jishie

Mistral Small 4

aki-io/mistral4-119b · family mistral-small · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$0.30
Blended $/1M (3:1)
$0.2
Input $/1M
$0.6
Output $/1M
$0.80
1M in + 1M out
—
Cache read $/1M
#2217 of 7,708
Cheapest rank
Provider
AKI.IO (aki-io)
Kind
text (outputs text)
Context
262,144 tokens
Max output
81,920 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Mistral Small 4” is offered by 12 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.26 blended.

ProviderInputOutputBlendedContext
EmpirioLabs AI$0.15$0.6$0.26256k
Kilo Gateway$0.15$0.6$0.26262k
OpenRouter$0.15$0.6$0.26262k
Pioneer$0.15$0.6$0.2632k
Eden AI$0.15$0.6$0.26262k
Tempr$0.15$0.6$0.26256k
Mistral$0.15$0.6$0.26256k
Cortecs$0.156$0.625$0.27262k
Requesty$0.165$0.66$0.29256k
AKI.IO (this)$0.2$0.6$0.30262k
Infomaniak$0.25$0.93$0.42256k
Opper$0.5811$2.44$1.05256k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at AKI.IO and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistral4-119b","messages":[{"role":"user","content":"hello"}]}'

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

← all AKI.IO models · model index · JSON