Mercury 2.5

by inception · family mercury

Facts

Release date	2026-09-08
Retired date	—
Knowledge cutoff	—
Context (max)	260,000
Max output	—
Modalities	text → text
Aliases	`mercury-2.5`
Open weights	no
Description	Inception's latest diffusion LLM (dLLM): parallel token generation and refinement, positioned as the fastest reasoning LLM; 260K context (up from Mercury 2's 128K) at $0.04/$0.15 per Mtok — about a quarter of Mercury 2's price. reasoning_effort control including the out-of-vocabulary instant value.

Unknown values are shown as —.

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenRouter	`inception/mercury-2.5`		chat-completions	openai-chat	ga	0.04 / 0.15	effort · default on · returns reasoning_content

Reasoning controls

OpenRouter· inception/mercury-2.5· chat-completions effort

reasoning_effort lowmediumhigh●

effort · default on · returns reasoning_content

Example requests

OpenRouter · openai-chat · inception/mercury-2.5

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "inception/mercury-2.5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "inception/mercury-2.5",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "inception/mercury-2.5",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())