Why OpenRouter?
- One API key for 100+ models -- no need to manage separate accounts for each provider.
- Automatic failover -- if one provider is down, OpenRouter can route to an alternative.
- Unified billing -- one bill for all model usage regardless of the underlying provider.
- Model discovery -- easily try new models without signing up for new services.
- Rate limit pooling -- OpenRouter manages rate limits across multiple provider accounts.
Setup
Step 1: Get an API Key
- Go to openrouter.ai and sign in or create an account.
- Navigate to the API Keys page.
- Create a new key and copy it (it starts with sk-or-).
- Add credits to your OpenRouter account for usage billing.
Step 2: Add the Key to Creor
Option A: Settings UI (recommended)
- Open Creor and go to Settings.
- Navigate to the Providers section.
- Find OpenRouter and enter your API key.
Option B: Environment Variable
export OPENROUTER_API_KEY="sk-or-your-key-here"
Configuration
Reference OpenRouter models using the openrouter/ prefix followed by the model identifier from openrouter.ai:
1
2
3
{
"model": "openrouter/anthropic/claude-sonnet-4"
}
Mix OpenRouter models across agents:
1
2
3
4
5
6
7
8
9
10
11
12
13
{
"agent": {
"build": {
"model": "openrouter/anthropic/claude-sonnet-4"
},
"plan": {
"model": "openrouter/openai/o3"
},
"explore": {
"model": "openrouter/google/gemini-2.5-flash-preview"
}
}
}
Popular Models on OpenRouter
| Model | OpenRouter ID | Provider |
|---|---|---|
| Claude 4 Sonnet | anthropic/claude-sonnet-4 | Anthropic |
| Claude 4 Opus | anthropic/claude-opus-4 | Anthropic |
| GPT-4o | openai/gpt-4o | OpenAI |
| o3-mini | openai/o3-mini | OpenAI |
| Gemini 2.5 Pro | google/gemini-2.5-pro-preview | |
| Gemini 2.5 Flash | google/gemini-2.5-flash-preview | |
| Grok 3 | x-ai/grok-3 | xAI |
| Llama 3.3 70B | meta-llama/llama-3.3-70b-instruct | Meta |
| DeepSeek V3 | deepseek/deepseek-chat-v3 | DeepSeek |
| Mistral Large | mistralai/mistral-large | Mistral |
Tip
Check openrouter.ai/models for the full up-to-date catalog with pricing. Model IDs may change as new versions are released.
Model Routing
OpenRouter supports special routing features that let you dynamically select models:
Auto Router
OpenRouter offers an auto-routing model that selects the best model based on your prompt. This is useful for experimentation:
1
2
3
{
"model": "openrouter/openrouter/auto"
}
Fallback Models
OpenRouter automatically handles provider outages by routing to alternative providers hosting the same model. This happens transparently -- you do not need to configure anything.
Advanced Options
HTTP Headers
Creor automatically sends the required HTTP-Referer and X-Title headers that OpenRouter uses for analytics. No manual configuration is needed.
Model Filtering
Restrict which OpenRouter models appear in the model selector:
1
2
3
4
5
6
7
8
9
10
11
{
"provider": {
"openrouter": {
"whitelist": [
"anthropic/claude-sonnet-4",
"openai/gpt-4o",
"google/gemini-2.5-pro-preview"
]
}
}
}
Request Timeout
1
2
3
4
5
6
7
{
"provider": {
"openrouter": {
"timeout": 600000
}
}
}
Best For
- Users who want to try many models without managing multiple API keys.
- Teams that need a single billing source for all model usage.
- Projects that benefit from automatic provider failover.
- Experimentation and model comparison across providers.
- Access to niche or newly released models not yet available elsewhere.