jishie

Ministral 3B

pioneer/ministral-3b · family ministral · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

$0.10
Blended $/1M (3:1)
$0.1
Input $/1M
$0.1
Output $/1M
$0.20
1M in + 1M out
$0.1
Cache read $/1M
#908 of 7,263
Cheapest rank
Provider
Pioneer (pioneer)
Kind
text (outputs text)
Context
128,000 tokens
Max output
4,000 tokens
Capabilities
tools text

Same model, other providers

“Ministral 3B” is offered by 5 providers — cheapest-effective first. Azure Cognitive Services is the cheapest at $0.04 blended.

ProviderInputOutputBlendedContext
Azure Cognitive Services$0.04$0.04$0.04128k
Azure$0.04$0.04$0.04128k
Pioneer (this)$0.1$0.1$0.10128k
NanoGPT$0.1$0.1$0.10131k
DevPass (LLM Gateway)$0.1$0.1$0.10131k

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":"ministral-3b","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