MiniMax API Pricing
MiniMax is a Shanghai-based lab whose MiniMax-M series pairs very long context windows (up to 1M+ tokens) with strong agentic and coding performance at aggressive prices. The models are open-weight and widely hosted.
Models
8 tracked
All tiers, latest pricing.
All MiniMax Models
| Model | Tier | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| MiniMax M2.5 | fast | $0.120 | $0.480 | 205K |
| MiniMax M2.7 | fast | $0.180 | $0.720 | 205K |
| MiniMax-01 | fast | $0.200 | $1.10 | 1M |
| MiniMax M2 | fast | $0.255 | $1.00 | 205K |
| MiniMax M2.1 | fast | $0.290 | $0.950 | 205K |
| MiniMax M3 | fast | $0.300 | $1.20 | 1M |
| MiniMax M2-her | fast | $0.300 | $1.20 | 66K |
| MiniMax M1 | fast | $0.400 | $2.20 | 1M |
Model Details
MiniMax M2.5
$0.120 inMiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
MiniMax M2.7
$0.180 inMiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
MiniMax-01
$0.200 inMiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding.
MiniMax M2
$0.255 inMiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.
MiniMax M2.1
$0.290 inMiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.
MiniMax M3
$0.300 inMiniMax M3 is MiniMax's a fast, low-cost model tuned for high-throughput tasks like classification, extraction, and simple chat. It costs $0.300 per million input tokens with a 1M-token context window and native image understanding.
MiniMax M2-her
$0.300 inMiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations.
MiniMax M1
$0.400 inMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference.
Calculate MiniMax API Costs
Use the TokenRate calculator to estimate exactly what MiniMax models will cost for your workload.
Open Calculator →Other Providers