MiniMax-M3

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

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

$0.3Input $/1M

$1.2Output $/1M

$1.501M in + 1M out

$0.06 −80%Cache read $/1M

#2269 of 5,000Cheapest rank

Provider: LLM Gateway (llmgateway)
Context: 1,048,576 tokens
Max output: 128,000 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.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	1000k
Kenari	free	free	$0.00	512k
MiniMax Token Plan (minimax.io)	free	free	$0.00	1000k
MiniMax Token Plan (minimaxi.com)	free	free	$0.00	1000k
Deep Infra	$0.28	$1.1	$0.49	524k
LLM Gateway (this)	$0.3	$1.2	$0.52	1049k
Fireworks AI	$0.3	$1.2	$0.52	512k
OpenCode Go	$0.3	$1.2	$0.52	1000k
Nebius Token Factory	$0.3	$1.2	$0.52	1049k

Call it

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

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

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