Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for anthropic

Anthropic: Claude Sonnet 4

anthropic/claude-sonnet-4

Compare

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.

Read more at the blog post hereOpens in new tab

Modalities

In / Out Price

$3 / $15per 1M

Context

1.0M

Released

May 22, 2025

Knowledge Cutoff

Jan 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Anthropic: Claude Sonnet 4 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) GPQA Diamond68.3%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) HLE4.3%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) IFBench45.4%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) τ²-Bench Telecom52.3%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) AA-LCR44.0%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) CritPt1.1%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) Terminal-Bench Hard27.3%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) AA-Omniscience Accuracy22.7%
Artificial AnalysisClaude 4 Sonnet (Non-reasoning) AA-Omniscience Non-Hallucination Rate59.0%
Artificial AnalysisClaude 4 Sonnet (Reasoning) Coding Index37.6
Artificial AnalysisClaude 4 Sonnet (Reasoning) GPQA Diamond77.7%
Artificial AnalysisClaude 4 Sonnet (Reasoning) HLE10.7%
Artificial AnalysisClaude 4 Sonnet (Reasoning) IFBench54.7%
Artificial AnalysisClaude 4 Sonnet (Reasoning) τ²-Bench Telecom64.6%
Artificial AnalysisClaude 4 Sonnet (Reasoning) AA-LCR70.3%
Artificial AnalysisClaude 4 Sonnet (Reasoning) GDPval-AA15.9%
Artificial AnalysisClaude 4 Sonnet (Reasoning) CritPt0.3%
Artificial AnalysisClaude 4 Sonnet (Reasoning) Terminal-Bench Hard31.1%
Artificial AnalysisClaude 4 Sonnet (Reasoning) AA-Omniscience Accuracy22.7%
Artificial AnalysisClaude 4 Sonnet (Reasoning) AA-Omniscience Non-Hallucination Rate70.9%
Design ArenaClaude Sonnet 4 (Thinking) Models Arena 3D Elo1154
Design ArenaClaude Sonnet 4 (Thinking) Models Arena Code Categories Elo1151
Design ArenaClaude Sonnet 4 (Thinking) Models Arena Data Visualization Elo1173
Design ArenaClaude Sonnet 4 (Thinking) Models Arena Game Development Elo1161
Design ArenaClaude Sonnet 4 (Thinking) Models Arena SVG Elo1103
Design ArenaClaude Sonnet 4 (Thinking) Models Arena UI Component Elo1140
Design ArenaClaude Sonnet 4 (Thinking) Models Arena Website Elo1152

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking

Frequently asked questions

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software...

Claude Sonnet 4 costs $3.00/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.30/M tokens, Cache Write at $3.75/M tokens and Cache Write (1h) at $6.00/M tokens.

Claude Sonnet 4 has a 1,000,000 token context window. It supports up to 64,000 completion tokens.

Yes. Claude Sonnet 4 accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

Claude Sonnet 4 accepts images, text and files such as PDFs as input and returns text.

Claude Sonnet 4 is served by 2 providers on OpenRouter: Amazon Bedrock and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Claude Sonnet 4 was released on May 22, 2025. Its knowledge cutoff is January 31, 2025.