Same open weights, served by 2 providers. Weights: MiniMaxAI/MiniMax-M2.7.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-10 | MiniMaxAI/MiniMax-M2.7 | flexFP80.8× standard | $0.20 | $0.80 | $0.04 | $0.35 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-09-10 | MiniMaxAI/MiniMax-M2.7 | standardFP8 | $0.25 | $1.0 | $0.05 | $0.438 | Verified 5h ago · Changed 7h ago | |
Together AI | MiniMaxAI/MiniMax-M2.7 | standardQuantization not disclosed | $0.30 | $1.2 | $0.06 | $0.525 | Verified 7h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-09-30 | MiniMaxAI/MiniMax-M2.7-Turbo | standardFP8 | $0.38 | $1.7 | $0.07 | $0.71 | Verified 5h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra fp8 | $45/mo |
| Together AI | $54/mo |
| DeepInfra fp8 | $72/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.