IQ Routing, a new AI gateway, claims to cut LLM call costs by 40 to 80 percent by routing each request to the cheapest model that meets a quality bar, with a five-step LangChain loop example dropping …
A developer built Vancine, a smaller OpenAI-compatible API focused on current Chinese frontier models from Qwen, Kimi, GLM, MiniMax, and DeepSeek, as an alternative to OpenRouter's broad catalog. The …
Z.ai confirmed that Ox Alpha is a new GLM-series model and will release its weights, potentially enabling self-hosting and inspection rather than API-only access. The model reportedly offers capabilit…
A developer testing the anonymous coding model Ox Alpha on OpenRouter found it remarkably fast at turning a frontend specification into a working interface, but the model became inaccessible the next …
A developer running an automated content pipeline on a Mac mini with 48GB of unified memory switched from a cloud LLM API to a local model after the provider's free tier rate limit dropped from 60 to …
Z.ai, the Chinese AI lab behind the GLM series, confirmed that the mysterious open-weight model Ox Alpha, which topped OpenRouter benchmarks, is the newest iteration of its GLM series. The company wil…
Z.AI, the Beijing AI lab co-founded by Zhang Peng, confirmed to Bloomberg on August 26 that the anonymous Ox Alpha model is a new iteration of its GLM series and plans to release its weights that nigh…
Ox Alpha, a model that appeared on OpenRouter on August 20, is behaviorally fingerprinted as part of the GLM family, with an exact 11-of-11 tokenizer match to the GLM-5.x vocabulary. The model censors…
A developer ran a week of real open source work on Ox Alpha, a free mystery coding model that appeared on OpenRouter under the identifier stealth/ox-alpha with no company attribution. The model handle…
FreeToken, a local inference tool, enables running mixture-of-experts models with over 290 billion parameters on a single consumer GPU by streaming only active experts from system RAM, avoiding the ne…
FreeToken, a new serving tool, enables running frontier mixture-of-experts (MoE) models with hundreds of billions of parameters on a single consumer GPU by keeping most experts in system RAM and strea…
Ox Alpha, an anonymous stealth AI model available for free on the Open Code coding agent platform, features a 1 million token context window, multimodal support, and a zero data retention claim, scori…
OX Alpha, a mysterious LLM on OpenRouter, has been identified as GLM developed by Z.ai through prompt injection and gzip-NCD compression analysis. The model's system prompt, extracted via a word-count…
Drew Breunig, in a blog post titled 'Fable & The End of the Free Lunch,' argues that Anthropic's Claude model 'Fable' marks the end of the era where new AI models automatically improve coding workflow…
A client-side fingerprinting engine identifies AI models deterministically by analyzing infrastructure artifacts such as tokenizer vocabularies, template offsets, error taxonomy, and response serializ…
A model-pinning policy is the one page that stops a production automation from changing behavior because a vendor changed what a name points to. The policy, published by the blog, covers five vendors—…
Chinese AI models are closing the gap with U.S. rivals in cost-effectiveness and quality, according to tests where seven Chinese models built a coffee shop website, challenging the dominance of U.S. f…
A developer's six-week, data-backed comparison of US and Chinese AI models reveals that Chinese models like DeepSeek V4 Flash and Qwen3-32B offer comparable quality at a fraction of the cost, with out…
A developer's comparison of Chinese and US AI APIs in 2026 reveals that Chinese models like DeepSeek V4 Flash offer comparable performance to GPT-4o at a fraction of the cost, with output tokens price…
An architect's load tests of 47 million requests through DeepSeek, Qwen, Kimi, and GLM via Global API's unified endpoint found DeepSeek V4 Flash offers the best price-to-quality ratio, holding 60 toke…