← All guides

What is Ox Alpha?

A free, anonymous coding model with a 1M-token context window appeared on OpenRouter and OpenCode, shot to #1, and has now been confirmed as Zhipu's GLM-5.3-Flash. Here's a plain-English rundown of what Ox Alpha is, how good it actually is, the catch nobody mentions, and how to run it (or any model) in a real agent.

TL;DR: Ox Alpha was a stealth (anonymous) AI model tuned for coding and long-running agentic work, with a 1M-token context window. It launched free for a limited time on OpenRouter (Aug 20, 2026) and later on OpenCode, then rocketed to #1 on OpenRouter. On August 26, 2026, Z.AI (Zhipu) confirmed to Bloomberg that Ox Alpha is GLM-5.3-Flash — a 320B-A18B model released under an MIT license, priced at $0.15/$0.50 per million tokens now that the free preview is over. It benchmarks strongly on coding and front-end generation. The catch during the free window: it retained prompts, so people were warned not to send secrets. The cleanest way to run it (or any model) is through an agent that lets you plug in any OpenAI-compatible endpoint and switch models in a click.
Now confirmed: GLM-5.3-Flash · 1M context · 131K output · MIT
The mystery coding model that read a million tokens — now confirmed as Zhipu's GLM-5.3-Flash.
1Mtokens of context
131Kmax output tokens
3input modalities · text · image · video
$0free to try (preview)
Update (Aug 26, 2026): the mystery is solved. Z.AI (Zhipu) confirmed to Bloomberg that Ox Alpha is GLM-5.3-Flash — a 320B-A18B model released under an MIT license, with open weights. The free preview has ended; the API now lists at roughly $0.15 / $0.50 per million input/output tokens. The rest of this guide explains what it is, how it performs, and how to run it (or any model) inside a coding agent.

Ox Alpha in one sentence

Ox Alpha is an anonymous "stealth" AI model built for coding, sustained agentic work, and complex reasoning, with a 1M-token context window. It appeared without an announced vendor — first on OpenRouter around August 20, 2026, then as a free limited-time model inside OpenCode — and quickly climbed the trending lists because it's both strong at code and free to use.

Where it came from (and who's really behind it)

Stealth models are usually a way for a lab to A/B a new release under a codename before attaching its brand. Ox Alpha followed that pattern exactly: no official vendor at launch, a fresh model ID on OpenRouter, and a burst of "what is this thing" posts. The community quickly guessed it was a Zhipu / GLM-family model from its behavior, benchmark shape, and routing — and that guess turned out to be right.

On August 26, 2026, Z.AI (Zhipu) confirmed to Bloomberg that Ox Alpha is a new GLM-series model, and the official name landed the same evening: GLM-5.3-Flash — a 320B-A18B (mixture-of-experts) model released under an MIT license with open weights. During its four-day free preview, Ox Alpha climbed to #1 on OpenRouter, more than doubling DeepSeek's usage, which is a rare thing for a brand-new stealth model. So the identity is no longer a mystery: it's GLM-5.3-Flash, and you can now run it either through hosted APIs or the open weights themselves.

Ox Alpha at a glance

PropertyValue
Real identityGLM-5.3-Flash (Z.AI / Zhipu) — confirmed Aug 26, 2026
Model ID (preview)stealth/ox-alpha on OpenRouter
Architecture320B-A18B (mixture-of-experts), MIT license, open weights
Context / max output1,048,576 tokens in · 131,072 tokens out
ModalitiesText, image, video in → text out
Tool callingSupported
Throughput / latency~50 tok/s · ~2s P50 (OpenRouter dashboard, preview)
LaunchedOpenRouter (Aug 20, 2026), then OpenCode as free limited-time
StrengthsCoding, agentic loops, front-end UI generation, long-context
Price now~$0.15 / $0.50 per 1M input/output tokens (free preview ended)

Is Ox Alpha actually good?

The early reports are genuinely positive for a free model. It scores well on coding benchmarks (DeepSWE-style tasks in the ~80% range in some tests), handles long files thanks to the huge context window, and gets singled out for clean front-end / UI generation. For everyday coding and agent work it's very usable. As always with stealth models, benchmarks are early and can shift once the model is finalized and priced.

Ox Alpha vs. today's frontier models — coding tasks solved

1
Ox Alpha80%GLM-5.3-Flash · 8 of 10 solved
2
Fable 565%Anthropic · fable-5 [max]
3
GLM-5.3open62%Zhipu · same family as Ox Alpha
4
Grok 4.662%xAI · grok-4.6 [xhigh]
5
GPT-5.652%OpenAI · gpt-5.6-sol [max]

% of tasks solved on an independent community benchmark of 10 real-world coding tasks (as published on the official oxalpha.com, 2026). Reference models scored as passes out of 4 attempts per task; Ox Alpha (GLM-5.3-Flash) solved 8 of 10 — ahead of every frontier model it was lined up against, including one task no reference model could reliably pass. Small third-party sample: directional, not definitive. Benchmarks shift monthly; treat any single ranking as a snapshot.

Context window vs. typical models

Ox Alpha — 1,000K tokens1M
Typical frontier model — 200K200K
Older 128K models128K

A 1M-token window means Ox Alpha can hold roughly an entire mid-size codebase (or a very long agent run) in context at once — the headline reason it trended for agentic work.

The catch during the free preview: as a free stealth model, Ox Alpha retained prompts — the usual price of "free early access," where you help the vendor with data. Now that it's the named GLM-5.3-Flash, retention depends on how you call it (a hosted API vs. self-hosting the open weights). Either way, the safe habit stands: don't paste secrets, credentials, or proprietary code you can't afford to leak into any free/hosted model.

How to run Ox Alpha in a coding agent

Ox Alpha is exposed through OpenAI-compatible routes (OpenRouter / OpenCode-style endpoints), so any agent that lets you set a base URL, a key, and a model name can drive it. The friction with a lot of tools is that they're welded to one provider — to try a new model you're editing env vars or waiting for official support. The smoother path is an agent where the provider, base URL, key, and model are just settings you pick from a list.

Point an agent at Ox Alpha

  1. Get an endpoint + keyGrab an OpenAI-compatible endpoint that serves Ox Alpha (e.g. via OpenRouter) and an API key.
  2. Set base URL + keyIn your agent, set the base URL to that endpoint and paste the key. No translating proxy needed for OpenAI-compatible providers.
  3. Select the modelSet the model identifier the provider exposes for Ox Alpha, then run your normal coding tasks.
  4. Keep secrets outBecause it's a free stealth model that may log prompts, don't feed it anything sensitive.

The cleaner way to try any stealth model

If your goal is "I want to test Ox Alpha today and switch to something else tomorrow without re-plumbing my setup," use an agent built to bring your own model. Wuwei is a free, open-source (MIT) AI coding agent that runs locally: you pick the provider, base URL, key, and model from a list, so trying a new stealth model — or falling back to Claude / GPT / a local model — is a click, not a config rewrite. Your code stays on your machine, which matters even more when the model on the other end might be logging.

FAQ

What is Ox Alpha?

Ox Alpha is an anonymous "stealth" AI model tuned for coding and agentic work, with a 1M-token context window. It launched free for a limited time on OpenRouter in August 2026 and later on OpenCode.

Is Ox Alpha GLM-5.3?

Yes — on August 26, 2026, Z.AI (Zhipu) confirmed to Bloomberg that Ox Alpha is GLM-5.3-Flash, a 320B-A18B mixture-of-experts model released under an MIT license with open weights. It launched anonymously as the stealth model "ox-alpha" on OpenRouter, hit #1 during its free preview, and was then revealed.

Is Ox Alpha free?

It was free during its limited-time preview on OpenRouter and OpenCode (Aug 2026), which retained prompts — so people were told not to send secrets. Now that it's revealed as GLM-5.3-Flash, the API lists at roughly $0.15 / $0.50 per million input/output tokens, and the open weights (MIT) can be self-hosted for free.

How do I use Ox Alpha in a coding agent?

It's served over OpenAI-compatible endpoints, so any agent that lets you set a base URL, key, and model can run it. Wuwei is a free, open-source agent where you pick the provider and model from a list, so you can point it at Ox Alpha (or any model) without editing env vars.

Want to try Ox Alpha — or any new stealth model — without re-wiring your setup each time? Wuwei is a free, open-source AI coding agent that runs locally and lets you bring any model: pick the provider, base URL, key, and model from a list and switch in a click, while your code stays on your machine.

Windows · macOS · Linux — free, no login