MiniMax M2.5

deepinfra/MiniMaxAI/MiniMax-M2.5 · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.40Blended $/1M (3:1)

$0.15Input $/1M

$1.15Output $/1M

$1.301M in + 1M out

$0.03 −80%Cache read $/1M

#1920 of 5,000Cheapest rank

Provider: Deep Infra (deepinfra)
Context: 196,608 tokens
Max output: 131,072 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“MiniMax M2.5” is offered by 9 providers — cheapest-effective first. Inceptron is the cheapest at $0.34 blended.

Provider	Input	Output	Blended	Context
Inceptron	$0.15	$0.9	$0.34	197k
Deep Infra (this)	$0.15	$1.15	$0.40	197k
Venice AI	$0.27	$0.95	$0.44	198k
D.Run (China)	$0.29	$1.16	$0.51	205k
Weights & Biases	$0.3	$1.2	$0.52	197k
NanoGPT	$0.3	$1.2	$0.52	205k
ZenMux	$0.3	$1.2	$0.52	205k
Amazon Bedrock	$0.3	$1.2	$0.52	197k
Merge Gateway	$0.3	$1.2	$0.52	205k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Deep Infra 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-M2.5","messages":[{"role":"user","content":"hello"}]}'

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