What Is Ox Alpha?
The evidence, in brief. August 21, 2026.
Best explanation: Zhipu's next-generation unified multimodal GLM
GLM-5.3's tokenizer, the GLM-5V line's video encoder, a stronger base than GLM-5.3 — i.e. an unreleased GLM-5.3V / GLM-5.5, stealth-testing at scale before launch. Confidence ~90%.
The model
stealth/ox-alpha— anonymous, appeared on OpenRouter August 20, 2026, free for one week.- 1,048,576-token context, 131,072 max output, text + image + video input, reasoning model.
- Fifth stealth release in a series; the previous four were all claimed by Chinese labs (Zhipu, Xiaomi, Ant, Meituan).
- Operator claims 100T tokens/day serving capacity; measured decode ~49–78 tokens/sec.
Evidence it's Zhipu
- Video encoder match (strongest). On four controlled test videos, ox-alpha spends token-for-token identical budgets to GLM-5V-Turbo — 296 / 296 / 884 / 1,064 — matching three independent encoder design choices: fps-invariant frame sampling, ~147 tokens/sec duration scaling, and per-frame resolution scaling. Every other candidate we tested (MiMo v2.5, Qwen 3.8 Max, GLM-4.6V) has a clearly different signature.
- Text tokenizer match. Independent fingerprinting found ox-alpha's token counts match GLM-5.3 exactly across 25 diverse prompts, modulo a constant +75-token hidden wrapper — requiring an identical vocabulary, not just shared lineage.
- Audio discriminator. Ox-alpha rejects audio input with the same routing behavior as GLM-5V (no audio endpoints); MiMo v2.5 — the leading rival theory — accepts and tokenizes audio, a headline V2.5 feature it would have had to drop.
- House style. Emoji-decorated syntheses (section emojis, red/yellow/green triage dots, checkmark lists) at ~1.3 emoji per 1,000 chars — the GLM/Qwen signature; Claude, GPT-5.6, and Grok traces on the same machine measure ~0.
- Working style. On DeepSWE, ox-alpha averages 117 agent steps per task — nearly identical to GLM-5.3's leaderboard profile (124), unlike GPT-5.6-sol (61) or Claude (88–99).
- Motive and precedent. Zhipu shipped GLM-5.3 text-only on August 14; a unified vision flagship was the community's top unmet ask. Zhipu has used this stealth channel before (Pony Alpha → GLM-5).
- Size economics. Decode speed within ~6% of GLM-5V-Turbo (744B total / 40B active) implies a ~40B-active MoE — the only size class where a free 100T-tokens/day week is a plausible fleet burn-in rather than fantasy.
Capability check
- DeepSWE (official harness, deterministic 10-task subset): 8/10 Pass@1, both misses near-misses.
- On those exact tasks, the leaderboard models average: Claude Fable 5 65%, GLM-5.3 62%, Grok 4.6 62%, GPT-5.6-sol 52% (4 attempts each).
- It solved
meriyah-explicit-resource-declarationssingle-shot — GLM-5.3, GPT-5.6-sol, and Grok 4.6 went 0/4 on it — while keeping 51,469 regression tests green. - Efficient agentic behavior: in a 69-tool-call orchestration session, one error, zero retry loops, minimal reasoning overhead.
- Implication: stronger than GLM-5.3 on identical tasks — consistent with a next-generation checkpoint, not a variant.
Ruled out
- Xiaomi MiMo — right size class (V2-Pro: 1T/42B, 1M context) and the same stealth playbook, but the video encoder and audio surface both contradict it.
- DeepSeek — no video capability ever shipped, different tokenizer, releases open weights instead of stealth previews.
- Google — tokenizer places ox-alpha in the Chinese-lab lineage despite the Gemini-like 220 context.
- Qwen — different encoder signature; just shipped 3.8 openly.
- xAI / OpenAI / Anthropic — tokenizer, style, and encoder all mismatch.
What settles it
- The free week ends ~August 27; every prior model in this stealth series was claimed at reveal.
- Full methodology, tables, and raw data: the long-form report; probe code in
~/Developer/sandbox/ox-alpha-probe.