MiniMax M2: API pricing, providers and specs
MiniMax M2 is a text model by MiniMax. 10 providers serve it, from $1 to $1.41 /1M; the lowest price is at DevPass (LLM Gateway).
A newer version is out: MiniMax M2.5 · released Feb 12, 2026
How MiniMax M2 compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $1 /1M against a median of $1.10; 49% of comparable models cost less.
- Its 205K-token context window is larger than 37% of them (median 262K), about 310 pages of text.
- On LMArena's Text board it ranks #67 of the 120 comparable models scored there.
- 10 providers serve it; 77% of comparable models have fewer.
- Its weights are open under the modified-mit license: commercial use under the maker's terms.
MiniMax M2 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| DevPass (LLM Gateway) | $0.20/1M | From$1/1M | $0.03/1M | — |
| OpenRouter | $0.255/1M | From$1.02/1M | — | 205K |
| ZenMux | $0.30/1M | $1.20/1M | $0.03/1M | 205K |
 Ofox | $0.30/1M | $1.20/1M | $0.03/1M | 205K |
| Vercel AI Gateway | $0.30/1M | $1.20/1M | $0.03/1M | 205K |
 Amazon Bedrock | $0.30/1M | From$1.20/1M | — | — |
 Requesty | $0.30/1M | From$1.20/1M | $0.30/1M | 200K |
 Vertex | $0.30/1M | $1.20/1M | $0.03/1M | — |
| AI/ML API | $0.30/1M | $1.20/1M | — | — |
 Cortecs | $0.35/1M | $1.41/1M | — | — |
- DevPass (LLM Gateway)From$1
- OpenRouterFrom$1.02
- ZenMux$1.20
- Ofox$1.20
- Vercel AI Gateway$1.20
- Vertex$1.20
- AI/ML API$1.20
- Amazon BedrockFrom$1.20
- RequestyFrom$1.20
- Cortecs$1.41
Specs
- Type
- Text
- Maker
- MiniMax
- Inputs
- Text
- Outputs
- Text
- Context
- 205K≈ 310 pages of text
- Max output
- 131K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling
- Released
- Oct 22, 2025
- License
- modified-mitcommercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 229B
- Arena score
- 1340Text
Alternatives to MiniMax M2
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| MiniMax M2this model | $1/1M | 205K | 1340 | 10 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| GLM-5.2 | $1.80/1M | 1M | 1604 | 44 |
| Grok Build 0.1 | $1.60/1M | 256K | — | 18 |
More from MiniMax
MiniMax H3MiniMax$0.02/secMiniMax H3 MaxMiniMax$0.048/secMiniMax-M3.1-FlashMiniMax$0.45/1MMiniMax-M3MiniMax$0.90/1M(Hailuo AI) Video 01MiniMax$0.50/videoMiniMax M2.5MiniMax$0.95/1MMiniMax H3 SingularityMiniMax$0.025/secMiniMax-M3.1-Flash-PreviewMiniMax$3.20/1MMiniMax M2 FAQ
The lowest price for MiniMax M2 is $1 /1M, at DevPass (LLM Gateway).
DevPass (LLM Gateway), at $1 /1M. 10 providers serve MiniMax M2; the table above lists every one with its price.
MiniMax M2 reads up to 205K tokens per request and writes up to 131K.
Yes. MiniMax M2's weights can be downloaded from its maker's Hugging Face page, under the modified-mit license.
About 229B, as the safetensors metadata of its official Hugging Face repo states.
10 API providers serve MiniMax M2. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us