Sonoma Sky Alpha

Image input Text input Text output Unavailable
Author's Description

This is a cloaked model provided to the community to gather feedback. A maximally 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:

Reasoning Structured Outputs Max Tokens Response Format Include Reasoning Tools Tool Choice
Features

This model supports the following features:

Structured Outputs Tools Reasoning Response Format
Performance Summary

Sonoma Sky Alpha, a frontier model from openrouter, demonstrates strong overall performance during its testing period. While its speed performance is competitive, ranking in the 47th percentile across benchmarks, specific pricing data is unavailable as it is currently free to use. A standout feature is its exceptional reliability, achieving a 100% success rate across all 15 benchmarks, indicating robust technical stability. The model excels in classification tasks, consistently achieving perfect 100% accuracy in Keyword Topic Relevance Classification and high accuracy in Email Classification (99.0%). It also shows perfect accuracy in Ethics, Hallucinations, General Knowledge, and Reasoning benchmarks, often ranking as the most accurate among models of similar speed or cost efficiency. In coding, Sonoma Sky Alpha performs well, with accuracies ranging from 91.4% to 93.9%, placing it in the 77th to 90th percentile. Its instruction following capability is solid at 72.4% accuracy. The model's primary strength lies in its high accuracy across a broad range of cognitive tasks, particularly in areas requiring semantic understanding, ethical reasoning, and factual recall, often achieving perfect scores. Its main area for potential improvement appears to be in processing speed, as its duration percentiles are generally lower, though still competitive.

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