Qwen3.8 Flash API
Qwen's chat model. Call it on 666 AI with the same API key as every other model. Pay as you go; prices follow the upstream in real time and this page updates hourly.
| Vendor | Qwen |
| Type | chat |
| Price | $0.2025 per 1M input tokens · $0.6345 per 1M output tokens |
| Context window | 128K tokens |
| Live test | Passed our live test in the last 7 days · 3 supply routes, automatic failover |
| Latency (short request) | Median ~1s (5+ calls in the last 7 days) |
| Model ID (use this in your request) | Qwen/Qwen3.8-Flash |
How to call Qwen3.8 Flash
The API is OpenAI-compatible. Replace YOUR-ENDPOINT with the endpoint shown on your API Key page after you sign up, and YOUR-KEY with your key.
curl https://YOUR-ENDPOINT/v1/chat/completions \
-H "Authorization: Bearer YOUR-KEY" \
-H "Content-Type: application/json" \
-d '{"model": "Qwen/Qwen3.8-Flash", "messages": [{"role": "user", "content": "Hello"}]}'from openai import OpenAI
client = OpenAI(base_url="https://YOUR-ENDPOINT/v1", api_key="YOUR-KEY")
r = client.chat.completions.create(
model="Qwen/Qwen3.8-Flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)Similar models — price comparison
| Model | Price |
|---|---|
| Mimo V2.6 Flash | $0.1607 per 1M input tokens · $0.378 per 1M output tokens |
| Mimo V2.5 | $0.2 per 1M input tokens · $0.3999 per 1M output tokens |
| GPT 6 Luna | $0.1215 per 1M input tokens · $0.6075 per 1M output tokens |
| Claude Haiku 5.5 | $0.135 per 1M input tokens · $0.675 per 1M output tokens |
| Hy3 | $0.189 per 1M input tokens · $0.783 per 1M output tokens |
| Hy3 Preview | $0.243 per 1M input tokens · $0.81 per 1M output tokens |
More models from Qwen
| Model | Price |
|---|---|
| Qwen Image 2.0 Pro | $0.1013 per image |
| Qwen3.6 Plus | $0.4388 per 1M input tokens · $2.63 per 1M output tokens |
| Qwen3.7 Max | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Qwen3.7 Plus | $0.432 per 1M input tokens · $1.73 per 1M output tokens |
| Qwen3.8 2.4T A95B | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| GLM 5.2 Fast Preview | $4.72 per 1M input tokens · $14.85 per 1M output tokens |
| Happyhorse 1.1 | $0.1334 – $0.1725 per second |
| Happyhorse 1.0 | $0.1334 – $0.2287 per second |
FAQ
How much does the Qwen3.8 Flash API cost?
On 666 AI, Qwen3.8 Flash costs $0.2025 per 1M input tokens · $0.6345 per 1M output tokens. You pay only for what you use — no monthly fee. Prices follow the upstream in real time; this page updates every hour.
Can I use the official OpenAI SDK?
Yes. The API is OpenAI-compatible: in the OpenAI Python or Node.js SDK just change base_url and api_key, and set model to Qwen/Qwen3.8-Flash.
How do I pay?
Bank card (including Google Pay / Apple Pay), USDT / ETH, or bank wire. Top up once and usage is deducted as you go.