Mercury 2.5 Preview API
About
Build advanced reasoning agents with Mercury 2.5 Preview, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.04/1M input and $0.15/1M output tokens, native tool calling support. Access Mercury 2.5 Preview via the OpenRouter API with up to 66K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsClosed
Limits
Context Window
260K
Tokens
Input Limit
260K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.04
Output
$0.15
Caching (per 1M tokens)
Read
$0.0040
Frequently Asked Questions
Mercury 2.5 Preview by OpenRouter costs $0.04 per 1M input tokens and $0.15 per 1M output tokens. Cached reads cost $0.0040 per 1M tokens.
Model Details
ID
inception/mercury-2.5-preview
Provider
OpenRouterFamily
mercury
Release Date
Aug 31, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@openrouter/ai-sdk-provider
Environment Variables
OPENROUTER_API_KEY
API Base URL
https://openrouter.ai/api/v1