M2 1 API
MiniMax's M2 1 costs $0.301 per million input tokens and $1.202 per million output tokens from 1 independent provider. Each request through the OpenAI-compatible API 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 m2-1 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.
About M2 1
M2 1 is a language model from MiniMax. It takes text, files and images and gives text. The largest offer takes 204,000 input tokens. 1 independent provider quotes it on this exchange now.
Facts
- Model name
- m2-1
- Maker
- MiniMax
- Context window
- 204K tokens
- Input price
- $0.301 per million tokens
- Output price
- $1.202 per million tokens
- Providers
- 1 independent provider
- Regions
- us
Providers
- Architect: us, $0.301 input and $1.202 output per million tokens, $0.301 cache read per million tokens, 204K tokens of context
Scores
- HLE: 23.2, #149 of 465
- GPQA: 83.0, #125 of 432
- AA-LCR: 67.7, #193 of 409
- Terminal-Bench Hard: 28.8, #110 of 311
- LiveCodeBench: 81.0, #22 of 250
- AIME 2025: 82.7, #31 of 199
- MMLU-Pro: 87.5, #10 of 253
- τ²-Bench: 85.4, #81 of 313
- IFBench: 69.9, #65 of 321
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": "m2-1",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is M2 1?
- M2 1 is a language model from MiniMax.
- How much does M2 1 cost?
- Offers now ask $0.301 per million input tokens and $1.202 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 M2 1?
- The largest offer takes 204,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can M2 1 do?
- Its providers list Documents, Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does M2 1 support?
- Text · Files · Images → Text.
- Which providers serve M2 1?
- 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 M2 1?
- Send "m2-1" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was M2 1 listed?
- The exchange first listed it on 10/10/2026. This is not its release date.