jishie

Magistral Small

pioneer/mistralai/Magistral-Small-2506 · family magistral · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.75
Blended $/1M (3:1)
$0.5
Input $/1M
$1.5
Output $/1M
$2.00
1M in + 1M out
$0.5
Cache read $/1M
#3600 of 7,708
Cheapest rank
Provider
Pioneer (pioneer)
Kind
text (outputs text)
Context
128,000 tokens
Max output
64,000 tokens
Capabilities
tools reasoning text

Same model, other providers

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

ProviderInputOutputBlendedContext
Pioneer (this)$0.5$1.5$0.75128k
Mistral$0.5$1.5$0.75128k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistralai/Magistral-Small-2506","messages":[{"role":"user","content":"hello"}]}'

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

← all Pioneer models · model index · JSON