Latest Release: Version 3.x supports AI SDK v6 stable with the Claude Agent SDK. For AI SDK v5 support, use the
ai-sdk-v5tag.
ai-sdk-provider-claude-code lets you use Claude via the Vercel AI SDK through the official @anthropic-ai/claude-agent-sdk and the Claude Code CLI.
| Provider Version | AI SDK Version | Underlying SDK | NPM Tag | Status | Branch |
|---|---|---|---|---|---|
| 3.x.x | v6 | @anthropic-ai/claude-agent-sdk |
latest |
Stable | main |
| 2.x.x | v5 | @anthropic-ai/claude-agent-sdk |
ai-sdk-v5 |
Stable | ai-sdk-v5 |
| 1.x.x | v5 | @anthropic-ai/claude-code (legacy) |
v1-claude-code-sdk |
Legacy | v1 |
| 0.x.x | v4 | @anthropic-ai/claude-code (legacy) |
ai-sdk-v4 |
Legacy | ai-sdk-v4 |
For AI SDK v6 (recommended):
npm install ai-sdk-provider-claude-code ai@^6.0.0
# or explicitly: npm install ai-sdk-provider-claude-code@latestFor AI SDK v5:
npm install ai-sdk-provider-claude-code@ai-sdk-v5 ai@^5.0.0For AI SDK v4 (legacy):
npm install ai-sdk-provider-claude-code@ai-sdk-v4 ai@^4.3.16
# or use specific version: npm install ai-sdk-provider-claude-code@^0.2.2Starting from v3.2.0, this package requires Zod 4.
npm install ai-sdk-provider-claude-code ai zod@^4.0.0Note: Zod 3 support was dropped in v3.2.0 due to the underlying
@anthropic-ai/claude-agent-sdk@0.2.xrequiring Zod 4. If you need Zod 3 support, useai-sdk-provider-claude-code@3.1.x.
npm install -g @anthropic-ai/claude-code
claude login# For AI SDK v6 (recommended)
npm install ai-sdk-provider-claude-code ai@^6.0.0
# For AI SDK v5
npm install ai-sdk-provider-claude-code@ai-sdk-v5 ai@^5.0.0
# For AI SDK v4 (legacy)
npm install ai-sdk-provider-claude-code@ai-sdk-v4 ai@^4.3.16This is an unofficial community provider and is not affiliated with or endorsed by Anthropic or Vercel. By using this provider:
- You understand that your data will be sent to Anthropic's servers through the Claude Code SDK
- You agree to comply with Anthropic's Terms of Service
- You acknowledge this software is provided "as is" without warranties of any kind
Please ensure you have appropriate permissions and comply with all applicable terms when using this provider.
import { streamText } from 'ai';
import { claudeCode } from 'ai-sdk-provider-claude-code';
const result = streamText({
model: claudeCode('haiku'),
prompt: 'Hello, Claude!',
});
const text = await result.text;
console.log(text);// npm install ai-sdk-provider-claude-code@ai-sdk-v5 ai@^5.0.0
import { streamText } from 'ai';
import { claudeCode } from 'ai-sdk-provider-claude-code';
const result = streamText({
model: claudeCode('haiku'),
prompt: 'Hello, Claude!',
});
const text = await result.text;
console.log(text);This version upgrades to AI SDK v6 stable with updated provider types:
usage.rawnow contains raw provider usage (previously inproviderMetadata['claude-code'].rawUsage)- Internal type changes for
LanguageModelV3UsageandLanguageModelV3FinishReason(transparent to most users)
This version migrates to @anthropic-ai/claude-agent-sdk with new defaults for better control:
- System prompt is no longer applied by default
- Filesystem settings (CLAUDE.md, settings.json) are no longer loaded by default
- See Migrating to Claude Agent SDK section below for migration details
See Breaking Changes Guide for details on migrating from v0.x to v1.x.
Key changes:
- Requires AI SDK v5
- New streaming API pattern
- Updated token usage properties
- Changed message types
opus- Claude Opus (most capable)sonnet- Claude Sonnet (balanced performance)haiku- Claude Haiku (fastest, most cost-effective)
You can also use full model identifiers directly (e.g., claude-opus-4-5, claude-sonnet-4-5-20250514).
- Usage Guide - Comprehensive examples and configuration
- Breaking Changes - v0.x to v1.x migration guide
- Troubleshooting - Common issues and solutions
- Examples - Sample scripts and patterns
- Tool Streaming Support - Event semantics and performance notes
Version 2.0.0 migrates from @anthropic-ai/claude-code to @anthropic-ai/claude-agent-sdk. Two defaults changed:
- System prompt is no longer applied by default.
- Filesystem settings (CLAUDE.md, settings.json) are not loaded by default.
Restore old behavior explicitly:
import { claudeCode } from 'ai-sdk-provider-claude-code';
const model = claudeCode('sonnet', {
systemPrompt: { type: 'preset', preset: 'claude_code' },
settingSources: ['user', 'project', 'local'],
});CLAUDE.md requires:
systemPrompt: { type: 'preset', preset: 'claude_code' }settingSourcesincludes'project'
New recommended behavior (explicit config):
const model = claudeCode('sonnet', {
systemPrompt: 'You are a helpful assistant specialized in ...',
settingSources: ['project'], // or omit for no filesystem settings
});CLI install and auth are unchanged:
npm install -g @anthropic-ai/claude-code
claude loginIf you're upgrading from version 1.x:
- Update the package:
npm install ai-sdk-provider-claude-code@latest - If you relied on default system prompt or CLAUDE.md, add explicit configuration:
const model = claudeCode('sonnet', { systemPrompt: { type: 'preset', preset: 'claude_code' }, settingSources: ['user', 'project', 'local'], });
- If you never used CLAUDE.md or custom system prompts, no changes needed - v2.0.0 works the same for you.
Benefits of v2.0.0:
- Predictable behavior across environments (no hidden filesystem settings)
- Better suited for CI/CD and multi-tenant applications
- Explicit configuration over implicit defaults
- Future-proof alignment with Claude Agent SDK design
This provider supports native structured outputs via the Claude Agent SDK (v0.1.45+). When using generateObject() or streamObject(), the SDK guarantees schema-compliant JSON responses through constrained decoding.
import { generateObject } from 'ai';
import { claudeCode } from 'ai-sdk-provider-claude-code';
import { z } from 'zod';
const result = await generateObject({
model: claudeCode('sonnet'),
schema: z.object({
name: z.string(),
age: z.number(),
email: z.string().email(),
}),
prompt: 'Generate a user profile for a software developer',
});
console.log(result.object); // Guaranteed to match schema
// { name: "Alex Chen", age: 28, email: "alex@example.com" }Benefits:
- ✅ Guaranteed schema compliance - Constrained decoding ensures valid output
- ✅ No JSON parsing errors - SDK handles all validation
- ✅ No prompt engineering - Schema enforcement is native to the SDK
- ✅ Better performance - No retry/extraction logic needed
Note: A schema is required for JSON output. Using
responseFormat: { type: 'json' }without a schema is not supported by Claude Code (matching Anthropic's official provider behavior). Anunsupported-settingwarning will be emitted and the call will be treated as plain text. Always usegenerateObject()orstreamObject()with a Zod schema for guaranteed JSON output.
- 🚀 Vercel AI SDK compatibility
- 🔄 Streaming support
- 💬 Multi-turn conversations
- 🎯 Native structured outputs with guaranteed schema compliance
- 🛑 AbortSignal support
- 🔧 Tool management (MCP servers, permissions)
- 🧩 Callbacks (hooks, canUseTool)
This provider exposes Agent SDK options directly. Key options include:
| Option | Description |
|---|---|
betas |
Enable beta features (e.g., ['context-1m-2025-08-07']) |
sandbox |
Configure sandbox behavior ({ enabled: true }) |
plugins |
Load custom plugins from local paths |
resumeSessionAt |
Resume session at a specific message UUID |
enableFileCheckpointing |
Enable file rewind support |
maxBudgetUsd |
Maximum budget in USD for the query |
tools |
Tool configuration (array of names or preset) |
allowDangerouslySkipPermissions |
Allow bypassing permissions |
persistSession |
When false, disables session persistence to disk (v3.2.0+) |
spawnClaudeCodeProcess |
Custom process spawner for VMs/containers (v3.2.0+) |
permissionMode |
Permission mode: 'default', 'acceptEdits', 'bypassPermissions', 'plan', 'delegate', 'dontAsk' |
Agent definitions (agents) now support additional fields (v3.2.0+):
disallowedTools- Tools to explicitly disallow for the agentmcpServers- MCP servers available to the agentcriticalSystemReminder_EXPERIMENTAL- Experimental critical reminder
See ClaudeCodeSettings for the full list of supported options (e.g., allowedTools, disallowedTools, hooks, canUseTool, env, settingSources).
For options not explicitly exposed, use the sdkOptions escape hatch. It overrides explicit settings,
but provider-managed fields are ignored (model, abortController, prompt, outputFormat).
If you set sdkOptions.resume, it also drives the streaming prompt session_id so the SDK
and prompt target the same session.
const model = claudeCode('sonnet', {
betas: ['context-1m-2025-08-07'],
sandbox: { enabled: true },
persistSession: false, // Don't persist session to disk
sdkOptions: {
maxBudgetUsd: 1,
resume: 'session-abc',
},
});- Enable streaming input (
streamingInput: 'always'or providecanUseTool) before sending images. - Supported payloads: data URLs (
data:image/png;base64,...), strings prefixed withbase64:<mediaType>,<data>, or objects{ data: '<base64>', mimeType: 'image/png' }. - Remote HTTP(S) image URLs are ignored with the warning "Image URLs are not supported by this provider; supply base64/data URLs." (
supportsImageUrlsremainsfalse). - When streaming input is disabled, image parts trigger the streaming prerequisite warning and are omitted from the request.
- Use realistic image payloads—very small placeholders may result in the model asking for a different image.
examples/images.tsaccepts a local image path and converts it to a data URL on the fly:npx tsx examples/images.ts /absolute/path/to/image.png.
Claude Code supports Skills - custom tools and capabilities defined in your user or project settings. To enable skills, configure both settingSources and allowedTools:
import { claudeCode } from 'ai-sdk-provider-claude-code';
import { streamText } from 'ai';
const result = await streamText({
model: claudeCode('sonnet', {
settingSources: ['user', 'project'],
allowedTools: ['Skill', 'Read', 'Write', 'Bash'],
}),
prompt: 'Use my /custom-skill to help with this task',
});Requirements:
settingSources- Where to load skills from ('user','project','local')allowedToolsmust include'Skill'to invoke skills
Where to define Skills:
- User:
~/.claude/skills/your-skill/SKILL.md - Project:
.claude/skills/your-skill/SKILL.md
Validation: If you add 'Skill' to allowedTools but forget to set settingSources, a validation warning will alert you that skills won't load.
See examples/skills-management.ts for more examples.
- Requires Node.js ≥ 18
- Image inputs require streaming mode with base64/data URLs (remote fetch is not supported)
- Some AI SDK parameters unsupported (temperature, maxTokens, etc.)
canUseToolrequires streaming input at the SDK level (AsyncIterable prompt). This provider supports it viastreamingInput: use'auto'(default whencanUseToolis set) or'always'. See GUIDE for details.
- In addition to
tool-callandtool-result, this provider emits a distincttool-errorstream event when a tool execution fails. - For parity with other tool events,
tool-errorincludesproviderExecuted: trueandproviderMetadata['claude-code'](e.g.,rawError). These fields are documented extensions; downstream consumers may safely ignore them if unused. - See Tool Streaming Support for full event list, ordering guarantees, and performance considerations.
We welcome contributions, especially:
- Code structure improvements
- Performance optimizations
- Better error handling
- Additional examples
See Contributing Guidelines for details.
For development status and technical details, see Development Status.
MIT