Data as of 2026-09-20.
Price spread

Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

Anthropic· 1M ctx
API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.0×

$15.00 – $18.00 · 11 providers · max÷min 1.2×

11 providers priced · 15 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
Xpersona
reseller
$0.90$5.55$0.09$0.81
Kilo Gateway
router / aggregator
$2.40$12.00$0.24$2.14
Poe
router / aggregator
$2.60$13.00$0.26$2.32
Anthropicfirst-party
first-party lab
$3.00$15.00$0.30$2.68
Auriko
unclassified
$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
ZenMux
router / aggregator
$3.00$15.00$0.30$2.68
Abacus
router / aggregator
$3.00$15.00—$4.09no cache price published
AIHubMixtiered
router / aggregator
$3.00$15.00$0.30$2.68
Amazon Bedrock
hyperscaler
$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
Requesty
router / aggregator
$3.00$15.00$0.30$2.68
routing.run
router / aggregator
$3.00$15.00—$4.09no cache price published
Vercel AI Gatewaytiered
router / aggregator
$3.00$15.00$0.30$2.68
302.AI
reseller
$3.00$15.00—$4.09no cache price published
CrossModel
router / aggregator
$3.00$15.00$0.30$2.68
DaoXE
reseller
$3.00$15.00$0.30$2.68
Databricks
inference host
$3.00$15.00$0.30$2.68
Eden AI
router / aggregator
$3.00$15.00$0.30$2.68
FastRouter
router / aggregator
$3.00$15.00—$4.09no cache price published
FreeModel
unclassified
$3.00$15.00$0.30$2.68
FrogBot
unclassified
$3.00$15.00$0.30$2.68
GMI Cloud
inference host
$3.00$15.00$0.30$2.37
Vertextiered
hyperscaler
$3.00$15.00$0.30$2.68
Vertex (Anthropic)tiered
hyperscaler
$3.00$15.00$0.30$2.68
Impossibl
unclassified
$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
Modelis
reseller
$3.00$15.00—$4.09no cache price published
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 Zen
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
Cortecs
router / aggregator
$3.20$15.94$0.32$2.85
Venice AIoutlier
inference host
$3.60$18.00$0.36$3.22
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-sonnet-4.6subscription plan
  • DevPass (LLM Gateway) claude-sonnet-4-6subscription plan
Unpriced · 1

Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.

  • Kenari claude-sonnet-4-6unpriced

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