{"slug": "glm-5-3-flash-on-amd-gpus-670-tok-s", "title": "GLM 5.3 flash on AMD GPUs 670 tok/s", "summary": "GLM 5.3 Flash is now live on RunInfra running on AMD GPUs, delivering 670 tokens per second on the Vercel AI Gateway at $0.11 per 1M input tokens, $0.45 per 1M output tokens and $0.03 per 1M cached tokens with a 1M token context window. The vendor-native FP8 release keeps the same model and API while adding capacity, and reports a 99.7% cache hit rate over the last 24 hours with cache logs visible in the dashboard. The model supports OpenAI-compatible chat completions and Anthropic-compatible /v1/messages endpoints, text and image input, tool calling, JSON mode and streaming, with zero data retention and no training on customer data.", "body_md": "we spent september rewriting the kernels behind GLM 5.3 Flash. major release is live on RunInfra today\n670 tok/s on Vercel AI Gateway\n$0.11 per 1M input, $0.45 per 1M output, $0.03 per 1M cached. 1M token context. FP8, vendor-native release\nit now runs on AMD. same model, same API, more capacity behind it\n99.7% cache hit rate over the last 24 hours. every hit and miss shows up in your dashboard, so you can track the cache logs yourself\nOpenAI-compatible chat completions and Anthropic-compatible /v1/messages. text and image input, tool calling, JSON mode, streaming\nzero data retention. never used for training", "url": "https://wpnews.pro/news/glm-5-3-flash-on-amd-gpus-670-tok-s", "canonical_source": "https://twitter.com/runinfrai/status/2105186912634057086", "published_at": "2026-09-30 06:57:30+00:00", "updated_at": "2026-09-30 07:17:47.673359+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "ai-chips", "ai-products", "developer-tools"], "entities": ["GLM 5.3 Flash", "RunInfra", "AMD", "Vercel AI Gateway", "OpenAI", "Anthropic"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/glm-5-3-flash-on-amd-gpus-670-tok-s", "markdown": "https://wpnews.pro/news/glm-5-3-flash-on-amd-gpus-670-tok-s.md", "text": "https://wpnews.pro/news/glm-5-3-flash-on-amd-gpus-670-tok-s.txt", "jsonld": "https://wpnews.pro/news/glm-5-3-flash-on-amd-gpus-670-tok-s.jsonld"}}