Sonoma Dusk Alpha

Image input Text input Text output Unavailable
Author's Description

This is a cloaked model provided to the community to gather feedback. A fast and intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling. 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
2M
Released
Sep 05, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Structured Outputs Max Tokens Response Format Tools Tool Choice
Features

This model supports the following features:

Structured Outputs Tools Response Format
Performance Summary

Sonoma Dusk Alpha, a frontier model from openrouter, demonstrates strong overall performance during its testing phase. It performs among the fastest models, ranking in the 79th percentile for speed across benchmarks. While specific cost data is unavailable, its current free usage offers exceptional value. The model exhibits outstanding reliability, achieving a 100% success rate across all benchmarks, indicating consistent and stable operation. Key strengths include perfect accuracy in Keyword Topic Relevance Classification and Ethics, where it also ranks among the top 3 in cost efficiency. Its Mathematics performance is particularly impressive, achieving 94.0% accuracy and ranking #1 in cost efficiency. The model also shows solid performance in General Knowledge and Coding. However, a notable weakness is its performance in Instruction Following and Reasoning, where accuracy falls to the 41st and 40th percentile respectively. Its Hallucinations accuracy is also moderate at 90.0%, suggesting room for improvement in acknowledging uncertainty.

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/sonoma-dusk-alpha 2M $0 / 1M tokens $0 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openrouter