Claude 3.7 Sonnet

Overview

The most intelligent Claude model and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can produce near-instant responses or extended, step-by-step thinking that is made visible to the user. Shows particularly strong improvements in coding and front-end web development.

Claude 3.7 Sonnet was released on February 24, 2025. API access is available through Anthropic, Bedrock, Google.

Benchmarks

Claude 3.7 Sonnet Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Fri Dec 12 2025

Pricing

Pricing, performance, and capabilities for Claude 3.7 Sonnet across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
Anthropic	$3.00	$15.00	200.0K	128.0K	0.4	42.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Bedrock	$3.00	$15.00	200.0K	128.0K	0.5	101.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Google	$3.00	$15.00	200.0K	128.0K	0.4	42.0 tok/s	—	Text Image Audio Video	Text Image Audio Video

Price Comparison for Claude 3.7 Sonnet

Price per 1M input tokens (USD), lower is better

llm-stats.com - Fri Dec 12 2025

Throughput Comparison for Claude 3.7 Sonnet

Tokens per second, higher is better

llm-stats.com - Fri Dec 12 2025

Latency Comparison for Claude 3.7 Sonnet

Time to first token (s), lower is better

llm-stats.com - Fri Dec 12 2025

Example Outputs

API Access