Mercury 2.5
- Family
- Mercury
- Released
- 2026-09-08
- Context
- 260K
- Max output
- 64K
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
Inception Labs is an AI company building diffusion-based large language models (dLLMs), a fundamentally different archit
Cheapest of 3 routes · OpenRouter
About
Mercury 2.5 is Inception Labs' diffusion LLM GA (API id mercury-2.5). 260K context, 65,536 max output. Tunable reasoning, tool calling, structured outputs. Distinct from Mercury 2.5 Preview. Docs list $0.20/$0.75 per 1M; launch promo $0.04/$0.15 still on API/OR.
Providers(3)
Compare all 3Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.040 | $0.150 | - | Serverless |
| Vercel AI Gateway | $0.040 | $0.150 | read $0.004 | Serverless |
| Inception | $0.200 | $0.750 | read $0.020 | Serverless Scheduled retirement: November 15, 2026 |
Capabilities
Benchmark peer barsfor RAG
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-2.5inception/mercury-2.5Mercury 2.5Inception Labs is an AI company building diffusion-based large language models (dLLMs), a fundamentally different archit
Cheapest of 3 routes · OpenRouter