Anthropic

The Anthropic provider speaks Claude's native /v1/messages API. Use it for Claude Opus/Sonnet/Haiku with vision, extended thinking (reasoning), prompt caching, and tool use. The same provider also drives Claude-on-Vertex — see Vertex.

Setup

The factory lives at the @deuz-sdk/core/anthropic subpath. It returns a Provider: call it with a model id to get a LanguageModel descriptor.

import { createAnthropic } from '@deuz-sdk/core/anthropic';

// Read the key at the app layer — the SDK core never touches process.env.
const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const model = anthropic('claude-opus-4-8');

A pre-built default provider is also exported for when the key is supplied at the call layer (via deps.keyProvider or a createClient):

import { anthropic } from '@deuz-sdk/core/anthropic';

const model = anthropic('claude-opus-4-8');

Factory options

createAnthropic(settings) accepts:

Settings are stashed on the descriptor via a private Symbol, so they never widen the public LanguageModel type or leak through JSON.stringify/Object.keys.

Models and capabilities

The descriptor { provider: 'anthropic', modelId, surface: 'anthropic' } is resolved against the registry, which is the single source of truth for per-model behavior. Pinned Claude slugs:

On Opus 4.7+, Sonnet 5 and Fable 5 the registry also flags samplingRestrictions — non-default temperature/top_p/top_k return HTTP 400 on those models, so the adapter never sends them.

Unknown slugs do not throw. A future claude-opus-4-9 falls back to conservative anthropic-surface defaults (tools/reasoning/structured-output off, max_tokens 4,096) and logs a warning via deps.logger, so new releases work without an SDK upgrade — pin a known slug to keep the full capability matrix.

Basic streaming

streamChat returns synchronously and never throws — failures surface as an error part on fullStream and reject the usage/finishReason promises. See streamChat.

import { streamChat } from '@deuz-sdk/core';
import { createAnthropic } from '@deuz-sdk/core/anthropic';

const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const result = streamChat({
  model: anthropic('claude-opus-4-8'),
  messages: [{ role: 'user', content: 'Write a haiku about TypeScript.' }],
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

const usage = await result.usage;
console.log('\ntokens:', usage.totalTokens);

For a one-shot, buffered call use generateText instead.

Extended thinking (reasoning)

Set effort to control Claude's thinking depth. The wire depends on the model generation (effortWire in the registry):

• Opus 4.7+, Sonnet 5, Fable 5 (effortWire: 'output_config'): the adapter sends output_config.effort with your level verbatim ('low' | 'medium' | 'high' | 'xhigh' | 'max'). Manual thinking.budget_tokens returns HTTP 400 on these models, so the adapter never sends a thinking block. Adaptive thinking is always available; omitting effort leaves the model default.
• Opus 4.6 and older (effortWire: 'budget_tokens'): the canonical level maps to a thinking.budget_tokens value:

On the legacy wire, max_tokens is automatically raised to at least budget_tokens + 1024, and temperature/topP are not sent (Anthropic requires them unset with thinking enabled). Thinking text streams as reasoning-delta parts on fullStream; a trailing reasoning-delta carries the block signature. Thinking tokens bill inside outputTokens; since May 2026 the API also breaks them out, so usage.reasoningTokens reports the output_tokens_details.thinking_tokens count (0 on older models).

import { streamChat } from '@deuz-sdk/core';
import { createAnthropic } from '@deuz-sdk/core/anthropic';

const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const result = streamChat({
  model: anthropic('claude-opus-4-8'),
  messages: [{ role: 'user', content: 'Is 9007199254740993 prime? Reason it through.' }],
  effort: 'high',
});

for await (const part of result.fullStream) {
  if (part.type === 'reasoning-delta') {
    if (part.text) process.stdout.write(`[think] ${part.text}`);
    if (part.signature) console.log('\n[signature attached]');
  } else if (part.type === 'text-delta') {
    process.stdout.write(part.text);
  }
}

The signature round-trips automatically inside the agentic loop — preserve any reasoning part you persist, or follow-up tool turns will be rejected.

Vision

Pass an image part. The value may be a base64 string, a data URL, an http(s) URL, or raw Uint8Array bytes; mediaType is forwarded as the source media_type.

import { generateText } from '@deuz-sdk/core';
import { createAnthropic } from '@deuz-sdk/core/anthropic';

const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const res = await generateText({
  model: anthropic('claude-opus-4-8'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What is in this image?' },
        {
          type: 'image',
          image: 'https://example.com/photo.jpg',
          mediaType: 'image/jpeg',
        },
      ],
    },
  ],
});

console.log(res.text);

Tools

Tools are plain objects keyed by name in a ToolSet. Each has a parameters schema (a Standard Schema like Zod, or a raw JSON Schema) and an optional execute. Provide maxSteps to let the agentic loop run tools and feed results back. See Tools.

import { generateText } from '@deuz-sdk/core';
import { createAnthropic } from '@deuz-sdk/core/anthropic';
import type { JSONSchema } from '@deuz-sdk/core';

const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const citySchema: JSONSchema = {
  type: 'object',
  properties: { city: { type: 'string' } },
  required: ['city'],
  additionalProperties: false,
};

const res = await generateText({
  model: anthropic('claude-opus-4-8'),
  messages: [{ role: 'user', content: 'What is the weather in Paris?' }],
  tools: {
    getWeather: {
      description: 'Look up the current weather for a city.',
      parameters: citySchema,
      execute: async ({ city }: { city: string }) => ({ city, tempC: 22 }),
    },
  },
  maxSteps: 5,
});

console.log(res.text);
console.log(res.steps?.length, 'steps');

toolChoice accepts 'auto', 'required', 'none', or { type: 'tool', toolName }. Note that forced tool choice is illegal alongside extended thinking — when effort is set, the adapter downgrades a forced choice to auto.

Prompt caching

All pinned Claude slugs have caching: true. The adapter reports cache token breakdowns on usage:

totalTokens includes input + cache reads + cache writes + output. Feed this breakdown into the pricing helper for correct cost — cache reads are billed at a fraction of input price.

Since 1.2.0 you can also write to the cache with one flag: promptCaching: 'auto' sends Anthropic's top-level automatic cache_control field — the API places the breakpoint on the last cacheable block and moves it forward as the conversation grows. 'auto-1h' uses the 1-hour TTL. Providers that cache implicitly (OpenAI, Gemini) ignore the flag.

const result = streamChat({ model, messages, promptCaching: 'auto' });

Edge cases (per Anthropic docs): if the last block already carries an explicit cache_control with the same TTL, automatic caching is a no-op; with a different TTL the API returns 400 — don't combine this flag with hand-written breakpoints via providerOptions. The flag is currently effective only on Anthropic; other providers cache implicitly and ignore it.

Server-side web search

anthropicWebSearch() (root export) adds Anthropic's provider-executed web search — the model decides to search, Anthropic runs it during the turn, and results stream back as canonical source parts. Searches are counted in usage.serverToolUses ($10 / 1,000 searches).

import { generateText, anthropicWebSearch } from '@deuz-sdk/core';

const res = await generateText({
  model: anthropic('claude-fable-5'),
  messages: [{ role: 'user', content: 'What shipped in AI this week?' }],
  tools: { web_search: anthropicWebSearch({ max_uses: 5 }) },
});

Defaults to web_search_20260318. On 20260209+ versions allowed_callers defaults to code-execution (dynamic filtering); models without programmatic tool calling need anthropicWebSearch({ allowed_callers: ['direct'] }) — the API 400s otherwise. Provider tools never run locally and never break the agentic loop as client tools.

providerOptions escape hatch

Request-body fields the SDK does not model ride providerOptions.anthropic (top-level, shallow; canonical fields always win) — e.g. the server-side fallbacks beta:

streamChat({
  model, messages,
  headers: { 'anthropic-beta': 'server-side-fallback-2026-06-01' },
  providerOptions: { anthropic: { fallbacks: [{ model: 'claude-opus-4-8' }] } },
});

Structured output

generateObject selects a strategy from capabilities. On Anthropic it uses the native output_config JSON-schema mode by default. With extended thinking enabled it is forced into json mode, because Anthropic rejects a forced tool-choice when thinking is on.

import { generateObject } from '@deuz-sdk/core';
import { createAnthropic } from '@deuz-sdk/core/anthropic';
import { z } from 'zod';

const anthropic = createAnthropic({ apiKey: process.env.ANTHROPIC_API_KEY! });

const { object } = await generateObject({
  model: anthropic('claude-opus-4-8'),
  messages: [{ role: 'user', content: 'Capital of France?' }],
  schema: z.object({ city: z.string() }),
});

console.log(object.city); // "Paris"

The /v1/messages wire

Requests go to ${baseURL}/v1/messages with x-api-key, anthropic-version: 2023-06-01, and content-type: application/json. The adapter normalizes everything to the canonical delta stream — it never proxies raw provider bytes.

Notable mappings:

• System messages are hoisted into the top-level system field.
• tool role messages are sent as user turns containing tool_result blocks.
• reasoning parts are ordered first in each content array (Anthropic requires thinking blocks before other content) and serialized as thinking / redacted_thinking blocks.

Streaming tool-call accumulation

Claude emits a content_block_start for each tool_use block (carrying the tool id and name), then a sequence of input_json_delta events whose partial_json fragments are the argument JSON. The adapter slots each fragment by block index, emits canonical tool-call-delta parts as strings, and parses the accumulated JSON once at block end. Text streams via text_delta, thinking via thinking_delta, and the block signature via signature_delta.

Claude on Vertex AI

The same Messages body works against Vertex AI: the model id moves into the URL, anthropic_version: vertex-2023-10-16 goes in the body, and auth becomes an OAuth Bearer token. This is wired through the Vertex provider — you do not configure it on createAnthropic directly.

Error mapping

Upstream errors are normalized to the typed error taxonomy from @deuz-sdk/core:

Retry-After is honored for pre-first-byte retries, and the upstream request-id is preserved on the error. Secrets are redacted from all logs and error payloads.