One API, clearly accounted for. https://xitter.cf/t.co/cq4kXVYy5V
Joined August 2026
- Tweets29
- Following11
- Followers69
- Likes22
Agents run on the official pi SDK (agent-host/), not the old built-in loop.
One durable runtime. Text events stream over SSE with cursor reconnect.Prompt templates live on the Go backend.
Dynamic context and the JSON contract are injected server-side and cannot be overwritten by a user template. Chapter extraction pulls characters, scenes, and props into pending assets.
The canvas is the product.
Smart reference: type an asset name, tag, or index (image 1) and Tab inserts a link to a connected node.
Batch tables cover global prompt overrides and reference reordering. Multi-angle uses a 3D editor; grid split does 4/9/16/25.
Models are yours to plug in.
xitter.cf/Beef_api/status/209752…
Assets are written to the local resource dir, then referenced to the provider. Project data is not synced to a SaaS store. Runtime data is SQLite + resource files + model config, with a DB backup before upgrades.
Media is handled locally first.
H.265 originals can be stored on the canvas without a browser decode step. Playback prefers the source; if it fails, an H.264 preview is generated on demand, single-threaded, resolution-capped, and reused. Windows builds ship the video tools — no separate FFmpeg install.
Hover preview is muted, first 3 seconds, one global decoder. Download and model reference always keep the original file.
BeefTV is a desktop AI workspace for video, not a chat that returns a clip.
One freeform canvas. Ideas, models, and media stay as nodes you can reconnect. Viewport rendering, node loading, media previews, and generation tasks are decoupled so a large canvas stays usable.
We're back. 🍻
挑战从零复刻 LibTV 的第七天！
目前进度：90/100%
经历了不到一周高强度开发，BeefTV 正式开源了！
如果你也受够了网页视频工作台的卡顿和缓慢
那就试试BeefTV，主打轻量、快速、高效⬇️
github.com/glanderness/BeefT…
虽然第一个阶段的开发基本上结束了
但是仍然还有很多事情要处理，包括Bug的修复、新功能的开发测试，以及和 Agent 的联动，都在快速推进当中
也欢迎各位老师点点star，提提意见！
中秋节继续加班，目标是打造出最好用的开源视频工作台🫡
Six more models on the global price list.
Gemini 3.7 Flash, Gemini 3.8 Flash, MiniMax M3, Qwen3.8 Max, Qwen3.8 27B, Kimi K2.7 Code.
27 → 33. Same key, USD credit, each request still itemized in Usage.
global.beefapi.com/pricing
Ensure we're the most stable& cheapest AI Router!
Try it -> global.beefapi.com/
Thanks for all Founding Testers first.
You didn’t wait for a finished product. you tested it, broke it, and helped us ship the next version.
That’s why this isn’t a promo code.
Your account keeps a permanent 20% recharge discount. For every top-up after this.
Seats are limited. When they close, they close.
global.beefapi.com/console/t…
Pix is live at checkout for Brazilian user!🇧🇷
If you open billing from a Brazilian IP and pick the $10 credit, Pix shows up as a payment option. Same prepaid USD credit, same Usage receipt after the request.
We added it because people asked. If the option doesn’t appear, say where you’re checking out from.
that sounds interesting~ If you're willing, you could join in our Discord and we're glad to introduce your program to our community!
Docs just grew up.
docs.global.beefapi.com/docs…
Images and Videos are in the docs now: gpt-image-2 generate / edit / save, and grok-imagine-video-1.5 from create → poll → MP4.
Quickstart now runs the whole loop — credit, key, request, result, cost. API reference has Responses and streaming. Prices in the docs point at pricing.usd.json on the global site.
Nine pages. Same base URL.
GPT-6 #Astra is live now on BeefAPI!
Same key. Same OpenAI-compatible client. About 70% less than running it through the usual checkout — public USD price before you send, a receipt after.
People who’ve been running it keep landing on the same feeling: Less like switching models, more like tuning one that actually listens.
Use it now: global.beefapi.com/pricing
When the next model drops, the setup shouldn’t change.
Same key, same @OpenAI -compatible client, public USD prices before you send, a receipt after.
We’ll add Astra the same way, soon.