api.model.yungnet.cn排名基于社区提交的测试数据与定期健康探测，仅供参考，非官方数据。
按 15 个模型行对比最新 audit、最新测速、吞吐、延迟与按 token 计费价格。
| 模型 | 输入 ($/M) | 输出 ($/M) | 检测 | 速度 | 延迟 | 测试数 |
|---|---|---|---|---|---|---|
| — | — | 76063100 | 46.5 t/s | 15.70 s | 5 | |
| — | — | 698463100 | 39.6 t/s | 17.42 s | 10 | |
auto | — | — | 5610063100 | 55.1 t/s | 5.84 s | 70 |
| — | — | — | 29.7 t/s | 4.15 s | 10 | |
| — | — | — | 76.4 t/s | 13.99 s | 5 | |
| — | — | — | 33.6 t/s | 12.51 s | 5 | |
doubao-seed-2.0-code | — | — | — | 48.6 t/s | 16.18 s | 5 |
| — | — | — | 35.0 t/s | 11.46 s | 15 | |
| — | — | — | 40.9 t/s | 52.91 s | 5 | |
| — | — | — | 36.0 t/s | 24.63 s | 5 | |
| — | — | — | 43.7 t/s | 17.44 s | 5 | |
| — | — | — | 35.1 t/s | 15.49 s | 5 | |
| — | — | — | 63.4 t/s | 18.56 s | 5 | |
| — | — | — | 69.3 t/s | 4.59 s | 5 | |
| — | — | — | 64.5 t/s | 17.71 s | 5 |
当前显示 15 / 15 个模型行
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| Jun 13, 11:09 AM | glm-5.2 | 46.51 tok/s | 15.70s |
| May 24, 11:36 AM | deepseek-v3.2 | 30.17 tok/s | 5.52s |
| May 24, 11:34 AM | deepseek-v3.2 | 29.31 tok/s | 2.78s |
| May 23, 10:56 AM | auto | 58.00 tok/s | 9.63s |
| May 21, 02:27 AM | auto | 56.62 tok/s | 2.93s |
| May 20, 02:12 AM | auto | 90.48 tok/s | 8.59s |
| May 20, 02:10 AM | auto | 52.17 tok/s | 12.00s |
| May 15, 07:35 AM | auto | 53.25 tok/s | 2.68s |
| May 15, 07:28 AM | auto | 45.59 tok/s | 3.49s |
| May 15, 07:24 AM | auto | 47.58 tok/s | 3.00s |
用 162 个 LMSpeed 信号，把 天云港模型开放平台 的 6 个相近 API 替代服务商放在一起比较：共享模型覆盖、价格、实测速度、可用性和免费模型。
| 服务商 | 对比理由 | 模型数 | 免费项 | 均价 | 速度 | 30 天可用性 |
|---|---|---|---|---|---|---|
| 天云港模型开放平台 api-model-yungnet-cn Yungnet Model Open Platform is a China-based unified LLM API gateway with an OpenAI-compatible relay at api.model.yungnet.cn, focusing on flagship Chinese models. | 当前服务商基线 | 16 | 0 | N/A | 49 tok/s | 100% |
| 天絮 API tianxu-api Tianxu API provides an AI model relay service with multiple access points and stable connectivity. |
| 344 | 1 | $22.18/M | 93 tok/s | 94.6% |
91vip-futureppo-top 91VIP is a non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups. |
| 211 | 1 | $1.97/M | 318 tok/s | 0% |
api-xinjianya-top Xinjianya API is an OpenAI-compatible API relay at api.xinjianya.top. Service availability may be limited. |
| 184 | 209 | $0.119/M | 67 tok/s | 100% |
edge-pieixan-icu Pie-Xian (小水管) provides an OpenAI-compatible API relay with multiple endpoints including api.pie-xian.com and edge nodes. |
| 172 | 2 | $3.46/M | 212 tok/s | 100% |
vsllm-com VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint. |
| 114 | 1 | $28.58/M | 184 tok/s | 99.2% |
ipv4-beta-lm-studio ChooseC API is a unified AI model aggregation gateway supporting 260+ mainstream models including Claude, GPT, Qwen, DeepSeek, Kimi, and GLM with OpenAI, Claude, and Gemini compatibility. |
| 77 | 13 | $31.37/M | 143 tok/s | 99.1% |
