LLM & Text GenerationDev1 min reading time

Mercury 3 now available on AI Gateway

Covered by 2 sources
Read the full article
Inception's Mercury 3 model, featuring diffusion-based text generation with a 1M-token context window and over 1,000 tokens per second speed, is now accessible on AI Gateway at a 50% launch discount. The model targets latency-sensitive tasks like browser agents and real-time search, and integrates with platforms such as Claude Code and Codex via AI Gateway's unified API.

Covered by 2 sources


More in LLM & Text Generation

“We were looking at it wrong”: The explosive claim that’s upended the AI world

MIT Technology Review

Together AI Launches Together Post-Training Service for Custom Models

Unite.AI

Push-based KV transfer to improve TTFT and TPOT for disaggregated inference in vLLM

AWS Blog