Ministral 3B

mistral· 2024-10-16· 128K ctx

open weightstool call quant: unknown

spread (output)

2.5×

$0.040 – $0.100 · 8 providers

8 providers priced

Provider	Input	Output	Cache rd	Blended
Vercel AI Gateway unknown	$0.040	$0.040	—	$0.040^*
Azure Cognitive Services unknown	$0.040	$0.040	—	$0.040^*
Mistral first party lab	$0.040	$0.040	—	$0.040^*
Azure hyperscaler	$0.040	$0.040	—	$0.040^*
Pioneer relay router	$0.100	$0.100	$0.100	$0.108
NanoGPT relay router	$0.100	$0.100	$0.050	$0.068
DevPass (LLM Gateway) relay router	$0.100	$0.100	—	$0.100^*
LLM Gateway relay router	$0.100	$0.100	—	$0.100^*

Cheapest (output)

Vercel AI Gateway

$0.040 /M

opencode.json

{
  "provider": {
    "vercel": {
      "npm": "@ai-sdk/gateway",
      "models": {
        "mistral/ministral-3b": {}
      }
    }
  }
}

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

Output $/M over time

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.