jishie

Pixtral 12B

mistral/pixtral-12b · family pixtral · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

$0.15Blended $/1M (3:1)
$0.15Input $/1M
$0.15Output $/1M
$0.301M in + 1M out
Cache read $/1M
#1003 of 5,000Cheapest rank
Provider
Mistral (mistral)
Context
128,000 tokens
Max output
128,000 tokens
Capabilities
toolstextimage

Same model, other providers

“Pixtral 12B” is offered by 4 providers — cheapest-effective first. This one (Mistral) is the cheapest.

ProviderInputOutputBlendedContext
Mistral (this)$0.15$0.15$0.15128k
Pioneer$0.15$0.15$0.15128k
Vercel AI Gateway$0.15$0.15$0.15128k
GreenPT$0.285$0.285$0.28128k

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":"pixtral-12b","messages":[{"role":"user","content":"hello"}]}'

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