# Qwen 3.8 Max API pricing

ALIBABA QWEN / TEXT

> Qwen 3.8 Max via one OpenAI-compatible key: $1.44 in / $4.32 out per 1M tokens. Model ID qwen3.8-max, base URL https://api.outrun.to/v1.

From $1.44 in / $4.32 out per 1M tokens

Qwen 3.8 Max costs $1.44 per 1M input tokens and $4.32 per 1M output tokens (cached input $0.18). Other context tiers are listed in the price table. Call it with model ID `qwen3.8-max` at `https://api.outrun.to/v1` using one prepaid Outrun key. Prices as of October 30, 2026.

`qwen3.8-max`OpenAI compatibleVision

USD / 1M TOKENS

## How much does Qwen 3.8 Max cost per 1M tokens?

[Get a key ↗](https://outrun.to/overview)

with cache_control

| Token type | Outrun |
| --- | --- |
| Input | **$1.44** |
| Cached input | **$0.18** |
| Cache write | **$1.80** |
| Output | **$4.32** |

standard

| Token type | Outrun |
| --- | --- |
| Input | **$1.44** |
| Cached input | **$0.18** |
| Cache write | **$1.44** |
| Output | **$4.32** |

Billed prices, rounded up to the cent. Prices as of October 30, 2026.

Context window

1,000,000 tokens

Max output

131,072 tokens

Input

Text + images

## What is Qwen 3.8 Max?

Qwen 3.8 Max is a text model in the Outrun catalog. Its developer describes it for coding, research and long-horizon workflows. The standard rate is $1.44 in / $4.32 out per 1M tokens.

## What are the Qwen 3.8 Max model details?

| Model detail | Value |
| --- | --- |
| Developer | Alibaba |
| Kind | Text |
| Parameters | 2.4T total / 95B active |
| Developer context | 1,000,000 tokens |
| Developer input | Text, Images, Video |
| Released | 2026-08-03 |

## How do I call Qwen 3.8 Max?

Use your Outrun key and the exact model ID. Requests use prepaid USD credit.

cURL

```
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen3.8-max",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 8192
}'
```

Python · OpenAI SDK

```
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
)
reply = client.chat.completions.create(
    model="qwen3.8-max",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=8192,
)
print(reply.choices[0].message.content)
```

## Which tools work with Qwen 3.8 Max?

Any client that accepts an OpenAI-compatible base URL and a model ID can use `qwen3.8-max`. Setup guides: [Cline (OpenAI Compatible)](https://outrun.to/docs/setup/cline), [OpenCode](https://outrun.to/docs/setup/opencode), [SillyTavern](https://outrun.to/docs/setup/sillytavern), [LiteLLM](https://outrun.to/docs/setup/litellm).

Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.

| Set this value | Value |
| --- | --- |
| API format | `OpenAI compatible` |
| Base URL | `https://api.outrun.to/v1` |
| Model ID | `qwen3.8-max` |

| Capability | Supported |
| --- | --- |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning | Yes |
| Structured output | Yes |
| Parallel tools | Yes |
| Image input | Yes |
| Roo Code ready | No |

## How does Qwen 3.8 Max compare on cost?

| Model | Input / output | 1,000 chat turns |
| --- | --- | --- |
| [Qwen 3.8 Flash](https://outrun.to/model/qwen3.8-flash) | $0.10 / $0.33 | $0.20 |
| [Qwen 3.7 Plus](https://outrun.to/model/qwen3.7-plus) | $0.29 / $1.14 | $0.63 |
| [Qwen 3.7 Max](https://outrun.to/model/qwen3.7-max) | $1.44 / $4.32 | $2.74 |
| [Qwen 3.8 Max](https://outrun.to/model/qwen3.8-max) This model | $1.44 / $4.32 | $2.74 |

Assumes 1,000 input + 300 output tokens per turn, repeated 1,000 times, at standard-tier rates without caching. Input / output shown per 1M tokens, rounded up to the cent.

## Which similar models can I try?

[Alibaba Qwen Qwen 3.7 Max $1.44 in / $4.32 out View model ↗](https://outrun.to/model/qwen3.7-max)[Alibaba Qwen Qwen 3.7 Plus $0.29 in / $1.14 out View model ↗](https://outrun.to/model/qwen3.7-plus)[Alibaba Qwen Qwen 3.8 Flash $0.10 in / $0.33 out View model ↗](https://outrun.to/model/qwen3.8-flash)

## Common questions about Qwen 3.8 Max

### How much does the Qwen 3.8 Max API cost?

Qwen 3.8 Max costs $1.44 per 1M input tokens and $4.32 per 1M output tokens (cached input $0.18). Other context tiers are listed in the price table. Prices as of October 30, 2026.

### What model ID and base URL do I use for Qwen 3.8 Max?

Use the model ID `qwen3.8-max` with the base URL `https://api.outrun.to/v1` and your Outrun API key.

### Does Qwen 3.8 Max accept images?

Yes. Qwen 3.8 Max accepts text and image input.

### Does Outrun store my prompts when I use Qwen 3.8 Max?

Outrun does not store your prompts, images or outputs unless you choose to save them.

## Where can I find more models?

[Alibaba Qwen guide ↗](https://outrun.to/qwen-api)[All model prices ↗](https://outrun.to/discounted-ai-api)[Model docs ↗](https://outrun.to/docs/models)[All model pages ↗](https://outrun.to/model/)

---
Source: https://outrun.to/model/qwen3.8-max
Outrun: https://outrun.to/ | API base: https://api.outrun.to/v1 | Prices (JSON): https://api.outrun.to/pricing | Docs: https://outrun.to/docs/