Model Library
XiaomiReleased April 22, 2026MiMo-V2.5
Xiaomi · Released April 22, 2026
Intelligence score
40
At a glance
- Intelligence
- 40
- Speed
- 84.9tokens/sec
- Latency
- 2.83stime to first token
- Input price
- $0.14per 1M tokens
- Output price
- $0.28per 1M tokens
- Context window
- 3tokens
- Parameters
- 310billions
Summary
Comparison summary
MiMo-V2.5 scores 40 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25). MiMo-V2.5 generates output at 84.9 tokens per second (based on Xiaomi's API), which is above average compared to other open weight models of similar size (median: 61.7 t/s). MiMo-V2.5 costs $0.14 per 1M input tokens (very competitive, median: $0.59) and $0.28 per 1M output tokens (very competitive, median: $2.20), based on Xiaomi's API.
Specifications
Technical specifications
| Model name | MiMo-V2.5 |
|---|---|
| Provider | Xiaomi |
| Release date | April 22, 2026 |
| Intelligence score | 40 |
| Speed | 84.9 tokens/sec |
| Latency (TTFT) | 2.83s |
| Input price | $0.14 / 1M tokens |
| Output price | $0.28 / 1M tokens |
| Context window | 3 tokens |
| Parameters | 310B |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Mit |
| API availability | — |
| Source | Model Intelligence legacy profile: mimo-v2-5-0424 |
Pricing
Token prices
Price per 1M tokens
MiMo-V2.5, as listed in the catalog record
- Input$0.14
- Output$0.28
| Token type | Price per 1M |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
Model Intelligence legacy profile: mimo-v2-5-0424
FAQ · 20
Frequently asked questions
MiMo-V2.5 was released on April 22, 2026.
MiMo-V2.5 was created by Xiaomi.
MiMo-V2.5 scores 40 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25).
MiMo-V2.5 generates output at 84.9 tokens per second (based on Xiaomi's API), which is above average compared to other open weight models of similar size (median: 61.7 t/s).
MiMo-V2.5 has a time to first token (TTFT) of 2.83s (based on Xiaomi's API), which is at the higher end compared to other open weight models of similar size (median: 2.01s).
MiMo-V2.5 costs $0.14 per 1M input tokens (very competitive, median: $0.59) and $0.28 per 1M output tokens (very competitive, median: $2.20), based on Xiaomi's API.
MiMo-V2.5 costs $0.14 per 1M input tokens and $0.28 per 1M output tokens (based on Xiaomi's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.06 per 1M tokens. Pricing may vary by provider.
Yes, MiMo-V2.5 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
MiMo-V2.5 supports text and image input.
MiMo-V2.5 supports text output.
Yes, MiMo-V2.5 supports image input and can analyze, describe, and answer questions about images.
Yes, MiMo-V2.5 is multimodal. It can process text and image input and generate text output.
MiMo-V2.5 has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, MiMo-V2.5 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
MiMo-V2.5 has 310 billion parameters (15 billion active).
MiMo-V2.5 is a Mixture of Experts (MoE) model with 310 billion total parameters, but only 15 billion active parameters are used during inference.
MiMo-V2.5 is released under the Mit license. This license allows commercial use.
MiMo-V2.5 achieves a score of 40 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, MiMo-V2.5 is available via API through 5 providers.
MiMo-V2.5 is available through 5 API providers.