Mistral Large 4
mistralai/mistral-large-4
spread (output, p90 ÷ p10)
— too few providers
$2.09 – $4.18 · 2 providers · max÷min 2.0×
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 |
|---|---|---|---|---|
OpenRouter router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
Requesty router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
Standard Compute router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
Vercel AI Gateway router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
OpenCode router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
Mistral first-party lab | $0.68 | $2.09 | $0.07 | $0.42 |
NanoGPT router / aggregator | $0.68 | $2.09 | $0.07 | $0.42 |
LowRouter unclassified | $0.71 | $2.19 | $0.07 | $0.44 |
Cortecs router / aggregator | $0.77 | $2.35 | $0.08 | $0.47 |
Ollama Cloud inference host | $1.36 | $4.18 | $0.14 | $0.84 |
LLM Gateway router / aggregator | $1.36 | $4.18 | $0.14 | $0.84 |
CommandCode unclassified | $1.36 | $4.18 | $0.14 | $0.84 |
Subscription plans (flat fee, not per-token) · 1
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- DevPass (LLM Gateway) mistral-large-4subscription plan
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.