Alibaba

Qwen3.5 0.8B

About

Qwen3.5 0.8B is a 0.8B open-weight model from Alibaba. Multimodal chat model with up to 64 images or one video per request. It accepts text, images, and video. Context window is 256K. Released February 28, 2026.

Parameters
0.8B
Published parameter count.
Context window
256K
Tokens of context on a request.
License
Apache-2.0
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$0.08
Cached input / 1M	$0.02
Output / 1M	$0.15

Compare

Qwen3.5 0.8B is the smallest of these chat models, at 0.8B, and its published input rate is the lowest, $0.08 / 1M input.

Model	What it does	Price	Parameters	Context
Qwen3.5 0.8B	Multimodal chat model with up to 64 images or one video per request.	$0.08 / 1M input	0.8B	256K
Qwen3.8 27B	Reasoning VLM (image + video + text)	$0.35 / 1M input	27B	164K
Gemini 3.5 Flash Lite	Fastest and cheapest Gemini tier. Multimodal chat; emits no reasoning tokens.	$0.30 / 1M input	—	1M
Gemini 3.7 Flash	Newest Gemini Flash tier with extended reasoning. Multimodal chat + native video.	$0.75 / 1M input	—	1M

Benchmarks

Published scores for Qwen3.5 0.8B, from the Qwen3.5-0.8B model card. Thinking-mode scores.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	MMMU: 49.
Cost and performance	Lower listed rate, mid-pack latency

Performance

Latency is the end-to-end round trip. Throughput is completion tokens divided by that time. It is a request rate, not decode speed.

Latency
40 ms
Throughput
633 tok/s
Requests
1,493

Examples

Counting tennis balls
Qwen3-VL 0.8B answers a counting question on a court photo.
{"answer":"4"}

Supported inputs

textYes
Text-only prompts are accepted.
image_urlYes
Up to 64 per request, read together as one prompt. See Image Inputs.
video_urlYes
One clip. Tune sampling with video_fps, video_max_frames, and video_resolution at the top level. See Video Inputs.
document_urlNo
A document_url part is a 400 capability error. Use an OCR model such as paddleocr/pp-ocrv6 for PDFs.

Default and only method: free-form chat (no method or method_params). response_format={"type":"json_schema"} is supported.
Context window 262,144 tokens (256K).
The larger qwen/qwen3.8-27b shares the same contract.
Weights: Qwen/Qwen3.5-0.8B.

Methods

Methods this model serves. Payload shapes are in the docs.

Method	Returns
chat (default)	The model's reply, verbatim

A chat VLM is pass-through. Text mode returns the reply with no wrapper, even with several images: the model reads them together and produces one reply. JSON mode returns the model's own JSON, with no data envelope. See Methods & Response Format.

Estimate cost

Estimate. An hour of video is 15 frames a minute at 256 tokens a frame, plus the audio in that request, and 500 output tokens a minute.

Hours of video

$32.15

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-0.8b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is happening in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.caption/car.jpg"
                    },
                },
            ],
        }
    ],
)

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

Response

A silver sedan is parked on a sunlit street beside a row of trees.

For video, pass a video_url part and tune sampling with video_fps / video_max_frames. See Video Inputs.