Model
Claude Opus 5 API pricing
Compare the published Claude Opus 5 (claude-opus-5) list rate with corouter's outlet rate, and estimate a monthly token bill. Claude Opus 5 lists at the same input and output rate as Opus 4.6, 4.7, and 4.8. Send claude-opus-5 when the client names Opus 5 rather than an Opus 4 ID.
Where this model fits
- Clients that already send claude-opus-5
- Opus tasks that should stay off the Opus 5.5 rate
- Long reasoning jobs at the shared Opus 4.8 list rate
Estimates only. Actual billing depends on your real token counts, cache hit rate, and the prices in effect at request time.
From the blog
- OpenAI vs Anthropic API pricingBoth vendors publish per-million-token rates, but they price context, output, and caching differently enough that the cheaper choice depends entirely on your workload shape.Read the post
- How to reduce your LLM API costsMost advice about cutting inference spend is vague. This is the concrete version: where the money goes, which five levers move it, and how much each one is worth on a real monthly volume.Read the post