Anthropic: Claude Sonnet 5 API Pricing
Anthropic: Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens (cache reads: $0.200). Context window: 1M. Prices verified 2026-10-21 · source
Alternatives to consider
91% cheaper with nearly identical quality (52 vs 55)
+2 quality points for 13% more
Cheapest anthropic model — 97% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $2.00 | — |
| Cache read | $0.200 | −90% |
| Cache write (5m) | $2.50 | +25% |
| Cache write (1h TTL) | $4.00 | +100% |
| Output | $10.00 | — |
| Web search tool | $10/1k searches | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Higher effort = deeper thinking = more reasoning tokens billed as output.
What would Anthropic: Claude Sonnet 5 cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $56.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $180.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $390.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $100.00 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Anthropic: Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Compare Anthropic: Claude Sonnet 5 with
Frequently asked questions
How much does Anthropic: Claude Sonnet 5 cost?
Anthropic: Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens; cached input tokens cost $0.200 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
1M tokens, with up to 128K output tokens per response. That's roughly 1250 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.200/1M, about 90% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 99% on a typical workload with comparable quality.
Official resources
- Anthropic: Claude Sonnet 5 on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis benchmarks → — independent intelligence and performance analysis.
- Anthropic model docs → — first-party model specifications and limits.
- LMArena leaderboard → — independent human-preference rankings.
- Shred your current bill — paste a CSV and see if switching saves money.