model comparison

vs

Claude Sonnet 5 vs Claude Opus 5

two Anthropic models, compared on listed price, real workload cost, context and capabilities.

the short answer

  • Claude Sonnet 5 lists lower input and output prices.
  • Claude Opus 5 offers the larger context window.
  • Claude Sonnet 5 reads cached input for less ($0.2/M against Claude Opus 5's $0.5/M), which decides the bill for agents that resend long context.
  • Claude Sonnet 5 retired on 6 October 2026; its numbers are kept for reference.
  • Claude Opus 5 retired on 4 October 2026; its numbers are kept for reference.

side-by-side specs

specClaude Sonnet 5Claude Opus 5
providerAnthropicAnthropic
input price$2/M$5/M
output price$10/M$25/M
cached input$0.2/M$0.5/M
blended price (3:1)$4/M$10/M
context window200k tokens1M tokens
max output128k tokens128k tokens
inputtext, imagestext, images
structured outputyesyes
weightsclosedclosed
releasedJune 30, 2026July 24, 2026
availabilityretired 6 October 2026retired 4 October 2026

same work, both models

workloadClaude Sonnet 5Claude Opus 5
one chat reply3,000 tokens in, 500 outClaude Opus 5 costs 2.5× as much as Claude Sonnet 5$0.01$0.03
summarise a 100-page report50,000 tokens in, 1,500 out, one request$0.12$0.29
1,000 classification calls500 tokens in, 20 out, per call$1.20$3.00
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$4.60$11.50
same session, cached85% of input read from the prompt cache, the rest written to it$1.69$4.23

at listed rates. token counts are typical sizes, not measurements.

Claude Sonnet 5 pricing notes

  • Anthropic made the $2 / $10 introductory rate permanent on 2026-08-10; the planned $3 / $15 rise was cancelled.
  • its updated tokenizer can turn the same text into roughly 1.0-1.35x as many tokens, by content type.
  • cache writes bill at the 5-minute rate ($2.50 per 1M); Anthropic's 1-hour tier ($4) is not modelled.

Claude Opus 5 pricing notes

  • cache writes bill at the 5-minute rate ($6.25 per 1M); Anthropic's 1-hour tier ($10) is not modelled.
  • Anthropic's fast mode costs twice the base price; the listed rate is standard speed.

when to pick which

Claude Sonnet 5

Claude Sonnet 5 was Anthropic's mid-tier Sonnet model, released June 2026 with adaptive thinking and text plus image input. it was retired in favour of Claude Sonnet 5.5, which kept the same $2 / $10 price.

pick it if

  • you wanted agentic work Anthropic placed close to Opus 4.8, at lower prices
  • you reused long prompts: cache reads billed at a tenth of input
  • you needed image input alongside adaptive thinking

skip it if

  • you are choosing today; Sonnet 5.5 replaced it at the same $2 / $10

Claude Opus 5

Claude Opus 5 was Anthropic's Opus model released July 2026, at Opus 4.8's $5 / $25 price, with adaptive thinking and text plus image input. it was retired in favour of Claude Opus 5.5, which costs less at $4 / $20.

pick it if

  • you wanted agentic coding and computer use Anthropic placed near Fable 5
  • you wanted Fable 5-class work at half of Fable 5's price
  • you needed image input alongside adaptive thinking

skip it if

  • you are choosing today; Opus 5.5 replaced it at a lower $4 / $20

faq

which is cheaper, Claude Sonnet 5 or Claude Opus 5?

Claude Sonnet 5 lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Claude Sonnet 5 costs $4.60 and Claude Opus 5 $11.50.

which has the larger context window?

Claude Opus 5 offers the larger context window. Claude Sonnet 5: 200k tokens; Claude Opus 5: 1M tokens.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18