Mistral Medium 3

mistralai/mistral-medium-3

Mistral AI· 131K ctx

API only quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$2.00 – $2.00 · 1 providers · max÷min 1.0×

1 provider priced · 1 offering

Including routers & resellers

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 assumptionsInput : output: 1Cache-hit share of input%

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
Eden AI router / aggregator	$0.40	$2.00	$0.04	$0.32
Vertex hyperscaler	$0.40	$2.00	—	$0.55no cache price published
Kilo Gateway router / aggregator	$0.40	$2.00	$0.04	$0.32
NanoGPT router / aggregator	$0.40	$2.00	$0.20	$0.42
OpenRouter router / aggregator	$0.40	$2.00	$0.04	$0.32
AI/ML API unclassified	$0.55	$2.75	$0.06	$0.44

Connect

Provider (default: cheapest output among direct providers)

$2.00 /M · hyperscaler

opencode.json

{
  "provider": {
    "google-vertex": {
      "npm": "@ai-sdk/google-vertex",
      "models": {
        "mistral-medium-3": {}
      }
    }
  }
}

Set GOOGLE_VERTEX_PROJECT, GOOGLE_VERTEX_LOCATION, GOOGLE_APPLICATION_CREDENTIALS in your environment. Generated — verify against the OpenCode docs.

Not enough history yet — the min/median/max sparkline fills in as the daily snapshot accumulates.

Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.