一个用于管理API请求的智能负载均衡平台。
GPT Load 是一个开源的智能负载均衡平台，旨在高效管理和分发 API 请求。它提供跨多个端点路由流量的工具，以优化性能和可靠性。主要功能包括支持多种 API 模型、可配置的路由规则以及与流行服务的集成。该平台面向需要可扩展 API 管理解决方案的开发者和团队，典型用例涉及 AI 模型 API、Web 服务和后端系统。它在 MIT 许可证下提供，并在 GitHub 上维护。
Performance Stats
Avg Speed
465.08t/s
Latency
3.01s
Total Tests
155
Models
21
About GPT Load
Supported Models
| Model | Speed | Latency | Tests |
|---|---|---|---|
| qwen-3-32b | 3044.37 t/s | 1.93s | 5 |
| qwen-3-235b-a22b-instruct-2507 | 1381.99 t/s | 1.49s | 20 |
| translate-model | 345.18 t/s | 3.10s | 45 |
| models/gemini-2.5-flash-lite | 259.93 t/s | 0.71s | 5 |
| DeepSeek-V3.1 | 257.63 t/s | 0.55s | 5 |
| DeepSeek-V3.1 | 257.63 t/s | 0.55s | 5 |
| DeepSeek-V3-0324 | 218.28 t/s | 0.90s | 5 |
| openai/gpt-oss-120b | 205.99 t/s | 8.90s | 5 |
| models/gemini-2.5-flash | 198.97 t/s | 7.95s | 15 |
| models/gemini-2.5-flash-preview-09-2025 | 175.68 t/s | 0.57s | 5 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 173.09 t/s | 1.54s | 5 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 173.09 t/s | 1.54s | 5 |
| qwen/qwen3-next-80b-a3b-instruct | 154.28 t/s | 0.79s | 10 |
| qwen/qwen3-next-80b-a3b-instruct | 154.28 t/s | 0.79s | 10 |
| gpt-oss:120b | 141.34 t/s | 1.35s | 5 |
| WiNGPT-Babel | 137.86 t/s | 1.40s | 5 |
| x-ai/grok-4.1-fast:free | 87.31 t/s | 6.31s | 5 |
| deepseek-v3.1:671b | 72.01 t/s | 2.63s | 5 |
| deepseek-v3.1:671b | 72.01 t/s | 2.63s | 5 |
| gpt-4.1-mini | 66.95 t/s | 1.58s | 5 |
| moonshotai/kimi-k2-instruct-0905 | 36.98 t/s | 5.74s | 5 |
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Nov 28, 08:51 AM | x-ai/grok-4.1-fast:free | 87.31 t/s | 6.31s |
| Nov 28, 08:38 AM | gpt-oss:120b | 141.34 t/s | 1.35s |
| Nov 28, 08:35 AM | DeepSeek-V3-0324 | 218.28 t/s | 0.90s |
| Nov 28, 08:34 AM | qwen-3-235b-a22b-instruct-2507 | 1843.26 t/s | 2.10s |
| Nov 28, 08:33 AM | qwen-3-235b-a22b-instruct-2507 | 377.69 t/s | 1.38s |
| Nov 28, 08:32 AM | models/gemini-2.5-flash | 194.64 t/s | 7.60s |
| Nov 28, 08:31 AM | Qwen/Qwen3-Next-80B-A3B-Instruct | 173.09 t/s | 1.54s |
| Nov 28, 08:29 AM | qwen/qwen3-next-80b-a3b-instruct | 149.87 t/s | 0.78s |
| Nov 28, 08:27 AM | openai/gpt-oss-120b | 205.99 t/s | 8.90s |
| Nov 28, 08:25 AM | qwen/qwen3-next-80b-a3b-instruct | 158.70 t/s | 0.80s |