How does adaptive thinking differ from the fixed thinking budgets in earlier models?

The model decides when and how much to reason based on the request, rather than applying a developer-specified token budget. For mixed workloads with varying complexity, this avoids over-spending thinking tokens on simple requests while still applying deep reasoning to hard ones.

Does Claude Sonnet 4.6 have the context window of 1M tokens?

Yes. The context window of 1M tokens is part of Sonnet 4.6's standard specification.

What does MCP support mean for tool use in Sonnet 4.6?

MCP (Model Context Protocol) support lets the model interact with larger, standardized tool ecosystems without requiring individual tool specification per interaction. The model can proactively execute tasks, delegate to subagents, and parallelize tool calls.

Can Sonnet 4.6 interleave thinking and tool calls?

Yes. Sonnet 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 for Sonnet 4.6 in the AI SDK?

Set the model to `anthropic/claude-sonnet-4.6`. Under `providerOptions.anthropic`, pass an `effort` level (for example, `medium`) and `thinking.type` set to `adaptive`.

What does "Opus-approaching intelligence" mean practically for my use cases?

Sonnet 4.6 narrows the gap between the Sonnet and Opus tiers. For tasks where Opus previously justified its higher cost, benchmark Sonnet 4.6 as a potentially equivalent alternative at lower per-token pricing.

What were the specific capability improvements in Sonnet 4.6 over previous Sonnet models?

Agentic coding, code review, frontend UI generation, and higher-fidelity instruction following all improved. The model approaches Opus-level intelligence while maintaining Sonnet-tier cost and latency.

Anthropic

Claude Sonnet 4.6

Claude Sonnet 4.6 brings Opus-approaching intelligence to the Sonnet tier with adaptive thinking, a context window of 1M tokens, strong agentic coding, frontend UI quality, and computer use accuracy improvements, plus MCP support for scaled tool use and interleaved thinking with tool calls. Your use is subject to Anthropic's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $3, Output $15, 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-sonnet-4.6',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Claude Sonnet 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 Sonnet 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	Cache Hit	Input	Output	Cache	Search	Capabilities	ZDR	No Training	Regional Inference	Free AI Gateway Credit	Release Date

Anthropic

Legal:Terms•Privacy

128K

0.8 s

52 tps

71%

$3/M+1 more

$15/M+1 more

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

Google Vertex AI

Legal:Terms•Privacy

128K

0.6 s

53 tps

—

$3/M+2 more

$15/M+2 more

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

Bedrock

Legal:Terms•Privacy

128K

0.7 s

90 tps

—

$3/M+2 more

$15/M+2 more

Read$0.30/M

Write$3.75/M

—

02/17/2026

Claude Platform on AWS

Legal:Terms•Privacy

128K

—

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

Getting started

Call Claude Sonnet 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-sonnet-4.6',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Sonnet 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-sonnet-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-sonnet-4.6`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Sonnet 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-sonnet-4.6',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['anthropic', 'vertexAnthropic'],
      },
    },
  });

  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-sonnet-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-sonnet-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-sonnet-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-sonnet-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	Search	Capabilities	Providers	ZDR	No Training	Free AI Gateway Credit	Release Date

anthropic/claude-haiku-5.5

0.7 s

234 tps

$0.10/M+1 more

$0.50/M+1 more

Read$0.01/M

Write$0.13/M

$10/K

10/07/2026

anthropic/claude-sonnet-5.5

1.1 s

155 tps

$2/M

$10/M

Read$0.10/M

Write$2.50/M

$10/K

09/28/2026

anthropic/claude-opus-5.5

1.6 s

119 tps

$4/M+1 more

$20/M+1 more

Read$0.20/M

Write$5/M

$10/K

09/22/2026

anthropic/claude-opus-5

1.3 s

176 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

0.8 s

109 tps

$2/M

$10/M

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

anthropic/claude-haiku-4.5

200K

0.4 s

117 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Copy link to headingAbout Claude Sonnet 4.6

Claude Sonnet 4.6 launched on AI Gateway on February 17, 2026. Anthropic described it as approaching Opus-level intelligence. Claude Sonnet 4.6 advances multiple capabilities the Sonnet tier developed across the 4.x generation: stronger agentic coding, improved code review, better frontend UI quality, and higher computer use accuracy.

Two architecture features define Claude Sonnet 4.6. First, adaptive thinking: the model decides when and how much to reason, rather than requiring a fixed extended thinking budget. Simpler requests get a proportionate response. Complex ones receive deeper reasoning automatically. You don't need to categorize each request in advance. This evolves the thinking mode introduced in Claude 3.7 Sonnet into a smarter, model-directed form.

Second, a 1M-token context window at Sonnet pricing. Claude Sonnet 4.5 was the first Sonnet-tier model to reach 1M tokens; Claude Sonnet 4.6 keeps that as standard. For teams working with large codebases, long document collections, or extended agent histories, Opus-approaching quality at 1M tokens and Sonnet pricing changes what's economically feasible.

MCP (Model Context Protocol) support for scaled tool use means Claude Sonnet 4.6 can participate in large tool ecosystems without specifying individual tools for each interaction. The model proactively executes tasks, delegates to subagents, and parallelizes tool calls.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Adaptive thinking calibrates token usage automatically. Pair it with the effort parameter to manage cost on mixed workloads where some requests benefit from deep reasoning and others don't.
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 Sonnet 4.6

Best for

Agentic coding and code review: Requiring strong intelligence with efficient reasoning, the primary capability improvements in this release
Frontend UI development: Quality of visual output matters, highlighted as an area of improvement over previous Sonnet versions
Computer use workflows: Higher accuracy on GUI automation and screen-driven agents ships as a 4.6 improvement, at Sonnet pricing rather than the Opus tier
Large-context agentic tasks: The context window of 1M tokens enables processing entire codebases or document sets at Sonnet pricing
MCP-based tool environments: The model needs to interact with large, diverse tool ecosystems

Consider alternatives when

Maximum intelligence ceiling: Claude Opus 4.6 provides full Opus depth with the same 1M context window
Tight latency budgets: Haiku 4.5 is faster and cheaper for well-bounded high-throughput requests
Explicit thinking budgets: Earlier models like Claude 3.7 Sonnet accept a fixed thinking token budget instead of adaptive mode

Copy link to headingConclusion

Claude Sonnet 4.6 combines context of 1M tokens, adaptive thinking, MCP (Model Context Protocol) support, and Opus-approaching intelligence at Sonnet pricing. It's a strong default for agentic coding, large-context analysis, and frontend development.

Copy link to headingFrequently Asked Questions

How does adaptive thinking differ from the fixed thinking budgets in earlier models?
The model decides when and how much to reason based on the request, rather than applying a developer-specified token budget. For mixed workloads with varying complexity, this avoids over-spending thinking tokens on simple requests while still applying deep reasoning to hard ones.
Does Claude Sonnet 4.6 have the context window of 1M tokens?
Yes. The context window of 1M tokens is part of Sonnet 4.6's standard specification.
What does MCP support mean for tool use in Sonnet 4.6?
MCP (Model Context Protocol) support lets the model interact with larger, standardized tool ecosystems without requiring individual tool specification per interaction. The model can proactively execute tasks, delegate to subagents, and parallelize tool calls.
Can Sonnet 4.6 interleave thinking and tool calls?
Yes. Sonnet 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 for Sonnet 4.6 in the AI SDK?
Set the model to anthropic/claude-sonnet-4.6. Under providerOptions.anthropic, pass an effort level (for example, medium) and thinking.type set to adaptive.
What does "Opus-approaching intelligence" mean practically for my use cases?
Sonnet 4.6 narrows the gap between the Sonnet and Opus tiers. For tasks where Opus previously justified its higher cost, benchmark Sonnet 4.6 as a potentially equivalent alternative at lower per-token pricing.
What were the specific capability improvements in Sonnet 4.6 over previous Sonnet models?
Agentic coding, code review, frontend UI generation, and higher-fidelity instruction following all improved. The model approaches Opus-level intelligence while maintaining Sonnet-tier cost and latency.

Claude Sonnet 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 Sonnet 4.6

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Sonnet 4.6

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions