> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-docs-router-model-page-pilot.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenRouter LLM Partner Nodes ComfyUI Official Example

> Use the OpenRouter LLM partner node in ComfyUI for chat, reasoning, vision, and web-grounded answers across multiple frontier models.

[OpenRouter](https://openrouter.ai) is a unified routing platform for large language models. It exposes many providers through one API so you can switch models without changing your integration. ComfyUI connects through the **OpenRouter LLM** partner node, which offers a curated list of text and multimodal models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Mistral, GLM, Kimi, and Perplexity Sonar) in a single node.

## What OpenRouter LLM is good at

* **Text chat**: prompts and optional `system_prompt` for role or task instructions
* **Vision**: attach reference images on supported models (slot count depends on the model)
* **Video input**: Gemini 3.5 Flash and Qwen 3.6 Plus/Flash support optional reference videos
* **Reasoning**: `reasoning_effort` on reasoning / frontier-reasoning models (`off`, `low`, `medium`, `high`)
* **Web search**: Perplexity Sonar models expose `search_context_size` for grounded answers

Token pricing is listed under [Partner Node Pricing](/tutorials/partner-nodes/pricing#openrouter).

## Supported models

| Model                            | Vision (max images) | Video   | Extra options                         |
| :------------------------------- | :------------------ | :------ | :------------------------------------ |
| `anthropic/claude-opus-4.7`      | 20                  | —       | Reasoning effort                      |
| `openai/gpt-5.5-pro`             | 20                  | —       | Reasoning effort                      |
| `openai/gpt-5.5`                 | 20                  | —       | Reasoning effort                      |
| `google/gemini-3.5-flash`        | 20                  | Up to 4 | Reasoning effort                      |
| `x-ai/grok-4.20`                 | 20                  | —       | Reasoning effort                      |
| `x-ai/grok-4.3`                  | 20                  | —       | Reasoning effort                      |
| `deepseek/deepseek-v4-pro`       | —                   | —       | Reasoning effort                      |
| `deepseek/deepseek-v4-flash`     | —                   | —       | Reasoning effort                      |
| `deepseek/deepseek-v3.2`         | —                   | —       | Reasoning effort                      |
| `qwen/qwen3.6-max-preview`       | —                   | —       | Reasoning effort                      |
| `qwen/qwen3.6-plus`              | 10                  | Up to 4 | Reasoning effort                      |
| `qwen/qwen3.6-flash`             | 10                  | Up to 4 | Reasoning effort                      |
| `mistralai/mistral-large-2512`   | 8                   | —       | —                                     |
| `mistralai/mistral-medium-3-5`   | 8                   | —       | Reasoning effort                      |
| `z-ai/glm-4.6`                   | —                   | —       | Reasoning effort                      |
| `z-ai/glm-5`                     | —                   | —       | Reasoning effort                      |
| `moonshotai/kimi-k2.6`           | 10                  | —       | Reasoning effort                      |
| `moonshotai/kimi-k2-thinking`    | —                   | —       | Reasoning effort                      |
| `perplexity/sonar-pro`           | —                   | —       | Search context size                   |
| `perplexity/sonar-reasoning-pro` | —                   | —       | Search context size, reasoning effort |
| `perplexity/sonar-deep-research` | —                   | —       | Search context size, reasoning effort |

## Use it in ComfyUI

<Card title="OpenRouter LLM workflows" icon="diagram-project" href="/tutorials/partner-nodes/openrouter/llm/workflow">
  Run the OpenRouter LLM chat workflow in ComfyUI, locally or on Comfy Cloud
</Card>