claude-sonnet-4-6
Claude Sonnet 4.6 is the model in the Sonnet series oriented towards high-quality production tasks, suitable for balancing performance, speed and cost. It can handle long documents, code tasks, complex tool calls, visual input, PDF, batch processing and agent workflows. It is also suitable for enterprise knowledge assistants, R&D assistants, operational automation and customer service upgrades. It supports adaptive thinking and large context, but whether to think by default depends on the request configuration; the output length, thinking strategy, tool permissions and failure fallback mechanism should be clearly set when deploying.
- Context
- 1000000 tokens
- Max output
- 128000 tokens
- Input
- llm image
- Output
- llm
Pricing
Input: $3 / 1M tokens
Output: $15 / 1M tokens
Cached input: $0.30000000000000004 / 1M tokens
Cache write: $6 / 1M tokens
Endpoints
- anthropic
- openai