Skip to content

Anthropic · Workhorse

Claude Sonnet 4.6

The previous-generation Sonnet. Still widely deployed and still supported; the main reason to stay on it is that its tokenizer produces fewer tokens than Sonnet 5 for the same text.

Model ID: claude-sonnet-4-6

What that means

A worked example

Per-token pricing is hard to feel. Take a moderately chatty production workload: 100 calls a day, roughly 10,000 tokens in and 2,000 out each time. On Claude Sonnet 4.6 that comes to about:

$180 / month

Before caching, batching or volume discounts, all of which move this number a long way. Illustrative only.

Strong at

  • -Balanced cost and quality
  • -Adaptive thinking

Typical use

  • -General production workloads

Same tier

What else to look at

Full table →
ModelDeveloperContextIn / 1MOut / 1M
Claude Sonnet 5Anthropic1M$3$15
GPT-5.6 TerraOpenAI1M$2$12
GPT-5.4OpenAI-$2.50$15
Gemini 3.6 FlashGoogle1M$1.50$7.50
Grok 4.20xAI-$1.25$2.50

Verified 2026-08-07.