Ox Alpha
- Score
- 80%
- Price
- Free
- API
- Yes
- Weights
- No
WHAT IT DOES
Ox Alpha is a stealth AI model that appeared on OpenRouter and OpenCode on 20 August 2026. Its creator is unidentified, and OpenRouter routes requests to an anonymous third-party provider. The model accepts text, images and video, outputs text, and supports a 1,048,576-token context window with up to 131,072 tokens of output. Independent serving-layer forensics published on 22 August 2026 point to Zhipu AI's GLM-5.x infrastructure as the leading theory — a Java stack trace naming Zhipu's internal API classes, matching error-code dialects, 30/30 tokenizer alignment with GLM-5.3, and identical video-encoder behaviour to GLM-5V-Turbo. Zhipu has not confirmed this.
WHY WE PICKED IT
The combination of a one-million-token context window, multimodal inputs, free pricing during the preview, and rapid adoption by coding-agent builders makes it worth tracking even before its creator is known. Within a day of launch, coding agents had pushed billions of tokens through it, suggesting real production interest rather than curiosity traffic. Preliminary independent DeepSWE testing also places it ahead of Claude Fable 5 and GPT-5.6 Sol on a small task subset.
QUICK FACTS
STRENGTHS
- ✓1M-token context window
- ✓Free during the preview period
- ✓Accepts text, images and video
- ✓Strong early developer adoption for coding agents
- ✓Available through OpenRouter's OpenAI-compatible API
- ✓Tool calling and structured JSON output supported
LIMITATIONS
- ⚠Creator and provider are unidentified
- ⚠No official benchmarks or model card; available scores are small-sample community tests
- ⚠Prompts and completions may be retained by the anonymous provider
- ⚠Free preview was announced as roughly one week, ending around 27 August 2026, with post-preview pricing unknown
- ⚠Not safe for confidential or proprietary data
- ⚠Zhipu/GLM attribution is forensics-based and unconfirmed
GETTING STARTED
Open the Ox Alpha page on OpenRouter, sign in, and try the playground, or call model ID `stealth/ox-alpha` through the OpenRouter API. OpenCode also offers it through its model catalog with the /models command. Use non-sensitive tasks first.
VIDEO WALKTHROUGH
Embedded creator video selected for this tool.
BENCHMARKS
QUICK TIPS
OFFICIAL LINKS
USE CASE EXAMPLES
Probe a Long Coding Task
Use the large context window to analyse a mid-sized codebase or a long bug report in one session.
- Pick a non-sensitive repository or bug report
- Send the relevant files or trace as a single long context
- Ask for a root-cause analysis and patch plan
- Compare the output against Claude or GPT on the same task
- Note where the model stalls or loops without acting
Benchmark Against a Named Model
Run the same deterministic coding or reasoning task on Ox Alpha and a known frontier model to isolate where the anonymous model wins or loses.
- Choose a non-proprietary task with a verifiable pass criterion
- Run it on Ox Alpha via `stealth/ox-alpha`
- Run it on Claude Fable 5, GPT-5.6 Sol or GLM-5.3
- Score outputs against the same rubric
- Document any systematic differences in tool calling or reasoning depth
PRICING
FEATURED IN GUIDES
CLAUDE.md In Practice: What Actually Earns A Place In The File
The most-starred CLAUDE.md on GitHub has four rules, not twelve, and the error rates everyone quotes...
Open Models: What They Cannot Do
The benchmark gap has largely closed: open models now score within a point of the closed frontier on...
Hardware For Local AI Models: What The Memory Shortage Changed
Capacity decides whether a model runs. Bandwidth decides how fast it talks, and it is the number mos...
How To Run AI Models Locally: Hardware, Quantisation And Engines
Running a frontier open model locally is a memory problem before it is a speed problem, and a bandwi...
Uncensored AI Models: What Abliteration Actually Does To Them
Abliteration removes a model's ability to refuse by deleting one direction from its activations. It ...
EXPLORE ALTERNATIVES
Compare Ox Alpha with 5+ similar llms AI tools.
FREQUENTLY ASKED QUESTIONS
Is Ox Alpha free?
Yes, Ox Alpha is completely free to use.
Does Ox Alpha have an API?
Yes, Ox Alpha offers an API for programmatic integration.
What is Ox Alpha best for?
Ox Alpha is best for Anonymous Preview. Ox Alpha is a stealth AI model that appeared on OpenRouter and OpenCode on 20 August 2026. The combination of a one-million-token context window, multimodal inputs, free pricing during the preview, and rapid adoption by coding-agent builders makes it worth tracking even before its creator is known. Within a day of launch, coding agents had pushed billions of tokens through it, suggesting real production interest rather than curiosity traffic. Preliminary independent DeepSWE testing also places it ahead of Claude Fable 5 and GPT-5.6 Sol on a small task subset.
What platforms does Ox Alpha support?
Ox Alpha supports api, web.
Is Ox Alpha open source?
No, Ox Alpha is not open source.
How do I get started with Ox Alpha?
Open the Ox Alpha page on OpenRouter, sign in, and try the playground, or call model ID `stealth/ox-alpha` through the OpenRouter API. OpenCode also offers it through its model catalog with the /models command. Use non-sensitive tasks first.
How do I use Ox Alpha?
Ox Alpha is a large language model for text generation, analysis, and conversation. Access through the web interface. Enter prompts or questions to get responses. It excels at 1m-token context window.
FEATURED ON CURATEDAI
Work on Ox Alpha? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.
