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

Model usage data, product updates, and research reports. One email each week.

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.

Favicon for anthropic

Anthropic: Claude Sonnet 4.5

anthropic/claude-sonnet-4.5

Compare

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.

Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

Modalities

In / Out Price

$3 / $15per 1M

Context

1.0M

Released

Sep 29, 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), Floor (cheapest), 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 4.5 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) Intelligence Index21.2
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) Coding Index52.1
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) Agentic Index17.5
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) GPQA Diamond83.4%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) HLE17.8%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) IFBench57.3%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) τ²-Bench Telecom78.1%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) AA-LCR72.3%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) GDPval-AA24.5%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) CritPt1.1%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) SciCode45.7%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) Terminal-Bench Hard35.6%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) AA-Omniscience Accuracy32.9%
Artificial AnalysisClaude 4.5 Sonnet (Reasoning) AA-Omniscience Non-Hallucination Rate50.9%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) GPQA Diamond72.7%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) HLE7.2%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) IFBench42.7%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) τ²-Bench Telecom70.5%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) AA-LCR54.0%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) CritPt0.0%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) Terminal-Bench Hard28.8%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) AA-Omniscience Accuracy28.4%
Artificial AnalysisClaude 4.5 Sonnet (Non-reasoning) AA-Omniscience Non-Hallucination Rate47.3%
Design ArenaClaude Sonnet 4.5 Models Arena 3D Elo1186
Design ArenaClaude Sonnet 4.5 Models Arena Asciiart Elo1193
Design ArenaClaude Sonnet 4.5 Models Arena Code Categories Elo1198
Design ArenaClaude Sonnet 4.5 Models Arena Data Visualization Elo1182
Design ArenaClaude Sonnet 4.5 Models Arena Game Development Elo1190
Design ArenaClaude Sonnet 4.5 Models Arena SVG Elo1131
Design ArenaClaude Sonnet 4.5 Models Arena UI Component Elo1176
Design ArenaClaude Sonnet 4.5 Models Arena Website Elo1202
Design ArenaClaude Sonnet 4.5 Agents Arena Full Stack Elo1060
Design ArenaClaude Sonnet 4.5 Agents Arena Mobile Apps Elo1165
Design ArenaClaude Sonnet 4.5 Agents Arena Webapps Elo1075

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
$3.00$15.00$0.301.21s37 tps
99.98%
$3.00$15.00$0.30----
98.81%
$3.00$15.00$0.301.53s32 tps
99.92%
$3.00$15.00$0.301.01s37 tps
99.85%
$3.00$15.00$0.301.17s34 tps
99.77%
Not used in Standard routing:Why these endpoints are not used
$3.30$16.50$0.33----
100.00%
$3.30$16.50$0.331.06s3 tps
100.00%

Throughput

37tok/s

P50, best across providers

Latency

1.01s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-BenchGoogle Vertex (US)82.1%74.0%Claude Platform on AWS80.7%74.7%Anthropic80.6%72.4%Amazon Bedrock (EU)81.7%71.2%Amazon Bedrock81.4%71.2%Google Vertex81.0%71.4%auto-routing81.7%70.0%
+1 more providers
Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

98.02%

Availability over the last 3 days

Last 72 hours
Availability 98.02%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
94.19%
Without Routing
92.22%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://chataigne.ai/
Chataigne
new
21.2Btokens
2.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
11.6Btokens
3.
Favicon for https://sillytavern.app/
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
11.5Btokens
4.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
9.79Btokens
5.
Favicon for https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
8.97Btokens

Frequently asked questions

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence.

Claude Sonnet 4.5 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, Cache Write (1h) at $6.00/M tokens, and Web Search at $10.00/1K calls.

Claude Sonnet 4.5 has a 1,000,000 token context window. It supports up to 64,000 completion tokens.

Yes. Claude Sonnet 4.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Claude Sonnet 4.5 accepts text, images, and files such as PDFs as input and returns text.

Claude Sonnet 4.5 is served by 5 providers on OpenRouter: Claude Platform on AWS, Azure, Amazon Bedrock, Anthropic, 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 4.5 was released on September 29, 2025. Its knowledge cutoff is January 31, 2025.

More models from Anthropic

Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Text1M context$10 / $50
Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Text1M context$5 / $25
Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context
Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$5 / $25
Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$2.50 / $12.50
Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$2 / $10
Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$1 / $5
Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Text1M context
Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Text1M context$10 / $50
Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Text1M context$5 / $25
Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context
Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$5 / $25
Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$2.50 / $12.50
Claude Opus 4.7

Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Text1M context
Claude Haiku Latest

This model always redirects to the latest model in the Claude Haiku family.

Text200K context
Claude Sonnet Latest

This model always redirects to the latest model in the Claude Sonnet family.

Text1M context
Claude Opus Latest

This model always redirects to the latest model in the Claude Opus family.

Text1M context
Claude Opus 4.7

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.

Beyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.

For users upgrading from earlier Opus versions, see our official migration guide here

Text1M context$5 / $25
Claude Opus 4.7

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.

Beyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.

For users upgrading from earlier Opus versions, see our official migration guide here

Text1M context$2.50 / $12.50
Claude Opus 4.6

Fast-mode variant of Opus 4.6 - identical capabilities with higher output speed at premium 6x pricing.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Text1M context