jishie

Devstral Small 2

mistral/labs-devstral-small-2512 · family devstral · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
—Cache read $/1M
#337 of 5,000Cheapest rank
Provider
Mistral (mistral)
Context
256,000 tokens
Max output
256,000 tokens
Capabilities
toolstextimage

Same model, other providers

“Devstral Small 2” is offered by 2 providers — cheapest-effective first. This one (Mistral) is the cheapest.

ProviderInputOutputBlendedContext
Mistral (this)freefree$0.00256k
Vercel AI Gateway$0.1$0.3$0.15256k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Mistral and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"labs-devstral-small-2512","messages":[{"role":"user","content":"hello"}]}'

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