# Qwen3.8 Max

> Qwen3.8 Max is a proprietary language model from Alibaba (Qwen), released on 3 Aug 2026. It accepts text, images, video and PDFs and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $1.65 per million input tokens and $4.95 per million output tokens (DeepInfra), across 3 providers we track.

Source page: https://www.aimodel.directory/models/qwen3-8-max
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 3 Aug 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Context window:** 1M (1,000,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Input:** Text, images, video and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.8-max.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepInfra | $1.65 | $4.95 | $0.21 | 256K |
| Alibaba Cloud Model Studio | $2 | $6 | $0.25 | 1M |
| Fireworks AI | $2 | $6 | $0.25 | 262K |
| Fireworks AI | $2 | $6 | $0.25 | 262K |

## FAQ

### What is the context window of Qwen3.8 Max?

Qwen3.8 Max has a context window of 1,000,000 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.

### How much does the Qwen3.8 Max API cost?

Through Alibaba Cloud Model Studio, Qwen3.8 Max costs $2 per million input tokens and $6 per million output tokens. The lowest listed price is $1.65 input / $4.95 output through DeepInfra. Prices last verified 4 Oct 2026.

### Is Qwen3.8 Max open source?

No. Qwen3.8 Max is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including DeepInfra, Alibaba Cloud Model Studio, Fireworks AI.

### When was Qwen3.8 Max released?

Alibaba (Qwen) released Qwen3.8 Max on 3 Aug 2026, according to models.dev.

### Which providers offer Qwen3.8 Max?

We track Qwen3.8 Max on 3 providers: DeepInfra, Alibaba Cloud Model Studio, Fireworks AI.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3.8 Max", https://www.aimodel.directory/models/qwen3-8-max