Claude 4 Sonnet (Reasoning)
Claude 4 Sonnet (Reasoning) is a text-based AI model by Anthropic. It features 52 tok/s output speed, $3.00/1M input tokens pricing. It scores 38.7 on the intelligence index.
Strengths
- +Solid intelligence score (38.7)
Benchmarks
Intelligence38.7Coding34.1Math74.3
MMLU-Pro
0.8
GPQA
0.8
LiveCodeBench
0.7
Intelligence
38.7
Coding
34.1
Math
74.3
Output Speed
52 tok/s
Latency (TTFT)
10.99s
Blended Price
$6.00/M
Pricing per 1M Tokens
| Input (Prompt) | $3.00 |
| Output (Completion) | $15 |
| 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 4 Sonnet (Reasoning) with:
Alternatives to Claude 4 Sonnet (Reasoning)
More from Anthropic
Frequently Asked Questions
How much does Claude 4 Sonnet (Reasoning) cost?
Claude 4 Sonnet (Reasoning) costs $3.00/1M input tokens and $15/1M output tokens.
Is Claude 4 Sonnet (Reasoning) good for coding?
Claude 4 Sonnet (Reasoning) has a moderate coding score of 34.1. It can handle basic programming tasks but may not be the best for complex coding.
How fast is Claude 4 Sonnet (Reasoning)?
Claude 4 Sonnet (Reasoning) generates output at 52 tok/s. Time to first token is 10.99s.
Is there a free version of Claude 4 Sonnet (Reasoning)?
No, Claude 4 Sonnet (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Claude 4 Sonnet (Reasoning)?
Last updated: