Horizon Beta

Text input Image input Text output Unavailable
Author's Description

This is a cloaked model provided to the community to gather feedback. This is an improved version of [Horizon Alpha](/openrouter/horizon-alpha) 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
Aug 01, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Structured Outputs Tool Choice Response Format Max Tokens
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Horizon Beta, provided by openrouter and created on August 1, 2025, demonstrates strong overall performance, particularly in speed and reliability. The model typically performs among the fastest models, ranking in the 79th percentile across five benchmarks. Currently, no cost data is available, suggesting it is offered as a free tier during this testing period. Horizon Beta exhibits exceptional reliability, achieving a 100% success rate across all benchmarks, indicating consistent and usable responses. In terms of benchmark performance, Horizon Beta excels in knowledge-based tasks, achieving perfect 100.0% accuracy in both General Knowledge and Ethics, often ranking #1 or in the top 3 for accuracy and cost efficiency in these categories. It also shows very strong performance in Coding, with 95.0% accuracy (97th percentile). While its Email Classification accuracy is respectable at 98.0%, its Instruction Following accuracy is lower at 77.9%, though still ranking in the 91st percentile for this specific benchmark. Key strengths include its perfect accuracy in complex knowledge domains and high reliability. A notable area for potential improvement is its Instruction Following accuracy, despite its high percentile ranking.

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-beta 256K $0 / 1M tokens $0 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openrouter