Claude Haiku 5.5
anthropic/claude-haiku-5.5
spread (output, p90 ÷ p10)
1.0×
$0.500 – $0.500 · 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 |
|---|---|---|---|---|
Vivgridtiered unclassified | $0.100 | $0.500 | $0.0100 | $0.0893 |
AIHubMixtiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
OpenCode Gotiered subscription plan | $0.100 | $0.500 | $0.0100 | $0.0893 |
OpenRoutertiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Requestytiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0897 |
Standard Computetiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Venice AItiered inference host | $0.100 | $0.500 | $0.0100 | $0.0893 |
Vercel AI Gatewaytiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
302.AI reseller | $0.100 | $0.500 | $0.0100 | $0.0893 |
Aixytiered reseller | $0.100 | $0.500 | $0.0100 | $0.0893 |
Amazon Bedrocktiered hyperscaler | $0.100 | $0.500 | $0.0100 | $0.0893 |
Anthropicfirst-partytiered first-party lab | $0.100 | $0.500 | $0.0100 | $0.0893 |
Azuretiered hyperscaler | $0.100 | $0.500 | $0.0100 | $0.0893 |
Azure Cognitive Servicestiered hyperscaler | $0.100 | $0.500 | $0.0100 | $0.0893 |
Cloudflare AI Gatewaytiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
CommandCodetiered unclassified | $0.100 | $0.500 | $0.0100 | $0.0893 |
CrossModeltiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Eden AItiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Vertextiered hyperscaler | $0.100 | $0.500 | $0.0100 | $0.0893 |
Vertex (Anthropic)tiered hyperscaler | $0.100 | $0.500 | $0.0100 | $0.0893 |
Kilo Gateway router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
LLM Gateway router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Merge Gateway router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
NanoGPT router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
NEAR AI Cloudtiered inference host | $0.100 | $0.500 | $0.0100 | $0.0893 |
Neontiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Ofoxtiered reseller | $0.100 | $0.500 | $0.0100 | $0.0893 |
OpenCodetiered router / aggregator | $0.100 | $0.500 | $0.0100 | $0.0893 |
Cortecs router / aggregator | $0.113 | $0.563 | $0.0110 | $0.100 |
AI/ML API unclassified | $0.130 | $0.650 | $0.0130 | $0.103 |
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.
- GitHub Copilot claude-haiku-5.5subscription plan
- DevPass (LLM Gateway) claude-haiku-5-5subscription plan
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.