LLM·Dex
Newsletter
ProprietaryAnthropicmidtextvision

Claude 3.7 Sonnet

The first Claude with an extended-thinking mode, ushered the reasoning-model paradigm into Anthropic's lineup.

Updated

Quick facts

Released
Feb 2025
Context
200K tokens
Output / 1M
$15.00 / 1M tokens
License
Proprietary

About Claude 3.7 Sonnet

Claude 3.7 Sonnet introduced Anthropic's extended-thinking feature, letting the model spend additional reasoning tokens before answering. It was the model that demonstrated Claude could compete with the o-series on hard reasoning tasks while keeping its prose quality intact.

By 2026 the 4.x line has subsumed most of its use cases, but 3.7 Sonnet remains a popular pick for users who specifically prefer its tone or have prompts tuned to it.

Benchmarks

Published scores from Anthropic's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
92.0
Python coding pass@1
MMLU
,
Broad academic knowledge
GPQA
,
Graduate-level reasoning
SWE-bench
62.3
Real software-engineering tasks
  • HumanEval92.0
  • SWE-bench Verified62.3

Capabilities

Strengths

  • First Claude with extended thinking
  • Excellent writing and coding quality
  • Mature, widely-tested

Tracked weaknesses

  • Superseded by 4.x for most new workloads

Pricing

Per-million-token rates as published by Anthropic.

TierPriceNotes
Input$3.00 / 1M tokensTokens you send to the model
Output$15.00 / 1M tokensTokens the model generates
Context200K tokensMax combined input + output

Call Claude 3.7 Sonnet from your code

Drop-in snippet for the Anthropic SDK. Set your API key in the environment and run.

typescript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
});

const message = await client.messages.create({
  model: "claude-3-7-sonnet",
  max_tokens: 1024,
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(message.content);

Best for

Tasks where Claude 3.7 Sonnet ranks among LLMDex's top picks.

Compare Claude 3.7 Sonnet with…

Frequently asked

  • How much does Claude 3.7 Sonnet cost per million tokens?
    Claude 3.7 Sonnet is priced at $3.00 / 1M tokens for input tokens and $15.00 / 1M tokens for output tokens via the official Anthropic API at the time of writing.
  • What is Claude 3.7 Sonnet's context window?
    Claude 3.7 Sonnet supports a context window of 200K tokens.
  • Is Claude 3.7 Sonnet open source?
    No. Claude 3.7 Sonnet is a closed-weight model, you can use it via Anthropic's API but the model weights are not publicly downloadable.
  • When was Claude 3.7 Sonnet released?
    Claude 3.7 Sonnet was released on Feb 24, 2025 by Anthropic.
  • What is Claude 3.7 Sonnet's knowledge cutoff?
    Claude 3.7 Sonnet's training data has a knowledge cutoff of Oct 2024. For information after that date you'll need a tool-use or web-search wrapper.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.