Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

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

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

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

Anthropic: Claude Opus 4.1

anthropic/claude-opus-4.1

Compare

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.

Modalities
In / out price
$15 / $75per 1M
Context
200K
Released
Aug 5, 2025
Knowledge cutoff
Jan 2025
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

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 and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Anthropic: Claude Opus 4.1 (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisClaude 4.1 Opus (Reasoning) GPQA Diamond80.9%
Artificial AnalysisClaude 4.1 Opus (Reasoning) HLE12.5%
Artificial AnalysisClaude 4.1 Opus (Reasoning) IFBench55.4%
Artificial AnalysisClaude 4.1 Opus (Reasoning) τ²-Bench Telecom71.4%
Artificial AnalysisClaude 4.1 Opus (Reasoning) AA-LCR76.0%
Artificial AnalysisClaude 4.1 Opus (Reasoning) CritPt0.0%
Artificial AnalysisClaude 4.1 Opus (Reasoning) LiveCodeBench65.4%
Artificial AnalysisClaude 4.1 Opus (Reasoning) Terminal-Bench Hard34.3%
Artificial AnalysisClaude 4.1 Opus (Reasoning) MMLU-Pro88.0%
Artificial AnalysisClaude 4.1 Opus (Reasoning) AIME 202580.3%
Design ArenaClaude Opus 4.1 Models Arena 3D Elo1150
Design ArenaClaude Opus 4.1 Models Arena Asciiart Elo1164
Design ArenaClaude Opus 4.1 Models Arena Code Categories Elo1163
Design ArenaClaude Opus 4.1 Models Arena Data Visualization Elo1162
Design ArenaClaude Opus 4.1 Models Arena Game Development Elo1162
Design ArenaClaude Opus 4.1 Models Arena SVG Elo1106
Design ArenaClaude Opus 4.1 Models Arena UI Component Elo1150
Design ArenaClaude Opus 4.1 Models Arena Website Elo1163
Vals AIClaude Opus 4.1 (Nonthinking) AIME44.2%
Vals AIClaude Opus 4.1 (Nonthinking) Finance Agent v146.1%
Vals AIClaude Opus 4.1 (Nonthinking) GPQA Diamond70.0%
Vals AIClaude Opus 4.1 (Nonthinking) IOI v112.5%
Vals AIClaude Opus 4.1 (Nonthinking) LiveCodeBench64.6%
Vals AIClaude Opus 4.1 (Nonthinking) LegalBench83.5%
Vals AIClaude Opus 4.1 (Nonthinking) MATH 50093.0%
Vals AIClaude Opus 4.1 (Nonthinking) MedCode41.4%
Vals AIClaude Opus 4.1 (Nonthinking) MedQA92.5%
Vals AIClaude Opus 4.1 (Nonthinking) MedScribe71.8%
Vals AIClaude Opus 4.1 (Nonthinking) MGSM94.2%
Vals AIClaude Opus 4.1 (Nonthinking) MMLU Pro87.2%
Vals AIClaude Opus 4.1 (Nonthinking) MMMU Pro73.7%
Vals AIClaude Opus 4.1 (Nonthinking) MortgageTax61.1%
Vals AIClaude Opus 4.1 (Nonthinking) SAGE v131.4%
Vals AIClaude Opus 4.1 (Nonthinking) TaxEval v271.5%

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.

API

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$15.00$75.00$1.503.73s12 tok/s
100.00%
ProviderInput / Output /M
ThroughputUptime
  • Favicon for Amazon Bedrock
    Input $15.00 / Output $75.00
    Throughput 12 tok/sUptime 100.00%
Throughput
12tok/s

P50, best across providers

Latency
3.73s

P50, best provider

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.
99.75%

Availability over the last 3 days

Last 72 hours
Availability 99.75%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.84%

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 provider routing options.

1.
Favicon for https://kilocode.ai/
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
192Mtokens
2.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
95.9Mtokens
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.
67.3Mtokens
4.
Favicon for https://chub.ai/
Chub AI
GenAI for everyone
49.5Mtokens
5.
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.
45.1Mtokens
Rest of OpenRouter
24.8M
Top 5 Apps
2.17M

Frequently asked questions

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning.

Claude Opus 4.1 costs $15.00/M input tokens and $75.00/M output tokens, with separate rates for Cache Read at $1.50/M tokens, Cache Write at $18.75/M tokens, and Cache Write (1h) at $30.00/M tokens.

Claude Opus 4.1 has a 200,000 token context window. It supports up to 32,000 completion tokens.

Yes. Claude Opus 4.1 accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

Claude Opus 4.1 accepts images, text, and files such as PDFs as input and returns text.

Claude Haiku 5.5, Claude Sonnet 5.5, Claude Opus 5.5 and 11 more are other text models from Anthropic.

Claude Opus 4.1 was released on August 5, 2025. Its knowledge cutoff is January 31, 2025.