MiniMax-M2

huggingface/MiniMaxAI/MiniMax-M2 · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.52Blended $/1M (3:1)

$0.3Input $/1M

$1.2Output $/1M

$1.501M in + 1M out

—Cache read $/1M

#2347 of 5,000Cheapest rank

Provider: Hugging Face (huggingface)
Context: 204,800 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“MiniMax-M2” is offered by 9 providers — cheapest-effective first. MiniMax Token Plan (minimax.io) is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
MiniMax Token Plan (minimax.io)	free	free	$0.00	197k
MiniMax Token Plan (minimaxi.com)	free	free	$0.00	197k
LLM Gateway	$0.2	$1	$0.40	197k
OpenRouter	$0.255	$1.02	$0.45	205k
Hugging Face (this)	$0.3	$1.2	$0.52	205k
MiniMax (minimax.io)	$0.3	$1.2	$0.52	197k
Kilo Gateway	$0.3	$1.2	$0.52	205k
NovitaAI	$0.3	$1.2	$0.52	205k
MiniMax (minimaxi.com)	$0.3	$1.2	$0.52	197k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"MiniMaxAI/MiniMax-M2","messages":[{"role":"user","content":"hello"}]}'

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