Data as of 2026-09-20.
Price spread

Claude Fable 5.1

anthropic/claude-fable-5.1

Anthropic· 1M ctx
API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.0×

$50.00 – $60.00 · 8 providers · max÷min 1.2×

8 providers priced · 10 offerings

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:
Blended $/M assumptions

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.

ProviderInputOutputCache rdBlended
Vivgrid
unclassified
$10.00$50.00$0.50$8.61
OpenRouter
router / aggregator
$10.00$50.00$0.25$8.45
Requesty
router / aggregator
$10.00$50.00$0.25$8.45
Vercel AI Gateway
router / aggregator
$10.00$50.00$0.25$8.45
302.AI
reseller
$10.00$50.00—$13.64no cache price published
Amazon Bedrock
hyperscaler
$10.00$50.00$0.25$8.45
Anthropicfirst-party
first-party lab
$10.00$50.00$0.25$8.45
Azure
hyperscaler
$10.00$50.00$0.25$8.45
Azure Cognitive Services
hyperscaler
$10.00$50.00$0.25$8.45
Cloudflare AI Gateway
router / aggregator
$10.00$50.00$0.25$8.45
CrossModel
router / aggregator
$10.00$50.00$0.25$8.45
DigitalOcean
inference host
$10.00$50.00$0.25$8.45
Eden AI
router / aggregator
$10.00$50.00$0.25$8.45
Vertex
hyperscaler
$10.00$50.00$0.25$8.45
Vertex (Anthropic)
hyperscaler
$10.00$50.00$0.25$8.45
Kilo Gateway
router / aggregator
$10.00$50.00$0.25$8.45
LLM Gateway
router / aggregator
$10.00$50.00$0.25$8.45
Merge Gateway
router / aggregator
$10.00$50.00$0.25$8.45
NanoGPT
router / aggregator
$10.00$50.00$0.25$8.45
Neon
router / aggregator
$10.00$50.00$0.25$8.45
Ofox
reseller
$10.00$50.00$0.25$8.45
OpenCode Zen
router / aggregator
$10.00$50.00$0.25$8.45
AIHubMix
router / aggregator
$11.00$55.00$0.28$9.30
Venice AIoutlier
inference host
$12.00$60.00$0.30$10.15
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-fable-5.1subscription plan
  • DevPass (LLM Gateway) claude-fable-5-1subscription plan

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.