Back to Models

Inception: Mercury 2

inception/mercury-2

Description

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).

API Usage Examples

OpenAI Compatible Endpoint

Use this endpoint with any OpenAI-compatible library. Model: Inception: Mercury 2 (inception/mercury-2)

curl https://api.ridvay.com/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer YOUR_API_KEY"   -d '{
    "model": "inception/mercury-2",
    "messages": [
      {
        "role": "user",
        "content": "Explain the capabilities of the Inception: Mercury 2 model"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Supported Modalities

  • Text

API Pricing

  • Input: 0.25$ / 1M tokens
  • Output: 0.75$ / 1M tokens

Token Limits

  • Max Output: 50,000 tokens
  • Max Context: 128,000 tokens

Subscription Tiers

  • free
  • pro
  • ultimate