Qwen 3.5 397B A17B
qwen/qwen3.5-397b-a17bVision · 131K context · Feb 2026 · 25 upstreamsupstream上游
Qwen 3.5 397B A17B is Alibaba's open-weight mixture-of-experts model with 397B total and 17B active parameters. It supports reasoning and function calling, and takes text, image and video input.
- contextngữ cảnh上下文
- 131K
- inputđầu vào输入 / 1M
- $0.40
- outputđầu ra输出 / 1M
- $1.60
- modalitiesphương thức模态
- text · image · video
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
25- 1QwenCloudPlatform$0.40 / $1.60
- 2Ollama CloudBYOKnot addedBilled to your key
- 3OpenRouterBYOKnot addedBilled to your key
- 4QwenCloudBYOKnot addedBilled to your key
- 5ChutesBYOKnot addedBilled to your key
- 6OVHcloudBYOKnot addedBilled to your key
- 7DeepInfraBYOKnot addedBilled to your key
- 8NovitaAIBYOKnot addedBilled to your key
- 9GMICloudBYOKnot addedBilled to your key
- 10Hugging FaceBYOKnot addedBilled to your key
- 11Venice AIBYOKnot addedBilled to your key
- 12Nous ResearchBYOKnot addedBilled to your key
- 13InfronBYOKnot addedBilled to your key
- 14PhalaBYOKnot addedBilled to your key
- 15AIHubMixBYOKnot addedBilled to your key
- 16OcarRouterBYOKnot addedBilled to your key
- 17NanoGPTBYOKnot addedBilled to your key
- 18Eden AIBYOKnot addedBilled to your key
- 19FluenceBYOKnot addedBilled to your key
- 20CortecsBYOKnot addedBilled to your key
- 21QiniuBYOKnot addedBilled to your key
- 22EmpirioLabs AIBYOKnot addedBilled to your key
- 23Jiekou.AIBYOKnot addedBilled to your key
- 24NEAR AI CloudBYOKnot addedBilled to your key
- 25Atlas CloudBYOKnot addedBilled to your key
Benchmarks
- GPQA Diamond
- 85.9%
Benchmark data from Epoch AI (CC-BY 4.0).
Compare
Compared with models of similar price and context window.
| Model | In / out per 1M | Context | GPQA Diamond | OTIS Mock AIME | |
|---|---|---|---|---|---|
| Qwen 3.5 397B A17B | $0.40 / $1.60 (second best) | 131K | 85.9% | 88.9% (best) | |
| Qwen3.5 Plus | $0.40 / $1.60 (second best) | 256K (second best) | 78.0% | 85.0% (second best) | |
| Qwen3 Coder 480B A35B | $0.40 / $1.60 (second best) | 262K (best) | – | – | |
| Qwen3.5-35B-A3B | $0.23 / $1.80 (best) | 262K (best) | 83.5% | 54.4% | |
| Qwen3.5-122B-A10B | $0.30 / $2.40 | 262K (best) | – | – |
Benchmark data from Epoch AI (CC-BY 4.0).
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.5-397b-a17b",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Qwen
- Kind
- Vision
- Released
- Feb 2026
- Context
- 131K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
- Tool-calling assistants
- Math and reasoning
- Image + text questions
Architecture and licenseKiến trúc và giấy phép架构与许可
- LicenseGiấy phép许可
- Apache-2.0 · Open weightsTrọng số mở开放权重[1]
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- qwen.ai
- Model cardThẻ mô hình模型卡
- huggingface.co
SourcesNguồn来源
- [1]Qwen3.5-397B-A17B model cardaccessedtruy cập访问于 2026-11-11
- [2]Qwen3.5-397B-A17B announcementaccessedtruy cập访问于 2026-11-11
Upstreams and pricingUpstream và giá上游与价格
Share cards26 images


























AliasesBí danh别名 (1)
Qwen/Qwen3.5-397B-A17B-TEE
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…