Models

Kombai gives you two ways to power a task:

• Models: Direct access to supported frontier, everyday, and lite models from providers like OpenAI, Anthropic, Google, xAI, DeepSeek, Moonshot, Qwen, MiniMax, Xiaomi, Meta, and Z.ai.
• Auto Router: Kombai’s internal router that automatically picks the ideal model for your task.

Each Model and Model Router has a credit multiplier that is applied to the base credit usage of a task. You can switch between Models and Model Routers at any point within the same chat.

​

Models

If you prefer to run a specific model, choose one directly. The tables below group models by provider and show each one’s credit multiplier.

​

OpenAI

​

Anthropic

​

DeepSeek

​

Mistral

​

Gemini

​

xAI

​

Moonshot

​

Qwen

​

MiniMax

​

Xiaomi

​

Meta

​

Z.ai

​

Model Router

Kombai benchmarks the latest LLMs from top providers across a wide range of frontend tasks, from interpreting complex UI logic to multi-file refactors, and the Auto model router automatically selects the best model for your task within the 0.1x-1x range. This gives you granular control over cost while ensuring you consistently get the best performance per dollar, even as newer and better models emerge, without having to manually test and benchmark them. Auto is the recommended default. It analyzes each task and routes it to the optimal model automatically, balancing quality and cost for you. Because it can pick a different model for each turn, its credit multiplier is a range: 0.1x to 1x.

​

Local agents

Alongside Kombai’s own Models and Model Routers, you can use your existing Claude Code or Codex subscription by locally installing its CLI. See Local agents to learn more.

​

Select a Model or Model Router

1. Click the Model dropdown in the chat input box.
2. Search or sort the list to quickly find the Model or Model Router you want to use.
3. Click a Model or Model Router to select it.

​

Sort the Model list

Sort options sit alongside search at the top of the list. The dropdown includes the following options:

• Recommended: The default Kombai-recommended order.
• Frontier first: Flagship models first, followed by standard and lite models.
• Cost efficient first: Lowest-cost and discounted models first.
• Newest first: Sorted by release date.
• Model routers first: Model Routers first, followed by individual models.
• Alphabetical (A to Z): Alphabetical by model name.

​

Pin a Model or Model Router

Click the pin icon on any row to move it to the top of the list, regardless of the active sort. Click it again to unpin. Selecting a Model or Model Router also pins it automatically.

​

Badges

A badge may appear in each row in the list to indicate whether the item is a router, recommended, new, or cost-efficient.

​

Model details

Each Model and Model Router has a detail view that opens when you hover over it in the list, or when you click Edit (in the IDE extension). The detail view shows the following information:

• Type: The model tier (Frontier, Everyday, or Lite).
• Cost: The credit tier (Low, Medium, or High) along with the credit multiplier.
• Context: The model’s context window size. Routers omit this because the active model varies per turn.
• Thinking Effort: The thinking effort levels available for that model.

​

Thinking effort

Thinking effort controls how deeply a model reasons before it responds. Higher effort improves planning, edge-case handling, and self-correction for complex tasks, while lower effort returns faster, cheaper responses for simpler ones. Not every model supports every level. When you open the thinking effort selector for a model, only the levels it supports are shown. Some models don’t expose a configurable thinking effort.

​

Change thinking effort

​

Supported thinking effort by model