Mercury 2
Mercury 2 generates responses by refining multiple tokens in parallel. Its release includes adjustable reasoning, tool use and schema-aligned JSON.
Deprecated API; check access details
What this generation added
Mercury 2 generates responses by refining multiple tokens in parallel. Its release includes adjustable reasoning, tool use and schema-aligned JSON.Inception: Introducing Mercury 2
Legacy access ends on a stated date
New users cannot access this model. Customers with usage before 19 October 2026 retain access until 15 November 2026. Enterprise agreements can provide continued support.Inception model access and retirement notice
Prepare a measured migration
Practical guidance. Compare complete outputs, schema compliance and failure cases on representative requests before you change an application's model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | mercury-2 |
| Context window | 128,000 tokens Advertised context. Inception: Introducing Mercury 2 |
| Maximum output | 50,000 tokens API output limit. Inception Platform model specifications |
| Input price | 0.25 USD per million tokens Current legacy rate. Inception Platform model specifications |
| Output price | 0.75 USD per million tokens Current legacy rate. Inception Platform model specifications |