About Claude Sonnet 5
Claude Sonnet 5 is Anthropic's middle tier, described in its documentation as the best combination of speed and intelligence in the lineup. It inherits what were flagship traits a generation earlier: the million-token context window, the large output ceiling, text-and-image input and adaptive thinking, delivered at noticeably lower latency than the Opus class.
The Sonnet line has historically been where Anthropic's production API traffic concentrates — capable enough for agents and coding assistants, fast enough for interactive products — and this generation keeps that role, with extended batch output available for the workloads that need very long generations.
Sonnet's rates land at a fraction of Opus pricing with the same structural discounts: cache reads at a tenth of input, batch at half price, and thinking tokens billed as output. Any pricing caveat Anthropic lists for this model appears in the callout at the top of this page — check it before budgeting long-term, as launch-window rates and standard rates can differ. The practical comparison is vertical: if your workload succeeds on Sonnet, the Opus premium is buying deliberation you don't need; if Haiku handles it, the same logic applies one tier down. The calculator above makes that comparison concrete for your token mix.
Frequently asked questions
How much does the Claude Sonnet 5 API cost?
Claude Sonnet 5 costs $2 per million input tokens and $10 per million output tokens, with cached input at $0.2 per million (90% off). Note: Launched as introductory pricing; Anthropic has since made $2 in / $10 out the standard rate (the planned rise to $3 / $15 on 1 Sep 2026 was cancelled).
How much does a typical chat message cost with Claude Sonnet 5?
A short chat message (about 500 input and 250 output tokens) costs roughly $0.0035 with Claude Sonnet 5. At 1,000 such requests a day, that is about $105.00 per month.
Is Claude Sonnet 5 cheap compared to similar models?
Claude Sonnet 5 has the #19 cheapest input rate of the 29 models we track. On a mixed workload (10K input / 2K output), it costs $0.040 per request, versus $0.036 for o3 and $0.044 for GPT-5.6 Terra.
What does Claude Sonnet 5 cost per 1,000 tokens?
Per 1,000 tokens, Claude Sonnet 5 costs $0.0020 for input and $0.0100 for output, or $0.00020 for cached input. Providers quote rates per million tokens ($2/M in, $10/M out here), so divide by a thousand for the per-1K figure older pricing pages used.
How large a prompt can Claude Sonnet 5 take?
Claude Sonnet 5 accepts up to 977K tokens of input context and can generate up to 125K tokens of output per request. At its input rate, filling the entire 977K-token window costs about $2.00 per request before any output.
Related
Compare all models at once ·Count tokens in your prompt · Claude Sonnet 5 vs GPT-5 head-to-head
All Anthropic model costs: Claude Fable 5.1 · Claude Fable 5 · Claude Opus 5 · Claude Haiku 4.5 · Claude Opus 4.8
Last updated 2026-09-03. Prices verified against Anthropic's official pricing page; see the methodology.