Plurence is currently in Public Beta. Features and pricing may change. Not recommended for production workloads. Beta Terms

Core Concepts

Models & Providers

Use the model name to select both the capability and the provider. Plurence routes based on the model identifier in your request.

Supported providers

auto_awesome OpenAI
  • gpt-4o
  • gpt-4o-mini
  • gpt-4-turbo
  • o1
  • o3-mini
psychology Anthropic
  • claude-3-5-sonnet-20241022
  • claude-3-5-haiku-20241022
  • claude-3-opus-20240229
search Google
  • gemini-1.5-pro
  • gemini-1.5-flash
  • gemini-2.0-flash

Model availability depends on your provider credentials. Configure provider keys in Settings → Providers.

Using a model

Specify the model name exactly as listed. The gateway resolves the provider from the model identifier automatically.

curl 
curl https://gateway.plurence.com/v1/chat/completions \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-5-sonnet-20241022",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Model catalog

Browse the live, build-time-generated list of currently supported models and prices at /models. It's also exposed via the API Explorer or queryable programmatically:

curl 
curl https://data.plurence.com/v1/models \
  -H "Authorization: Bearer YOUR_JWT"

Related