An LLM API aggregation platform offering plug-and-play access to multiple AI model providers including DeepSeek, OpenAI, Google, Zhipu GLM, Qwen, Moonshot Kimi, and MiniMax, with customizable routing, fallback mechanisms, and per-token pricing.
https://dashboard.thorbase.comhttps://tokengo.com完成站点认证，解锁以下权益：
Thorbase是一个API聚合接口，提供对DeepSeek、Google、Kimi、Minimax、OpenAI、Qwen和Zhipu等多个大型语言模型的即插即用访问。该平台提供企业级控制功能，包括可定制的路由、故障转移机制和使用管理。
主要功能：
可用模型包括GLM-5、DeepSeek V3.1/V3.2、Qwen3.5-397B-A17B、Kimi K2.5等，具有不同的上下文窗口、参数和每百万令牌定价。平台包含模型排名排行榜，提供基准分数和价值指数，用于比较性能与成本。
典型用例包括需要多个模型选项的AI应用开发、需要路由灵活性的企业AI部署以及成本优化的AI工作负载。
按 13 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 | 模型可用性 | 速度 | 延迟 |
|---|---|---|---|---|---|---|
z-ai/glm-5.2default | $1.26/M | $3.96/M | — | 58% | — | — |
moonshotai/kimi-k2.6default | $0.610/M | $3.07/M | — | 58% | — | — |
deepseek/deepseek-v4-prodefault | $0.435/M | $0.870/M | — | 58% | — | — |
deepseek/deepseek-v4-flashdefault | $0.098/M | $0.196/M | — | 58% | — | — |
deepseek/deepseek-v3.1default | $0.190/M | $0.710/M | — | 58% | — | — |
qwen/qwen3.5-397b-a17bdefault | $0.400/M | $2.65/M | — | 58% | 41.3 t/s | 21.79 s |
z-ai/glm-5.1default | $0.880/M | $2.80/M | — | 58% | — | — |
| - | - | — | 58% | 54.5 t/s | 27.76 s | |
| - | - | — | 58% | 42.5 t/s | 18.50 s | |
minimax/minimax-m2.5default | $0.140/M | $0.810/M | — | 58% | — | — |
z-ai/glm-5default | $0.480/M | $1.54/M | — | 58% | 42.9 t/s | 24.10 s |
| - | - | — | 58% | 39.5 t/s | 10.60 s | |
deepseek/deepseek-v3.2default | $0.217/M | $0.326/M | — | 58% | 56.1 t/s | 1.98 s |
当前显示 13 / 13 个模型行
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| Apr 21, 08:05 AM | minimax/minimax-m2.7 | 55.00 tok/s | 22.21s |
| Apr 21, 07:56 AM | minimax/minimax-m2.7 | 30.07 tok/s | 14.78s |
| Apr 21, 07:52 AM | qwen/qwen3.6-plus | 54.49 tok/s | 27.76s |
| Apr 15, 02:03 PM | z-ai/glm-5 | 39.75 tok/s | 26.78s |
| Apr 15, 02:02 PM | moonshotai/kimi-k2.5 | 47.33 tok/s | 14.63s |
| Apr 15, 02:00 PM | qwen/qwen3.5-397b-a17b | 41.98 tok/s | 21.15s |
| Apr 15, 01:49 PM | qwen/qwen3.5-397b-a17b | 43.10 tok/s | 21.48s |
| Apr 15, 01:42 PM | qwen/qwen3.5-397b-a17b | 38.93 tok/s | 22.74s |
| Apr 15, 01:35 PM | moonshotai/kimi-k2.5 | 38.87 tok/s | 7.79s |
| Apr 13, 02:16 AM | moonshotai/kimi-k2.5 | 32.41 tok/s | 9.36s |
用 191 个 LMSpeed 信号，把 TokenGo 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 |
|---|---|---|---|---|---|---|
| TokenGo thorbase An LLM API aggregation platform offering plug-and-play access to multiple AI model providers including DeepSeek, OpenAI, Google, Zhipu GLM, Qwen, Moonshot Kimi, and MiniMax, with customizable routing, fallback mechanisms, and per-token pricing. | 当前服务商基线 | 22 | 0 | $1.08/M | 44 tok/s | 99.2% |
| 向量引擎 api-vectorengine-ai Vector Engine provides an API platform aggregating access to over 500 AI large models with OpenAI API compatibility and global deployment. |
| 182 | 6 | $5.75/M | 89 tok/s | 99.6% |
| N1N api-n1n-ai N1N provides API access to a wide range of AI models including GPT-4, Claude 3, Gemini, and others for text, image, and video generation. |
| 177 | 6 | $8.65/M | 90 tok/s | 99.7% |
| X666 API x666-me X666 API is an OpenAI-compatible API relay offering access to multiple AI models with competitive pricing and high availability. |
| 25 | 0 | $0.0014/M | 77 tok/s | 99.3% |
| CaMeL AI api-kr777-top CaMeL AI provides an OpenAI-compatible API gateway with extensive model coverage and pricing options. |
| 194 | 4 | $88.30/M | 93 tok/s | 99.1% |
| Future Hub api-futureppo-top Future Hub is a large-scale OpenAI-compatible API gateway at api.futureppo.top with extensive model coverage and pricing data. |
| 132 | 223 | N/A | 263 tok/s | 0.6% |
| CatClaw API catclaw-moetu-vip CatClaw API is an OpenAI-compatible LLM gateway at catclaw.moetu.vip, offering multi-model API access with transparent pricing. |
| 32 | 0 | $0.037/M | 62 tok/s | 0.6% |
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。
