---
id: "z-ai/glm-4.6v"
also: ["z-ai/glm-4.6-20251208", "zai-org/GLM-4.6V", "hf/zai-org/GLM-4.6V", "vercel/zai/glm-4.6v"]
card_usd_per_m: "0.3 in, 0.9 out, at z-ai/fp8"
cheapest_list_usd_per_m: "0.3 in, 0.9 out, at novita/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.227 in, 0.899 out, at z-ai/fp8 on openrouter"
context: 131072
max_output: 32768
input: ["image", "text", "video"]
output: ["text"]
released: "2025-12-08"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 4
gateways: "openrouter (2), hf (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Z.ai: GLM 4.6V

GLM-4.6V series are Z.ai’s iterations in a multimodal large language model. GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales.