compact · May 2026
Qwen3.5 35B-A3B
Compact MoE model with strong reasoning at minimal cost per token.
By Alibaba · Text · Apache 2.0
Model details
Specs & substance
Spec sheet
Developed byAlibaba
Model familyQwen
Categorycompact
ModalityText
Context window128K tokens
ArchitectureMoE 3B active
Version3.5
LicenseApache 2.0
Pricing$0.15 in$1.00 out · $0.05 cache
ReleasedMay 2026
Endpointparasail-qwen3p5-35b-a3b
Compact MoE model with strong reasoning at minimal cost per token.
Qwen3.5 35B-A3B is part of the Qwen family by Alibaba, categorized as a compact model. It supports a 128K tokens context window and is built on a MoE 3B active architecture.
Key strengths: efficient. Parasail serves Qwen3.5 35B-A3B on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.
Integrate
Drop-in via the OpenAI SDK
Point any OpenAI-compatible chat client at Parasail and change the model name. That's it.
pythonparasail · Qwen3.5 35B-A3B
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.parasail.io/v1"
)
response = client.chat.completions.create(
model="parasail-qwen3p5-35b-a3b",
messages=[
{"role": "user", "content": "Hello, what can you do?"}
],
stream=True,
stream_options={"include_usage": True},
top_p=1,
max_tokens=1000,
temperature=1
)
for chunk in response:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)bashparasail · Qwen3.5 35B-A3B
curl https://api.parasail.io/v1/chat/completions \
-H "Authorization: Bearer $PARASAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "parasail-qwen3p5-35b-a3b",
"messages": [{"role": "user", "content": "Hello, what can you do?"}],
"stream": true,
"max_tokens": 1000
}'More models