Gemini 4 Argon
google/gemini-4-argon
spread (output, p90 ÷ p10)
— too few providers
$10.00 – $12.50 · 3 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 |
|---|---|---|---|---|
Vercel AI Gateway router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
AIHubMix router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
Cloudflare AI Gateway router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
CommandCode unclassified | $2.00 | $10.00 | $0.10 | $1.52 |
Vertex hyperscaler | $2.00 | $10.00 | $0.10 | $1.52 |
Kilo Gateway router / aggregator | $2.00 | $10.00 | $0.10 | $1.53 |
Merge Gateway router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
NanoGPT router / aggregator | $2.00 | $10.00 | $0.10 | $1.53 |
Ofox reseller | $2.00 | $10.00 | $0.10 | $1.52 |
OpenCode router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
OpenRouter router / aggregator | $2.00 | $10.00 | $0.10 | $1.53 |
Prime Inference unclassified | $2.00 | $10.00 | — | $2.73no cache price published |
Requesty router / aggregator | $2.00 | $10.00 | $0.10 | $1.52 |
CrossModel router / aggregator | $2.00 | $10.00 | $0.10 | $1.68 |
Googlefirst-party first-party lab | $2.00 | $10.00 | $0.10 | $1.52 |
302.AI reseller | $4.00 | $10.00 | $0.20 | $2.16 |
Cortecs router / aggregator | $2.25 | $11.25 | $0.11 | $1.71 |
Venice AI inference host | $2.50 | $12.50 | $0.13 | $1.90 |
Eden AI router / aggregator | $4.00 | $20.00 | $0.20 | $3.07 |
LLM Gateway router / aggregator | $4.00 | $20.00 | $0.20 | $3.07 |
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 gemini-4-argonsubscription plan
- DevPass (LLM Gateway) gemini-4-argonsubscription plan
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.