Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Input modalities
Output modalities
Capabilities
65,536 tokens
Recent tweets and retweets from OpenRouter
How to run Fable-level intelligence at half the cost.
OpenRouter recently deployed Fusion - the smartest compound model in the world.
Here's exactly how you can use it now (set up in <60 seconds):
1. Web Chat Interface (Quickest to Try)
Go to: openrouter.ai/fusion
Sign in…
GLM-5.2 on Together AI is showing up fast on @OpenRouter ⚡️
The model is strong, and our serving path makes that strength usable in the loop.
Together has been pushing hard on inference so long-context coding and agent workloads get more tokens per GPU while staying fast.
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.