ModelInfo
English
All models

Mercury 2.5

Latest reasoning diffusion model for fast chat, agents and structured workflows.

Inception Labsmercury-2.52026-09-08Report incorrect data

Specs

Context
260K
Max output
65.5K
Input price
$0.2/ 1M tokens
Output price
$0.75/ 1M tokens
Released
2026-09-08

Context

Context window
260K
Max input
—
Max output
65.5K

Pricing · USD / 1M tokens

Input
$0.2
Output
$0.75
Cache read
$0.02
Cache write
—

Modalities

Input
Text
Output
Text

API

API types
chat

Reasoning

Reasoning
Yes
Levels
instantlowmediumhigh

Info

Status
Active
Released
2026-09-08
Knowledge cutoff
—

Features

Confirmed
toolsstructured_outputstreaming
Source · official docsVerified 2026-10-11

How to call

1 provider

inceptionmodel = mercury-2.5reasoning = reasoning_effort

chat
POSThttps://api.inceptionlabs.ai/v1/chat/completions

JSON

Standard format
mercury-2.5.json
{
  "id": "mercury-2.5",
  "object": "model",
  "created": 1788825600,
  "owned_by": "inception",
  "name": "Mercury 2.5",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": 260000,
    "input": null,
    "output": 65536
  },
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": [
      "instant",
      "low",
      "medium",
      "high"
    ]
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 0.2,
    "output": 0.75,
    "cache_read": 0.02,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming"
  ],
  "info": {
    "status": "active",
    "release_date": "2026-09-08",
    "knowledge_cutoff": null,
    "description": "Latest reasoning diffusion model for fast chat, agents and structured workflows.",
    "docs": "https://docs.inceptionlabs.ai/get-started/models",
    "verified_at": "2026-10-11"
  }
}

Official sources

5