Xiaomi: MiMo-V2.5-Pro
by XiaomiXiaomi: MiMo-V2.5-Pro is a large language model from Xiaomi. It costs $0.435 per million input tokens and $0.870 per million output tokens. Its context window is 1.1M tokens.
- Input / 1M tokens
- $0.435
- Output / 1M tokens
- $0.870
- Cached input / 1M
- $0.0036
- Context window
- 1.1M
On repeated prefixes
tokens
Who serves it cheapest
7 hosts serve MiMo-V2.5-Pro. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| GMICloudCheapestbf16 | $0.304 | $0.609 | 1.1M | - | 94.1% |
| AtlasCloudfp8 | $0.435 | $0.870 | 1.0M | - | 73.5% |
| Xiaomifp8 | $0.435 | $0.870 | 1.0M | - | 99.1% |
| DeepInfrafp8 | $0.390 | $1.17 | 1.0M | - | 95.9% |
| Novita | $0.480 | $0.960 | 1.0M | - | 98.5% |
| StreamLake | $0.522 | $1.04 | 1M | - | 93.0% |
| DigitalOcean | $0.480 | $1.80 | 262K | - | 98.4% |
The spread between GMICloud and DigitalOcean is 2.1× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 26.4
- Coding index
- 60.2
- Agentic index
- 22.7
About MiMo-V2.5-Pro
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
Specifications
| Model ID | xiaomi/mimo-v2.5-pro |
|---|---|
| Provider | Xiaomi |
| Context window | 1.1M tokens |
| Max output | 131K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - XiaomiMiMo/MiMo-V2.5-Pro |
| Released | April 22, 2026 |
Cheaper alternatives
Models that cost less than MiMo-V2.5-Pro while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Xiaomi: MiMo-V2.5-Pro cost?
$0.435 per million input tokens and $0.870 per million output tokens. Cached input reads cost $0.0036 per million tokens.
What is the context window of Xiaomi: MiMo-V2.5-Pro?
1.1M tokens, with up to 131K tokens of output per request.
Which provider serves Xiaomi: MiMo-V2.5-Pro cheapest?
GMICloud at $0.304 per million input tokens - 2.1× cheaper than DigitalOcean, the most expensive of the 7 hosts serving it.