Model Library
AlibabaReleased September 22, 2025Qwen3 Omni 30B A3B
Alibaba · Released September 22, 2025
Intelligence score
5
At a glance
- Intelligence
- 5
- Speed
- 93.0tokens/sec
- Latency
- 2.08stime to first token
- Input price
- $0.25per 1M tokens
- Output price
- $0.97per 1M tokens
- Context window
- 66Ktokens
- Parameters
- 35.3billions
Summary
Comparison summary
Qwen3 Omni 30B A3B Instruct scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6). Qwen3 Omni 30B A3B Instruct generates output at 93.0 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3 Omni 30B A3B Instruct costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.97 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 Omni 30B A3B |
|---|---|
| Provider | Alibaba |
| Release date | September 22, 2025 |
| Intelligence score | 5 |
| Speed | 93.0 tokens/sec |
| Latency (TTFT) | 2.08s |
| Input price | $0.25 / 1M tokens |
| Output price | $0.97 / 1M tokens |
| Context window | 66,000 tokens |
| Parameters | 35.3B |
| Reasoning | No |
| Input modalities | text, image, audio, video |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-omni-30b-a3b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 Omni 30B A3B, as listed in the catalog record
- Input$0.25
- Output$0.97
| Token type | Price per 1M |
|---|---|
| Input | $0.25 |
| Output | $0.97 |
Model Intelligence legacy profile: qwen3-omni-30b-a3b-instruct
FAQ · 20
Frequently asked questions
Qwen3 Omni 30B A3B Instruct was released on September 22, 2025.
Qwen3 Omni 30B A3B Instruct was created by Alibaba.
Qwen3 Omni 30B A3B Instruct scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6).
Qwen3 Omni 30B A3B Instruct generates output at 93.0 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Qwen3 Omni 30B A3B Instruct has a time to first token (TTFT) of 2.08s (based on Alibaba's API), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Qwen3 Omni 30B A3B Instruct costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.97 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Qwen3 Omni 30B A3B Instruct costs $0.25 per 1M input tokens and $0.97 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.32 per 1M tokens. Pricing may vary by provider.
No, Qwen3 Omni 30B A3B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Omni 30B A3B Instruct supports text, image, speech, and video input.
Qwen3 Omni 30B A3B Instruct supports text and speech output.
Yes, Qwen3 Omni 30B A3B Instruct supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3 Omni 30B A3B Instruct is multimodal. It can process text, image, speech, and video input and generate text and speech output.
Qwen3 Omni 30B A3B Instruct has a context window of 66k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 Omni 30B A3B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Omni 30B A3B Instruct has 35.3 billion parameters (3 billion active).
Qwen3 Omni 30B A3B Instruct is a Mixture of Experts (MoE) model with 35.3 billion total parameters, but only 3 billion active parameters are used during inference.
Qwen3 Omni 30B A3B Instruct is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 Omni 30B A3B Instruct achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Omni 30B A3B Instruct is available via API through 1 provider.
Qwen3 Omni 30B A3B Instruct is available through 1 API provider.