Mistral Small 3.2 24B Instruct 2506

mistralai/mistral-small-3.2-24b-instruct-2506

Mistral AI· 33K ctx

open weightstool callstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.310 – $0.350 · 3 providers · max÷min 1.1×

3 providers priced · 3 offerings · 1 omitted (stale)

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
OVHcloud AI Endpoints inference host	$0.100	$0.310	—	$0.119no cache price published
Cortecs router / aggregator	$0.100	$0.312	—	$0.119no cache price published
Berget.AI inference host	$0.330	$0.330	—	$0.330no cache price published
Scaleway inference host	$0.150	$0.350	—	$0.168no cache price published

Stale offerings (not in the spread) · 1

Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.

NanoGPT chutesai/Mistral-Small-3.2-24B-Instruct-2506pay per token

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.

Meganova mistralai/Mistral-Small-3.2-24B-Instruct-2506unpriced

Connect

Provider (default: cheapest output among direct providers)

$0.310 /M · inference host

opencode.json

{
  "provider": {
    "ovhcloud": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
      },
      "models": {
        "mistral-small-3.2-24b-instruct-2506": {}
      }
    }
  }
}

Set OVHCLOUD_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

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