GLM 5.3 flash on AMD GPUs 670 tok/s

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.

we spent september rewriting the kernels behind GLM 5.3 Flash. major release is live on RunInfra today 670 tok/s on Vercel AI Gateway $0.11 per 1M input, $0.45 per 1M output, $0.03 per 1M cached. 1M token context. FP8, vendor-native release it now runs on AMD. same model, same API, more capacity behind it 99.7% 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 OpenAI-compatible chat completions and Anthropic-compatible /v1/messages. text and image input, tool calling, JSON mode, streaming zero data retention. never used for training