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
- Contexto
- 1M tokens
- Máx. completion
- 131,072
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-10-16
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
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"}]
}'Preguntas frecuentes
- ¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: inception/mercury-3.
- ¿Mercury 3 es gratis?
- No. El input cuesta $0.109 / 1M tokens y el output $0.3815 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Mercury 3?
- Mercury 3 tiene una ventana de 1M tokens. Soporta hasta 131,072 tokens de completion.
- ¿Mercury 3 soporta tool calling y structured outputs?
- Mercury 3 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Mercury 3?
- Mercury 3 se lanzó el 16 de octubre de 2026.