Mercury 3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such as search agents, voice pipelines, and coding subagents. Its distinguishing trait is speed: more than 40x larger than the first Mercury model while generating at the same throughput, because it produces and refines tokens in parallel rather than one at a time.
inception/mercury-3
- Context
- 1M tokens
- Completion cap
- 131,072
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-10-16
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inception/mercury-3",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Mercury 3?
- Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such as search agents, voice pipelines, and coding subagents. Its distinguishing trait is speed: more than 40x larger than the first Mercury model while generating at the same throughput, because it produces and refines tokens in parallel rather than one at a time. Mercury 3 runs on the Geek Hub API (OpenAI-compatible). Model id: inception/mercury-3.
- Is Mercury 3 free?
- No. Input is $0.109 per 1M tokens and output is $0.3815 per 1M tokens on Geek Hub (markup included).
- What is the context length of Mercury 3?
- Mercury 3 has a 1M tokens context window. It supports up to 131,072 completion tokens.
- Does Mercury 3 support tool calling and structured outputs?
- Mercury 3 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Mercury 3 released?
- Mercury 3 was released on 2026-10-16.