Claude Sonnet 4.5 (latest)
anthropic/claude-sonnet-4.5
spread (output, p90 ÷ p10)
1.0×
$15.00 – $18.75 · 8 providers · max÷min 1.3×
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 |
|---|---|---|---|---|
QiHang reseller | $0.43 | $2.14 | — | $0.59no cache price published |
Poe router / aggregator | $2.60 | $13.00 | $0.26 | $2.32 |
Jiekou.AI reseller | $2.70 | $13.50 | — | $3.68no cache price published |
Anthropicfirst-party first-party lab | $3.00 | $15.00 | $0.30 | $2.68 |
Azure hyperscaler | $3.00 | $15.00 | $0.30 | $2.68 |
Azure Cognitive Services hyperscaler | $3.00 | $15.00 | $0.30 | $2.68 |
Cloudflare AI Gateway router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Vertex hyperscaler | $3.00 | $15.00 | $0.30 | $2.68 |
Vertex (Anthropic) hyperscaler | $3.00 | $15.00 | $0.30 | $2.68 |
Helicone router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Impossibl unclassified | $3.00 | $15.00 | $0.30 | $2.68 |
Kilo Gateway router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
LLM Gateway router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Merge Gateway router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
NanoGPT router / aggregator | $3.00 | $15.00 | $0.30 | $2.37 |
NEAR AI Cloud inference host | $3.00 | $15.00 | $0.30 | $2.68 |
Neon router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Ofox reseller | $3.00 | $15.00 | $0.30 | $2.68 |
OpenCode Zentiered router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
OpenRoutertiered router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Opper router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
OrcaRouter router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Perplexity Agent first-party lab | $3.00 | $15.00 | $0.30 | $2.37 |
Pioneer unclassified | $3.00 | $15.00 | $0.30 | $2.68 |
Requestytiered router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
ZenMux router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
Abacus router / aggregator | $3.00 | $15.00 | — | $4.09no cache price published |
Vercel AI Gateway router / aggregator | $3.00 | $15.00 | $0.30 | $2.68 |
302.AI reseller | $3.00 | $15.00 | — | $4.09no cache price published |
Venice AIoutlier inference host | $3.75 | $18.75 | $0.38 | $3.35 |
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-sonnet-4-5-20250929pay per token
Subscription plans (flat fee, not per-token) · 2
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-sonnet-4-5subscription plan
- DevPass (LLM Gateway) claude-sonnet-4-5-20250929subscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.