MiniMax M3 API

MiniMax's MiniMax M3, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send MiniMax-M3 as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: MiniMax-M3
Maker: MiniMax
Context window: 516.1K tokens
Input price: $0.350 per million tokens
Output price: $1.375 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Pera: us, $0.350 input and $1.375 output per million tokens, $0.350 cache read per million tokens, 516.1K tokens of context

Scores

Intelligence: 18.9, #29 of 41
HLE: 39.0, #52 of 273
GPQA: 92.9, #12 of 250
AA-LCR: 83.0, #15 of 237
SciCode: 47.1, #71 of 123
Terminal-Bench Hard: 42.4, #25 of 166
τ²-Bench: 88.9, #41 of 169
IFBench: 82.9, #1 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M3",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is MiniMax M3?: MiniMax M3 is a model from MiniMax.
How much does MiniMax M3 cost?: Offers now ask $0.350 per million input tokens and $1.375 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of MiniMax M3?: The largest offer takes 516,096 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can MiniMax M3 do?: Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does MiniMax M3 support?: Text · Images → Text.
Which providers serve MiniMax M3?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call MiniMax M3?: Send "MiniMax-M3" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was MiniMax M3 listed?: The exchange first listed it on 9/29/2026. This is not its release date.