---
id: "inception/mercury-2.5"
also: ["inception/mercury-2.5-20260908", "vercel/inception/mercury-2.5"]
card_usd_per_m: "0.04 in, 0.15 out, at inception"
cheapest_list_usd_per_m: "0.04 in, 0.15 out, at inception on openrouter"
cheapest_effective_usd_per_m: "0.04 in, 0.15 out, at inception on vercel"
context: 260000
max_output: 65536
input: ["text"]
output: ["text"]
released: "2026-09-08"
reasoning: ["high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# Inception: Mercury 2.5

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...