Model reference · Synced 2025-04-29
MiniMax-M2.1
MiniMax-M2.1 is an AI model from MiniMax Coding Plan (minimax.io). 205K context window. Capabilities: reasoning, tool calling, open weights. Available on 22 providers. Cheapest listing: $0 input / $0 output per 1M tokens.
Quick facts
- Cheapest input: $0 per 1M tokens (MiniMax Coding Plan (minimax.io))
- Cheapest output: $0 per 1M tokens
- Context window: 205K tokens
- Max output: 131K tokens
- Release date: 2025-12-23
- Capabilities: reasoning, tool calling, open weights
- Provider count: 22
Provider pricing
Same model, different providers, different prices. Cheapest first.
| Provider | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| MiniMax Coding Plan (minimax.io) | $0 | $0 | 205K | 2025-12-23 |
| MiniMax Coding Plan (minimaxi.com) | $0 | $0 | 205K | 2025-12-23 |
| Nvidia | $0 | $0 | 205K | 2025-12-23 |
| Deep Infra | $0.28 | $1.2 | 197K | 2025-12-23 |
| Meganova | $0.28 | $1.2 | 197K | 2025-12-23 |
| 302.AI | $0.3 | $1.2 | 1M | 2025-12-19 |
| OpenRouter | $0.3 | $1.2 | 205K | 2025-12-23 |
| Fireworks AI | $0.3 | $1.2 | 200K | 2025-12-23 |
| Jiekou.AI | $0.3 | $1.2 | 205K | 2026-01 |
| Hugging Face | $0.3 | $1.2 | 205K | 2025-12-23 |
| ZenMux | $0.3 | $1.2 | 204K | 2025-12-22 |
| NovitaAI | $0.3 | $1.2 | 205K | 2025-12-23 |
| OpenCode Zen | $0.3 | $1.2 | 205K | 2025-12-23 |
| Amazon Bedrock | $0.3 | $1.2 | 205K | 2025-12-23 |
| Vercel AI Gateway | $0.3 | $1.2 | 205K | 2025-10-27 |
| MiniMax (minimax.io) | $0.3 | $1.2 | 205K | 2025-12-23 |
| LLM Gateway | $0.3 | $1.2 | 205K | 2025-12-23 |
| MiniMax (minimaxi.com) | $0.3 | $1.2 | 205K | 2025-12-23 |
| NanoGPT | $0.33 | $1.32 | 200K | 2025-12-19 |
| Cortecs | $0.34 | $1.34 | 196K | 2025-12-23 |
| Synthetic | $0.55 | $2.19 | 205K | 2025-12-23 |
| Moark | $2.1 | $8.4 | 205K | 2025-12-23 |
Prices synced daily from models.dev + provider docs.
How to use this model
If you're picking MiniMax-M2.1 for a project, the three things that matter most:
- Compare it side-by-side with one or two alternatives in the live comparison tool. Pricing differences matter more than benchmarks at scale.
- Pick the cheapest provider that meets your latency / SLA need. Big spread across providers for the same weights.
- Re-evaluate every 3 months. Frontier prices drop fast; a model that's cheapest today may not be in a quarter.
Related models
FAQ
How much does MiniMax-M2.1 cost? $0 input / $0 output per 1M tokens at the cheapest listing. See the table above for other providers.
What is the context window? 205K tokens.
Which providers offer it? 302.AI, NanoGPT, MiniMax Coding Plan (minimax.io), OpenRouter, Fireworks AI, Moark, MiniMax Coding Plan (minimaxi.com), Jiekou.AI, Hugging Face, ZenMux, and others — see the full table above.
Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.