Frequently asked questions
Common questions about Essevin integration, keys, protocols, models, and clients.
No. Essevin is directly accessible from mainland China without a proxy.
OpenAI protocols for GPT, Codex, and third-party clients include /v1. The Anthropic protocol for Claude Code and the Anthropic SDK does not; those clients append the API path themselves.
Use the OpenAI Images protocol: POST https://api.essevin.com/v1/images/generations with model, prompt, and size. All GPT Image models use the same client-side request shape. Check GET /v1/models for models available to the current key, then see the Image API for generation and editing fields.
No. Each key serves the model family chosen under Use with when it was created. Use a GPT key for GPT and a Claude key for Claude. When your application needs both families, create one key for each in API keys — both draw from the same plan credits.
Yes. The console's one-click integration dialog provides a Windows PowerShell command. Each manual setup page also includes Windows instructions.
The command contains a single-use integration token that expires after 15 minutes, not the API key itself. The script only updates local configuration and backs up existing settings.
Yes. Usage from the same key is combined under one account. Separate named keys per device make usage easier to attribute.
Essevin runs on a monthly subscription only. A plan grants one shared credit allowance each month; chat, image, and video requests all draw on it. The allowance resets every month and does not carry over, and there is no pay-as-you-go balance, top-up, or per-token price.
Subscriptions are open. Register, then choose a plan on the console Subscription page and pay by card; plans renew automatically every month or every year. You can cancel the renewal from the same page at any time, and the plan stays usable until the end of the period already paid for. The plan line-up and prices are on the home page.
No. Essevin is operated separately from any business or API service: its own site, accounts, subscription, and credits. Nothing transfers between them.
Sign in to the console. Usage History shows the model, token count, and credits spent for every request, along with what is left in the current month.
This usually means the model is temporarily unavailable or the response timed out. Retry with backoff, or switch to another model in the same family. If it persists past 10 minutes, contact us with the X-Request-ID from the response headers.
Direct browser connections are supported. Web clients often do not append an API path. For OpenAI or GPT modes, enter the complete https://api.essevin.com/v1 URL. For Anthropic mode and Claude, omit /v1.