Mercury 2.5
Release Date: Sept 8, 2026 Creator: Inception
Mercury 2.5 is a diffusion model from inception, which is a very fast reasoning model best suited for coding tasks.
Access Mercury 2.5 securely with complete privacy. Our local-first approach means your text chats and prompts are stored exclusively on your browser via IndexedDB, never on a remote server. When you delete a chat, it is permanently wiped locally, and we ensure zero prompt training is used across all model endpoints.
Try Mercury 2.5 instantly
Here
🔒 Requires a secure session. Sign in with Google to protect your data.
| Model Specifications | ||
|---|---|---|
| Knowledge Cutoff | Early 2026 | N/A |
| Context (VividLLM) | 64,000 Tokens | N/A |
| With a context window of 64,000 tokens, this model can 'remember' and analyze up to 96 pages of data at once. This makes it a top choice for processing technical manuals and multi-chapter reports. | ||
| Context (Native) | 256,000 Tokens | N/A |
| Input Modalities | TextImagePDF | TextImagePDF |
| Tool Calling | yes | N/A |
| Output Type | Text | Text |
| Default Max Output | 8192 | 8192 |
| Input Weight | 0.750 x (Casual) | N/A |
| Output Weight | 0.750 x (Casual) | N/A |
Disclaimer: We are providing Image Upload options to only limit models as of now, so some models which have image upload options might now have that feature on our site.