> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/openrouter.md).

# OpenRouter

OpenRouter is a **unified gateway**that lets you access 200+ providers’ chat models with one key (GPT, Claude, Gemini, Llama, DeepSeek, etc.), billed by token usage, suitable for users comparing multiple models or unable to register accounts for each provider one by one.

## Get API Key

* Go to [OpenRouter](https://openrouter.ai/) Register account
* `Settings → Keys` → `Create Key`, copy `sk-or-...` key
* Top up any amount (minimum $1)

## Configure in Cherry Studio

* After opening `Settings → Model Services`, find **OpenRouter** Provider to enter the details page
* **API key** enter `sk-or-...`
* **API Address** By default `https://openrouter.ai/api`, no need to modify
* Click **Get model list**, OpenRouter will return hundreds of available models

## Recommended usage

OpenRouter model IDs look like `<vendor>/<model>`:

| Model ID examples                   | What it actually is       |
| ----------------------------------- | ------------------------- |
| `openai/gpt-4o`                     | OpenAI GPT-4o             |
| `anthropic/claude-sonnet-4`         | Anthropic Claude Sonnet 4 |
| `google/gemini-2.0-flash`           | Google Gemini Flash       |
| `meta-llama/llama-3.3-70b-instruct` | Meta Llama 3.3 70B        |
| `deepseek/deepseek-chat`            | DeepSeek V3               |
| `x-ai/grok-4`                       | xAI Grok                  |

## Applicable scenario

* **Multi-model A/B comparison**: freely switch models under the same Cherry Studio Provider, no need to switch Providers
* **Avoid registering one by one**: one key and one invoice can use 200+ models
* **Niche models**: many smaller vendors are only available on OpenRouter (such as Cohere, Reka, etc.)

## Native web access and URL reading

OpenRouter’s chat models can use native web search and URL content reading. When selecting a model, look for the 🌐 icon next to the name, and enable 🌐 in the chat input box.

If \[Settings] → \[Web Search] → \[Prefer configured search services] remains enabled, Cherry Studio will prioritize external search services; after turning off this option, it will prioritize OpenRouter’s native model capabilities. Providers may charge separately for network requests, and actual costs are subject to the OpenRouter bill.

## Relationship with the Anthropic protocol

By default, OpenRouter wraps all upstream models in the OpenAI protocol format. This means:

* ✅ General chat, knowledge base, and quick assistants all work
* ⚠️ [Cherry Agent](/docs/en-us/cherry-studio/preview/agent.md) **It is recommended to use** Anthropic / CherryIN directly, and not go through OpenRouter (Agent requires Anthropic’s native protocol)

{% hint style="info" %}

* OpenRouter adds a small markup on top of the original provider price (usually 5-10%), in exchange for "one account for all"
* Some models can use the "free" version (free but rate-limited); when filtering, pay attention to entries with the `(free)` suffix
* See the detailed pricing table at [OpenRouter Models](https://openrouter.ai/models)
  {% endhint %}

***

### Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) for the official channels provided.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/openrouter.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.