InceptionMercury
Mercury 3
Mercury 3 expands the Mercury family to a one-million-token context. Inception serves it through its API and distribution partners.
Diffusion at larger scale
Inception reports a model more than forty times larger than its first Mercury release. It does not disclose an exact parameter count.Inception: Introducing Mercury 3
Reasoning and launch pricing
The API exposes instant, low, medium and high reasoning effort. The displayed launch prices are half the regular input and output rates.Inception Platform model specificationsInception: Introducing Mercury 3
Measure the complete workflow
Practical guidance. Include tool execution and response validation when you measure request time. A high token rate does not establish how quickly a multi-step task finishes.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | mercury-3 |
| Context window | 1,000,000 tokens Advertised 1M context. Inception: Introducing Mercury 3 |
| Maximum output | 131,072 tokens API output limit. Inception Platform model specifications |
| Input price | 0.1 USD per million tokens Launch discount. Inception: Introducing Mercury 3 |
| Output price | 0.35 USD per million tokens Launch discount. Inception: Introducing Mercury 3 |
| Input and output | TextInception Platform model specifications |