This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Xiaomi has launched a newer release, MiMo-V2-Flash (Feb 2026). We suggest considering it instead.
MiMo-V2-Flash: Intelligence, Performance & Price Analysis
Available providers
Model summary
Performance
Verbosity
MiMo-V2-Flash (Reasoning) supports text input, outputs text, and has a 256k tokens context window.
Pricing for MiMo-V2-Flash (Reasoning) is $0.10 per 1M input tokens (competitively priced, median: $0.43) and $0.30 per 1M output tokens (competitively priced, median: $1.84).
| Input modality | Supports: text |
|---|---|
| Output modality | Supports: text |
| Context window | 256k ~384 A4 pages of size 12 Arial font |
| Total parameters | 309B |
| Active parameters | 15B Number of parameters active per token during inference |
| License | MIT |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic real-world work tasks, Elo
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Frequently Asked Questions
Common questions about MiMo-V2-Flash
MiMo-V2-Flash was released on December 16, 2025.
MiMo-V2-Flash was created by Xiaomi.
MiMo-V2-Flash costs $0.10 (reasoning) per 1M input tokens and $0.30 (reasoning) per 1M output tokens, based on Xiaomi's API. MiMo-V2-Flash (Reasoning) is very competitive on input price (median: $0.43) and very competitive on output price (median: $1.84).
MiMo-V2-Flash costs $0.10 (reasoning) per 1M input tokens and $0.30 (reasoning) per 1M output tokens (based on Xiaomi's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.12 (reasoning) per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, MiMo-V2-Flash (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, MiMo-V2-Flash (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
MiMo-V2-Flash supports text input.
MiMo-V2-Flash supports text output.
No, MiMo-V2-Flash does not support image input. It can only process text.
No, MiMo-V2-Flash is not multimodal. It only supports text input.
MiMo-V2-Flash has a context window of 256k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, MiMo-V2-Flash is open weights. The model weights are publicly available and can be downloaded for self-hosting.
MiMo-V2-Flash has 309B parameters (15B active).
MiMo-V2-Flash is a Mixture of Experts (MoE) model with 309B total parameters, but only 15B active parameters are used during inference.
MiMo-V2-Flash is released under the MIT license. This license allows commercial use. View license
Yes, MiMo-V2-Flash is available via API through 1 provider. Compare API providers
MiMo-V2-Flash is available through 1 API provider. Compare providers