Qwen3 Omni 30B A3B Thinking
Qwen3 Omni 30B A3B Thinking is the reasoning version of Alibaba's open omni-modal Qwen3 Omni MoE model, taking text, image, audio and video input and responding in text.
- Input / output price
- $0.25 / $0.97 per 1M
- Context
- 66K tokens
- Released
- Sep 22, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
NovitaRetiring novita/qwen3-omni-30b-a3b-thinking | $0.25/M | $0.97/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.25 per 1M
- Output
- $0.97 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
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 better14tokens/sacross providers
Response latency
Lower is better1.1sacross providers
Benchmarks
6 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 63.2% | huggingface.co | Sep 22, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA Diamondhuggingface.co | 73.1% | huggingface.co | Sep 22, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2025huggingface.co | 73.7% | huggingface.co | Sep 22, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-Reduxhuggingface.co | 88.8% | huggingface.co | Sep 22, 2025 |
| IFEvalhuggingface.co | 85.1% | huggingface.co | Sep 22, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Arena-Hard v2huggingface.co | 55.1% | huggingface.co | Sep 22, 2025 |
Apps
Use Qwen3 Omni 30B A3B Thinking 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 Omni 30B A3B Thinking FAQ
Short answers, built from the data on this page.
Qwen3 Omni 30B A3B Thinking is a model from Qwen, released on Sep 22, 2025. Qwen3 Omni 30B A3B Thinking is the reasoning version of Alibaba's open omni-modal Qwen3 Omni MoE model, taking text, image, audio and video input and responding in text.
On the Respan gateway, Qwen3 Omni 30B A3B Thinking costs $0.25 per 1M input tokens and $0.97 per 1M output tokens on Novita, after gateway discounts.
Qwen3 Omni 30B A3B Thinking is served by Novita.
Qwen3 Omni 30B A3B Thinking accepts up to 66K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-omni-30b-a3b-thinking". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3 Omni 30B A3B Thinking has 6 published benchmark scores, including BFCL-v3 63.2%, GPQA Diamond 73.1%, and AIME 2025 73.7%. 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.