> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kombai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Models
> Choose from Kombai's model routers and a curated set of frontier models, and control the trade-off between quality, speed, and credit consumption.
Please ensure you're on the latest version of Kombai to access these models and routers.
Kombai gives you two ways to power a task:
* **Model Routers**: Kombai's internal routers that automatically pick the ideal model for your task within a chosen cost tier.
* **Models**: Direct access to individual frontier models from providers like OpenAI, Anthropic, Google, xAI, Moonshot, and Qwen.
Each model and router has a **credit multiplier** that is applied to the base credit usage of a task. You can switch between routers and models at any point within the same chat.
The credit multiplier is relative to the baseline (`1x`). For example, a task that consumes 10 credits on a `1x` model would consume approximately 5 credits on a `0.5x` model and 25 credits on a `2.5x` model.
## Model Routers
Model Routers are powered by a continuously optimized and benchmarked model stack. 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 internal router automatically selects the best model for the task within the cost tier you choose.
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 any effort to manually test and benchmark them.
| Router | Credits |
| ------------- | ------- |
| Kombai-Auto | Auto |
| Kombai-Ultra | 2x |
| Kombai-High | 1x |
| Kombai-Medium | 0.5x |
| Kombai-Mini | 0.33x |
**Kombai-Auto** is the recommended default. It analyzes each task and routes it to the optimal model automatically, balancing quality and cost for you.
## Models
If you prefer to run a specific model, choose one directly. Models are grouped by provider, and each shows its credit multiplier.
### OpenAI
| Model | Credits |
| ------------- | ------- |
| GPT 5.4 | 1x |
| GPT 5.4 Mini | 0.5x |
| GPT 5.4 Nano | 0.33x |
| GPT 5.5 | 2.5x |
| GPT 5.6 Sol | 2.5x |
| GPT 5.6 Terra | 1x |
| GPT 5.6 Luna | 0.5x |
### Anthropic
| Model | Credits |
| ----------------- | ------- |
| Claude Fable 5 | 4x |
| Claude Opus 4.8 | 2x |
| Claude Opus 4.7 | 2x |
| Claude Sonnet 4.6 | 1x |
| Claude Haiku 4.5 | 0.5x |
| Claude Opus 4.6 | 2x |
### Gemini
| Model | Credits |
| --------------------- | ------- |
| Gemini 3.5 Flash | 0.5x |
| Gemini 3.1 Pro | 1x |
| Gemini 3 Flash | 0.33x |
| Gemini 3.1 Flash Lite | 0.1x |
### xAI
| Model | Credits |
| -------------- | ------- |
| Grok Build 0.1 | 0.33x |
| Grok 4.5 | 1x |
### Moonshot
| Model | Credits |
| --------- | ------- |
| Kimi K2.5 | 0.33x |
| Kimi K2.6 | 0.5x |
### Qwen
| Model | Credits |
| ------------ | ------- |
| Qwen 3.6 27B | 0.5x |
## 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.
| Effort | When to use |
| ------- | -------------------------------------------------------------------- |
| None | No additional reasoning. Fastest responses for trivial changes. |
| Minimal | Very light reasoning for simple, well-defined tasks. |
| Low | Light reasoning that keeps responses quick. |
| Med | Balanced reasoning suitable for most everyday tasks. |
| High | Deep reasoning for complex logic, refactors, and architectural work. |
| Xhigh | Maximum reasoning depth available on supported OpenAI models. |
| Max | Maximum reasoning depth available on supported Anthropic models. |
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 (such as Grok Build 0.1, Kimi K2.5, Kimi K2.6, and Qwen 3.6 27B) don't expose a configurable thinking effort.
### Supported thinking effort by model
| Model | Supported thinking efforts |
| ------------------------------------------------------------------ | ------------------------------------ |
| Kombai-Auto, Kombai-Ultra, Kombai-High, Kombai-Medium, Kombai-Mini | Low, High |
| GPT 5.4 / 5.4 Mini / 5.4 Nano / 5.5 | None, Minimal, Low, Med, High, Xhigh |
| GPT 5.6 Sol / 5.6 Terra / 5.6 Luna | None, Minimal, Low, Med, High, Xhigh |
| Claude Fable 5 | Low, Med, High, Xhigh, Max |
| Claude Opus 4.8 | None, Low, Med, High, Xhigh, Max |
| Claude Opus 4.7 | None, Low, Med, High, Xhigh, Max |
| Claude Sonnet 4.6 | None, Low, Med, High, Max |
| Claude Haiku 4.5 | None, Minimal, Low, Med, High |
| Claude Opus 4.6 | None, Low, Med, High, Max |
| Gemini 3.5 Flash / 3.1 Pro / 3 Flash / 3.1 Flash Lite | Minimal, Low, Med, High |
| Grok 4.5 | Low, Med, High (default) |
| Grok Build 0.1, Kimi K2.5, Kimi K2.6, Qwen 3.6 27B | Not configurable |
Higher thinking effort increases generation time and cost, but it does not consume your context window, allowing the agent to think deeply without losing track of large codebases.
## Select a model
You can switch models and routers directly from the chat input box:
1. Click the model dropdown in the Kombai chat input box.
2. Search for a model, or pick one from the **Model Router** or **Models** group (grouped by provider).
3. To adjust reasoning depth, click the current [thinking effort](#thinking-effort) shown beside the brain () icon on the model's row, then choose a level from the list.
Your selection applies to all subsequent messages in the conversation until you change it.
## Manage available models
You can control which routers and models appear in the chat dropdown from the **Models** tab of the [Settings page](/account/settings).
1. Click the icon in Kombai's top menubar to open the **Settings** page.
2. Select the **Models** tab from the left sidebar.
3. Use the toggle beside each entry under **Model Routers** and **Models** to show or hide it in the model dropdown.
Hiding a model only removes it from the dropdown, it does not affect any chat that is already using it.