Mercury 2

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. Mercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the [blog post](https://www.inceptionlabs.ai/blog/introducing-mercury-2).

ChatInception128k tokens$0.2725 / $0.8175 · 1M

inception/mercury-2

Contexto
128k tokens
Máx. completion
50,000
Tools
Sí
JSON
Sí
Lanzamiento
2026-03-04

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-2",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Mercury 2?
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. Mercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the [blog post](https://www.inceptionlabs.ai/blog/introducing-mercury-2). Mercury 2 corre en el API de Geek Hub (compatible con OpenAI). Id: inception/mercury-2.
¿Mercury 2 es gratis?
No. El input cuesta $0.2725 / 1M tokens y el output $0.8175 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Mercury 2?
Mercury 2 tiene una ventana de 128k tokens. Soporta hasta 50,000 tokens de completion.
¿Mercury 2 soporta tool calling y structured outputs?
Mercury 2 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó Mercury 2?
Mercury 2 se lanzó el 4 de marzo de 2026.