Claude Haiku 4.5 (latest)
anthropic/claude-haiku-4.5
spread (output, p90 ÷ p10)
1.0×
$5.00 – $5.00 · 8 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 |
|---|---|---|---|---|
QiHang reseller | $0.140 | $0.710 | — | $0.192no cache price published |
Xpersona reseller | $0.60 | $3.70 | $0.06 | $0.54 |
Poe router / aggregator | $0.85 | $4.30 | $0.09 | $0.77 |
Jiekou.AI reseller | $0.90 | $4.50 | — | $1.23no cache price published |
Cortecs router / aggregator | $1.00 | $4.98 | $0.10 | $0.88 |
Azure hyperscaler | $1.00 | $5.00 | $0.10 | $0.89 |
Azure Cognitive Services hyperscaler | $1.00 | $5.00 | $0.10 | $0.89 |
Cloudflare AI Gateway router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
CrossModel router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
DaoXE reseller | $1.00 | $5.00 | $0.10 | $1.20 |
DigitalOcean inference host | $1.00 | $5.00 | $0.10 | $0.89 |
FreeModel unclassified | $1.00 | $5.00 | $0.10 | $0.89 |
FrogBot unclassified | $1.00 | $5.00 | $0.10 | $0.89 |
Vertex hyperscaler | $1.00 | $5.00 | $0.10 | $0.89 |
Vertex (Anthropic) hyperscaler | $1.00 | $5.00 | $0.10 | $0.89 |
Helicone router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
Impossibl unclassified | $1.00 | $5.00 | $0.10 | $0.89 |
Kilo Gateway router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
LLM Gateway router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
Merge Gateway router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
NanoGPT router / aggregator | $1.00 | $5.00 | $0.10 | $0.79 |
NEAR AI Cloud inference host | $1.00 | $5.00 | $0.10 | $0.89 |
Neon router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
Ofox reseller | $1.00 | $5.00 | $0.10 | $0.89 |
OpenCode Zen router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
OpenRouter router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
Opper router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
OrcaRouter router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
Perplexity Agent first-party lab | $1.00 | $5.00 | $0.10 | $0.79 |
Pioneer unclassified | $1.00 | $5.00 | $0.10 | $0.89 |
Requesty router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
ZenMux router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
302.AI reseller | $1.00 | $5.00 | — | $1.36no cache price published |
Abacus router / aggregator | $1.00 | $5.00 | — | $1.36no cache price published |
Anthropicfirst-party first-party lab | $1.00 | $5.00 | $0.10 | $0.89 |
Vercel AI Gateway router / aggregator | $1.00 | $5.00 | $0.10 | $0.89 |
UnoRouter reseller | $1.20 | $6.00 | — | $1.64no 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-haiku-4-5-20251001pay per token
Subscription plans (flat fee, not per-token) · 3
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- GitHub Copilot claude-haiku-4.5subscription plan
- DevPass (LLM Gateway) claude-haiku-4-5subscription plan
- DevPass (LLM Gateway) claude-haiku-4-5-20251001subscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.