Capabilities and specifications
- Creator
- Xiaomi
- Model family
- mimo
- Knowledge cutoff
- 2024-12
- License
- Not documented
- Release date
- 2026-04-22
- Model ID
xiaomi/mimo-v2.5
Open MiMo model for multimodal coding agents and long-context automation
xiaomi/mimo-v2.5Provider-specific identifiers, limits, and prices per million tokens.
| Provider | Provider model ID | Context | Input | Output | Cache read | Capabilities | Source |
|---|---|---|---|---|---|---|---|
mimo-v2-5 |
1.04858M | Not listed | Not listed | - | ReasoningTools | Docs | |
mimo-v2.5 |
1.04858M | Not listed | Not listed | - | ReasoningTools | Docs | |
mimo-v2.5 |
1.04858M | Not listed | Not listed | - | ReasoningTools | Docs | |
mimo-v2.5 |
1.04858M | Not listed | Not listed | - | ReasoningTools | Docs | |
xiaomi/mimo-v2.5 |
1.05M | $0.14 | $0.28 | $0.003 | ReasoningTools | Docs | |
xiaomi-mimo-v2-5 |
1M | $0.14 | $0.28 | $0.05 | ReasoningToolsJSON | Docs | |
XiaomiMiMo/MiMo-V2.5 |
1.05M | $0.14 | $0.28 | $0.003 | ReasoningTools | Docs | |
mimo-v2.5 |
1M | $0.14 | $0.28 | $0.003 | ReasoningTools | Docs | |
mimo-v2.5 |
1.04858M | $0.14 | $0.28 | $0.003 | ReasoningTools | Docs | |
xiaomi/mimo-v2.5 |
1.05M | $0.14 | $0.28 | $0.003 | ReasoningToolsJSON | Docs | |
xiaomi/mimo-v2.5 |
1.04858M | $0.14 | $0.28 | $0.003 | ReasoningToolsJSON | Docs | |
cline-pass/mimo-v2.5 |
1.04858M | $0.14 | $0.28 | $0.003 | ReasoningTools | Docs | |
xiaomi/mimo-v2.5 |
1M | $0.16 | $0.32 | $0.004 | ReasoningTools | Docs | |
xiaomi/mimo-v2.5 |
1.04858M | $0.4 | $2 | $0.08 | ReasoningTools | Docs | |
XiaomiMiMo/MiMo-V2.5 |
262.144K | $0.4 | $2 | $0.08 | ReasoningToolsJSON | Docs | |
xiaomi/mimo-v2.5 |
1.04858M | $0.4 | $2 | $0.08 | ReasoningTools | Docs | |
xiaomi/mimo-v2.5 |
1.04858M | $0.4 | $2 | $0.08 | ReasoningToolsJSON | Docs | |
XiaomiMiMo/MiMo-V2.5 |
262.144K | $0.4 | $2 | - | ReasoningToolsJSON | Docs |
Capability badges appear only when the provider catalog explicitly lists support.
Observed serving measurements stay separate from model specifications and are never estimated from price or model size.
Generation speed; higher is faster.
Time until the first output token arrives.
Successful requests over a measured period.
Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.
Raw results remain attached to their original source and version.
Detected changes from successful source imports.
Fetch the complete source-linked model record without an API key.
GET https://www.modelbench.lol/api/v1/models/xiaomi/mimo-v2.5curl "https://www.modelbench.lol/api/v1/models/xiaomi/mimo-v2.5"