.
3.0.134
20 Oct 2026Add MiniMax M3.1 Flash support with reasoning effort, image detail, video input and frame sampling, prompt cache control, and sampling controls.
3.0.132 – 3.0.1332 releases that only update dependencies@ai-sdk/provider-utils 4.0.61@ai-sdk/provider 3.0.19Show each
3.0.131
15 Oct 2026Fall back to automatic tool choice with a warning when manual thinking is enabled with a required or named tool choice, avoiding an Anthropic API 400 error. Named tool choices send only the selected tool.
Patch Changes
Fall back to automatic tool choice with a warning when manual thinking is enabled with a required or named tool choice, avoiding an Anthropic API 400 error. Named tool choices send only the selected tool.
3.0.130
13 Oct 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.58
3.0.129
9 Oct 2026anthropic: Preserve tools when disabling tool calls
anthropic: Preserve failed tool search results in conversation history
3.0.128
7 Oct 2026anthropic: Add Claude Haiku 5.5 support
3.0.127
30 Sep 2026provider/anthropic: Add
safeguardsprovider option andsafeguardResultsprovider metadata (dangerous tool use classifier)
3.0.126
30 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.57
3.0.125
28 Sep 2026anthropic: Add Claude Sonnet 5.5 support
eeabdce: Normalize dangling programmatic tool caller references in conversation history after pruning. Before a subsequent user message, omit caller metadata whose source code execution call is missing and emit a warning, preserving the retained tool calls and results. Keep caller metadata unchanged for active tool continuations.
3.0.124
28 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.56
3.0.123
27 Sep 2026Preserve effort updates on empty system messages at the beginning of a conversation, including consecutive updates.
Patch Changes
Preserve effort updates on empty system messages at the beginning of a conversation, including consecutive updates.
3.0.121 – 3.0.1222 releases that only update dependencies@ai-sdk/provider-utils 4.0.54@ai-sdk/provider 3.0.17Show each
3.0.120
22 Sep 2026anthropic: Add Claude Opus 5.5 support
3.0.119
21 Sep 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.52
3.0.118
11 Sep 2026anthropic: Expand preserved thinking support to cover
prefix_mismatch_behavior: 'error'
3.0.117
9 Sep 2026Only updates dependencies:@ai-sdk/provider 3.0.16@ai-sdk/provider-utils 4.0.51
3.0.116
2 Sep 2026anthropic: Add fable 5.1 support
3.0.112 – 3.0.1154 releases that only update dependencies@ai-sdk/provider-utils 4.0.50Show each
- 3.0.11530 Aug 2026@ai-sdk/provider-utils 4.0.50
- 3.0.11426 Aug 2026@ai-sdk/provider-utils 4.0.49
- 3.0.11325 Aug 2026@ai-sdk/provider-utils 4.0.48
- 3.0.11224 Aug 2026@ai-sdk/provider-utils 4.0.47
3.0.111
14 Aug 2026Preserve Anthropic server-tool caller metadata in multi-turn conversations.
Patch Changes
Preserve Anthropic server-tool caller metadata in multi-turn conversations.
3.0.107 – 3.0.1104 releases that only update dependencies@ai-sdk/provider-utils 4.0.45@ai-sdk/provider 3.0.15Show each
- 3.0.11011 Aug 2026@ai-sdk/provider-utils 4.0.45
- 3.0.10911 Aug 2026@ai-sdk/provider 3.0.15@ai-sdk/provider-utils 4.0.44
- 3.0.10810 Aug 2026@ai-sdk/provider-utils 4.0.43
- 3.0.1077 Aug 2026@ai-sdk/provider-utils 4.0.42
3.0.105
3 Aug 2026Preserve Anthropic prompt-cache matches by replaying complete code-execution transcripts in their original wire shape.
3.0.104
29 Jul 2026Only updates a dependency:@ai-sdk/provider-utils 4.0.41
3.0.103
26 Jul 2026anthropic: Report thinking tokens as reasoning token usage
3.0.102
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)
3.0.101
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.
3.0.100
22 Jul 2026Warn when an unknown model uses the default 4096 max output token limit.
3.0.99
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
3.0.98
17 Jul 2026provider/anthropic: Preserve web search citations when replaying assistant messages
Patch Changes
provider/anthropic: Preserve web search citations when replaying assistant messages
3.0.96 – 3.0.972 releases that only update dependencies@ai-sdk/provider-utils 4.0.39@ai-sdk/provider 3.0.14Show each
3.0.95
7 Jul 2026More precise default message for tool execution denial
Patch Changes
More precise default message for tool execution denial
3.0.94
6 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.
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.