AI Observatory / Model Radar
Inception / inception/mercury-2
Inception: Mercury 2
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...
128,000
Context
50,000
Max output
$0.25 / 1M
Prompt price
2026-03-04
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Inception | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.25 / 1M |
| Completion price | $0.75 / 1M | Request price | N/A |
| Context length | 128,000 | Max completion tokens | 50,000 |
| Supported parameters | include_reasoning, max_tokens, reasoning, response_format, stop, structured_outputs, temperature, tool_choice, tools | ||
Best for
inception/mercury-2
Inception: Mercury 2
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...
Deep analysis
Image generation
High-volume usage
Coding workflows
new
tool-capable
image-gen
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.