Claude Opus 4.5 (Reasoning)
Claude Opus 4.5 (Reasoning) is a text-based AI model by Anthropic. It features 57 tok/s output speed, $5.00/1M input tokens pricing. It scores 49.7 on the intelligence index.
Strengths
- +Top-tier intelligence score (49.7)
- +Strong coding performance (47.8)
Benchmarks
Intelligence49.7Coding47.8Math91.3
MMLU-Pro
0.9
GPQA
0.9
LiveCodeBench
0.9
Intelligence
49.7
Coding
47.8
Math
91.3
Output Speed
57 tok/s
Latency (TTFT)
10.41s
Blended Price
$10.00/M
Pricing per 1M Tokens
| Input (Prompt) | $5.00 |
| Output (Completion) | $25 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Claude Opus 4.5 (Reasoning) with:
Alternatives to Claude Opus 4.5 (Reasoning)
More from Anthropic
Frequently Asked Questions
How much does Claude Opus 4.5 (Reasoning) cost?
Claude Opus 4.5 (Reasoning) costs $5.00/1M input tokens and $25/1M output tokens.
Is Claude Opus 4.5 (Reasoning) good for coding?
Yes, Claude Opus 4.5 (Reasoning) has a strong coding score of 47.8, placing it among the top coding models.
How fast is Claude Opus 4.5 (Reasoning)?
Claude Opus 4.5 (Reasoning) generates output at 57 tok/s. Time to first token is 10.41s.
Is there a free version of Claude Opus 4.5 (Reasoning)?
No, Claude Opus 4.5 (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Claude Opus 4.5 (Reasoning)?
Last updated: