# About Y-API — Y-API

> What Y-API does, how it works, and what makes it different — an OpenAI-compatible API gateway serving 12 models from DeepSeek, Qwen, MiniMax, Z.ai, Moonshot AI, and Xiaomi with pay-per-token billing and no monthly fee.

This is the markdown representation of https://y-api.bestvirtualgoods.com/about. This page describes the service architecture and policies. Generated by `scripts/generate-seo-assets.mjs` from the same copy the page renders — do not edit by hand.

## What Y-API does

Y-API is an OpenAI-compatible API gateway. It provides programmatic access to large language models through a single endpoint: you call https://api.y-api.bestvirtualgoods.com/v1/chat/completions or /v1/messages, and Y-API routes the request to the upstream provider hosting the model you selected. Currently serving 12 models from DeepSeek, Qwen, MiniMax, Z.ai, Moonshot AI, and Xiaomi.

## Protocol compatibility

Y-API implements two wire protocols: OpenAI's Chat Completions API (the /chat/completions endpoint) and Anthropic's Messages API (the /messages endpoint). If your code is already built on the OpenAI SDK or Anthropic SDK, switching to Y-API means changing only the base_url and api_key — no call-layer rewrite required.

## How billing works

Pay per token, with no monthly fee and no minimum spend. Top up $1 to receive $20 of account credit (limited-time rate; reverts to 1:10 afterwards). Each API call deducts credit based on actual input and output token counts; multipliers differ per model and are listed on the pricing page. New accounts receive $1 of credit on sign-up. When credit runs out, the API returns HTTP 429; top up to restore access immediately — keys stay valid.

## Response times

API latency follows upstream provider behavior: Y-API adds routing overhead (typically under 100ms) to the model's own inference time. For support inquiries sent to support@bestvirtualgoods.com, typical response time is within 1 business day.

## Upstream dependency

Y-API does not train or host models. All inference capacity comes from upstream model providers. When an upstream provider experiences an outage, requests to models hosted by that provider will fail until the provider recovers. The system status page (https://y-api.bestvirtualgoods.com/status) tracks known incidents.

## Data handling

Request and response content is forwarded to upstream providers in real time and never stored by Y-API — the prompts you send and the text the model returns are never written to any database or log. Call metadata (time, model name, token counts, latency, credit deducted, key name) is retained for the life of the account for billing reconciliation and dispute handling. Account information (email, display name, avatar from OAuth sign-in) is kept until the account is deleted. See the Privacy Policy for full details.

## Links

- HTML version of this page: https://y-api.bestvirtualgoods.com/about
- Site index for agents: https://y-api.bestvirtualgoods.com/llms.txt
- Full reference (single file): https://y-api.bestvirtualgoods.com/llms-full.txt
- OpenAPI 3.1 spec: https://y-api.bestvirtualgoods.com/openapi.json
- Model catalog (JSON, no key needed): https://y-api.bestvirtualgoods.com/models.json
- API base URL: `https://api.y-api.bestvirtualgoods.com/v1`
- Contact: support@bestvirtualgoods.com
- Contact: https://y-api.bestvirtualgoods.com/contact
- Privacy Policy: https://y-api.bestvirtualgoods.com/privacy
- Available models: https://y-api.bestvirtualgoods.com/models
- Pricing: https://y-api.bestvirtualgoods.com/pricing