Don't show again
Qwen3 Max
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.
Features
Serverless API
Docs
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.
On-demand Deployments
Docs
On-demand deployments allow you to use qwen/qwen3-max on dedicated GPUs with high-performance serving stack with high reliability and no rate limits.
Available Serverless
Run queries immediately, pay only for usage
Input$2.11 / M Tokens
Output$8.45 / M Tokens
Tiered pricing
| Input length | Input price (M tokens) | Output Price (M tokens) |
|---|---|---|
| 0 < 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 |
Use the following code examples to integrate with our API:
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)Info
Provider
Qwen
Quantization
fp8
Supported Functionality
Context Length
262144
Max Output
65536
Structured Output
Supported
Function Calling
Supported
Input Capabilities
text
Output Capabilities
text