Models#

#Set a default

To set one of these as the default model, you can set the model key in your MiMo Code config.

1{
2  "$schema": "https://mimo.xiaomi.com//config.json",
3  "model": "mimo/mimo-v2.5-pro"
4}

Here the full ID is provider_id/model_id. For example, if you're using the MiMo Platform, you would use mimo/mimo-v2.5-pro.

If you've configured a custom provider, the provider_id is key from the provider part of your config, and the model_id is the key from provider.models.

#Configure models

You can globally configure a model's options through the config.

1{
2  "$schema": "https://mimo.xiaomi.com//config.json",
3  "provider": {
4    "mimo": {
5      "models": {
6        "mimo-v2.5-pro": {
7          "options": {
8            "reasoningEffort": "high",
9            "textVerbosity": "low",
10            "reasoningSummary": "auto",
11          },
12        },
13      },
14    },
15  },
16}

Here we're configuring global settings for the mimo-v2.5-pro model when accessed via the mimo provider. The built-in provider and model names can be found on Models.dev.

You can also configure these options for any agents that you are using. The agent config overrides any global options here. Learn more.

You can also define custom variants that extend built-in ones. Variants let you configure different settings for the same model without creating duplicate entries:

1{
2  "$schema": "https://mimo.xiaomi.com//config.json",
3  "provider": {
4    "mimo": {
5      "models": {
6        "mimo-v2.5-pro": {
7          "variants": {
8            "high": {
9              "reasoningEffort": "high",
10              "textVerbosity": "low",
11              "reasoningSummary": "auto",
12            },
13            "low": {
14              "reasoningEffort": "low",
15              "textVerbosity": "low",
16              "reasoningSummary": "auto",
17            },
18          },
19        },
20      },
21    },
22  },
23}

#Variants

Many models support multiple variants with different configurations. MiMo Code ships with built-in default variants for popular providers.

#Built-in variants

MiMo Code ships with default variants for many providers:

Anthropic:

• high - High thinking budget (default)
• max - Maximum thinking budget

OpenAI:

Varies by model but roughly:

• none - No reasoning
• minimal - Minimal reasoning effort
• low - Low reasoning effort
• medium - Medium reasoning effort
• high - High reasoning effort
• xhigh - Extra high reasoning effort

Google:

• low - Lower effort/token budget
• high - Higher effort/token budget

#Custom variants

You can override existing variants or add your own:

1{
2  "$schema": "https://mimo.xiaomi.com//config.json",
3  "provider": {
4    "mimo": {
5      "models": {
6        "mimo-v2.5-pro": {
7          "variants": {
8            "thinking": {
9              "reasoningEffort": "high",
10              "textVerbosity": "low",
11            },
12            "fast": {
13              "disabled": true,
14            },
15          },
16        },
17      },
18    },
19  },
20}

#Cycle variants

Use the keybind variant_cycle to quickly switch between variants. Learn more.