Mystery Model Ox Alpha Appears, Suspected Zhipu GLM Release
Around August 21, an anonymous model named Ox Alpha quietly appeared on OpenRouter and OpenCode—no vendor attribution, no paper, no announcement. It offers a 1 million token context window, multimodal input across text/image/video, nearly a week of free access, and claims zero data retention. Multiple testers have reported stunning performance, and the community widely suspects, based on black-box fingerprinting tests, that it's built on the Zhipu GLM-5.3 architecture, though as of this writing no official claim has been made and its identity remains a mystery.
Confirmed
- Ox Alpha is available on OpenRouter and OpenCode, with a 1M context window and multimodal input; currently free with nearly unlimited quota, and OpenCode claims compute capacity of 100 trillion tokens processed per day
- Scored roughly 80% on the DeepSWE 10-task benchmark, beating GPT-5.6-sol (52%) and Fable (65%)
- @Teknium tested OX Alpha Max in Hermes Bot and called its frontend quality beyond expectations—abnormally intelligent
- @FlunkyGraphics ran three black-box fingerprint tests (tokenizer consistency, etc.) and confirmed Ox Alpha is based on the GLM-5.3 architecture
- @omarsar0 (Elvis) said an informed source confirmed the model's true identity to him (not yet public), describing it as spectacular and saying it will change the expected timeline of the multimodal agent race
Unconfirmed
- The model's owner: the prevailing guess is Zhipu—possibly a GLM-5.3 vision variant, GLM 5.3 Flash, a faster small variant, or even something to be named GLM-6 (a leak relayed by @hunarbatra); @teortaxesTex inferred from speed, TTFT, cache hit rate, and other measurements that it belongs to the GLM family rather than DeepSeek, and said that if it turns out to be a non-Chinese model (e.g., Grok), a reassessment would be needed
- @rickasaurus relayed that the model claims to be Mistral's Le Chaton Fat, which contradicts other evidence and is of questionable credibility
- @trollkhan noted that the claim of SWE scores surpassing Fable matches m9's data, but these are all community tests rather than official benchmarks
Why it matters
If the fingerprint tests hold up, this would be yet another anonymous surprise release from Zhipu's GLM family showcasing frontier coding and agent capabilities. According to @hunarbatra's relayed information, its SWE/Cyber benchmark performance has reached mythical levels—outperforming existing frontier models—and could reshape the multimodal agent landscape; the free, unlimited access also lets developers test and verify it first-hand.
2026-08-21 ~ 2026-08-22 · 37 related posts
- Episode 1: Mystery Model Ox Alpha Appears, Suspected Zhipu GLM Release(2026-08-21, 37 posts)
- Episode 2: Cola Launches Ox Model Claiming Terra-Level Capability at Flash Speed(2026-08-21, 2 posts)
Primary sources
- OpenCode Offers Free Access to Ox Alpha: 1M Context and Multimodal — TJLarkin23 · 2026-08-21
- OpenRouter's stealth model Ox Alpha sparks guesses about Chinese AI vendors — lxfater · 2026-08-21
- Mystery Model Ox Alpha Suspected to be Zhipu GLM — teortaxesTex · 2026-08-21
- New Ox Alpha model leaked with 1M context and multimodal input — External_Mood4719 · 2026-08-21
- Rumor: Ox Alpha is a joint ZAI and GLM model — scaling01 · 2026-08-21
- Stealth Model 'Ox Alpha' Hits 80% on DeepSWE Benchmark — AccBalanced · 2026-08-21
- Speculation suggests OpenAI o1 uses GLM architecture, rivaling Claude — teortaxesTex · 2026-08-21
- Mystery Model OX Alpha Max Impresses with Unlimited Access via OpenRouter — Teknium · 2026-08-21
- Tests suggest O1 Alpha is a GLM-based model with advanced coding capabilities — teortaxesTex · 2026-08-21
- Lab praised for high compute efficiency and rapid model delivery — teortaxesTex · 2026-08-21
- Stealth Model Ox-Alpha Released, Outperforms Fable on SWE Benchmark — troll_khan · 2026-08-21
- Mysterious Lab Expected to Rapidly Deliver Frontier-Level SWE Models — teortaxesTex · 2026-08-21
- Internal Models Strong Yet Rely on Older US Base Models — teortaxesTex · 2026-08-21
- Mystery stealth model 'Ox Alph' appears on OpenRouter, China lab suspected — Neosinic · 2026-08-21
- Ox Alpha open-source model benchmarks near Anthropic level — liminal_bardo · 2026-08-21
- [source] Ox Alpha Stealth Model Leaked with 1M+ Context & Multimodal Capabilities — WorldofAI · 2026-08-21
- Users Praise Mystery Model '0xalpha' as Absurdly Capable — cephaloform · 2026-08-21
- Speculation: ox-alpha Model Might Actually Be GLM 5.3-vision — teortaxesTex · 2026-08-21
- Community bets mystery model Ox Alpha is Zhipu's GLM 5.3 vision variant — teortaxesTex · 2026-08-21
- Ox Alpha on OpenRouter identified as GLM-5.3 variant with alignment tax — airesearch12 · 2026-08-21
- Anonymous "Ox Alpha" model researches, builds and QA's its own site in one prompt — Acceptable-Object390 · 2026-08-21
- [source] Black-box fingerprint confirms Ox Alpha is based on GLM-5.3 — FlunkyGraphics · 2026-08-21
- Ox-alpha solves coding task others failed; GLM-5V matches token count — eyishazyer · 2026-08-21
- Mystery model ox-alpha likely Zhipu's GLM: token fingerprints match GLM-5.3 exactly — eyishazyer · 2026-08-21
- Zhipu's GLM-6 Leaks: reportedly Outperforms Frontier Models in SWE Benchmarks — hunarbatra · 2026-08-21
- Mystery Model OX ALPHA Appears on OpenRouter with Top-Tier Coding Benchmarks and No Filters — heypearlai · 2026-08-21
- OpenRouter's stealth model Ox Alpha sparks guessing game over its identity — AccBalanced · 2026-08-21
- Mystery Model 'Ox Alpha' Appears on OpenRouter with 1M Context — basedjensen · 2026-08-21
- [source] Insider confirms stealth model Ox Alpha is spectacular, resets AGI timelines — omarsar0 · 2026-08-21
- Ox Alpha is a Chinese model — Bindu Reddy bets it's Xiaomi, not GLM — bindureddy · 2026-08-21
- Rumor: Ox Alpha might be based on Zhipu GLM 5.3 Flash — andrew_n_carr · 2026-08-22
- Mystery Model Ox Alpha Review: Near-Fable Performance, Unique Vision/Logic Profile — Afinetheorem · 2026-08-22
- Mystery model 'Ox alpha' appears on OpenRouter and OpenCode — altryne · 2026-08-22
- Mystery Model ox-alpha Leaks: Open Reasoning Traces, No Vision Support — zainhas · 2026-08-22
- Mystery Model OxAlpha Reveals Itself as Mistral's Le Chaton Fat — rickasaurus · 2026-08-22
- Mysterious 'Ox Alpha' model offers 1M context, huge compute claims — udmrzn · 2026-08-22
1 near-duplicate retellings: heypearlai