qianfan.baidubce.com完成站点认证,解锁以下权益:
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 5 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 |
|---|---|---|---|---|---|
| - | - | — | 37.7 t/s | 7.34 s | |
| - | - | — | 56.4 t/s | 12.23 s | |
qwen2.5-7b-instruct | - | - | — | 42.0 t/s | 1.36 s |
| - | - | — | 165.2 t/s | 1.77 s | |
| - | - | — | 9.9 t/s | 27.26 s |
当前显示 5 / 5 个模型行
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| May 27, 06:29 AM | kimi-k2.5 | 56.44 tok/s | 12.23s |
| May 27, 06:26 AM | deepseek-v4-pro | 37.67 tok/s | 7.34s |
| Nov 21, 02:50 AM | qwen3-0.6b | 150.90 tok/s | 2.38s |
| Jul 24, 09:57 AM | qwen2.5-7b-instruct | 25.48 tok/s | 2.24s |
| Jul 17, 07:22 PM | qwen3-0.6b | 151.91 tok/s | 0.33s |
| Jul 17, 07:21 PM | qwen2.5-7b-instruct | 46.17 tok/s | 1.11s |
| Jul 17, 07:03 PM | qwen2.5-7b-instruct | 54.46 tok/s | 0.74s |
| Jun 11, 02:53 AM | qwen3-0.6b | 192.66 tok/s | 2.60s |
| Feb 8, 01:41 PM | deepseek-r1 | 9.88 tok/s | 27.26s |
用 179 个 LMSpeed 信号,把 百度千帆 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 |
|---|---|---|---|---|---|---|
| 百度千帆 baidu-qianfan Baidu Qianfan is Baidu Intelligent Clouds enterprise AI platform, providing access to ERNIE series models and other LLM capabilities through developer APIs. | 当前服务商基线 | 26 | 0 | N/A | 81 tok/s | 70.9% |
| GLM BigModel Relay glm-bigmodel-relay A third-party API relay providing access to GLM/ChatGLM models through OpenAI-compatible endpoints. |
| 113 | 0 | $0.704/M | 52 tok/s | 99.5% |
dashscope Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models. |
| 56 | 0 | N/A | 73 tok/s | 89.9% |
volcengine-ark Volcengine Ark is ByteDance's enterprise AI platform, offering Doubao series models and third-party LLMs via OpenAI-compatible API. |
| 32 | 0 | N/A | 40 tok/s | 99.2% |
api-suanli-cn Gongji Compute (共绩算力) provides pay-as-you-go, standard API access to mainstream LLMs and elastic GPU computing for AI applications. |
| 6 | 5 | N/A | 36 tok/s | 80% |
mistral-ai-api Mistral AI API provides access to frontier AI models including Mistral Large, Medium, Small, and Codestral for chat, code, and embeddings. |
| 4 | 0 | N/A | 132 tok/s | 99.4% |
google-gemini-api Google Gemini API offers access to Gemini models and an OpenAI-compatible interface for application development and model inference. |
| 1 | 0 | N/A | 157 tok/s | 97.9% |