| Spec | MiniMax M3 | MiniMax M3.1 Flash |
|---|---|---|
| Lowest input | $0.28DeepInfra | $0.15StreamLake |
| Lowest output | $1.10DeepInfra | $0.60StreamLake |
| Lowest cached input | $0.056DeepInfra | $0.015StreamLake |
| Context | 524K | 1M |
| Max output | 131K | 512K |
| Providers | 3 | 1 |
| Released | June 1, 2026 | October 19, 2026 |
| Weights | Open | Open |
| Lab | MiniMax | MiniMax |
| Model ID | minimax/minimax-m3 | minimax/minimax-m3.1-flash |
USD per 1M tokens, as of November 5, 2026.
| Provider | MiniMax M3 | MiniMax M3.1 Flash |
|---|---|---|
| StreamLake | $0.60 / $2.40 | $0.15 / $0.60 |
| DeepInfra | $0.28 / $1.10 | – |
| Nebius | $0.30 / $1.20 | – |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| MiniMax M3DeepInfra | $1.11 | $19.50 | $195.00 |
| MiniMax M3.1 FlashStreamLake | $0.60 | $10.50 | $105.00 |
On each model's cheapest provider by input plus output list price.
Input: MiniMax M3.1 Flash at $0.15 per million input tokens vs $0.28 (MiniMax M3), 87% lower. Output: MiniMax M3.1 Flash at $0.60 per million output tokens vs $1.10 (MiniMax M3), 83% lower. Lowest listed prices as of November 5, 2026.
MiniMax M3.1 Flash, with 1M tokens vs 524K.
1 provider serves both: StreamLake. MiniMax M3 has 3 providers in total and MiniMax M3.1 Flash has 1.
MiniMax M3 from $0.056 per million cached input tokens (DeepInfra). MiniMax M3.1 Flash from $0.015 (StreamLake).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "minimax/minimax-m3" to "minimax/minimax-m3.1-flash".
