Mercury 2.5 Preview

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs. It delivers a 10+ point jump in intelligence over Mercury 2, comparable quality to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5. Mercury 2.5 supports tunable reasoning levels, parallel tool calls, and schema-aligned JSON output. It's built for production workloads where latency compounds: search agents, voice pipelines, and coding subagents.

ChatInception260k tokens$0.0436 / $0.1635 · 1M

inception/mercury-2.5-preview

Context
260k tokens
Completion cap
65,536
Tools
Yes
JSON
Yes
Released
2026-08-31

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-2.5-preview",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Mercury 2.5 Preview?
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs. It delivers a 10+ point jump in intelligence over Mercury 2, comparable quality to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5. Mercury 2.5 supports tunable reasoning levels, parallel tool calls, and schema-aligned JSON output. It's built for production workloads where latency compounds: search agents, voice pipelines, and coding subagents. Mercury 2.5 Preview runs on the Geek Hub API (OpenAI-compatible). Model id: inception/mercury-2.5-preview.
Is Mercury 2.5 Preview free?
No. Input is $0.0436 per 1M tokens and output is $0.1635 per 1M tokens on Geek Hub (markup included).
What is the context length of Mercury 2.5 Preview?
Mercury 2.5 Preview has a 260k tokens context window. It supports up to 65,536 completion tokens.
Does Mercury 2.5 Preview support tool calling and structured outputs?
Mercury 2.5 Preview accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Mercury 2.5 Preview released?
Mercury 2.5 Preview was released on 2026-08-31.

More models from Inception