MiniMax M2.1 vs MiniMax M3
minimax/minimax-m2.1 · minimax/minimax-m3
As of November 4, 2026, MiniMax M2.1 is the cheaper API on UberLLM: $0.0004 per million input tokens and $0.0014 per million output, versus $0.0170 / $0.0682 for MiniMax M3, about 98% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose MiniMax M2.1 to cut cost; choose MiniMax M3 when context size wins. MiniMax M3 carries the larger context window (200,000 vs 198,000 tokens), which can matter for long-document work.
MiniMax M2.1 vs MiniMax M3, side by side
| Spec | MiniMax M2.1 | MiniMax M3 |
|---|---|---|
| Price · input / 1M | $0.0004 | $0.0170 |
| Price · output / 1M | $0.0014 | $0.0682 |
| Context length | 198,000 | 200,000 |
| Max output tokens | 32,768 | 32,768 |
| Input modalities | text | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | — | Yes |
| Reasoning | Yes | — |
| % off list | 99.9% off | 94.3% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 4, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
MiniMax M2.1 vs MiniMax M3 — FAQ
Is MiniMax M2.1 or MiniMax M3 cheaper?
MiniMax M2.1 is cheaper on a blended token mix, by about 98%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between MiniMax M2.1 and MiniMax M3?
MiniMax M2.1: $0.0004 in / $0.0014 out per 1M tokens. MiniMax M3: $0.0170 in / $0.0682 out per 1M tokens. That's roughly a 98% blended difference. Prices are live; UberLLM adds no fee.
Can I use both MiniMax M2.1 and MiniMax M3 with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.