jishie

Mistral Small 4

venice/mistral-small-2603 · family mistral-small · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$0.33Blended $/1M (3:1)
$0.1875Input $/1M
$0.75Output $/1M
$0.941M in + 1M out
Cache read $/1M
#1798 of 5,000Cheapest rank
Provider
Venice AI (venice)
Context
256,000 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“Mistral Small 4” is offered by 9 providers — cheapest-effective first. Cortecs is the cheapest at $0.25 blended.

ProviderInputOutputBlendedContext
Cortecs$0.143$0.568$0.25262k
Pioneer$0.15$0.6$0.26262k
EmpirioLabs AI$0.15$0.6$0.26256k
Mistral$0.15$0.6$0.26256k
Kilo Gateway$0.15$0.6$0.26262k
OpenRouter$0.15$0.6$0.26262k
AKI.IO$0.2$0.6$0.30262k
Venice AI (this)$0.1875$0.75$0.33256k
Infomaniak$0.25$0.93$0.42256k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistral-small-2603","messages":[{"role":"user","content":"hello"}]}'

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