Horizon Alpha

Text input Image input Text output Unavailable
Author's Description

This is a cloaked model provided to the community to gather feedback. Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

Key Specifications
Cost
$
Context
256K
Released
Jul 30, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Max Tokens Structured Outputs Tools Response Format
Features

This model supports the following features:

Tools Structured Outputs Response Format
Performance Summary

Horizon Alpha, a cloaked model from openrouter, demonstrates strong overall performance during its testing period. It consistently ranks among the fastest models, achieving the 83rd percentile in speed across six benchmarks. While no cost data is available, suggesting potential free tier usage, its performance across benchmarks frequently highlights exceptional cost efficiency. The model exhibits outstanding reliability, achieving a perfect 100th percentile, indicating minimal technical failures and consistent response delivery. Across benchmark categories, Horizon Alpha excels in Coding (97.0% accuracy, 100th percentile) and Ethics (100.0% accuracy), often leading in accuracy and cost efficiency. It also shows strong capabilities in General Knowledge (99.5% accuracy) and Instruction Following (84.0% accuracy). Its primary area for improvement appears to be Reasoning, where it achieved 66.0% accuracy, placing it in the 61st percentile. Overall, Horizon Alpha presents as a highly reliable and fast model with exceptional performance in specific domains, offering significant value, particularly given its current free usage.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0
Completion $0

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Stealth
Stealth | openrouter/horizon-alpha 256K $0 / 1M tokens $0 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by openrouter