Model catalogue
Inception
Mercury 2
inception/mercury-2
Specification
Published by the vendor; the platform bills at the target's declared price.
Mercury 2
reasoning toolsInception 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...
- Input $/1M
- $0.25
- Output $/1M
- $0.75
- Context
- 128K
- Max output
- 50K
- Released
- Mar 4, 2026
- Modalities
- text
Intelligence index-
Coding index31
Agentic index4
Cached input reads $0.03 per 1M
On this deployment
No routing target resolves to this model yet. Declare one and the router picks it up without retraining.
Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs Mercury 2
targets:
- id: mercury-2
kind: llm
name: Mercury 2
metadata:
model: inception/mercury-2 # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 128000
cost:
usd_per_1k_tokens: 0.000500Price among Inception models
Input list price per million tokens; Mercury 2 is the most expensive of 2 listed.
- 1$0.04
- 2$0.25Mercury 2
More from Inception
Other models by the same vendor in the catalogue.