Model
Claude Opus 4.6 API pricing
Compare the published Claude Opus 4.6 (claude-opus-4-6) list rate with corouter's outlet rate, and estimate a monthly token bill. Claude Opus 4.6 is the earliest Opus 4 ID still on this rate card, at the same list rate as Opus 4.7. Send claude-opus-4-6 only when that older ID is the one in the request.
Where this model fits
- Older clients that still send claude-opus-4-6
- Keeping an Opus 4.6 runbook unchanged
- Checking that its list rate matches Opus 4.7 before you switch IDs
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