Qwen3 VL 30B A3B Instruct
Open vision-language MoE model for image and video understanding, documents, and visual agents
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $0.55 → $0.4185
- ↓ lowerInput $0.15 → $0.1046
- ↑ higherOutput $0.43 → $0.55
- ↑ higherInput $0.108 → $0.15
- ↓ lowerOutput $0.52 → $0.43
- ↓ lowerInput $0.13 → $0.108
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestQwen/Qwen3-VL-30B-A3B-Instruct | SiliconFlow (China) | $0.1046 | $0.4185 | $0 | 262K |
| models.devQwen/Qwen3-VL-30B-A3B-Instruct | NEAR AI Cloud | $0.15 | $0.55 | $0.03 | 16K |
| models.devQwen/Qwen3-VL-30B-A3B-Instruct | DeepInfra | $0.15 | $0.6 | $0.015 | 262K |
| models.devdeepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct | Eden AI | $0.15 | $0.6 | $0 | 262K |
| models.devqwen/qwen3-vl-30b-a3b-instruct | Kilo Gateway | $0.15 | $0.6 | $0 | 262K |
| models.devdeepinfra/qwen3-vl-30b-a3b-instruct | LLM Gateway | $0.15 | $0.6 | $0 | 262K |
| models.devqwen/qwen3-vl-30b-a3b-instruct | Merge Gateway | $0.15 | $0.6 | $0.0216 | 131K |
| OpenRouterqwen/qwen3-vl-30b-a3b-instruct | OpenRouter | $0.15 | $0.6 | $0 | 262K |
| models.devqwen3-vl-30b-a3b-instruct | DevPass (LLM Gateway) | $0.15 | $0.6 | $0 | 262K |
| LiteLLMQwen/Qwen3-VL-30B-A3B-Instruct | N/A | $0.15 | $0.6 | $0.015 | N/A |
| LiteLLMQwen3-VL-30B-A3B-Instruct | N/A | $0.15 | $0.6 | $0.015 | N/A |
| LiteLLMaccounts/fireworks/models/qwen3-vl-30b-a3b-instruct | N/A | $0.15 | $0.6 | $0.015 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct | N/A | $0.15 | $0.6 | $0.015 | N/A |
| models.devQwen/Qwen3-VL-30B-A3B-Instruct | Hugging Face | $0.2 | $0.7 | $0 | 131K |
| models.devnovita/qwen3-vl-30b-a3b-instruct | LLM Gateway | $0.2 | $0.7 | $0 | 131K |
| models.devqwen/qwen3-vl-30b-a3b-instruct | Novita AI | $0.2 | $0.7 | $0 | 131K |
| models.devqwen/qwen3-vl-30b-a3b-instruct | Prime Inference | $0.2 | $0.7 | $0 | 262K |
| LiteLLMqwen/qwen3-vl-30b-a3b-instruct | N/A | $0.2 | $0.7 | $0.02 | N/A |
| LiteLLMnovita/qwen/qwen3-vl-30b-a3b-instruct | N/A | $0.2 | $0.7 | $0.02 | N/A |
| models.devQwen/Qwen3-VL-30B-A3B-Instruct | SiliconFlow | $0.29 | $1 | $0 | 262K |
Capabilities
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.