Provider config
Requesty
Learn how to use Requesty with Sypha to access and optimize over 150 large language models.
Sypha accommodates model access through the Requesty AI platform. Requesty delivers a streamlined and optimized API for interacting with 150+ large language models (LLMs).
Website: https://www.requesty.ai/
Obtaining an API Key
- Account Creation/Login: Access the Requesty website and establish an account or authenticate.
- Acquire API Key: You can obtain an API key from the API Management section of your Requesty dashboard.
Available Models
Requesty delivers access to a broad spectrum of models. Sypha will automatically retrieve the current list of available models. You can view the complete list of available models on the Model List page.
Sypha Configuration
- Access Sypha Configuration: Select the settings icon (⚙️) within the Sypha panel.
- Choose Provider: Pick "Requesty" from the "API Provider" selector.
- Insert API Key: Place your Requesty API key into the "Requesty API Key" field.
- Choose Model: Select your preferred model from the "Model" selector.
Important Considerations
- Optimizations: Requesty provides a spectrum of in-flight cost optimizations to reduce your expenses.
- Unified and simplified billing: Unrestricted access to all providers and models, automatic balance replenishment and more via a single API key.
- Cost tracking: Monitor cost per model, coding language, modified file, and more via the Cost dashboard or the Requesty VS Code extension.
- Stats and logs: View your coding stats dashboard or examine your LLM interaction logs.
- Fallback policies: Maintain your LLM operational with fallback policies when providers experience downtime.
- Prompt Caching: Certain providers accommodate prompt caching. Search models with caching.