Claude 3.7 Sonnet (thinking)

Provider: Anthropic US

No longer listed on OpenRouter since 2026-05-11. The figures below are the last recorded values.
Input price
$3.00
/ 1M tokens
Output price
$15.00
/ 1M tokens
Cache price
$0.30
/ 1M tokens (read)
Context
200K tokens
Max output 64K tokens

Overview

Anthropic's Claude 3.7 Sonnet (thinking) is a mid-tier model designed for versatile workloads. It targets applications requiring a balance of advanced reasoning capabilities, multimodal understanding, and structured interaction.

Strengths

  • Supports advanced multimodal understanding with vision capabilities.
  • Enables structured application integration through function-calling.
  • Offers substantial output generation with a 64,000 token maximum.
  • Features a cost-effective cache read price of $0.30 per million tokens.
  • Provides robust performance for complex "thinking" tasks.

Best use cases

  • Automating workflows requiring external tool interaction via function-calling.
  • Analyzing and extracting information from diverse visual inputs like documents or images.
  • Generating extensive summaries or creative long-form content.
  • Tackling complex problem-solving scenarios requiring advanced reasoning.
  • Efficiently retrieving cached responses for repetitive queries.

Pricing position

Claude 3.7 Sonnet (thinking) is priced at $3 per million input tokens and $15 per million output tokens. This places it significantly above the cost-optimized Claude Haiku series, which start as low as $0.25/$1.25 per million tokens. However, its input/output pricing is identical to its sibling models, Claude Sonnet 4.5 and 4.6, as well as multiple similarly-priced peer models like Grok 4 and Sonar Pro from other providers.

Caveats

While offering a 200,000 token context window, users needing larger contexts at the same price point might consider Claude Sonnet 4.5 or 4.6 which provide 1 million tokens. For less complex tasks, Anthropic's more cost-optimized Haiku models offer a significantly lower price point. This model does not offer a free tier for initial development or low-volume use.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
64K tokens
Tracked since
2026-05-08
Last updated
2026-05-11

Features

Image inputFunction callingReasoning

Price history

  • 2026-05-11 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $1.05
1M (small app) 1 0.5 $10.50
10M (mid scale) 10 5 $105.00
100M (large) 100 50 $1050.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Anthropic

Similar-priced models

Source: OpenRouter API