Qwen3 VL 30B A3B Instruct
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal 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.
- Input / output price
- $0.15 / $0.60 per 1M
- Context
- 262K tokens
- Released
- Oct 4, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/qwen3-vl-30b-a3b | $0.15/M | $0.60/M |
DeepInfra deepinfra/qwen3-vl-30b-a3b-instruct | $0.15/M | $0.60/M |
Novita novita/qwen3-vl-30b-a3b-instruct | $0.20/M | $0.70/M |
OpenRouter openrouter/qwen3-vl-30b-a3b-instruct | $0.15/M | $0.60/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.16 per 1M
- Average output
- $0.63 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better12tokens/sacross providers
Response latency
Lower is better1.1sacross providers
Benchmarks
7 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBencharxiv.org | 42.6% | arxiv.org | Nov 27, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA Diamondarxiv.org | 70.4% | arxiv.org | Nov 27, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalarxiv.org | 85.8% | arxiv.org | Nov 27, 2025 |
| MMLU-Proarxiv.org | 77.8% | arxiv.org | Nov 27, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Arena-Hard v2arxiv.org | 58.5% | arxiv.org | Nov 27, 2025 |
Apps
Use Qwen3 VL 30B A3B Instruct in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen3 VL 30B A3B Instruct FAQ
Short answers, built from the data on this page.
Qwen3 VL 30B A3B Instruct is a model from Qwen, released on Oct 4, 2025. Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal 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.
On the Respan gateway, Qwen3 VL 30B A3B Instruct costs from $0.15 per 1M input tokens and $0.60 per 1M output tokens on Concentrate, DeepInfra, and OpenRouter, after gateway discounts. Averaged across its 4 providers, it costs $0.16 per 1M input tokens and $0.63 per 1M output tokens.
Qwen3 VL 30B A3B Instruct is available through 4 providers: Concentrate, DeepInfra, Novita, and OpenRouter.
Qwen3 VL 30B A3B Instruct accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-vl-30b-a3b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3 VL 30B A3B Instruct has 7 published benchmark scores, including LiveCodeBench 42.6%, BFCL-v3 66.3%, and GPQA Diamond 70.4%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.