Model catalogue
Inception
Mercury 2.5 Preview
inception/mercury-2.5-preview
Specification
Published by the vendor; the platform bills at the target's declared price.
Mercury 2.5 Preview
reasoning toolsInception inception/mercury-2.5-preview
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
- Input $/1M
- $0.04
- Output $/1M
- $0.15
- Context
- 260K
- Max output
- 66K
- Released
- Aug 31, 2026
- Modalities
- text
Cached input reads $0.004 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 2.5 Preview
targets:
- id: mercury-2-5-preview
kind: llm
name: Mercury 2.5 Preview
metadata:
model: inception/mercury-2.5-preview # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 260000
cost:
usd_per_1k_tokens: 0.000095Price among Inception models
Input list price per million tokens; Mercury 2.5 Preview is the cheapest of 2 listed.
- 1$0.04Mercury 2.5 Preview
- 2$0.25
More from Inception
Other models by the same vendor in the catalogue.