jishie

Mistral Small 3.1 24B

watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 · family mistral-small · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

$0.16Blended $/1M (3:1)
$0.106Input $/1M
$0.318Output $/1M
$0.421M in + 1M out
—Cache read $/1M
#1120 of 5,000Cheapest rank
Provider
watsonx.ai (watsonx)
Context
131,072 tokens
Max output
16,384 tokens
Capabilities
toolstextimage

Same model, other providers

“Mistral Small 3.1 24B” is offered by 2 providers — cheapest-effective first. This one (watsonx.ai) is the cheapest.

ProviderInputOutputBlendedContext
watsonx.ai (this)$0.106$0.318$0.16131k
OpenRouter$0.351$0.555$0.40128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at watsonx.ai 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-3-1-24b-instruct-2503","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):