Newsletter | Synthetic

Newsletter | Synthetic

It looks like you're new here. Interested in running open-source LLMs? Sign up and start using Synthetic, or just read the blog.

A flat monthly subscription to open-source LLMs

Published 2025-08-28

Subscriptions
On-demand GPU pricing
Bugfixes and general improvements
Future plans

Open-sourcing Octofriend, a coding agent that works with GPT-5, Claude, and open LLMs

Published 2025-08-07

Octofriend
Open-sourcing diff-apply and fix-json models
New model support
Free trials for new users
Bugfixes and reliability improvements
Future plans

Rebrand, multimodal UI support, and more!

Published 2025-06-07

Rebrand to Synthetic
Discord server
Multimodal image input in the UI
Bugfixes and reliability improvements
Future plans

Multimodal API support, additional architectures, and more!

Published 2025-05-10

Multimodal API support
More model architectures
Improved UI
Better performance and reliability for on-demand models
Future plans

Referral credits, price drops, and more!

Published 2025-03-14

Referral credits
Price drops for DeepSeek R1
New and improved API endpoint
New payment provider support
Bugfixes, performance improvements, and UI tweaks
Future plans

Cheap, always-on LoRA support

Published 2025-02-06

LoRA support
Higher rate limits
New sampler parameters in the UI
DeepSeek V3 and R1
Bugfixes, performance improvements, and UI tweaks
Future plans

Billing launch

Published 2025-01-01

Billing launch
Free credits
Privacy policy
System prompt editing in the UI
Bugfixes, performance improvements, and UI tweaks
Future plans

Hello World

Published 2024-11-19

Support for the VSCode coding assistant plugin, Cline
Neovim CodeCompanion support
More robust GPU allocation
Model download progress UI
vLLM updates for better model support
Various bugfixes, performance improvements, and UI tweaks
Future plans

...And that's it!