MiniMax M2.7是第一个模型深度参与迭代自己的模型。 M2.7 能够自行构建复杂 Agent Harness,并基于 Agent Teams、复杂 Skills、Tool Search Tool 等能力,完成高度复杂的生产力任务。例如,在研发M2.7的过程中,我们基于模型构建强化学习Harness 中的数十个复杂的 skills,更新自己的 memory,驱动模型自身的强化学习,并基于结果优化强化学习过程和Harness,开启模型的自我进化。
from openai import OpenAI
client = OpenAI(
base_url="https://api.openroute.cn/v1",
api_key="<ONTOROUTE_API_KEY>",
)
completion = client.chat.completions.create(
model="minimax/MiniMax-M2.7",
messages=[
{
"role": "user",
"content": "Write a one-sentence bedtime story about a unicorn.",
}
],
)
print(completion.choices[0].message.content)暂无调用数据
Prices are CNY (¥) per million tokens, billed as you go. Cache reads can cut the cost of repeated context.
| Provider | Input | Output | Cache read | Context length | Latency | Uptime | Status |
|---|---|---|---|---|---|---|---|
openai minimax/minimax-m2.7 | ¥1.68 | ¥5.04 | — | 205K | — | 0.00% | Lowest |
minimax minimax/MiniMax-M2.7 | ¥2.10 | ¥8.40 | Supported | 205K | 765ms | 0.00% |
This model does not publish tunable parameters.