← All models
Z.AI: GLM 5.3 FlashXNEW
z-ai/glm-5.3-flashxtextVisionReasoningVideo
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture (320B total parameters, 18B active), it is suited for efficient coding, visual understanding, and long-horizon agent tasks with a 1M-token context window. Accepts text, images and video as input.
Price in / out
Cache, read / write
Context / Max output
1.05M / 131K
Released
Sep 18, 2026
Parameters
messagesrequiredreasoning_effortlow · high · maxmax_tokensoptional · alias max_completion_tokensstreamtrue · falsetoolsfunction calling (OpenAI format)tool_choiceauto · none · requiredresponse_formatjson_object · json_schemaweb_search · · · providerrouting: order · only · ignore · sortstream_options{"include_usage": true}image_urlimage (data: URL)Fine-tuning · 3
temperature0–2top_p0–1top_koptionalHow to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
model="z-ai/glm-5.3-flashx",
messages=[{"role": "user", "content": "Привет"}],
reasoning_effort="low", # low · high · max
temperature=0.7,
max_tokens=1024,
stream=False,
)
print(resp.choices[0].message.content)
# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
model="z-ai/glm-5.3-flashx",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
