AIHubMixAIHubMix
Models
Qwen3.5 397B A17B
Compare
Qwen logo

Qwen3.5 397B A17B

qwen3.5-397b-a17bllms.txt
Qwen
The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.

Pricing

TierPricingWeb Search
Input<=128K
$0.164$0.986
$0.000548/request
128K<Input<=256K
$0.411$2.466
$0.000548/request

Input Modalities

  • Text
  • Vision
  • Video

Output Modalities

  • Text

Context length

  • 262K tokens

Max output

  • 65.5K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

Alibaba Cloud alicloud-qwen3.5-397b-a17b
Pricing$0.164$0.986
Web Search$0.000548/request
Pricing$0.411$2.466
Web Search$0.000548/request
Context254K
Max output64K
Latency1.3S
Throughput7.4TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today

Performance for qwen3.5-397b-a17b

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="qwen3.5-397b-a17b",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Qwen3.5 397B A17B?

The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect