Ministral 3B
llmgateway/ministral-3b-2512 · family mistral · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.
$0.10
Blended $/1M (3:1)
$0.1
Input $/1M
$0.1
Output $/1M
$0.20
1M in + 1M out
—
Cache read $/1M
#942 of 7,713
Cheapest rank
- Provider
- DevPass (LLM Gateway) (
llmgateway) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 8,192 tokens
- Capabilities
- text image
Same model, other providers
“Ministral 3B” is offered by 5 providers — cheapest-effective first. Azure is the cheapest at $0.04 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Azure | $0.04 | $0.04 | $0.04 | 128k |
| Azure Cognitive Services | $0.04 | $0.04 | $0.04 | 128k |
| DevPass (LLM Gateway) (this) | $0.1 | $0.1 | $0.10 | 131k |
| NanoGPT | $0.1 | $0.1 | $0.10 | 131k |
| Pioneer | $0.1 | $0.1 | $0.10 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at DevPass (LLM Gateway) and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"ministral-3b-2512","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):