Claude Sonnet 4.5
Claude Sonnet 4.5 is a coding model from Anthropic with strong benchmark scores, including 77.2% on SWE-bench Verified and 61.4% on OSWorld for computer use, sustaining 30+ hour agentic coding sessions, and delivering substantial gains across coding, reasoning, math, and domain-specific expertise. 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
import { streamText } from 'ai'
const result = streamText({ model: 'anthropic/claude-sonnet-4.5', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Claude Sonnet 4.5 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 4.5
Claude Sonnet 4.5
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Claude Sonnet 4.5 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Claude Sonnet 4.5 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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-4.5. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Claude Sonnet 4.5 supports up to 64,000 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 |
| — | 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'anthropic/claude-sonnet-4.5', 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 |
|---|
| 1M | 0.9 s | 218 tps | $0.10/M+1 more | $0.50/M+1 more | Read$0.01/M Write$0.13/M | $10/K | +4 |  +1 | 10/07/2026 | |||||
| 1M | 1.0 s | 177 tps | $2/M | $10/M | Read$0.10/M Write$2.50/M | $10/K | +4 | +1 | 09/28/2026 | |||||
| 1M | 1.7 s | 123 tps | $4/M+1 more | $20/M+1 more | Read$0.20/M Write$5/M | $10/K | +4 | +1 | 09/22/2026 | |||||
| 1M | 1.3 s | 149 tps | $5/M+1 more | $25/M+1 more | Read$0.50/M Write$6.25/M | $10/K | +4 | +1 | 07/24/2026 | |||||
| 1M | 0.8 s | 105 tps | $2/M | $10/M | Read$0.20/M Write$2.50/M | $10/K | +4 | +1 | 06/29/2026 | |||||
| 200K | 0.4 s | 112 tps | $1/M | $5/M | Read$0.10/M Write$1.25/M | $10/K | +4 | +1 | 10/15/2025 |
Copy link to headingAbout Claude Sonnet 4.5
Claude Sonnet 4.5 launched on September 29, 2025. The OSWorld result backed Anthropic's computer use claims directly: 61.4%, up from Sonnet 4's 42.2% four months earlier. On SWE-bench Verified, Claude Sonnet 4.5 scored 77.2% and maintained focus for 30+ hours on complex multi-step tasks, a duration threshold that changes what's architecturally feasible for autonomous engineering work.
Domain expert evaluation reinforced the benchmark numbers. Finance, law, medicine, and STEM specialists found substantially better domain-specific knowledge and reasoning compared to older models including Opus 4.1. Devin increased planning performance by 18% and end-to-end scores by 12%, the biggest jump since Claude Sonnet 3.6. Cursor, GitHub Copilot, and Figma Make reported significant gains in their specific domains. Claude Code shipped checkpoints and rollback, a native VS Code extension, and a refreshed terminal interface alongside this model.
At release, Claude Sonnet 4.5 included substantial alignment improvements over prior Claude models. Safety gains are concrete: substantial reductions in sycophancy, deception, power-seeking, and tendency to encourage delusional thinking. Prompt injection defense for computer use and agentic capabilities improved considerably. Anthropic released Claude Sonnet 4.5 under ASL-3 (AI Safety Level 3) protections, the first Claude model at that safety level, with CBRN (chemical, biological, radiological, and nuclear) classifiers active.
The Claude Agent SDK launched alongside Claude Sonnet 4.5, giving you access to the same infrastructure that powers Claude Code: memory management, permission systems, and subagent coordination for building custom agents.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Claude Sonnet 4.5's computer use capability is protected by ASL-3 (AI Safety Level 3) safeguards: classifiers that screen for potentially dangerous inputs and outputs. These may occasionally flag normal content. Anthropic has substantially reduced false positive rates since the classifiers were first deployed.
- 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 4.5
Best for
- Computer use and software automation: Strong results on OSWorld at release among models evaluated then
- Extended autonomous coding sessions: Documented 30+ hour capability for complex multi-step engineering tasks
- Complex agent workflows: Anthropic explicitly positioned Claude Sonnet 4.5 for agent workloads at release
- Finance, law, medicine, and STEM applications: Expert evaluation showed substantial gains in domain knowledge and reasoning compared to Opus 4.1
- Strong alignment properties: Reduced sycophancy and deception compared to earlier Claude releases at that time
Consider alternatives when
- Primary cost constraint: Haiku 4.5 may offer sufficient capability-per-cost for lighter workloads
- Simple latency-sensitive tasks: Claude Sonnet 4.5's capability depth comes with higher per-token cost than lighter models
- Sonnet-tier large context: Claude Sonnet 4.6 covers both 1M tokens context and Sonnet pricing
- Earlier-model parity: Earlier models handle some specific computer use or coding tasks equivalently
Copy link to headingConclusion
Claude Sonnet 4.5 represents a generation step in multiple capability areas simultaneously: computer use, agentic duration, domain expertise, and safety alignment all advanced in the same release. For teams building agents that do real work in real software environments over extended periods, this is the release where those capabilities came together.
Copy link to headingFrequently Asked Questions
What was Claude Sonnet 4.5's OSWorld score and why does it matter?
61.4%, up from Sonnet 4's 42.2% four months earlier. OSWorld measures AI performance on real-world computer tasks: navigating software, filling forms, and clicking UI elements. It focuses on operational computer-use scenarios rather than abstract reasoning alone.
How long can Claude Sonnet 4.5 maintain focus on a single agentic coding task?
More than 30 hours on complex, multi-step tasks. Anthropic noted this duration changes what's architecturally feasible for autonomous engineering work. Individual results vary by task structure.
What is ASL-3 and why does it apply to Sonnet 4.5?
ASL-3 (AI Safety Level 3) is Anthropic's framework level for models requiring additional safeguards. Sonnet 4.5 is the first Claude model released under ASL-3 protections, which include classifiers screening inputs and outputs for CBRN-related content. False positive rates have decreased by a factor of 10 since initial deployment.
What is the Claude Agent SDK and how does it relate to this model?
The Claude Agent SDK launched alongside Sonnet 4.5. It gives you access to the same agent infrastructure that powers Claude Code: memory management across long tasks, permission systems, and subagent coordination. Use it to build custom agents on the same foundation.
What alignment improvements came with Sonnet 4.5?
Substantial reductions in sycophancy, deception, power-seeking, encouragement of delusional thinking, and compliance with harmful system prompts, measured via an automated behavioral auditor. The model also improved defenses against prompt injection attacks for computer use and agentic capabilities.
Why did specialists in finance, law, medicine, and STEM find Sonnet 4.5 significantly better than previous models?
Professionals assessed domain-specific knowledge and reasoning in Anthropic's expert evaluations. Results showed substantially better performance compared to older models, including Opus 4.1. The intelligence improvements extend beyond coding benchmarks.
Is Sonnet 4.5 priced differently from Sonnet 4?
Current pricing is shown on this page. AI Gateway routes across providers, and rates may vary by provider.