MiniMax M2.7

venice/minimax-m27 · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.66Blended $/1M (3:1)

$0.375Input $/1M

$1.5Output $/1M

$1.881M in + 1M out

$0.06875 −82%Cache read $/1M

#2597 of 5,000Cheapest rank

Provider: Venice AI (venice)
Context: 198,000 tokens
Max output: 32,768 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“MiniMax M2.7” is offered by 8 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.26 blended.

Provider	Input	Output	Blended	Context
EmpirioLabs AI	$0.15	$0.6	$0.26	200k
AIHubMix	$0.3	$1.2	$0.52	205k
Merge Gateway	$0.3	$1.2	$0.52	205k
Vercel AI Gateway	$0.3	$1.2	$0.52	205k
NovitaAI	$0.3	$1.2	$0.52	205k
ZenMux	$0.3055	$1.2219	$0.53	205k
NanoGPT	$0.315	$1.26	$0.55	205k
Venice AI (this)	$0.375	$1.5	$0.66	198k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"minimax-m27","messages":[{"role":"user","content":"hello"}]}'

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