Claude Opus 4.1 (latest)
anthropic/claude-opus-4.1
spread (output, p90 ÷ p10)
1.0×
$75.00 – $75.00 · 4 providers · max÷min 1.0×
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published
A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Poe router / aggregator | $13.00 | $64.00 | $1.30 | $11.50 |
Jiekou.AI reseller | $13.50 | $67.50 | — | $18.41no cache price published |
Azure hyperscaler | $15.00 | $75.00 | $1.50 | $13.40 |
Azure Cognitive Services hyperscaler | $15.00 | $75.00 | $1.50 | $13.40 |
FastRouter router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
Vertex hyperscaler | $15.00 | $75.00 | $1.50 | $13.40 |
Vertex (Anthropic) hyperscaler | $15.00 | $75.00 | $1.50 | $13.40 |
Helicone router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
Kilo Gateway router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
LLM Gateway router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
Merge Gateway router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
NanoGPT router / aggregator | $15.00 | $75.00 | $1.50 | $11.86 |
Neon router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
OpenCode Zen router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
OpenRouter router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
Pioneer unclassified | $15.00 | $75.00 | $1.50 | $13.40 |
Requesty router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
302.AI reseller | $15.00 | $75.00 | — | $20.45no cache price published |
ZenMux router / aggregator | $15.00 | $75.00 | $1.50 | $13.40 |
Abacus router / aggregator | $15.00 | $75.00 | — | $20.45no cache price published |
Stale offerings (not in the spread) · 1
Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.
- NanoGPT claude-opus-4-1-20250805pay per token
Subscription plans (flat fee, not per-token) · 1
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- DevPass (LLM Gateway) claude-opus-4-1-20250805subscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.