Mercury 2.5 Preview
- Family
- Mercury
- Context
- 256K
- Specialization
- agentic
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
Inception Labs is an AI company building diffusion-based large language models (dLLMs), a fundamentally different archit
Cheapest of 1 route · OpenRouter · cache read $0.020
About
Inception Mercury 2.5 (Preview) is a reasoning diffusion LLM (dLLM) listed on Inception's models page as the lab's most intelligent reasoning dLLM at its lowest list price. First-party product page (inceptionlabs.ai/models, retrieved 2026-09-01): 256K context window; reasoning, tool use, and structured output; use cases rapid coding iteration, agents/subagents, customer support, and enterprise search. List pricing on that page: USD 0.20 / 1M input, USD 0.02 / 1M cached input, USD 0.75 / 1M output. Site banner: live on OpenRouter.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.200 | $0.750 | read $0.020 | Serverless |
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
mercury-2.5-previewInception Labs is an AI company building diffusion-based large language models (dLLMs), a fundamentally different archit
Cheapest of 1 route · OpenRouter · cache read $0.020