Model Library/Qwen3 Max
qwen/qwen3-max

Qwen3 Max

合作伙伴

qwen/qwen3-max
Qwen/qwen3-max, Enhanced with specialized upgrades in agent programming and tool calling. This official release achieves domain SOTA performance, supporting more complex agent scenarios.

功能

Serverless API

文档

qwen/qwen3-max is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

可用的 Serverless

立即运行查询,仅按用量付费

输入$2.11 / M Tokens
输出$8.45 / M Tokens

阶梯定价

输入长度输入价格(百万 tokens)输出价格(百万 tokens)
1 <= tokens < 32,768$0.845$3.38
32,768 <= tokens < 131,072$1.4$5.64
131,072 <= tokens < 258,048$2.11$8.45

使用以下代码示例与我们的 API 集成:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="qwen/qwen3-max",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=65536,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

信息

提供商
Qwen
量化
fp8

支持的功能

上下文长度
262144
最大输出
65536
Serverless
支持
Function Calling
支持
Structured Output
支持
输入能力
text
输出能力
text

构建生产级 AI 所需的一切。

200+ 个模型、按需 GPUs 和安全的智能体运行时——统一在一个 API 下。免费开始,随业务增长灵活扩展。