Loading model…正在加载模型详情…
Use Claude Opus 5, Anthropic's model for complex reasoning and end-to-end coding, to work through demanding tasks in chat or through the API.
- From $2.10 in / $10.50 out per 1M tokensSave up to 58%
- OpenAI- and Anthropic-compatible API
- Coding · Reasoning · Analysis
What can I help you with?
Use it inClaude CodeClaude desktop app
What is Claude Opus 5?
Anthropic positions Claude Opus 5 for demanding reasoning, agentic coding and enterprise knowledge work. Its description emphasizes following a task from planning through implementation, verification and revision, with attention to project context and dependencies.
On UniRoute, send a message in the workspace or use the model ID claude-opus-5 through Chat Completions or Anthropic Messages. The API section provides request examples for both formats.
Claude Opus 5 follows Claude Opus 4.8. Anthropic highlights more proactive task execution, end-to-end coding and stronger problem-solving on unfamiliar assignments; the benchmark table below contains the reported evaluation results.
What you can do
What Claude Opus 5 is built for.
End-to-end engineering
Work through a feature or refactor with implementation constraints, dependencies and verification steps in view.
Complex reasoning
Explore an unfamiliar problem, identify missing information and compare candidate approaches before committing to a plan.
Tool-assisted workflows
Use API function calls to connect the model with your own tools and feed results back into the conversation.
This page accepts text messages; file inputs and function calling need the API, while search and structured output are not exposed by the current model configuration.
Specs & variants
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Claude Opus 5 | claude-opus-5 | Chat and text generation | Chat messages | Streaming; Thinking; Context window: Not stated on this page | $2.10 input / $10.50 output per 1M tokens |
Pricing
Priced per token. Input and output are billed separately.
| Usage | Official API | UniRoute | Save |
|---|---|---|---|
| Input | $5.00 | $2.10 | Save 58% |
| Output | $25.00 | $10.50 | Save 58% |
| Cache read | $0.50 | $0.21 | Save 58% |
| Cache write (5 min) | $6.25 | $2.625 | Save 58% |
| Cache write (1 hour) | $10.00 | $4.20 | Save 58% |
Official price: platform.claude.com · 2026-11-07
Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
API
Call Claude Opus 5 through OpenAI- or Anthropic-compatible endpoints.
curl 'https://api.uniroute.app/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "claude-opus-5", "messages": [ { "role": "user", "content": "Hello" } ], "stream": false}'curl 'https://api.uniroute.app/v1/messages' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'anthropic-version: 2023-06-01' \ -H 'Content-Type: application/json' \ -d '{ "model": "claude-opus-5", "max_tokens": 1024, "messages": [ { "role": "user", "content": "Hello" } ]}'Parameters
| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
messages | Body | The conversation as a list of role and content messages. |
max_tokens | Body | Upper limit on generated tokens (Anthropic Messages). |
stream | Body | Set to true to receive the response as a stream. |
anthropic-version | Header | Protocol version header for the Anthropic Messages API. |
Guides
Benchmarks & ranking
Published scores next to the models they were compared with.
| Evaluation Area | Benchmark | Claude Opus 5 | Claude Fable 5 | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|---|---|---|
| Agentic Terminal Coding | Frontier-Bench v0.1 | 43.3% | 33.7% | 21.1% | 34.4% |
| Knowledge Work | GDPval-AA v2 | 1861 | 1747 | 1593 | 1736 |
| Novel Problem-Solving | ARC-AGI 3 | 30.2% | — | 1.5% | 7.8% |
| Agentic Search | BrowseComp | 90.8% | 87.4% | 84.3% | 90.4% |
| Multidisciplinary Reasoning | Humanity’s Last Exam, No Tools | 56.3% | 56.5% | 49.8% | — |
| Multidisciplinary Reasoning | Humanity’s Last Exam, With Tools | 64.7% | 63.9% | 57.9% | — |
| Computer Use | OSWorld 2.0 | 70.6% | 66.1% | 55.7% | 62.6% |
| Agentic Coding | DeepSWE v1.1 | 68.8% | 69.7% | 59.0% | 72.7% |
| Agentic Coding | FrontierCode v1.1, Main | 53.4% | 53.5% | 46.5% | 47.5% |
| Business Workflows | AutomationBench | 26.0% | 17.4% | 17.0% | 18.1% |
| Legal | Legal Agent Benchmark, Held-Out | 11.7% | 13.3% | 10.4% | 2.5% |
| Health | HealthBench Professional | 59.8% | 66.0%† | 57.4% | 60.5% |
| Biology | BioMysteryBench, Hard | 49.4% | 46.5% | 42.4% | — |
| Biology | BioMysteryBench, Human-Solved | 90.1% | 89.0%† | 88.5% | — |
Figures published by Anthropic from its own evaluations. Results depend on each benchmark’s configuration.
Use cases
Typical ways to put Claude Opus 5 to work.
Repository migrations
Plan a migration across files and dependencies, then ask for implementation and test changes in manageable stages.
Root-cause investigations
Supply logs and code context to investigate the cause of a failure and review the proposed fix.
Professional analysis
Combine supplied technical or business material into structured findings, assumptions and open questions.
FAQ
Common questions about Claude Opus 5.
What is Claude Opus 5?
Anthropic positions Claude Opus 5 for demanding reasoning, agentic coding and enterprise knowledge work. Its description emphasizes following a task from planning through implementation, verification and revision, with attention to project context and dependencies.
How much does Claude Opus 5 cost?
From $2.10 input / $10.50 output per 1M tokens. Input and output are billed separately according to usage. The pricing table and worked examples show how the rates apply (prices updated 2026-11-08).
Which API formats can I use?
Use the model ID claude-opus-5 with Chat Completions or Anthropic Messages. The API section shows both request formats and their parameters.
What can I send in the chat box?
The workspace on this page accepts text messages. File inputs need the API; they cannot be attached in this chat box.
Can I adjust reasoning effort?
The current UniRoute model configuration does not expose a reasoning-effort setting. Use the API parameters listed on this page as the supported request surface.
Is there a free trial or free credits?
No. Requests are paid from your wallet balance. You can read this page and review the prices without paying, and you need an account with funds to send a message.
Related models
Other versions, models from the same provider and alternatives.
