Qwen3.5 397B A17B

Chat Completions

qwen3.5-397b-a17b

Qwen|Created Feb 16, 2026|262.1k context

Chat Completions

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that combines a linear attention mechanism with a sparse mixture-of-experts approach, delivering improved inference efficiency. It achieves state-of-the-art results comparable to top-tier models across a broad range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interaction. Thanks to its strong code-generation and agent capabilities, the model demonstrates solid generalization across a wide variety of agents.

Overview Specifications Activity Performance Uptime Examples

Pricing-50%

Pay-as-you-go rates for this model. More details can be found here.

Input Tokens (1M)

$0.30

Output Tokens (1M)

$1.30

Capabilities

Input Modalities

TextImage

Output Modalities

Text

Supported Parameters

Available parameters for API requests

Frequency PenaltyLogit BiasLogprobsMax Completion TokensPresence PenaltyResponse FormatStopTemperatureTop PReasoning EffortToolsTool Choice

Usage Analytics

Token usage of this model on our platform

Throughput

Time-To-First-Token (TTFT)

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="qwen3.5-397b-a17b",
    messages=[
        {"role": "user", "content": "What's 2+2?"}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)