Mistral Medium 3

empiriolabs/mistral-medium-3 · family mistral-medium · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

freeBlended $/1M (3:1)

freeInput $/1M

freeOutput $/1M

free1M in + 1M out

—Cache read $/1M

#255 of 5,000Cheapest rank

Provider: EmpirioLabs AI (empiriolabs)
Context: 130,000 tokens
Max output: 40,000 tokens
Capabilities: toolstextimage

Same model, other providers

“Mistral Medium 3” is offered by 8 providers — cheapest-effective first. This one (EmpirioLabs AI) is the cheapest.

Provider	Input	Output	Blended	Context
EmpirioLabs AI (this)	free	free	$0.00	130k
Nvidia	free	free	$0.00	131k
NanoGPT	$0.4	$2	$0.80	131k
Azure Cognitive Services	$0.4	$2	$0.80	128k
Azure	$0.4	$2	$0.80	128k
Mistral	$0.4	$2	$0.80	131k
Merge Gateway	$0.4	$2	$0.80	128k
OpenRouter	$0.4	$2	$0.80	131k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at EmpirioLabs 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-medium-3","messages":[{"role":"user","content":"hello"}]}'

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