Claude Sonnet 5
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,...
Modalities
Text
Image
File
In / Out price
$2.00 / $10.00 per 1M
Context
1M · 128K out
Released
Jun 29, 2026
Providers
Live list prices and uptime across 10 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| Claude Platform on AWS | $2.00 | $10.00 | $0.20 | 1M | 128K | 99.98% |
| Azure | $2.00 | $10.00 | $0.20 | 1M | 128K | 99.83% |
| $2.00 | $10.00 | $0.20 | 1M | 128K | 99.94% | |
| Amazon Bedrock | $2.00 | $10.00 | $0.20 | 1M | 128K | 99.92% |
| Anthropic | $2.00 | $10.00 | $0.20 | 1M | 128K | 99.99% |
| Amazon Bedrock | $2.20 | $11.00 | $0.22 | 1M | 128K | 99.90% |
| Azure | $2.20 | $11.00 | $0.22 | 1M | 128K | 99.99% |
| $2.20 | $11.00 | $0.22 | 1M | 128K | 100.00% | |
| $2.20 | $11.00 | $0.22 | 1M | 128K | 99.97% | |
| Amazon Bedrock | $2.20 | $11.00 | $0.22 | 1M | 128K | 100.00% |
No implicit prompt caching; cache reads require explicit cache control.
Capabilities
Tool calling
Reasoning
Moderated
Include reasoning
Max completion tokens
Max tokens
Reasoning effort
Response format
Stop
Structured outputs
Tool choice
Verbosity
Pricing detail
- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.20
- Cache write
- $2.50
USD per 1M tokens.