# Qwen3.8 Max API Pricing

As of October 10, 2026, Qwen3.8 Max costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on Alibaba Cloud Model Studio, with cache reads at $0.25 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $1.65 to $2.00. It has a 991,808-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/qwen3.8-max
- Lab: Alibaba
- LiteLLM model name: `dashscope/qwen3.8-max`
- Context window: 991,808 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: August 7, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Alibaba Cloud Model Studio | `dashscope/qwen3.8-max` | $2.00 | $6.00 | $0.25 | – | – | 992K |
| AIHubMix | `aihubmix/qwen3.8-max` | $1.69 | $5.07 | $0.169 | – | – | 1M |
| DeepInfra | `deepinfra/Qwen/Qwen3.8-Max` | $1.65 | $4.951 | $0.206 | – | – | 256K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/qwen3p8-max` | $2.00 | $6.00 | $0.25 | – | – | 256K |
| Fireworks AI | `fireworks_ai/qwen3p8-max` | $2.00 | $6.00 | $0.25 | – | – | 256K |
| Novita AI | `novita/qwen/qwen3.8-max` | $2.00 | $6.00 | $0.25 | – | – | 1M |
| Qianwen AI Platform | `qwen_ai_platform/qwen3.8-max` | $2.00 | $6.00 | $0.25 | – | – | 992K |
| QwenCloud | `qwencloud/qwen3.8-max` | $2.00 | $6.00 | $0.25 | – | – | 992K |
| SCX.ai | `scx-ai/Qwen3.8-Max` | $1.65 | $4.99 | $0.21 | – | – | 1M |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Alibaba Cloud Model Studio: $7.00
- DeepInfra: $5.776
- SCX.ai: $5.795
- AIHubMix: $5.915

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Alibaba Cloud Model Studio: $21.20
- DeepInfra: $17.49
- SCX.ai: $17.50
- AIHubMix: $17.91

## Features

Supported: Function calling, Structured output, Image input, Reasoning, Prompt caching, Web search.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="dashscope/qwen3.8-max",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

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

Qwen3.8 Max costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on Alibaba Cloud Model Studio, with cache reads at $0.25 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $1.65 to $2.00.

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

Qwen3.8 Max has a 991,808-token context window and returns up to 131,072 tokens per response.

### Which providers offer Qwen3.8 Max?

Qwen3.8 Max is available from 8 providers through LiteLLM: Alibaba Cloud Model Studio, AIHubMix, DeepInfra, Fireworks AI, Novita AI, Qianwen AI Platform, QwenCloud and SCX.ai. The lowest price is on DeepInfra.

### How do I call Qwen3.8 Max with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="dashscope/qwen3.8-max", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Qwen3.8 Max support?

Qwen3.8 Max supports function calling, structured output, image input, reasoning, prompt caching and web search.

### When did LiteLLM add Qwen3.8 Max?

Qwen3.8 Max was added to LiteLLM's model price file on August 7, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json