Inception: Mercuryinception
Bottom Line
Inception: Mercury: $0.25/1M input, $0.75/1M output, 128K context. 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...
API Pricing (per 1M tokens)
| Input | $0.25 |
| Output | $0.75 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.38 |
Specs & Performance
| Context Length | 128K |
| Max Output | 32K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from inception
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Inception: Mercury API cost?
Inception: Mercury costs $0.25/1M input tokens and $0.75/1M output tokens. Blended cost at a 3:1 ratio is about $0.38/1M tokens.
What is the context window of Inception: Mercury?
Inception: Mercury supports a 128K token context window with up to 32K output tokens.
Is Inception: Mercury worth it?
Inception: Mercury has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.