← All models
Qwen: Qwen 3.8 Max PrimeNEW
qwen/qwen3.8-max-primetextVisionReasoningVideo
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. Same capabilities as Qwen3.8 Max: tool calling, structured outputs and configurable reasoning effort. Accepts text, image and video input, 1M-token context window.
Price in / out
Cache, read / write
Context / Max output
1M / 131K
Released
Sep 23, 2026
Parameters
messagesrequiredreasoning_effortminimal · low · medium · high · xhighmax_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 · 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="qwen/qwen3.8-max-prime",
messages=[{"role": "user", "content": "Привет"}],
reasoning_effort="minimal", # minimal · low · medium · high · xhigh
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="qwen/qwen3.8-max-prime",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
