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 4.7

anthropic/claude-opus-4.7

Compare

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 hereOpens in new tab

Modalities
In / out price
$5 / $25per 1M
Context
1.0M
Released
Apr 16, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityDocumentationFAQExplore

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 Floor (cheapest).

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 4.7 (Artificial Analysis and Vals AI)
SourceBenchmarkScore
Artificial AnalysisClaude Opus 4.7 (Max) Coding Index73.6
Artificial AnalysisClaude Opus 4.7 (Max) Agentic Index38.6
Artificial AnalysisClaude Opus 4.7 (Max) GPQA Diamond91.4%
Artificial AnalysisClaude Opus 4.7 (Max) HLE42.3%
Artificial AnalysisClaude Opus 4.7 (Max) IFBench58.6%
Artificial AnalysisClaude Opus 4.7 (Max) τ²-Bench Telecom88.6%
Artificial AnalysisClaude Opus 4.7 (Max) AA-LCR78.7%
Artificial AnalysisClaude Opus 4.7 (Max) τ-Bench Banking34.6%
Artificial AnalysisClaude Opus 4.7 (Max) GDPval-AA43.1%
Artificial AnalysisClaude Opus 4.7 (Max) CritPt12.0%
Artificial AnalysisClaude Opus 4.7 (Max) Terminal-Bench Hard51.5%
Artificial AnalysisClaude Opus 4.7 (Max) Terminal-Bench 2.183.1%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) GPQA Diamond88.5%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) HLE33.3%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) IFBench43.6%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) τ²-Bench Telecom74.0%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) AA-LCR75.7%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) CritPt5.1%
Artificial AnalysisClaude Opus 4.7 (Non-reasoning, High) Terminal-Bench Hard54.5%
Vals AIClaude Opus 4.7 AIME96.3%
Vals AIClaude Opus 4.7 CaseLaw v268.4%
Vals AIClaude Opus 4.7 Code Migration43.9%
Vals AIClaude Opus 4.7 CorpFin v266.1%
Vals AIClaude Opus 4.7 EMB63.7%
Vals AIClaude Opus 4.7 Finance Agent (v2)51.5%
Vals AIClaude Opus 4.7 GPQA Diamond90.2%
Vals AIClaude Opus 4.7 Harvey's Legal Agent Benchmark v16.7%
Vals AIClaude Opus 4.7 IOI v147.1%
Vals AIClaude Opus 4.7 LiveCodeBench85.1%
Vals AIClaude Opus 4.7 LegalBench85.3%
Vals AIClaude Opus 4.7 Legal Research Bench38.5%
Vals AIClaude Opus 4.7 MedCode54.9%
Vals AIClaude Opus 4.7 MedScribe83.0%
Vals AIClaude Opus 4.7 MMLU Pro89.9%
Vals AIClaude Opus 4.7 MMMU Pro85.5%
Vals AIClaude Opus 4.7 MortgageTax70.3%
Vals AIClaude Opus 4.7 ProgramBench0.0%
Vals AIClaude Opus 4.7 ProofBench v154.0%
Vals AIClaude Opus 4.7 Vals RSI Index19.1%
Vals AIClaude Opus 4.7 SAGE v156.1%
Vals AIClaude Opus 4.7 SWE-bench82.0%
Vals AIClaude Opus 4.7 Tax Agent Bench23.7%
Vals AIClaude Opus 4.7 TaxEval v275.3%
Vals AIClaude Opus 4.7 Terminal-Bench 2.168.5%
Vals AIClaude Opus 4.7 Vals Index56.1%
Vals AIClaude Opus 4.7 Vals Multimodal Index67.4%
Vals AIClaude Opus 4.7 Vibe Code Bench v1.171.0%

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.

Anthropic: Claude Opus versions

Available through EU in-region routing

Anthropic: Claude Opus 4.7 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe
Amazon Bedrock, Google Vertex
Prices in Europe
  • Amazon Bedrock: $5.50/M tokens input, $27.50/M tokens output
  • Google Vertex: $5.50/M tokens input, $27.50/M tokens output
Base URL
https://eu.openrouter.ai/api/v1
Plan
Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Anthropic: Claude Opus 4.7 on OpenRouter.

  • Claude 4.7 Migration GuideCookbook
  • Opus 4.7's New Tokenizer: What It Actually CostsBlog post

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$5.00$25.00$0.501.14s47 tok/s
100.00%
$5.00$25.00$0.501.32s55 tok/s
100.00%
$5.00$25.00$0.501.25s67 tok/s
100.00%
$5.00$25.00$0.50----
--
$5.00$25.00$0.500.59s33 tok/s
100.00%
Not used in Standard routing:Why these endpoints are not used
$5.50$27.50$0.550.52s101 tok/s
--
$5.50$27.50$0.551.17s58 tok/s
100.00%
$5.50$27.50$0.550.38s83 tok/s
--
ProviderInput / Output /M
ThroughputUptime
  • Favicon for Claude Platform on AWS
    Input $5.00 / Output $25.00
    Throughput 47 tok/sUptime 100.00%
  • Favicon for Amazon Bedrock
    Input $5.00 / Output $25.00
    Throughput 55 tok/sUptime 100.00%
  • Favicon for Google
    Input $5.00 / Output $25.00
    Throughput 67 tok/sUptime 100.00%
  • Favicon for Azure
    Input $5.00 / Output $25.00
    Throughput --Uptime --
  • Favicon for Anthropic
    Input $5.00 / Output $25.00
    Throughput 33 tok/sUptime 100.00%
  • Not used in Standard routing:Why these endpoints are not used
  • Favicon for Google
    Input $5.50 / Output $27.50
    Throughput 101 tok/sUptime --
  • Favicon for Amazon Bedrock
    Input $5.50 / Output $27.50
    Throughput 58 tok/sUptime 100.00%
  • Favicon for Google
    Input $5.50 / Output $27.50
    Throughput 83 tok/sUptime --
Throughput
101tok/s

P50, best across providers

Latency
0.38s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchAmazon Bedrock90.4%78.6%Anthropic89.8%78.8%Google Vertex (US)90.4%77.9%Google Vertex90.2%77.8%Azure89.6%78.4%auto-routing89.5%77.8%Amazon Bedrock (EU)89.6%76.2%Google Vertex (EU)89.9%75.8%
+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.
99.88%

Availability over the last 3 days

Last 72 hours
Availability 99.88%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.82%
Without Routing
98.02%

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://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.
7Btokens
2.
Favicon for https://mizzen.chat/
qa_worker
new
5.15Btokens
3.
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.
2.99Btokens
4.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
2.88Btokens
5.
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.
2.57Btokens
Rest of OpenRouter
1.88B
Top 5 Apps
572M

Frequently asked questions

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.

The Claude Opus 4.7 documentation on OpenRouter includes the Claude 4.7 Migration Guide cookbook and the Opus 4.7's New Tokenizer: What It Actually Costs blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Claude Opus 4.7 costs $5.00/M input tokens and $25.00/M output tokens, with separate rates for Cache Read at $0.50/M tokens, Cache Write at $6.25/M tokens, Cache Write (1h) at $10.00/M tokens, and Web Search at $10.00/1K calls.

Claude Opus 4.7 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.

Yes. Claude Opus 4.7 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Claude Opus 4.7 accepts text, images, and files such as PDFs as input and returns text.

Claude Opus 4.7 is served by 5 providers on OpenRouter: Claude Platform on AWS, Azure, Google Vertex, Amazon Bedrock, and Anthropic. 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 Opus 4.7 was released on April 16, 2026.