Introduction
Welcome to Vergora — one workspace for accessing the world’s leading AI models.
Vergora brings model selection, API access, API key management, account balance, and request records into one console. You can compare model capabilities and pricing, integrate your application through an interface supported by the selected model, and review status, usage, latency, and cost for each request.
Unified access does not mean that every model supports the same parameters, input types, or output formats. Before switching models, check the supported interfaces, capabilities, and limits for the selected model.
What you can do with Vergora
- Access currently available models through a unified API workflow.
- Choose a Model ID based on your task, required capabilities, and pricing.
- Create and manage API keys for different applications and environments.
- Review balance, request status, token usage, latency, and cost in the console.
- Use a Request ID to troubleshoot an API call and review its request record.
Start with your task
| What you want to do | Recommended section | What you will get |
|---|---|---|
| Call the API for the first time | Quickstart | A successful response and its request record |
| Migrate an existing application | Migrate an existing application | Updated connection settings and a minimal verification result |
| Create or manage credentials | Authentication and API keys | An access credential for the target application environment |
| Choose a model | Models and compatibility | An available Model ID, interface, and supported parameter range |
| Test a model response | Playground | A test response with usage and cost information |
| Review requests and spend | Request records and cost review | Request status, usage, latency, and cost details |
| Troubleshoot a failed request | Errors and retries; Limits and quotas | Relevant troubleshooting steps and next actions |
Concepts to know before you begin
| Concept | Description |
|---|---|
| Base URL | The base address used by a client to access the Vergora API. It serves a different purpose from the Vergora website URL. |
| API key | A private credential used to authenticate API requests. Never expose a complete key in browser code, public repositories, logs, or screenshots. |
| Model ID | The model identifier used in an API request. Copy it from the model catalog instead of using the display name. |
| Workspace | The scope in the console where API keys, balance, request records, and related settings are managed. |
| Request ID | An identifier used to locate a request for troubleshooting and cost review. |
Recommended workflow
- Sign in to Vergora and open the console.
- Confirm the available balance and target environment.
- Create and securely store an API key.
- Copy a Model ID from the model catalog.
- Send a minimal request.
- Review its status, usage, latency, and cost in request records.
- Integrate Vergora into your production workflow after the verification succeeds.
Next, open Quickstart to complete your first API request.