ModelPickr

Compare / Claude

Claude · canonical pair

Claude Sonnet 4.6 vs Claude Sonnet 5

Alphabetical by model id, so this URL is the one to index. Claude Sonnet 4.6 is anthropic/claude-sonnet-4-6. Claude Sonnet 5 is anthropic/claude-sonnet-5. Both are among the models the most providers list, inside the Claude group.

A

Claude Sonnet 4.6

$40.50

per month at the reference workload

  • Reasoning
  • Tool use
  • Vision
  • Long context

vs

B

Claude Sonnet 5

$27.00

per month at the reference workload

  • Reasoning
  • Tool use
  • Vision
  • Long context
100 requests a day, 2,000 input tokens and 500 output tokens, no cache hits. A light chat workload so the rate cards are comparable.
SpecClaude Sonnet 4.6Claude Sonnet 5
Monthly, reference workload$40.50$27.00
Input / 1M$3.00$2.00
Output / 1M$15.00$10.00
Cache read / 1M$0.30$0.20
Cache write / 1M$3.75$2.50
Context1,000,0001,000,000
Max output64,000128,000
ReasoningYesYes
Tool callsYesYes
VisionYesYes
Open weightsNoNo
Providers4442
Released2026-02-172026-06-30

Same workload, your numbers

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Claude Sonnet 4.6 costs $13.50 more per month than Claude Sonnet 5 at these inputs.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000