Model Library
XiaomiReleased April 22, 2026MiMo-V2.5-Pro
Xiaomi · Released April 22, 2026
Intelligence score
28
At a glance
- Intelligence
- 28
- Speed
- 59.1tokens/sec
- Latency
- 2.38stime to first token
- Input price
- $0.66per 1M tokens
- Output price
- $1.72per 1M tokens
- Context window
- 3tokens
- Parameters
- 41.7billions
Summary
Comparison summary
MiMo-V2.5-Pro (Non-reasoning) scores 28 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17). MiMo-V2.5-Pro (Non-reasoning) generates output at 59.1 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). MiMo-V2.5-Pro (Non-reasoning) costs $0.66 per 1M input tokens (somewhat higher than average, median: $0.60) and $1.72 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | MiMo-V2.5-Pro |
|---|---|
| Provider | Xiaomi |
| Release date | April 22, 2026 |
| Intelligence score | 28 |
| Speed | 59.1 tokens/sec |
| Latency (TTFT) | 2.38s |
| Input price | $0.66 / 1M tokens |
| Output price | $1.72 / 1M tokens |
| Context window | 3 tokens |
| Parameters | 41.7B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Mit |
| API availability | — |
| Source | Model Intelligence legacy profile: mimo-v2-5-pro-non-reasoning |
Pricing
Token prices
Price per 1M tokens
MiMo-V2.5-Pro, as listed in the catalog record
- Input$0.66
- Output$1.72
| Token type | Price per 1M |
|---|---|
| Input | $0.66 |
| Output | $1.72 |
Model Intelligence legacy profile: mimo-v2-5-pro-non-reasoning
FAQ · 20
Frequently asked questions
MiMo-V2.5-Pro (Non-reasoning) was released on April 22, 2026.
MiMo-V2.5-Pro (Non-reasoning) was created by Xiaomi.
MiMo-V2.5-Pro (Non-reasoning) scores 28 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17).
MiMo-V2.5-Pro (Non-reasoning) generates output at 59.1 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
MiMo-V2.5-Pro (Non-reasoning) has a time to first token (TTFT) of 2.38s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 2.33s).
MiMo-V2.5-Pro (Non-reasoning) costs $0.66 per 1M input tokens (somewhat higher than average, median: $0.60) and $1.72 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
MiMo-V2.5-Pro (Non-reasoning) costs $0.66 per 1M input tokens and $1.72 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.36 per 1M tokens. Pricing may vary by provider.
No, MiMo-V2.5-Pro (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
MiMo-V2.5-Pro (Non-reasoning) supports text input.
MiMo-V2.5-Pro (Non-reasoning) supports text output.
No, MiMo-V2.5-Pro (Non-reasoning) does not support image input. It can only process text.
No, MiMo-V2.5-Pro (Non-reasoning) is not multimodal. It only supports text input.
MiMo-V2.5-Pro (Non-reasoning) 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-Pro (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
MiMo-V2.5-Pro (Non-reasoning) has 1.0 trillion parameters (41.7 billion active).
MiMo-V2.5-Pro (Non-reasoning) is a Mixture of Experts (MoE) model with 1.0 trillion total parameters, but only 41.7 billion active parameters are used during inference.
MiMo-V2.5-Pro (Non-reasoning) is released under the Mit license. This license allows commercial use.
MiMo-V2.5-Pro (Non-reasoning) achieves a score of 28 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, MiMo-V2.5-Pro (Non-reasoning) is available via API through 4 providers.
MiMo-V2.5-Pro (Non-reasoning) is available through 4 API providers.