Qwen: Qwen3 VL 30B A3B Thinking✓ Catalog verified
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.
Overview
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.
Access: available through the official Qwen API. Context window: 131K.
Specifications
| API identifier | qwen/qwen3-vl-30b-a3b-thinking |
| Provider | Qwen |
| Model type | Multimodal LLM |
| Context window | 131K catalog |
| Input modalities | text · image |
| Output modalities | text |
| Released | Oct 6, 2025 |
| Tokenizer | Qwen3 |
| Moderated | No |
| Architecture modality | text+image->text |
API defaults
{
"top_k": 20,
"top_p": 0.95,
"temperature": 0.8,
"presence_penalty": null,
"frequency_penalty": null,
"repetition_penalty": 1
}Pricing
Live pricing components for qwen/qwen3-vl-30b-a3b-thinking as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $1.3e-7 | $0.13 / 1M | Per input token |
| Completion tokens | $0.00000156 | $1.56 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.38Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | ✓ Supported | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | ✓ Supported | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Qwen: Qwen3 VL 30B A3B Thinking through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="qwen/qwen3-vl-30b-a3b-thinking",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| AionLabs: Aion-1.0 | Aion Labs | 131K | $4.00 | View → |
| AionLabs: Aion-1.0-Mini | Aion Labs | 131K | $0.70 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Qwen: Qwen3 VL 30B A3B Thinking cost?
$0.13 per 1M input tokens and $1.56 per 1M output tokens on the official Qwen API.
What is the context window of Qwen: Qwen3 VL 30B A3B Thinking?
Qwen: Qwen3 VL 30B A3B Thinking supports up to 131K tokens of context.
Does Qwen: Qwen3 VL 30B A3B Thinking support tool / function calling?
Yes, Qwen: Qwen3 VL 30B A3B Thinking supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Qwen: Qwen3 VL 30B A3B Thinking?
Use the official Qwen API with the model id `qwen/qwen3-vl-30b-a3b-thinking`. See the Quick start section above for code examples.