# Qwen2.5-Omni 7B

> Qwen2.5-Omni 7B is an open-weight language model from Alibaba (Qwen), released on Dec 2024. It accepts text, images, audio and video and generates text and audio, with a 33K-token context window and up to 2K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.10 per million input tokens and $0.40 per million output tokens (Alibaba Cloud Model Studio), across 1 provider we track.

Source page: https://www.aimodel.directory/models/qwen2-5-omni-7b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** Dec 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Max output:** 2K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Knowledge cutoff:** Apr 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Input:** Text, images, audio and video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Output:** Text and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-omni-7b.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Alibaba Cloud Model Studio | $0.10 | $0.40 | – | 33K |

## FAQ

### What is the context window of Qwen2.5-Omni 7B?

Qwen2.5-Omni 7B has a context window of 32,768 tokens (33K) and can generate up to 2,048 tokens in a single response, according to models.dev.

### How much does the Qwen2.5-Omni 7B API cost?

Through Alibaba Cloud Model Studio, Qwen2.5-Omni 7B costs $0.10 per million input tokens and $0.40 per million output tokens. Prices last verified 4 Oct 2026.

### Is Qwen2.5-Omni 7B open source?

Qwen2.5-Omni 7B is an open-weight model. Check the license terms before commercial use.

### When was Qwen2.5-Omni 7B released?

Alibaba (Qwen) released Qwen2.5-Omni 7B on Dec 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen2.5-Omni 7B", https://www.aimodel.directory/models/qwen2-5-omni-7b