OpenRouter

OpenRouter is aunified gateway, which lets you access 200+ providers’ chat models with one key (GPT, Claude, Gemini, Llama, DeepSeek, etc.), billed by tokens, suitable for multi-model comparison / users who can’t register accounts one by one.

Get an API Key

• Go to OpenRouter Register account
• Settings → Keys → Create Key, copy sk-or-... Key
• Top up any amount (minimum $1)

Configure in Cherry Studio

• Open Settings → Model Services, find OpenRouter Provider to enter the details page
• API key Fill in sk-or-...
• API address 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>:

Example model IDs	Who 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 scenarios

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

Relationship with the Anthropic protocol

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

• ✅ Works for regular chat, knowledge bases, and quick assistants
• ⚠️ Cherry Agent Recommended to use directly Anthropic / CherryIN; do not use OpenRouter (Agent requires the native Anthropic protocol)

• OpenRouter adds a small markup on top of the original provider’s price (usually 5-10%), in exchange for "one account for all"
• Some models have a "free" version (free with rate limits); when filtering, pay attention to items with the (free) suffix
• See the detailed pricing table at OpenRouter Models

---

💡 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 the official channels provided there.