Understanding MiniMax API Pricing
MiniMax is a leading Chinese AI company offering competitive large language models for developers and enterprises. From the flagship M2.7 to the efficient M2.5, MiniMax provides cost-effective options for AI chatbot development and complex workflow automation.
Key Takeaways
- ●MiniMax-M2.7 is the latest flagship model at just $0.30/M input tokens with $1.20/M output tokens.
- ●Highspeed variants (M2.7-highspeed, M2.5-highspeed) deliver faster inference at $0.60/M input tokens.
- ●Prompt caching offers significant savings — cache reads from $0.03-$0.06/M tokens and writes at $0.375/M tokens.
- ●M2-her is a specialized conversational model at $0.30/M input tokens with no caching support.
MiniMax Pricing Overview
| Model | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Cache Write ($/1M) |
|---|---|---|---|---|
| Current Models | ||||
| MiniMax-M2.7 | $0.30 | $1.20 | $0.06 | $0.375 |
| MiniMax-M2.7-highspeed | $0.60 | $2.40 | $0.06 | $0.375 |
| MiniMax-M2.5 | $0.30 | $1.20 | $0.03 | $0.375 |
| MiniMax-M2.5-highspeed | $0.60 | $2.40 | $0.03 | $0.375 |
| M2-her | $0.30 | $1.20 | — | — |
| Legacy Models | ||||
| MiniMax-M2.1 | $0.30 | $1.20 | $0.03 | $0.375 |
| MiniMax-M2.1-highspeed | $0.60 | $2.40 | $0.03 | $0.375 |
| MiniMax-M2 | $0.30 | $1.20 | $0.03 | $0.375 |
MiniMax-M2.7: Flagship Performance
MiniMax-M2.7 is the company's most capable model, delivering strong reasoning and generation quality at a competitive $0.30 per million input tokens. The highspeed variant doubles the throughput for latency-sensitive applications at $0.60/M tokens.
Prompt Caching: Read vs Write
MiniMax employs a two-tier caching system. Cache writes ($0.375/M tokens) are charged when prompts are first cached, while cache reads ($0.03-$0.06/M tokens) provide massive savings on subsequent requests with the same prompt prefix. This makes repetitive workloads extremely cost-efficient.
M2-her: Specialized Conversational AI
M2-her is a specialized model optimized for natural, empathetic conversations. Priced at $0.30/M input tokens and $1.20/M output tokens, it's an efficient choice for building AI voice agents and companion-style chatbots.
MiniMax API Pricing FAQs
Got questions? We've got answers. Here are the most common questions we get from potential clients.