Anthropic: Claude Opus 4.1
Model Overview
| Property |
Value |
| Model ID |
anthropic/claude-opus-4-1-20250805 |
| Name |
Claude Opus 4.1 |
| Released |
2025-08-05 |
| Type |
Language Model |
Description
Hybrid reasoning model pushing frontier for coding and AI agents with extended thinking capabilities. Achieves 74.5% on SWE-bench Verified with 32K max output tokens.
Description
Model Overview
| Property |
Value |
| Model ID |
anthropic/claude-opus-4-1-20250805 |
| Name |
Claude Opus 4. |
Specifications
| Spec |
Value |
| Context Window |
200,000 tokens |
| Input Modalities |
Text, Vision |
| Output Modalities |
Text |
| Max Output Tokens |
32,000 |
Pricing
| Type |
Price |
| Input |
$15.00 per 1M tokens |
| Output |
$75.00 per 1M tokens |
Capabilities
- Tool Use: Yes
- Vision: Yes
- Batch Processing: Yes
- Extended Thinking: Yes (hybrid reasoning)
- Web Search: Additional $10 per 1,000 searches
- Web Fetch: Included (no additional cost)
Key Features
- Extended thinking capabilities for complex reasoning
- State-of-the-art coding and software engineering performance
- Optimized for AI agents and autonomous workflows
- Superior performance on complex multi-step tasks
- Industry-leading SWE-bench scores (74.5% on Verified)
- Vision understanding with text analysis
Best For
- Complex software engineering and code generation
- AI agent development and automation
- Extended reasoning tasks requiring deep analysis
- Hybrid reasoning workflows combining analysis and action
- High-stakes decision support systems
- Research and scientific problem-solving
- Strategic planning and scenario analysis
API Endpoints
- List Models: GET /v1/models
- Get Model: GET /v1/models/claude-opus-4-1-20250805
- Chat Completion: POST /v1/messages