RentGPU RentGPU
GPUs Providers Hosted AI AI Models
VRAM fit calculator Self-host vs API breakeven API monthly bill GPU side-by-side Which GPU should I rent? Training cost estimator Fine-tuning cost calculator Inference cost calculator Rent vs buy calculator Tools →
Leaderboards Articles
EN VI DE ES ZH FR
Find a GPU →
GPUs Providers Hosted AI AI Models VRAM fit calculator Self-host vs API API monthly bill GPU compare Tools → Leaderboards Articles About
EN VI DE ES ZH FR
Home › AI Models › Inception
AI model maker

Inception.

Models from Inception.

?

Inception: Mercury 2

text
by Inception · 128,000 ctx

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Me...

?

Inception: Mercury 2.5

text
by Inception · 260,000 ctx

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, ...

?

Inception: Mercury 2.5 Preview

text
by Inception · 260,000 ctx

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, ...

Ad
RentGPU

The cheapest cloud GPUs for AI, training, and inference.

en vi de es zh fr
Browse
  • All GPUs
  • Providers
  • Hosted AI
  • AI models
  • Tools
  • Articles
About
  • Methodology
  • About
  • Editorial policy
  • Contact
  • Mining crypto? → MiningBoard
Legal & policies
  • Privacy policy
  • Terms of use
© 2026 RentGPU. Some links are affiliate links — we may earn a commission when you sign up. This never affects ranking.
§ FIELD REPORT

Something off?

Thirty seconds keeps the numbers honest.

Type
▲
RECEIVED

Thanks for the ping — we'll take a look.

✕ Couldn't send

Check your connection and try again, or email [email protected].