Qwen3.5 35B A3B inference overview

Price per 1M tokens

$0.25 (input)
$1.25 (output)

Parameters

3B (active)
35B (total)

Context Window

262K

Release Date

Feb 2026

Qwen3.5 35B A3B inference details

Qwen3.5-35B-A3B is a multimodal mixture-of-experts model built for fast, efficient inference across chat, reasoning, coding, agents, and vision-language workloads. With 35B total parameters, 3B active parameters, a 262,144-token context window, and support for 201 languages and dialects, it’s a strong choice for production applications that need long context and broad multimodal capability.

Created by: 

Alibaba

License: 

apache-2.0

Model card: 

				
					import openai
import weave

# Weave autopatches OpenAI to log LLM calls to W&B
weave.init("<team>/<project>")

client = openai.OpenAI(
    # The custom base URL points to W&B Inference
    base_url='https://api.inference.wandb.ai/v1',

    # Get your API key from https://wandb.ai/authorize
    # Consider setting it in the environment as OPENAI_API_KEY instead for safety
    api_key="<your-apikey>",

    # Optional: Team and project for usage tracking
    project="<team>/<project>",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me a joke."}
    ],
)

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

Qwen3.5 35B A3B resources

Screenshot 2025-07-30 at 12.59.45 PM
Guide
Running Qwen3 Coder on W&B Inference
Screenshot 2025-07-30 at 1.03.14 PM
Course
AI engineering course: Agents
Inference_logo
Guide
W&B Inference powered by CoreWeave