# Available models — Y-API

> Y-API currently supports 11 models from vendors including DeepSeek, Qwen, Z.ai, Moonshot AI, Tencent, and Xiaomi — all through one OpenAI-compatible endpoint; switching models only means changing the model field.

This is the markdown representation of https://y-api.bestvirtualgoods.com/models. Catalog and prices synced 2026-09-26. Generated by `scripts/generate-seo-assets.mjs` from the same copy the page renders — do not edit by hand.

## Catalog

Every model is called through the same base_url and the same key — switching models only means changing the model field. The model IDs below are ready to copy.

| Model ID | Vendor | Input / 1M tokens | Output / 1M tokens |
| --- | --- | --- | --- |
| `deepseek/deepseek-v4-flash` | DeepSeek | $0.00 | $0.00 |
| `deepseek/deepseek-v4-pro` | DeepSeek | $0.50 | $1.00 |
| `deepseek/deepseek-v4.1-flash` | DeepSeek | $0.20 | $1.00 |
| `qwen/qwen3.8-flash` | Qwen | $0.20 | $0.50 |
| `z-ai/glm-5.2` | Z.ai | $1.40 | $4.40 |
| `z-ai/glm-5.3` | Z.ai | $1.40 | $5.00 |
| `z-ai/glm-5.3-flash` | Z.ai | $0.15 | $0.50 |
| `moonshotai/kimi-k3` | Moonshot AI | $3.00 | $15.00 |
| `moonshotai/kimi-k2.6` | Moonshot AI | $0.95 | $4.00 |
| `tencent/hy3` | Tencent | $0.00 | $0.00 |
| `xiaomi/mimo-v2.5` | Xiaomi | $0.00 | $0.00 |

Prices are in USD credit (limited-time: a $1 top-up adds $20 credit; reverts to 1:10 afterwards). The catalog and prices may change; the console "Models" page shows the current list at your account's own rate.

## What you actually pay

The table above is quoted in account credit. Divide any figure by 20 for the USD actually paid: `z-ai/glm-5.3-flash` at $0.15 in credit is $0.0075 per 1M input tokens in cash. The cash price is what compares against another provider's list price. Both prices, computed per model, are published as JSON at https://y-api.bestvirtualgoods.com/pricing.json.

## Calling any of them

Every model above shares one base URL and one key — switching models means changing the `model` field and nothing else. The example model used throughout the docs is `deepseek/deepseek-v4-flash`.

A model ID that is not in this catalog comes back as **503**, not 404, and the official SDKs retry 503 twice before your code sees it. The error reference explains that one.

## Links

- HTML version of this page: https://y-api.bestvirtualgoods.com/models
- 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
- Pricing and billing: https://y-api.bestvirtualgoods.com/pricing.md
- Price comparison against other providers: https://y-api.bestvirtualgoods.com/compare/prices
- Integration guide: https://y-api.bestvirtualgoods.com/docs
- Error code reference: https://y-api.bestvirtualgoods.com/docs/errors