AI 模型 API 平台AI model API platform
从算子做起的
Token 平台The token platform
built from the kernel up
TokenFly 是通用 Token 平台,一个接口调用文本、图像、语音和视频模型。技术底座由清华技术团队打造,核心技术是基于 RSI 的自演进算子优化。TokenFly is a general token platform: one API for text, image, audio and video models. It is built by a Tsinghua engineering team, on RSI-based self-evolving operator optimization.
| deepseek-v4.1-flash77% off | $0.14 | |
| deepseek-v4.1-flash-101777% off | $0.14 | |
| glm-5.368% off | $1.39 | |
| glm-5.3-flash56% off | $0.22 | |
| minimax-h3768P · 42% off | $0.05/sec |
高质量High quality
接口兼容主流调用方式,工具调用、流式和 JSON 模式照常使用。自研优化同时检查速度和质量,不达标的方案不会上线。Compatible with the mainstream APIs, so tools, streaming and JSON mode work as before. Our own optimizations are checked for speed and quality, and those that fail never ship.
低价格Low prices
输入和输出单价都不高于厂商官方价。按实际用量计费,每笔费用都能在控制台查看。用量大可以签约获得专属价格和额度。Input and output prices never exceed the maker's list price. You pay for what you use, and every charge is in the dashboard. High-volume customers can sign for dedicated prices and capacity.
清华技术团队Tsinghua engineering
技术底座由清华技术团队打造,研究方向覆盖大模型、强化学习和推理系统,并把研究成果落到线上服务。Built by a Tsinghua team working across large models, reinforcement learning and inference systems, with the research running in production.
核心技术:
基于 RSI 的自演进算子优化Core technology:
RSI-based self-evolving operators
RSI 即递归自我改进。智能体持续提出并实现算子优化,自动门控检查质量和速度。通过的代码与经验成为下一轮的起点。目前已在 330 亿参数视频模型上线验证。RSI is recursive self-improvement. Agents keep proposing and implementing operator optimizations, an automatic gate checks quality and speed, and what passes becomes the next round's starting point. It is validated in production on a 33B-parameter video model.
提出并实现Propose and build
智能体定位瓶颈,改写算子和执行路径。Agents find bottlenecks and rewrite operators and execution paths.
自动门控Automatic gate
与官方实现做数值对齐,再测速度。Numerics are checked against the reference, then speed is measured.
存档与继承Archive and inherit
只保留通过检验的代码和经验报告。Only code and reports that passed are kept.
人工终审Human sign-off
发布前评审,不参与优化反馈。Reviewed before release, outside the optimization loop.
算子优化的实测加速Measured operator speedups
MiniMax-H3,单次前向或单项对比MiniMax-H3, single forward pass or single comparison
各项为单独测量,刻度 0–3×。Measured separately; scale 0–3×.
更快但不达标的方案,我们拒绝了Faster, but rejected
门控记录节选From the gate log
| 候选方案Candidate | 未通过的原因Why it failed |
|---|---|
| 融合算子,快 7 倍Fused operator, 7× faster | 视频与音频的数值偏差超标Video and audio numerics out of tolerance |
| 8 步加速 LoRA8-step acceleration LoRA | 画质指标未达标Image quality below target |
| 编译版 VAECompiled VAE | 输出 148 帧,应为 124 帧Output 148 frames instead of 124 |
一行命令,切换到 TokenFlyOne command to switch to TokenFly
正在加载…Loading…
粘贴到终端回车,输入 API Key(不显示)后运行Paste into a terminal, enter your API key (hidden), then run claude。适用于 macOS / Linux,Windows 请用 WSL。. macOS / Linux; on Windows use WSL.
从一个 API Key,到专属部署From one API key to a dedicated deployment
用量小可以直接开始,用量大可以签约获得专属价格和额度。Start right away at small volumes. At high volumes, sign for dedicated prices and capacity.
Token 平台Token platform
一个接口调用文本、图像、语音和视频模型,按用量计费,随充随用。One API for text, image, audio and video models. Pay as you go, top up any time.
开发者和技术团队Developers and engineering teams查看价格See prices企业合同Enterprise contract
用承诺量换专属价格,把 API 一键导入自己的平台,并约定问题响应。Commit volume for dedicated prices, import the API into your platform in one step, and agree response times.
用量大的企业和平台High-volume companies and platforms了解方案Learn more私有化与推理优化Private deployment and optimization
部署到你的环境,或为你的模型和硬件做算子优化。Deploy in your environment, or have operators tuned for your models and hardware.
数据敏感企业、算力中心、服务器厂商Data-sensitive companies, compute centers, server makers了解私有化Learn more告诉我们你的业务规模Tell us your scale
带上你的模型和预估用量,我们会先判断是否适合,再安排样本测试。Bring your models and expected volume. We will check the fit first, then set up a sample test.
微信联系Contact on WeChat 查看二维码Show QR code
使用微信扫一扫联系,或保存图片后在微信中识别。Scan with WeChat, or save the image and open it in WeChat.
查看原图Open full-size image飞书联系Contact on Feishu 查看二维码Show QR code
使用飞书扫一扫,添加联系人;也可保存二维码后在飞书中识别。Scan with Feishu to add us, or save the image and scan it in Feishu.
查看原图Open full-size image