Mistral Small 3
deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 · family mistral-small · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.06
Blended $/1M (3:1)
$0.05
Input $/1M
$0.08
Output $/1M
$0.13
1M in + 1M out
—
Cache read $/1M
#763 of 8,275
Cheapest rank
- Provider
- Deep Infra (
deepinfra) - Kind
- text (outputs text)
- Context
- 32,768 tokens
- Max output
- 16,384 tokens
- Capabilities
- text
Same model, other providers
“Mistral Small 3” is offered by 3 providers — cheapest-effective first. This one (Deep Infra) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra (this) | $0.05 | $0.08 | $0.06 | 33k |
| Kilo Gateway | $0.05 | $0.08 | $0.06 | 33k |
| OpenRouter | $0.05 | $0.08 | $0.06 | 33k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Deep Infra and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistralai/Mistral-Small-24B-Instruct-2501","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):