VISION & MULTIMODAL · 紅葉
GLM
3 models from Z.ai, living in Maple Highlands.
| Model | Context | Input | Output | Accepts |
|---|---|---|---|---|
| GLM 5V Turboz-ai/glm-5v-turbo | 203K | $1.20 | $4.00 | text, images, video |
| GLM 4.6Vz-ai/glm-4.6v | 131K | $0.300 | $0.900 | text, images, video |
| GLM 4.5Vz-ai/glm-4.5v | 66K | $0.600 | $1.80 | text, images |
Questions and answers
Which GLM model has the largest context window?
GLM 5V Turbo (Z.ai), with 203K tokens.
Which GLM model is cheapest per input token?
GLM 4.6V, at $0.300 per million input tokens ($0.900 per million output tokens).
Which GLM models accept images?
GLM 5V Turbo, GLM 4.6V, GLM 4.5V (3 of 3).
Which GLM models support reasoning?
GLM 5V Turbo, GLM 4.6V, GLM 4.5V (3 of 3).
Answers are computed from the 2026-10-24 catalog snapshot.