Inception Mercury 3 Launches on AI Gateway with 50% Off Pricing

·2026.10.19 09:00

Key point

The model uses diffusion for parallel text refinement and supports a 1M-token context window for latency-sensitive workloads.

Inception Mercury 3 is now available on AI Gateway with 50% off launch pricing.
Generation speeds exceed 1,000 tokens per second, targeting latency-sensitive applications like browser agents and real-time search.
The model features a 1M-token context window to handle long documents and extended conversation histories.
AI Gateway offers a unified API with no markup on provider pricing and no platform fee for inference, including Bring Your Own Key (BYOK) requests.
Integration requires setting the AI_GATEWAY_API_KEY environment variable and using inception/mercury-3 as the model name.
Compatible with Claude Code, Codex, and Cursor via the latest Vercel CLI setup.

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.