What's new in 0.30.0:
1. Many more models: OpenRouter Fusion, Gemini 3.5 Flash, Grok 4.3, Qwen 3.7, Kimi K2.7 Code, DeepSeek V4 Flash, GPT-5.5 Pro & more
2. Set a default model in Settings
3. Improved: model picker organized by maker with cost indicators
What's new in 0.27.0:
1. More image models: Flux, Ideogram & Recraft
2. Edit images with flux-kontext
3. LoRA support
4. More video models: Kling v3 Pro & Veo3
5. Music & speech generation
6. Audio plays inline in chat
As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models.
Here’s what this means for you:
Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error.
On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models.
We know this is a disruption to your workflows; we appreciate your patience and support.
What's new in 0.26.0:
1. Switch AI model anytime mid-chat
2. New model: Claude Fable 5
3. Note breadcrumbs
4. Cleaner sidebar with top-level Inbox
5. Bugfix: agent note title & icon edits show live
Just switched from @cursor_ai to @zeddotdev .
Why?
I found myself barely write code. The only thing I need is a code viewer + multiple tab terminal emulator.
Zed is the fastest one I see.
Correct me if I am wrong.