vision · Jan 2025
Qwen2.5-VL 72B
Proven vision-language model for OCR, document QA, and visual grounding.
By Alibaba · Text + Vision · Apache 2.0
Model details
Specs & substance
Spec sheet
Developed byAlibaba
Model familyQwen
Categoryvision
ModalityText + Vision
Context window128K tokens
ArchitectureDense VL
VersionVL 72B
LicenseApache 2.0
Pricing$0.80 in$1.00 out · $0.40 cache
ReleasedJan 2025
Endpointparasail-qwen25-vl-72b-instruct
Proven vision-language model for OCR, document QA, and visual grounding.
Qwen2.5-VL 72B is part of the Qwen family by Alibaba, categorized as a vision model. It supports a 128K tokens context window and is built on a Dense VL architecture.
Key strengths: vision, document. Parasail serves Qwen2.5-VL 72B 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 · Qwen2.5-VL 72B
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-qwen25-vl-72b-instruct",
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 · Qwen2.5-VL 72B
curl https://api.parasail.io/v1/chat/completions \
-H "Authorization: Bearer $PARASAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "parasail-qwen25-vl-72b-instruct",
"messages": [{"role": "user", "content": "Hello, what can you do?"}],
"stream": true,
"max_tokens": 1000
}'More models