Mercury 2 pricing
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... This page tracks 1 listing in total. Highlighted lows are $0.250 per million input and $0.750 per million output (see table for which seller matches each).
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 1 offer is listed for Mercury 2. Best input in this view: Openrouter.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.250 | $0.750 | — | — |
Input vs output · 1M tokens
Cost calculator
Use this block to stress test Mercury 2 cost without a spreadsheet. All estimates come from public list rates in this page.
0.025000¢ / req
0.037500¢ / req
Model specifications
Context length, caps, and capability flags for Mercury 2. Values follow the main provider (Inception) record in our index.
- Context window
- 128,000 tokens
- Max output
- 50,000 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Mar 2026
- Primary provider
- Inception
- Model family
- N/A
Compare Mercury 2
Open a pair page to see Mercury 2 next to another model with a shared provider matrix. 6 shortcuts below.
Locked
Compare with
Pick a model on both sides.
Popular Mercury 2 comparisons
- Mercury 2 vs GPT-4o
Compare pricing side by side
- Mercury 2 vs GPT-4o mini
Compare pricing side by side
- Mercury 2 vs Claude Sonnet 4.6
Compare pricing side by side
- Mercury 2 vs Gemini 2.0 Flash
Compare pricing side by side
- Mercury 2 vs o3
Compare pricing side by side
- Mercury 2 vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Quick frequently asked items for Mercury 2 pricing and limits. The short model note from our index: 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...
Also from Inception
Other models by Inception with live pricing in our catalog.