claude-opus-4-5-20251101
Claude Opus 4.5 is the high-capacity model in the Opus 4 series, suitable for workflows that require strong reasoning, complex code collaboration, visual understanding and multi-step task execution. The official prompt guide states that this generation has strong performance in system prompt following, visual processing, image information extraction and computer use. It can be used for code review, product prototypes, complex data research, interface understanding and long-task agents. When using it, you should avoid copying the mandatory prompts of "tools must be called frequently" from the old model era. It is usually more stable to use normal and specific task instructions.
- Context
- 1000000 tokens
- Max output
- 128000 tokens
- Input
- llm image
- Output
- llm
Pricing
Input: $5 / 1M tokens
Output: $25 / 1M tokens
Cached input: $0.5 / 1M tokens
Cache write: $6.25 / 1M tokens
Endpoints
- anthropic
- openai