Fast, low-cost sibling of GLM-5.3 for high-volume agentic and chat workloads. Multimodal input.
1 to 16,384 in the playground. For a longer reply, call the API with streaming.
$0.15 per 1M input tokens, $0.03 per 1M cached input tokens, $0.50 per 1M output tokens
Run a prompt to see the reply.