What's new in Claude Sonnet 5 compared with Claude Sonnet 4.6?

Claude Sonnet 5 improves on Claude Sonnet 4.6 across reasoning, tool use, coding, and knowledge work. Anthropic reports strict gains on agentic search and computer use evaluations, plus lower hallucination and sycophancy rates.

How do effort levels work on Claude Sonnet 5?

Effort controls how deeply Claude Sonnet 5 reasons per request, from efficient low-effort responses to an extra-high `xhigh` level. Higher effort can match Opus-tier output on some tasks; medium effort keeps mixed workloads cost-efficient.

Does Claude Sonnet 5 use a new tokenizer?

Yes. Claude Sonnet 5 uses an updated tokenizer, so the same input can produce more tokens than earlier Sonnet models. Re-measure token usage with AI Gateway observability before locking in cost estimates.

What context window does Claude Sonnet 5 support?

Claude Sonnet 5 has a context window of 1M tokens and supports up to 128K tokens output tokens per request, at Sonnet pricing.

Does AI Gateway support Zero Data Retention for Claude Sonnet 5?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

What is the pricing for Claude Sonnet 5?

AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference. Rates are listed on this page and shift when providers update their pricing.

Anthropic

Claude Sonnet 5

Claude Sonnet 5 is the most agentic Sonnet model yet from Anthropic, with gains over Claude Sonnet 4.6 across reasoning, tool use, coding, and knowledge work. Claude Sonnet 5 makes plans, uses tools like browsers and terminals, runs autonomously, and is available on AI Gateway via Anthropic, Google Vertex AI, Bedrock, Claude Platform on AWS.

View API reference

Input and output price: Prices from: Input $2, Output $10, 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-5',
  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 5 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 5

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.

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

2.4 s

92 tps

$2/M+1 more

$10/M+1 more

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

Google Vertex AI

Legal:Terms•Privacy

128K

1.5 s

102 tps

$2/M+2 more

$10/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

Bedrock

Legal:Terms•Privacy

128K

2.3 s

89 tps

$2/M+2 more

$10/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

Claude Platform on AWS

Legal:Terms•Privacy

128K

4.7 s

116 tps

$2/M

$10/M

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

Getting started

Call Claude Sonnet 5 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-5',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Sonnet 5 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-5',
    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-5`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Sonnet 5 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-5',
    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-5',
    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-5',
    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-5',
    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-5',
    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

3.3 s

78 tps

$10/M

$50/M

Read$0.25/M

Write$12.50/M

$10/K

08/31/2026

anthropic/claude-opus-5

1.4 s

83 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

07/24/2026

anthropic/claude-opus-4.8

1.1 s

104 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

0.8 s

74 tps

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

anthropic/claude-opus-4.6

1.2 s

53 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

02/05/2026

anthropic/claude-haiku-4.5

200K

0.5 s

115 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Copy link to headingAbout Claude Sonnet 5

Claude Sonnet 5 became available on AI Gateway on June 29, 2026. Anthropic calls Claude Sonnet 5 the most agentic Sonnet model yet: Claude Sonnet 5 makes plans, uses tools like browsers and terminals, and runs autonomously at a level that recently required larger, more expensive models.

The gains over Claude Sonnet 4.6 land across reasoning, tool use, coding, and knowledge work. Anthropic reports strict improvements over Claude Sonnet 4.6 on agentic search and computer use evaluations, along with lower hallucination and sycophancy rates. Anthropic also reports overall performance that approaches its Opus line at a lower price, and Claude Sonnet 5 launched with real-time cyber safeguards enabled by default.

Effort levels define the cost-performance curve. Claude Sonnet 5 supports configurable effort, including an extra-high xhigh level, and higher effort can match Opus-tier output on some tasks while medium effort keeps mixed workloads efficient. Claude Sonnet 5 also uses an updated tokenizer, so the same input can map to more tokens than earlier Sonnet models; verify budgets against real usage rather than prior baselines.

Through AI Gateway, Claude Sonnet 5 is available with the standard unified API, observability, retries, and failover across Anthropic, Google Vertex AI, Bedrock, Claude Platform on AWS. Set the model to anthropic/claude-sonnet-5 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Configurable effort spans a wide cost-performance range, including an extra-high xhigh level for the hardest requests. Tune effort per workload so simple traffic stays cheap and hard tasks get deeper reasoning.
Configuration: Claude Sonnet 5 uses an updated tokenizer, so the same input can produce more tokens than earlier Sonnet models. Re-measure token usage with AI Gateway observability instead of reusing Claude Sonnet 4.6 baselines. Cyber safeguards are enabled by default and can block requests that resemble dangerous cybersecurity work.
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 5

Best for

Agentic Coding Workflows: Multi-step engineering work where Claude Sonnet 5 plans, edits, runs terminals, and verifies output
Autonomous Tool Use: Browser, terminal, and API workflows that run with minimal supervision
Everyday Professional Work: Drafting, analysis, and knowledge work at Sonnet pricing and scale
Large-Context Agents: A context window of 1M tokens covers whole codebases and long agent histories
Mixed-Complexity Production Traffic: Configurable effort keeps simple requests cheap while hard requests get deeper reasoning

Consider alternatives when

Maximum Capability Ceiling: Claude Fable 5 is Anthropic's most capable widely released model for the hardest reasoning and longest-horizon work
Latency-Critical Simple Tasks: A Haiku-tier model is faster and cheaper for well-bounded, high-throughput requests
Stable Token Baselines: Claude Sonnet 4.6 keeps the earlier tokenizer if you need consistent token counts mid-migration

Copy link to headingConclusion

Claude Sonnet 5 is a strong default for production agents: plan-and-execute coding, autonomous tool use, and everyday professional work at Sonnet pricing. Start at medium effort, raise effort where quality gaps appear, and route the hardest long-horizon work to Claude Fable 5.

Copy link to headingFrequently Asked Questions

What's new in Claude Sonnet 5 compared with Claude Sonnet 4.6?
Claude Sonnet 5 improves on Claude Sonnet 4.6 across reasoning, tool use, coding, and knowledge work. Anthropic reports strict gains on agentic search and computer use evaluations, plus lower hallucination and sycophancy rates.
How do effort levels work on Claude Sonnet 5?
Effort controls how deeply Claude Sonnet 5 reasons per request, from efficient low-effort responses to an extra-high xhigh level. Higher effort can match Opus-tier output on some tasks; medium effort keeps mixed workloads cost-efficient.
Does Claude Sonnet 5 use a new tokenizer?
Yes. Claude Sonnet 5 uses an updated tokenizer, so the same input can produce more tokens than earlier Sonnet models. Re-measure token usage with AI Gateway observability before locking in cost estimates.
What makes Claude Sonnet 5 agentic?
Claude Sonnet 5 makes plans, uses tools like browsers and terminals, and runs autonomously at a level that recently required larger, more expensive models. Anthropic calls Claude Sonnet 5 the most agentic Sonnet model yet.
What context window does Claude Sonnet 5 support?
Claude Sonnet 5 has a context window of 1M tokens and supports up to 128K tokens output tokens per request, at Sonnet pricing.
Does AI Gateway support Zero Data Retention for Claude Sonnet 5?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
What is the pricing for Claude Sonnet 5?
AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference. Rates are listed on this page and shift when providers update their pricing.
How do I call Claude Sonnet 5 through AI Gateway?
Set the model to anthropic/claude-sonnet-5 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. AI Gateway handles authentication, retries, and failover across anthropic, vertex, bedrock, claudeaws.

Your use is subject to Anthropic's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Claude Sonnet 5

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 5

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Sonnet 5

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions