Tool directory · Coding Agents · Issue #2
Mercury 3
New this weekLast checked
A diffusion-based LLM that Inception says runs at more than 1,000 tokens per second with a 1M-token context window. It's OpenAI API compatible and available on Inception's API, OpenRouter, Baseten and Vercel.
Our Take
Mercury 3 is for browser agents, voice bots and subagents where speed matters more than raw intelligence. Inception claims 1,068 tokens per second on NVIDIA GPUs, a 1M-token context window and quality on par with GPT-6 Luna and Claude Haiku 5.5. All benchmarks are Inception's own. It costs $0.20/$0.70 per million input/output tokens, and is half that during launch. Source
Get the Weekly Roundup
The week's new AI tools, every Friday
One short, free email with the newest AI tool drops, from big launches to indie projects. Each one comes with a plain-English summary, what it costs, and a direct link.
- Catch new AI tools the week they ship, including small indie projects
- Get what each tool does and what it costs, explained in plain language
- Go straight to each tool with a direct link, or browse the full directory at toolsmithweekly.com