What is adaptive thinking and how does it differ from extended thinking?

Adaptive thinking (`thinking: { type: 'adaptive' }`) lets the model decide when and how much to reason internally. Unlike extended thinking, you don't set a fixed thinking token budget. The model calibrates reasoning depth per request.

How is the context window of 1M tokens significant for Opus 4.6?

This is the first Opus model to support 1M tokens. Previous Opus models had a 200K context limit. This enables Opus-level analysis of entire large codebases, extensive document collections, or long agent histories in a single request.

Can Opus 4.6 interleave thinking and tool calls in one response?

Yes. Claude Opus 4.6 can interleave thinking and tool calls within a single response, reasoning about a problem, calling a tool, reasoning about the result, and calling another tool, all in one turn.

How do I configure adaptive thinking and effort together in the AI SDK?

Under `providerOptions.anthropic` in the AI SDK, set `thinking.type` to `adaptive` and pass an `effort` level (for example, `max`). Set the model to `anthropic/claude-opus-4.6`.

Does the effort parameter work the same way in Opus 4.6 as in Opus 4.5?

Yes, the effort parameter controls overall token usage across all token types, defaults to a high level, and operates independently of the thinking configuration. Both parameters can be set separately.

What real-world work is Opus 4.6 specifically designed to handle?

Programming, analysis, and creative tasks across the development lifecycle. The hybrid reasoning architecture lets you use extended thinking for complex problems while keeping latency low for straightforward queries.

Anthropic

Claude Opus 4.6

Claude Opus 4.6 is the first Opus model with a context window of 1M tokens, introduces adaptive thinking for model-decided reasoning depth, supports interleaved thinking and tool calls in a single response, and delivers equal or better performance than fixed extended thinking across programming, analysis, and creative tasks. Your use is subject to Anthropic's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $5, Output $25, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'anthropic/claude-opus-4.6',
  prompt: 'Why is the sky blue?',
  providerOptions: {
    anthropic: {
      speed: 'fast',
    },
    gateway: {
      only: ['anthropic'],
    },
  },
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Claude Opus 4.6 by Anthropic. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Claude Opus 4.6

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Checking availability for your team

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Anthropic

Legal:Terms•Privacy

128K

1.2 s

49 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

02/05/2026

Bedrock

Legal:Terms•Privacy

128K

1.3 s

43 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

—

02/05/2026

Google Vertex AI

Legal:Terms•Privacy

128K

1.6 s

56 tps

$5/M+2 more

$25/M+2 more

Read$0.50/M

Write$6.25/M

$10/K

02/05/2026

Getting started

Call Claude Opus 4.6 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Opus 4.6 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `anthropic/claude-opus-4.6`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Opus 4.6 supports up to `128,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 1M-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK anthropic provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['anthropic', 'bedrock'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-opus-4.6',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Anthropic

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

anthropic/claude-fable-5.1

1.7 s

86 tps

$10/M

$50/M

Read$0.25/M

Write$12.50/M

$10/K

08/31/2026

anthropic/claude-opus-5

1.8 s

129 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

07/24/2026

anthropic/claude-sonnet-5

1.8 s

126 tps

$2/M

$10/M

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

anthropic/claude-opus-4.8

1.3 s

107 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

05/28/2026

anthropic/claude-sonnet-4.6

0.7 s

64 tps

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

anthropic/claude-haiku-4.5

200K

0.4 s

104 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Copy link to headingAbout Claude Opus 4.6

Claude Opus 4.6 launched on AI Gateway on February 5, 2026, bringing two advances to the Opus tier. First, the context window of 1M tokens. This is the first time an Opus model supports this context size, matching what Sonnet 4.5 gained. For teams needing both Opus-level intelligence and large context capacity, this closes a capability gap.

Second, adaptive thinking: a new thinking type parameter (set as thinking: { type: 'adaptive' }) that lets the model decide when and how much to reason, rather than requiring you to specify a fixed thinking budget. Claude Opus 4.6 also supports interleaved thinking and tool calls within a single response. The model can reason, call a tool, reason further about the result, and call another tool, all in one response rather than requiring separate turns. This applies to complex agentic workflows where the best next tool call depends on reasoning about previous results.

Anthropic described Claude Opus 4.6 as built to power agents that handle real-world work, with strength across the development lifecycle. To use Claude Opus 4.6, set the model to anthropic/claude-opus-4.6 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. When using the AI SDK, configure providerOptions.anthropic with the thinking and effort parameters as needed.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Requests using the context window of 1M tokens generate higher per-request token volumes than typical API calls. AI Gateway cost tracking per request is useful for budgeting large-context workloads.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Claude Opus 4.6

Best for

Opus intelligence at large context: Entire large codebases, extensive document sets, or long conversation histories where prior Opus models hit context limits
Interleaved reasoning and tool use: Complex multi-step pipelines where reasoning about tool results before the next call improves outcomes
Adaptive thinking efficiency: Letting the model calibrate its own reasoning depth avoids over-spending thinking tokens on simpler requests in mixed workloads
Programming, analysis, and creative tasks: At Opus depth, Claude Opus 4.6 excels across all three categories
Development lifecycle agents: The announced strength area for this checkpoint

Consider alternatives when

Primary cost constraint: Sonnet 4.6 approaches Opus-level intelligence at lower cost per token
Smaller context sufficient: Earlier Opus versions handle workloads that don't need the context window of 1M tokens
Maximum speed required: Sonnet and Haiku variants serve latency-sensitive use cases better

Copy link to headingConclusion

Claude Opus 4.6 closes the context window gap between the Opus and Sonnet tiers while introducing adaptive thinking, a more efficient approach to reasoning that performs on par with or better than fixed thinking budgets. For teams that need Opus-level intelligence at large context scale, this is the model.

Copy link to headingFrequently Asked Questions

What is adaptive thinking and how does it differ from extended thinking?
Adaptive thinking (thinking: { type: 'adaptive' }) lets the model decide when and how much to reason internally. Unlike extended thinking, you don't set a fixed thinking token budget. The model calibrates reasoning depth per request.
How is the context window of 1M tokens significant for Opus 4.6?
This is the first Opus model to support 1M tokens. Previous Opus models had a 200K context limit. This enables Opus-level analysis of entire large codebases, extensive document collections, or long agent histories in a single request.
Can Opus 4.6 interleave thinking and tool calls in one response?
Yes. Claude Opus 4.6 can interleave thinking and tool calls within a single response, reasoning about a problem, calling a tool, reasoning about the result, and calling another tool, all in one turn.
How do I configure adaptive thinking and effort together in the AI SDK?
Under providerOptions.anthropic in the AI SDK, set thinking.type to adaptive and pass an effort level (for example, max). Set the model to anthropic/claude-opus-4.6.
Does the effort parameter work the same way in Opus 4.6 as in Opus 4.5?
Yes, the effort parameter controls overall token usage across all token types, defaults to a high level, and operates independently of the thinking configuration. Both parameters can be set separately.
What real-world work is Opus 4.6 specifically designed to handle?
Programming, analysis, and creative tasks across the development lifecycle. The hybrid reasoning architecture lets you use extended thinking for complex problems while keeping latency low for straightforward queries.
When was Opus 4.6 made available on AI Gateway?
February 5, 2026.

Claude Opus 4.6

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Anthropic

Copy link to headingAbout Claude Opus 4.6

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Opus 4.6

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions