Anthropic
ReferenceClaude Opus 5
Anthropic's flagship Claude model for demanding reasoning, advanced coding, visual analysis, and long-horizon agent workflows.
Reference pricing
Imported snapshot values per 1M tokens. Your customer portal is authoritative for actual kineticRouter billing.
| Component | Mirrored snapshot | Official reference | Snapshot savings |
|---|---|---|---|
| Input | $1/M | $5/M | 80% |
| Output | $5/M | $25/M | 80% |
| Cache read | $0.1/M | $0.5/M | 80% |
| Cache write | $1.25/M | $6.25/M | 80% |
| 5m cache write | $1.25/M | $6.25/M | 80% |
| 1h cache write | $2/M | $10/M | 80% |
API example
The Anthropic-native route is planned and its configuration is shown only as a reference.
About this model
Anthropic's flagship Claude model for demanding reasoning, advanced coding, visual analysis, and long-horizon agent workflows.
Snapshot FAQ
Imported reference copy; verify runtime behavior before production use.
How is Claude Opus 5 billed on kineticRouter?＋
kineticRouter bills actual request usage. Input, output, cache, and any other applicable rates follow the live pricing table on this page, and final request costs are available in the console.
What are the context window and maximum output for Claude Opus 5?＋
Claude Opus 5 provides a 1M-token context window and up to 128K output tokens in the current kineticRouter model catalog.
How can I call Claude Opus 5 through kineticRouter?＋
Use model ID anthropic/claude-opus-5 through kineticRouter's OpenAI-compatible or Anthropic-compatible API. The code examples on this page show the current Base URL and SDK configuration.
Which capabilities does Claude Opus 5 support?＋
The current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching, PDF input, structured outputs, and Claude Code fast mode.