qwenQwen (Alibaba) Models
Access the Qwen 3.x family through AI Gateway — Qwen3.8-Max, Qwen3.8-Flash and more via one OpenAI-compatible API with per-token credit billing.
Alibaba's Qwen family covers a wide capability/speed range, with strong multilingual performance. The tiers below are available through AI Gateway's single OpenAI-compatible endpoint.
Available Models
| Model | Context | Best For |
|---|---|---|
qwen3.8-max | 1M | Flagship quality |
qwen3.8-flash | 128K | Fast everyday calls |
qwen3.7-max | 1M | Complex reasoning tasks |
qwen3.7-plus | 1M | Balanced production default |
qwen3.7-flash | 128K | High-volume, low-latency |
qwen3.6-plus / qwen3.6-flash | 1M / 128K | Previous-generation value |
qwen3.5-plus | 1M | Stable long-context work |
Live per-model credit pricing is on the Models page.
Quick Start
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://your-domain.com/api/ai/v1"
)
response = client.chat.completions.create(
model="qwen3.8-max",
messages=[{"role": "user", "content": "Translate this product document into English."}]
)
print(response.choices[0].message.content)
Replace
your-domain.comwith your AI Gateway site domain. Get your API key from the dashboard after sign-up.
Why through AI Gateway
- One API key across Qwen, GPT, Claude, Gemini, DeepSeek…
- OpenAI-compatible — existing SDKs work unchanged
- Credits never expire — pay per token
Related Pages
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
Why through AI Gateway
- One unified interface: call every provider through a single OpenAI-compatible base URL
- One key: no per-vendor accounts; credits are shared and never expire
- Per-token billing: cache hits billed at steep discounts
- Flexible switching: change one string to move between models or vendors
About this data
Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.
| Model | Context | Type |
|---|---|---|
qwen3.5-plus | 1M | chat |
qwen3.6-flash | 131K | chat |
qwen3.6-plus | 1M | chat |
qwen3.7-flash | 131K | chat |
qwen3.7-max | 1M | chat |
qwen3.7-plus | 1M | chat |
qwen3.8-flash | 131K | chat |
qwen3.8-max | 1M | chat |
qwen3.8-max-0902 | 131K | chat |
Why through AI Gateway
- One unified interface: call every provider through a single OpenAI-compatible base URL
- One key: no per-vendor accounts; credits are shared and never expire
- Per-token billing: cache hits billed at steep discounts
- Flexible switching: change one string to move between models or vendors
Capabilities
9 shipping models, context windows from 131K to 1M tokens; tiers: light ×3, flagship ×2, balanced ×2, previous generation ×2.
Pricing & billing
Per-token credit billing; cache hits at steep discounts. Live rates on the Models pricing page — numbers intentionally not fixed here.
FAQ
How large is the context window of Qwen (Alibaba)?
1,000,000 Token (1M)
How is it billed?
Per-token credit billing with cache-hit discounts. Live rates on the Models page.
Do I need a provider account?
No. One AI Gateway API key covers this model and every other model on the site.
About this data
Specs and prices come from the platform live catalog; performance figures from vendor or third-party publications. Updated 2026-10-13.
All Models
Each model has its own page with specs, official reference pricing, credit prices and code examples.
Ready to build with Qwen?
One API Key, every model. Transparent pay-as-you-go pricing with credits that never expire.
Create free account