MiniMax
Creator of the MiniMax M-series models built for real-world agentic productivity. Requesty routes to 5 MiniMax models starting at $0.30 per 1M input tokens with context windows up to 200K tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
MiniMax-M2MMLU Pro
79.2%
GPQA
62.5%
HumanEval
88.1%
SWE-Bench
69.3%
All MiniMax models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
MiniMax-M2.7 | 200K | 128K | $0.30 | $1.20 | 👁🧠🔧⚡ | — |
MiniMax-M2.7-highspeed | 200K | 128K | $0.60 | $2.40 | 👁🧠🔧⚡ | — |
MiniMax-M2.5-highspeed | 200K | 128K | $0.60 | $2.40 | 👁🧠🔧⚡ | — |
MiniMax-M2.5 | 200K | 128K | $0.30 | $1.20 | 👁🧠🔧⚡ | — |
MiniMax-M2 | 200K | 128K | $0.30 | $1.20 | 🔧 | 69% |
About MiniMax on Requesty
How many MiniMax models are available through Requesty?
Requesty routes to 5 MiniMax models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest MiniMax model?
The cheapest MiniMax model starts at $0.30 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on MiniMax pricing?
No. Requesty passes through exactly what MiniMax charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train MiniMax models?
MiniMax's training policy varies by product and tier. See their privacy policy for specifics, and contact Requesty for enterprise-grade data controls.
Where are MiniMax models hosted?
MiniMax models are hosted in 🇸🇬 Singapore. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the MiniMax rows in the models explorer.