Inception
Mercury 2
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Model facts
- Context window
- 128K tokens
- Maximum output
- 5K tokens
- Cheapest paid input
- $0.25 per 1M tokens
- Cheapest paid output
- $0.75 per 1M tokens
- Open weights
- no
- Providers
- 7
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 21.9 | 31.1 | not measured | 854.3 |
Observed price history
- 2026-08-24: $0.25 input / $0.75 output per 1M tokens
API providers
- Inception — model id mercury-2; $0.25 input / $0.75 output per 1M tokens; provider documentation
- Kilo Gateway (Inception) — model id inception/mercury-2; $0.25 input / $0.75 output per 1M tokens; provider documentation
- NanoGPT — model id mercury-2; $0.25 input / $0.75 output per 1M tokens; provider documentation
- OpenRouter — model id inception/mercury-2; $0.25 input / $0.75 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id inception/mercury-2; $0.25 input / $0.75 output per 1M tokens; provider documentation
- Venice AI — model id mercury-2; $0.312 input / $0.938 output per 1M tokens; provider documentation
- Arena — model id mercury-2; not published input / not published output per 1M tokens; provider documentation