Mercury pricing
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude... Below you will find 1 current row with input and output dollars per million. Right now the lowest input is $0.250 and the lowest output is $0.750.
Pricing across providers
Every row is a seller of Mercury with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| 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 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. Values follow the main provider (Inception) record in our index.
- Context window
- 128,000 tokens
- Max output
- 32,000 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Jun 2025
- Primary provider
- Inception
- Model family
- N/A
Compare Mercury
Open a pair page to see Mercury next to another model with a shared provider matrix. 6 shortcuts below.
Locked
Compare with
Pick a model on both sides.
Popular Mercury comparisons
- Mercury vs GPT-4o
Compare pricing side by side
- Mercury vs Claude Sonnet 4.6
Compare pricing side by side
- Mercury vs Gemini 2.0 Flash
Compare pricing side by side
- Mercury vs Llama 3.1 70B
Compare pricing side by side
- Mercury vs Mistral 7B
Compare pricing side by side
- Mercury vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Read these after the table if you want plain language around Mercury rates. The short model note from our index: Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude...
Related models
Models close to Mercury by family, provider, and context window — each with live pricing in our catalog.