一个 Base URL,调用全部大模型
已接入 13 家上游、66 个模型;支持 Chat Completions / Responses / Anthropic Messages 三种协议,按套餐统一限速与计量。
66可用模型
13上游供应商
DeepSeek-V4.1-Flash默认模型
未连接本地 Ollama
快速接入
在用户控制台创建 API Key,把 Base URL 指向下面地址即可,任何 OpenAI SDK / 客户端都能直接用。
Base URL:https://newapi.ypvps.com/v1
curl https://newapi.ypvps.com/v1/chat/completions \
-H "Authorization: Bearer sk-你的KEY" \
-H "Content-Type: application/json" \
-d '{"model":"DeepSeek-V4.1-Flash","messages":[{"role":"user","content":"你好"}]}'若反代链路会丢弃 Authorization 头,可改用路径写法:https://newapi.ypvps.com/k/<你的KEY>/v1
平台状态
Web 网关:运行中
默认模型:DeepSeek-V4.1-Flash
可用模型:66 个 · 上游供应商 13 家
模型配置由环境变量自动播种,重新部署后自动恢复;登录后可在 用户控制台 创建 Key、查看用量/订单/工单。
模型广场
共 66 个可用模型| 模型 ID | 上游 | 能力 | 协议 |
|---|---|---|---|
| DeepSeek-V4.1-Flash | amd | text | chat_completions |
| qwen2.5-coder-14b-ms:latest | 本地 Ollama | text | chat_completions |
| DeepSeek-V4-Flash | amd | text | chat_completions |
| DeepSeek-V4-Flash-Vision-Exp | amd | text | chat_completions |
| Gemma-4-31B-IT | amd | text | chat_completions |
| GLM-5.3-Flash | amd | text | chat_completions |
| MiMo-V2.6-Flash | amd | text | chat_completions |
| MinerU2.5-Pro | amd | ocr | ocr |
| MiniCPM5-2B | amd | text | chat_completions |
| Qwen3.8-27B | amd | text | chat_completions |
| Qwen3.8-Flash-Next | amd | text | chat_completions |
| z-ai/glm-5.3-free | token | text | chat_completions |
| orcarouter/free | orca | text | chat_completions |
| tencent/hy3-free | orca | text | chat_completions |
| deepseek/deepseek-v4-flash-free | orca | text | chat_completions |
| deepseek-v4-flash | sensenova | text | chat_completions |
| glm-5.2 | sensenova | text | chat_completions |
| sensenova-6.8-flash-lite | sensenova | text | chat_completions |
| kimi-k3 | sensenova | text | chat_completions |
| deepseek-flash | sensenova | text | chat_completions |
| agnes-3.0-flash | agnescom | text | chat_completions |
| agnes-2.5-flash | agnescom | text | chat_completions |
| agnes-2.5-flash | agnescn | text | chat_completions |
| agnes-2.5-pro | agnescn | text | chat_completions |
| agnes-2.5-pro-alpha | agnescn | text | chat_completions |
| agnes-2.5-pro-beta | agnescn | text | chat_completions |
| agnes-3.0-flash | agnescn | text | chat_completions |
| agnes-2.5-flash | bynara | text | chat_completions |
| LongCat-2.5-Preview | longcat | text | chat_completions |
| LongCat-2.0 | longcat | text | chat_completions |
| laguna-s-2.1 | bynara | text | chat_completions |
| nemotron-3-ultra-free | bynara | text | chat_completions |
| nemotron-3.5-lightning-free | bynara | text | chat_completions |
| deepseek-ai/deepseek-v4.1-flash | nvidia | text | chat_completions |
| google/diffusiongemma-26b-a4b-it | nvidia | text | chat_completions |
| google/gemma-4-31b-it | nvidia | text | chat_completions |
| meta/llama-3.2-11b-vision-instruct | nvidia | text | chat_completions |
| meta/llama-3.2-90b-vision-instruct | nvidia | text | chat_completions |
| meta/llama-guard-4-12b | nvidia | text | chat_completions |
| meta/muse-glimmer-30b | nvidia | text | chat_completions |
| moonshotai/kimi-k3 | nvidia | text | chat_completions |
| nvidia/ai-synthetic-video-detector | nvidia | text | chat_completions |
| Qwen3.6-35b-a3b-nvfp4 | winclaw | text | chat_completions |
| nvidia/ising-calibration-1.5-31b | nvidia | text | chat_completions |
| nvidia/llama-3.1-nemoguard-8b-content-safety | nvidia | text | chat_completions |
| nvidia/llama-3.1-nemoguard-8b-topic-control | nvidia | text | chat_completions |
| nvidia/llama-3.1-nemotron-safety-guard-8b-v3 | nvidia | text | chat_completions |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | nvidia | text | chat_completions |
| nvidia/nemotron-3-super-120b-a12b | nvidia | text | chat_completions |
| nvidia/nemotron-3-ultra-550b-a55b | nvidia | text | chat_completions |
| nvidia/nemotron-3.5-content-safety | nvidia | text | chat_completions |
| nvidia/nemotron-3.5-lightning-30b-a3b | nvidia | text | chat_completions |
| nvidia/nemotron-parse-2.0 | nvidia | text | chat_completions |
| nvidia/riva-translate-4b-instruct-v2 | nvidia | text | chat_completions |
| openai/gpt-oss-20b | nvidia | text | chat_completions |
| poolside/laguna-xs-2.1 | nvidia | text | chat_completions |
| z-ai/glm-5.3 | nvidia | text | chat_completions |
| z-ai/glm-5.3-flash | nvidia | text | chat_completions |
| gpt-5.4 | 52ccl | text | chat_completions |
| gpt-5.4-mini | 52ccl | text | chat_completions |
| gpt-5.5 | 52ccl | text | chat_completions |
| gpt-5.6-luna | 52ccl | text | chat_completions |
| gpt-6-luna | 52ccl | text | chat_completions |
| codex-auto-review | moyuu | text | chat_completions |
| gpt-5.5 | moyuu | text | chat_completions |
| gpt-5.6-terra | moyuu | text | chat_completions |