claude-sonnet-5
Claude Sonnet 5 is the workhorse production model of the Claude family that balances intelligence, speed and cost, and is suitable for the vast majority of enterprise workloads. It can be used in scenarios such as knowledge assistant, complex customer service, code assistance, document analysis, table and file processing, structured extraction, tool calling, and web page operations. Compared with Sonnet 4.6, it uses adaptive thinking by default and adopts a new tokenizer, so the number of tokens and the actual call cost of the same text may change. It is suitable to use it as a universal main model, upgrade to Opus for difficult tasks, and move to Haiku for high-frequency simple tasks.
- Context
- 1000000 tokens
- Max output
- 128000 tokens
- Input
- llm image
- Output
- llm
Pricing
Input: $2 / 1M tokens
Output: $10 / 1M tokens
Cached input: $0.2 / 1M tokens
Cache write: $4 / 1M tokens
Endpoints
- anthropic
- openai