@ai-sdk/anthropic 3.0.127 → 3.0.128

package/docs/05-anthropic.mdx

@@ -200,9 +200,18 @@ verify that a tool call was made.
 
 ### Effort
 
-Anthropic introduced an `effort` option with `claude-opus-4-5` that affects thinking, text responses, and function calls. Effort defaults to `high` and you can set it to `medium` or `low` to save tokens and to lower time-to-last-token latency (TTLT). `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `claude-fable-5`, `claude-fable-5-1`, `claude-sonnet-5`, and `claude-sonnet-5-5` additionally support `xhigh` for maximum reasoning effort.
+Anthropic introduced an `effort` option with `claude-opus-4-5` that affects thinking, text responses, and function calls. Effort defaults to `high` and you can set it to `medium` or `low` to save tokens and to lower time-to-last-token latency (TTLT). `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `claude-fable-5`, `claude-fable-5-1`, `claude-sonnet-5`, `claude-sonnet-5-5`, and `claude-haiku-5-5` additionally support `xhigh` for maximum reasoning effort.
 
-On `claude-opus-5`, thinking can only be disabled at effort levels up to and including `high`. When you combine `thinking: { type: 'disabled' }` with `effort: 'xhigh'` or `effort: 'max'`, the AI SDK lowers the effort to `high` and emits a warning instead of sending a request that the API would reject.
+On `claude-opus-5` and `claude-haiku-5-5`, thinking can only be disabled at effort levels up to and including `high`. When you combine `thinking: { type: 'disabled' }` with `effort: 'xhigh'` or `effort: 'max'`, the AI SDK lowers the effort to `high` and emits a warning instead of sending a request that the API would reject.
+
+`claude-haiku-5-5` is the first Haiku model with effort levels and supports all
+five of them. It uses adaptive thinking and does not support thinking token
+budgets: the AI SDK converts `thinking: { type: 'enabled', budgetTokens }` to
+`{ type: 'adaptive' }` and emits a warning. Use `effort` to control how much it
+thinks. Unlike `claude-sonnet-5-5`, thinking can still be turned off with
+`thinking: { type: 'disabled' }`, but only at `low`, `medium`, and `high` effort.
+Start at `medium` effort and test other levels rather than carrying over the
+settings you used on `claude-haiku-4-5`.
 
 On `claude-opus-5-5`, thinking is always adaptive and cannot be disabled, so
 `effort` is the main control for latency and cost. The API default effort for
@@ -325,6 +334,8 @@ The `inferenceGeo` option accepts `'us'` (US-only infrastructure) or `'global'`
 
 Claude Fable 5 has safeguards that limit its performance in certain areas like cybersecurity, biology, and chemistry, and automated safety checks are run on every request.
 
+Claude Haiku 5.5 has the same biology safeguards as Claude Sonnet 5 and 5.5, plus safeguards that prevent cyber misuse.
+
 Claude Sonnet 5.5 also has safety classifiers enabled, including for cybersecurity, biology, and reasoning extraction. Requests that ask the model to reproduce its internal reasoning in the response text can be declined with the `reasoning_extraction` category; use `thinking: { type: 'adaptive', display: 'summarized' }` and read the reasoning parts instead.
 
 When one of these checks blocks a request, the API does not answer it. Instead it returns a classifier block: a `200` response with a `refusal` stop reason and an optional `stop_details` object describing the category that triggered the block. The AI SDK surfaces this as a `content-filter` finish reason, with the details available on `providerMetadata.anthropic.stopDetails`.
@@ -2012,6 +2023,7 @@ and the `mediaType` should be set to `'application/pdf'`.
 | `claude-opus-5`     | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `claude-sonnet-5-5` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `claude-sonnet-5`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `claude-haiku-5-5`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `claude-fable-5`    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `claude-opus-4-8`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `claude-opus-4-7`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/anthropic",
-  "version": "3.0.127",
+  "version": "3.0.128",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",

package/src/anthropic-messages-language-model.ts

@@ -340,6 +340,7 @@ export class AnthropicMessagesLanguageModel implements LanguageModelV3 {
       rejectsSamplingParameters,
       rejectsThinkingDisabledAboveHighEffort,
       rejectsThinkingDisabled,
+      rejectsBudgetThinking,
       rejectsForcedToolUse,
       supportsBetweenToolsThinking,
       isKnownModel,
@@ -488,9 +489,9 @@ export class AnthropicMessagesLanguageModel implements LanguageModelV3 {
         toolsetNames,
       });
 
-    // Some models always run adaptive thinking and reject `disabled` and
-    // budget-based `enabled` thinking with a 400. Drop the unsupported
-    // setting and keep the request adaptive so it still succeeds.
+    // Some models always run adaptive thinking and reject `disabled` thinking
+    // with a 400. Drop the unsupported setting and keep the request adaptive
+    // so it still succeeds.
     if (rejectsThinkingDisabled && anthropicOptions?.thinking != null) {
       const requestedThinking = anthropicOptions.thinking;
       const requestedType =
@@ -514,18 +515,30 @@ export class AnthropicMessagesLanguageModel implements LanguageModelV3 {
             `The thinking setting has been removed. Lower 'effort' to reduce thinking.`,
         });
         anthropicOptions.thinking = undefined;
-      } else if (requestedType === 'enabled') {
-        warnings.push({
-          type: 'unsupported',
-          feature: 'providerOptions.anthropic.thinking',
-          details:
-            `budget-based thinking is not supported by ${this.modelId}; it always uses adaptive thinking. ` +
-            `Using adaptive thinking instead. Use 'effort' to control how much the model thinks.`,
-        });
-        anthropicOptions.thinking = { type: 'adaptive' };
       }
     }
 
+    // Models that only support adaptive thinking reject budget-based thinking
+    // with a 400. Use adaptive thinking instead and let `effort` control how
+    // much the model thinks.
+    if (
+      rejectsBudgetThinking &&
+      anthropicOptions?.thinking != null &&
+      'type' in anthropicOptions.thinking &&
+      anthropicOptions.thinking.type === 'enabled'
+    ) {
+      warnings.push({
+        type: 'unsupported',
+        feature: 'providerOptions.anthropic.thinking',
+        details: rejectsThinkingDisabled
+          ? `budget-based thinking is not supported by ${this.modelId}; it always uses adaptive thinking. ` +
+            `Using adaptive thinking instead. Use 'effort' to control how much the model thinks.`
+          : `budget-based thinking is not supported by ${this.modelId}. ` +
+            `Using adaptive thinking instead. Use 'effort' to control how much the model thinks.`,
+      });
+      anthropicOptions.thinking = { type: 'adaptive' };
+    }
+
     const thinking = anthropicOptions?.thinking;
     const thinkingType =
       thinking != null && 'type' in thinking ? thinking.type : undefined;
@@ -2970,6 +2983,11 @@ export function getModelCapabilities(modelId: string): {
    * are rejected with a 400.
    */
   rejectsThinkingDisabled: boolean;
+  /**
+   * Budget-based thinking (`thinking.type` `enabled` with `budget_tokens`) is
+   * rejected with a 400. Only adaptive thinking is supported.
+   */
+  rejectsBudgetThinking: boolean;
   /**
    * Forced tool use (`tool_choice` `any` or a named tool) is rejected with a 400.
    */
@@ -2988,6 +3006,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: true,
       rejectsThinkingDisabled: true,
+      rejectsBudgetThinking: true,
       rejectsForcedToolUse: true,
       supportsBetweenToolsThinking: true,
       isKnownModel: true,
@@ -2999,10 +3018,24 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: true,
       rejectsThinkingDisabled: true,
+      rejectsBudgetThinking: true,
       rejectsForcedToolUse: true,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
     };
+  } else if (modelId.includes('claude-haiku-5-5')) {
+    // Thinking can be turned off, but only up to `high` effort.
+    return {
+      maxOutputTokens: 128000,
+      supportsStructuredOutput: true,
+      rejectsSamplingParameters: true,
+      rejectsThinkingDisabledAboveHighEffort: true,
+      rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: true,
+      rejectsForcedToolUse: false,
+      supportsBetweenToolsThinking: false,
+      isKnownModel: true,
+    };
   } else if (modelId.includes('claude-opus-5')) {
     return {
       maxOutputTokens: 128000,
@@ -3010,6 +3043,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: true,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3021,6 +3055,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: true,
+      rejectsBudgetThinking: true,
       rejectsForcedToolUse: true,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3032,6 +3067,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: true,
+      rejectsBudgetThinking: true,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3047,6 +3083,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3061,6 +3098,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3076,6 +3114,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3087,6 +3126,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3098,6 +3138,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3109,6 +3150,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3120,6 +3162,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: true,
@@ -3133,6 +3176,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: false,
@@ -3147,6 +3191,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: true,
       rejectsThinkingDisabledAboveHighEffort: true,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: false,
@@ -3160,6 +3205,7 @@ export function getModelCapabilities(modelId: string): {
       rejectsSamplingParameters: false,
       rejectsThinkingDisabledAboveHighEffort: false,
       rejectsThinkingDisabled: false,
+      rejectsBudgetThinking: false,
       rejectsForcedToolUse: false,
       supportsBetweenToolsThinking: false,
       isKnownModel: false,

package/src/anthropic-messages-options.ts

@@ -5,6 +5,7 @@ export type AnthropicMessagesModelId =
   | 'claude-3-haiku-20240307'
   | 'claude-haiku-4-5-20251001'
   | 'claude-haiku-4-5'
+  | 'claude-haiku-5-5'
   | 'claude-opus-4-0'
   | 'claude-opus-4-20250514'
   | 'claude-opus-4-1-20250805'