Same open weights, served by 3 providers. Weights: MiniMaxAI/MiniMax-M3.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | MiniMaxAI/MiniMax-M3 | standardFP8 | $0.28 | $1.1 | $0.056 | $0.485 | Verified 3h ago · Changed 6h ago | |
Together AI | MiniMaxAI/MiniMax-M3 | standardQuantization not disclosed | $0.30 | $1.2 | $0.06 | $0.525 | Verified 5h ago · Changed 5h ago | |
Fireworks AI | accounts/fireworks/models/minimax-m3 | standardQuantization not disclosedReduced context (512k of 524k) | $0.30 | $1.2 | $0.06 | $0.525 | Verified 5h ago · Changed 5h ago | |
Fireworks AI | accounts/fireworks/routers/minimax-latest | standardQuantization not disclosedReduced context (512k of 524k) | $0.30 | $1.2 | $0.06 | $0.525 | Verified 5h ago · Changed 5h 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 | $50/mo |
| Together AI | $54/mo |
| Fireworks AI | $54/mo |
| Fireworks AI | $54/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.