← All models
Z.AI: GLM 5.3 PrimeNEW
z-ai/glm-5.3-primetextReasoning
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. Coding and agentic workloads, long-horizon multi-turn agent orchestration, streaming code generation and real-time conversation. 1M-token context, up to 128K output tokens.
Price in / out
Cache, read / write
Context / Max output
1M / 131K
Released
Sep 23, 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}Fine-tuning · 9
temperature0–2stopoptionalseedoptionaltop_p0–1top_koptionalfrequency_penalty−2…2presence_penalty−2…2logprobstrue · falsetop_logprobs0–20How 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-prime",
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-prime",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
