GLM 5.3 Flash glm-5.3-flash

Z.ai's natively multimodal MoE for fast, low-cost coding and agentic work over a 1M-token context.

From the live catalog

View .md

Input

$0.10 / 1M tokens

Output

$0.35 / 1M tokens

Context

1M tokens

Max output

1M tokens

region SEA quantization nvfp4 reasoning Hugging Face RedHatAI/GLM-5.3-Flash-NVFP4

Inputs

Input	Accepts
`text`	context 1M tokens
`image`	sources url, base64 formats png, jpeg, webp, gif
`file`	sources url, base64 formats application/pdf, text/plain, text/markdown, text/html, text/csv, application/json max size 100 MB
`video`	sources url, base64 formats mp4, webm

Parameters

Streams with stream: true.

Parameter	Type	Values
`temperature`	number	0–2
`top_p`	number	0–1
`frequency_penalty`	number	-2–2
`presence_penalty`	number	-2–2
`max_tokens`	integer	1–1048576 tokens
`stop`	array	up to 4 items
`seed`	integer
`continue_final_message`	boolean
`top_k`	integer	at least 0
`repetition_penalty`	number	0–2
`n`	integer	at least 1
`logprobs`	boolean
`top_logprobs`	integer	0–20
`response_format`	object	type: text, json_object, json_schema
`structured_outputs`	boolean
`reasoning_effort`	string	ultra, max, xhigh, high, medium, low, minimal
`reasoning`	object
`tools`	boolean

Endpoints

POST/v1/chat/completions Create Chat Completion POST/v1/responses Create Response POST/v1/messages Create Message POST/v1/chat/completions/RAG RAG Chat Completion

A request

curl https://api.vultrinference.com/v1/chat/completions \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [
      {
        "role": "system",
        "content": "Answer in one sentence."
      },
      {
        "role": "user",
        "content": "Why is the sky blue?"
      }
    ],
    "max_completion_tokens": 512
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "glm-5.3-flash",
        "messages": [
            {
                "role": "system",
                "content": "Answer in one sentence.",
            },
            {
                "role": "user",
                "content": "Why is the sky blue?",
            },
        ],
        "max_completion_tokens": 512,
    },
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "glm-5.3-flash",
    "messages": [
      {
        "role": "system",
        "content": "Answer in one sentence."
      },
      {
        "role": "user",
        "content": "Why is the sky blue?"
      }
    ],
    "max_completion_tokens": 512
  }),
});
console.log(await response.json());