Merius

Cheap inference is usually slow. Ours isn't. GLM-5.2 on Merius: top-tier throughput, bottom-tier price. $10 free credits for every new signup — limited time merius.ai/models/glm-5.2…

Kimi K3, now flat-rate in Merius Frontier ($149/mo) 🎉 No metering, no waitlist — point opencode, Cline, or your agent at it and go. Free 30-min test available on our dashboard. (Also on per-token API if you prefer — $2.50 in / $13.00 out per 1M.)

@TencentHunyuan Love this. The 1-bit/4-bit release makes Hy3 incredibly accessible for local runs. For teams who'd rather not manage the GPU, we put Hy3 on a hosted API at Merius — free all of July. Same model, zero setup: merius.ai/models/hy3-ten…

We’ve just released the 1-bit & 4-bit version of Hy3, a flagship-scale 295B model that can be served on a single GPU. 👌 Run Hy3 with llama.cpp, enable MTP, and experience powerful intelligence on dramatically lower hardware.🚀🚀🚀 Can’t wait to see what you build. #Hy3 #Hy #GGUF #llamacpp

Hy3 is free on Merius for all of July. ⚡ Tencent's 295B MoE — reasoning, coding, agents — served fast, at zero cost this month. Swap your base URL, keep your OpenAI SDK, start building. merius.ai/models/hy3-ten…

@TotalWorldApps Yeah GLM-5's solid. Scaling usually comes down to the serving layer more than the model — that's the part we handle, so throughput holds up as you scale.

@merius_ai glm-5 is solid for inference but i'm not sure how it scales to ton apps.

Cheap inference is usually slow. Ours isn't. GLM-5.2 on Merius: top-tier throughput, bottom-tier price. $10 free credits for every new signup — limited time merius.ai/models/glm-5.2…