MiMo-V2.5-Pro
Summary
MiMo-V2.5-Pro is an open-weight language model from Xiaomi (MiMo), released on 22 Apr 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $0.52 per million input tokens and $1.04 per million output tokens (Novita AI), across 3 providers we track. It is scheduled for retirement on 21 Oct 2026.
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Xiaomi (MiMo) |
|---|---|
| Release date | 22 Apr 2026 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 1T [Hugging Face] |
| Context window | 1M (1,048,576 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Knowledge cutoff | Dec 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Retirement date | 21 Oct 2026 [OpenRouter] |
| Hugging Face | XiaomiMiMo/MiMo-V2.5-Pro [Hugging Face] |
MiMo-V2.5-Pro API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter xiaomi/mimo-v2.5-pro | $0.48 | $1.80 | $0.10 | 262K | OpenRouter, 19 Nov 2026 |
| Novita AI xiaomimimo/mimo-v2.5-pro | $0.52 | $1.04 | $0.0043 | 1M | models.dev, 19 Nov 2026 |
| Hugging Face Inference Providers XiaomiMiMo/MiMo-V2.5-Pro | $1 | $3 | – | 1M | models.dev, 19 Nov 2026 |
Running MiMo-V2.5-Pro locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 620 GB | 625 GB | 635 GB |
| Q8_0 (8-bit) | 1087 GB | 1091 GB | 1102 GB |
| FP16 / BF16 (16-bit) | 2046 GB | 2051 GB | 2061 GB |
At 4-bit with an 8K conversation, MiMo-V2.5-Pro needs about 625 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of MiMo-V2.5-Pro?
MiMo-V2.5-Pro has a context window of 1,048,576 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the MiMo-V2.5-Pro API cost?
MiMo-V2.5-Pro is listed from $0.52 per million input tokens and $1.04 per million output tokens (Novita AI). Prices last verified 19 Nov 2026.
Is MiMo-V2.5-Pro open source?
MiMo-V2.5-Pro is an open-weight model: its weights are published on Hugging Face as XiaomiMiMo/MiMo-V2.5-Pro under the mit license. Check the license terms before commercial use.
When was MiMo-V2.5-Pro released?
Xiaomi (MiMo) released MiMo-V2.5-Pro on 22 Apr 2026, according to models.dev.
Which providers offer MiMo-V2.5-Pro?
We track MiMo-V2.5-Pro on 3 providers: OpenRouter, Novita AI, Hugging Face Inference Providers.
How much VRAM does MiMo-V2.5-Pro need?
About 625 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 1091 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| MiniMax-M3 | MiniMax | 1 Jun 2026 | 1M | $0.28 | $1.10 | Open |
| LongCat-2.0 | Meituan | 30 Jun 2026 | 1M | $0.30 | $1.20 | Open |
| Qwen3.8 27B | Alibaba (Qwen) | 14 Aug 2026 | 1M | $0.06 | $1.49 | Open |
| GLM-5.3 | Zhipu AI (Z.ai) | 14 Aug 2026 | 1M | $0.07 | $1.40 | Open |
| GLM-5.2 | Zhipu AI (Z.ai) | 13 Jun 2026 | 1M | $0.007 | $2.40 | Open |
| Nemotron 3 Ultra 550B A55B | NVIDIA | 4 Jun 2026 | 1M | $0.50 | $2.20 | Open |
Change history
- OpenRouter price changed: input $0.43 → $0.48, output $0.87 → $1.80 per 1M tokens
- OpenRouter price changed: input $0.48 → $0.43, output $1.80 → $0.87 per 1M tokens
- No longer listed on vercel
- OpenRouter price changed: input $0.30 → $0.48, output $0.61 → $1.80 per 1M tokens
- OpenRouter price changed: input $0.43 → $0.30, output $0.87 → $0.61 per 1M tokens
- No longer listed on xiaomi
- Status changed from active to deprecated
- vercel price changed: input $0.43 → $0.30, output $0.87 → $0.61 per 1M tokens
- Retirement date changed from none to 21 Oct 2026
Sources
- https://openrouter.ai/xiaomi/mimo-v2.5-pro
- https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2.5-pro.toml
- https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/xiaomimimo/mimo-v2.5-pro.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/XiaomiMiMo/MiMo-V2.5-Pro.toml