OpenRouter Adds Mercury 2.5 Preview from Inception AI
OpenRouter announced the model from Inception AI is now live exclusively on its platform.
OpenRouter posted that Mercury 2.5 Preview from Inception AI is now live exclusively on its platform. The announcement states the model reaches 1,107 tokens per second through parallel token generation. It lists tunable reasoning, parallel tool calls, and schema-aligned JSON as features. The post describes the model as built for latency-sensitive workloads. No other details or independent confirmations appear in the packet.
Combined views
38K
2 posts, first seen 3h ago
OpenRouter Adds Mercury 2.5 Preview from Inception AI
OpenRouter announced the model from Inception AI is now live exclusively on its platform.
OpenRouter posted that Mercury 2.5 Preview from Inception AI is now live exclusively on its platform. The announcement states the model reaches 1,107 tokens per second through parallel token generation. It lists tunable reasoning, parallel tool calls, and schema-aligned JSON as features. The post describes the model as built for latency-sensitive workloads. No other details or independent confirmations appear in the packet.
Reactions
2 postsOP 
OpenRouter@OpenRouter1/ The fastest reasoning LLM is now live exclusively on OpenRouter. Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON. Built for latency-sensitive workloads.
- likes: 290
- replies: 36
- bookmarks: 98
- reposts: 20
OP OpenRouter@OpenRouter1/ The fastest reasoning LLM is now live exclusively on OpenRouter. Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON. Built for latency-sensitive workloads.
- likes: 290
- replies: 36
- bookmarks: 98
- reposts: 20