Mercury 2
by Inception · family mercury · listed Feb 2026RT
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Current rates USD per 1M tokens
Input$0.25
Output$0.75
Cache read$0.025
Cache write—
Against the market
On the record
- Model id
mercury-2- Context window
- 128K tokens
- Max output
- 50K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Jan 2025
- Released
- 2026-02-24
- Last updated
- 2026-02-24
- Provider docs
- platform.inceptionlabs.ai/docs
Back of the envelope
≈
Also listed at
- NanoGPT$0.25 in · $0.75 out
- OpenRouter$0.25 in · $0.75 out
- Vercel AI Gateway$0.25 in · $0.75 out
- Kilo Gateway$0.25 in · $0.75 out
- Venice AI$0.313 in · $0.938 out