---
id: "z-ai/glm-5.3-flash"
also: ["z-ai/glm-5.3-flash-20260826", "zai-org/GLM-5.3-Flash", "hf/zai-org/GLM-5.3-Flash", "requesty/zai/glm-5.3-flash", "vercel/zai/glm-5.3-flash"]
card_usd_per_m: "0.15 in, 0.5 out, at z-ai/fp8"
cheapest_list_usd_per_m: "0.0375 in, 0.125 out, at pareto on vercel"
cheapest_effective_usd_per_m: "0.0125 in, 0.125 out, at pareto on vercel"
context: 1048576
max_output: 131072
input: ["text", "image", "video"]
output: ["text"]
released: "2026-08-26"
reasoning: ["max", "high", "low"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 105
gateways: "openrouter (56), vercel (31), requesty (11), hf (7)"
no_training: 75
trains: 11
retains_prompts: 21
intelligence: 27.8000
coding: 71.5000
agentic: 50.9000
---
# Z.ai: GLM 5.3 Flash

GLM-5.3-Flash is Z.ai’s native multimodal coding model, featuring 320B total parameters, 18B activated parameters, and a 1M-token context window. Its efficient hybrid attention architecture supports visual coding, tool use, and end-to-end professional workflows across code, browsers, documents, and graphical interfaces.