Free stealth reasoning model for coding, agentic work, and multimodal workflows available through OpenRouter
Hardware checker for open AI models
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free
Free
Pricing
$0 per million input tokens, $0 per million output tokens during preview; TryOXAlpha hosted chat offers 5 free guest replies, 15 additional replies after account creation, and 100 AI replies for $4.99 one-time purchase
Not given
Key features
1,048,576-token context window
Multimodal inputs: text, image, and video
Tool calling and structured outputs
Configurable reasoning efforts: low, high, and max
OpenAI-compatible API endpoint
Supported through OpenRouter model ID stealth/ox-alpha
131,072 output tokens maximum
Interactive GPU/Mac checker
Coverage of language, image and video models
Memory estimates from official sources and benchmarks
Runs entirely in browser with no accounts
Open data export under CC BY 4.0
Independent review of data accuracy
Linked sources for all numbers
What makes it different
1M token context window for repository-scale coding tasks
Multimodal support combining code with screenshots and diagrams
Free preview pricing during stealth release
Tool calling and structured output for agentic workflows
Free and independent, no ads or sponsorships
Uses only official sources and published benchmarks
Transparent labeling of estimates vs official measurements