Claude Sonnet 5 pricing across providers
Across tracked provider offerings, input runs $2.00–$3.00 per million tokens and output $10.00–$15.00 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Claude Platform on AWS at $0.306 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 5 of 6 offerings publish a cache-read rate; 5 of 6 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Claude Sonnet 5
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Claude Sonnet 5
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Claude Platform On Aws | unknown | $2.00 | $10.00 | $0.200 | $0.306 | 100.00% |
| Azure | unknown | $2.00 | $10.00 | $0.200 | $0.306 | 100.00% |
| unknown | $2.00 | $10.00 | $0.200 | $0.306 | 100.00% | |
| Amazon | unknown | $2.00 | $10.00 | $0.200 | $0.306 | 100.00% |
| Anthropic | unknown | $2.00 | $10.00 | $0.200 | $0.306 | 100.00% |
| DeepInfra | — | $3.00 | $15.00 | — | $3.06 | — |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.