MiMo V2.5
Xiaomi’s open-weight (MIT) flagship — multimodal, 1M context, reasoning. Strong agentic and coding work at low cost.
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Xiaomi’s open-weight (MIT) flagship — multimodal, 1M context, reasoning. Strong agentic and coding work at low cost.
| Field | Value |
|---|---|
| Model ID | mimo-v2.5 |
| Best for | Multimodal reasoning and agentic work at low cost |
| Context window | 1.05M |
| Max output tokens | 16K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Prompt caching | No |
| Vision | Yes |
| Reasoning | Yes |
| Speed | Medium |
| Cost band | Cheap |
| Release stage | Stable |
| Per 1M tokens | |
|---|---|
| Input | $0.1859 |
| Output | $0.3718 |
from openai import OpenAI
client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")
response = client.chat.completions.create(
model="mimo-v2.5",
messages=[{"role": "user", "content": "..."}],
tools=[...], # function calling supported
)
curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=frontier-open"