MiMo-V2.5: API pricing, providers and specs
MiMo-V2.5 is a text model by Xiaomi. 10 providers serve it, from $0.224 to $2 /1M; the lowest price is at CometAPI.
How MiMo-V2.5 compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.224 /1M, its lowest price undercuts 82% of comparable models (median $1.10).
- Its 1.05M-token context window is larger than 95% of them (median 262K), about 1580 pages of text.
- On LMArena's WebDev board it ranks #55 of the 64 comparable models scored there.
- 10 providers serve it; 77% of comparable models have fewer.
- Its weights are open under the MIT license: commercial use allowed.
MiMo-V2.5 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 CometAPI | $0.112/1M | $0.224/1M | $0.002/1M | — |
| Vercel AI Gateway | $0.119/1M | $0.238/1M | $0.003/1M | 1.05M |
| OpenRouter | $0.119/1M | From$0.238/1M | $0.003/1M | 1.05M |
 Requesty | $0.14/1M | From$0.28/1M | $0.003/1M | 1.05M |
 Hugging Face | $0.14/1M | From$0.28/1M | — | — |
 Impossibl | $0.14/1M | $0.28/1M | $0.003/1M | — |
| Atlas Cloud | $0.14/1M | $0.28/1M | $0.003/1M | — |
| AI/ML API | $0.148/1M | $0.296/1M | $0.003/1M | — |
 Prime Inference | $0.168/1M | $0.336/1M | — | — |
 Venice AI | $0.40/1M | $2/1M | $0.08/1M | — |
- CometAPI$0.224
- Vercel AI Gateway$0.238
- OpenRouterFrom$0.238
- Impossibl$0.28
- Atlas Cloud$0.28
- RequestyFrom$0.28
- Hugging FaceFrom$0.28
- AI/ML API$0.296
- Prime Inference$0.336
- Venice AI$2
Specs
- Type
- Text
- Maker
- Xiaomi
- Inputs
- Audio, Image, Text, Video
- Outputs
- Text
- Context
- 1.05M≈ 1580 pages of text
- Max output
- 945K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling, Vision
- Released
- Apr 27, 2026
- License
- MITcommercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 311B
- Arena score
- 1438WebDev
- Monthly searches
- 10K
Alternatives to MiMo-V2.5
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| MiMo-V2.5this model | $0.224/1M | 1.05M | 1438 | 10 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
| DeepSeek V4 Pro | $0.418/1M | 1.05M | — | 33 |
More from Xiaomi
MiMo-V2.5 FAQ
The lowest price for MiMo-V2.5 is $0.224 /1M, at CometAPI.
CometAPI, at $0.224 /1M. 10 providers serve MiMo-V2.5; the table above lists every one with its price.
MiMo-V2.5 reads up to 1.05M tokens per request and writes up to 945K.
Yes. MiMo-V2.5's weights can be downloaded from its maker's Hugging Face page, under the MIT license.
About 311B, as the safetensors metadata of its official Hugging Face repo states.
10 API providers serve MiMo-V2.5. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us