Claude Opus 4.6
ClaudeFlagship
ThinkingTool UseVisionStructured Output
About this model
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Performance Tier
Flagship
Claude Opus 4.6 is a flagship model from Claude : the most capable in their lineup.
Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $5.00 |
| Output (completion) | $25.00 |
| Cache read | $0.500 |
| Cache write | $6.25 |
Capabilities
Context Length1.0M
Max Output Tokens128K
TokenizerClaude
Inputtext, image
Outputtext
Release DateFebruary 4, 2026
Benchmarks
General Intelligence
MMLU
91.1%
GPQA Diamond
91.3%
Mathematics
MATH-500
96.4%
AIME 2025
99.8%
Programming
HumanEval
95.2%
SWE-bench Verified
80.8%
Reasoning
IFEval
92%
ARC-AGI-2
68.8%
Humanity's Last Exam
53.1%
Agentic
Terminal-Bench 2.0
65.4%
Recommended Use Cases
CodingAnalysisResearchCreative Writing
Strengths
- State-of-the-art reasoning and agentic capabilities
- Top-tier software engineering performance (SWE-bench 80.8%)
- Nuanced, high-quality writing with reliable instruction following
- Strong long-context performance up to 1M tokens
Limitations
- Higher cost per token than smaller models
- Slower response time compared to Haiku/Sonnet
Resources
This model may use your data for training
