MiniMax M2.1 pricing
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. MiniMax M2.1 from MiniMax costs $0.300 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.030 per 1M. Context window 204,800 tokens.
API id minimax-m2.1 · MiniMax · source · updated 2026-08-15 · general-purpose
$0.300
Input / 1M tokens
$1.20
Output / 1M tokens
$0.030
Cached input / 1M
205K
Context window
What MiniMax M2.1 costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0009 |
| Document summary | 50,000 | 2,000 | $0.02 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $0.54 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does MiniMax M2.1 cost per 1M tokens?
- MiniMax M2.1 costs $0.300 per 1M input tokens and $1.20 per 1M output tokens on the standard tier. Cached input is $0.030 per 1M.
- What is MiniMax M2.1's context window?
- MiniMax M2.1 accepts up to 204,800 tokens in a single request, and can return up to 131,072 output tokens.
- Is there a cheaper MiniMax model than MiniMax M2.1?
- Yes. MiniMax-01 is $0.200 per 1M input tokens versus $0.300 for MiniMax M2.1, with a 1,000,192 token context window.
- Where does this MiniMax M2.1 price come from?
- From the OpenRouter catalogue, because MiniMax does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from MiniMax's own — verify before committing spend.