← All models
Perceptron: Perceptron Mk1.5NEW
perceptron/perceptron-mk1.5textVisionReasoningVideoAudio
Perceptron's embodied reasoning model for physical agents: text, image, video and audio input, answering with text plus optional structured annotations — points, boxes, polygons, tracks and clips (the annotation_format parameter). Graded reasoning (minimal…high), function tool calling and structured outputs via JSON Schema.
Price in / out
Context / Max output
37K / 8K
Released
Sep 25, 2026
Parameters
messagesrequiredreasoning_effortoff · minimal · low · medium · highmax_tokensoptional · alias max_completion_tokensstreamtrue · falsetoolsfunction calling (OpenAI format)tool_choiceauto · none · requiredweb_search · · · providerrouting: order · only · ignore · sortstream_options{"include_usage": true}image_urlimage (data: URL)Fine-tuning · 5
temperature0–2top_p0–1top_koptionalfrequency_penalty−2…2presence_penalty−2…2How 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="perceptron/perceptron-mk1.5",
messages=[{"role": "user", "content": "Привет"}],
reasoning_effort="minimal", # off · minimal · low · medium · high
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="perceptron/perceptron-mk1.5",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
