Z.ai: GLM 4.6V

GLM 4.6V is a multimodal model from Z.ai that accepts text, images, and video as input, with a 131,072-token context window and a maximum of 32,768 output tokens. It supports tool use and reasoning, which makes it capable of agentic and multi-step workflows. Structured output support is unconfirmed, so developers who depend on guaranteed JSON schemas should verify that independently before committing. At $0.30 per million input tokens and $0.90 per million output tokens, the pricing is competitive for a model handling video alongside text and images. However, its blended benchmark score of 16.8 across only one independent benchmark offers a limited basis for quality comparison, so performance claims should be treated as provisional. Teams processing multimodal content on a moderate budget may find it worth evaluating, but those prioritizing well-documented quality should wait for broader benchmark coverage before relying on it for critical workloads.