Same open weights, served by 1 provider. Weights: XiaomiMiMo/MiMo-V2.5.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-09-29Promo pricing | XiaomiMiMo/MiMo-V2.5 | flexFP8Reduced context (262k of 1M)0.8× standard | $0.112 | $0.224 | $0.0022 | $0.14 | Verified 6h ago · Changed 8h ago | |
DeepInfra Deprecated, 2026-09-29Promo pricing | XiaomiMiMo/MiMo-V2.5 | standardFP8Reduced context (262k of 1M) | $0.14 | $0.28 | $0.0028 | $0.175 | Verified 6h ago · Changed 8h ago | |
DeepInfra Deprecated, 2026-09-29Promo pricing | XiaomiMiMo/MiMo-V2.5 | priorityFP8Reduced context (262k of 1M)1.5× standard | $0.21 | $0.42 | $0.0042 | $0.263 | Verified 6h ago · Changed 8h 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 | $19.6/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.