← All models
MiniMax: MiniMax M3
minimax/minimax-m3textVisionReasoningVideo
MiniMax multimodal foundation model: fast and inexpensive, 1M context and up to 512k output. Suited for long-horizon agentic work, coding and large documents. Image input.
Price in / out
Cache, read / write
Context / Max output
524K / 512K
Released
May 31, 2026
Additional rates
Flex, in / out
Parameters
messagesrequiredmax_tokensoptional · alias max_completion_tokensstreamtrue · falsetoolsfunction calling (OpenAI format)tool_choiceauto · none · requiredresponse_formatjson_object · json_schemaweb_search · · · providerrouting: order · only · ignore · sortservice_tierflexstream_options{"include_usage": true}image_urlimage (data: URL)Fine-tuning · 11
temperature0–2stopoptionalseedoptionaltop_p0–1top_koptionalmin_p0–1frequency_penalty−2…2presence_penalty−2…2repetition_penalty0–2logprobstrue · 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="minimax/minimax-m3",
messages=[{"role": "user", "content": "Привет"}],
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="minimax/minimax-m3",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
# эконом-тир: тот же ответ вдвое дешевле, но ниже приоритет в очереди
cheap = client.chat.completions.create(
model="minimax/minimax-m3",
messages=[{"role": "user", "content": "Привет"}],
extra_body={"service_tier": "flex"},
)
