blog/

📄 Lilac is now self-serve — plus GLM 5.1 and Gemma 4 are live 533w HTML · MD

📄 The GPU Scarcity Paradox 1,398w HTML · MD

📄 We're partnering with MiniMax to bring M2.7 to Lilac 550w HTML · MD

📄 How to keep frontier open weights viable 552w HTML · MD

📄 GPU Inference API Pricing Compared 685w HTML · MD

📄 GLM 5.1 Inference Benchmark 422w HTML · MD

📄 Cache read pricing is now live on Lilac 419w HTML · MD

📄 Introducing Lilac: Turn Idle GPU Capacity into Revenue 382w HTML · MD

📄 Kimi K2.6 is live on Lilac 266w HTML · MD

📄 How Idle GPUs Make Cheap Inference Possible 390w HTML · MD

📄 Blog 317w HTML · MD

Pages