jishie

MiniMax-M3

tensorx/minimax/minimax-m3 · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

$0.80Blended $/1M (3:1)
$0.4Input $/1M
$2Output $/1M
$2.401M in + 1M out
$0.1 −75%Cache read $/1M
#2875 of 5,000Cheapest rank
Provider
TensorX (tensorx)
Context
1,048,576 tokens
Max output
131,072 tokens
Capabilities
toolsreasoningtextimagevideo

Same model, other providers

“MiniMax-M3” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.001000k
Kenarifreefree$0.00512k
MiniMax Token Plan (minimax.io)freefree$0.001000k
MiniMax Token Plan (minimaxi.com)freefree$0.001000k
Deep Infra$0.28$1.1$0.49524k
Fireworks AI$0.3$1.2$0.52512k
OpenCode Go$0.3$1.2$0.521000k
Nebius Token Factory$0.3$1.2$0.521049k
TensorX (this)$0.4$2$0.801049k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m3","messages":[{"role":"user","content":"hello"}]}'

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