Qwen
Qwen3.5 397B A17B
Released 2026-02-16
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
You send / 1M
$0.500
tokens in
It replies / 1M
$3.60
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0024
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.450 | $3.00 | 100% | Read |
| DigitalOcean | $0.550 | $3.50 | 84% | Read |
| Phala | $0.550 | $3.50 | 96% | Read |
| Parasail · fp8 | $0.500 | $3.60 | 100% | Read |
| Novita | $0.600 | $3.60 | 95% | Read |
| Venice | $0.750 | $4.50 | 95% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image, video
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 236K tokens
- Repeated text is billed at $0.300 per 1M (prompt caching)
- Intelligence score: 21.4 / 100 (Artificial Analysis)
Similar models
- Gemini 3.7 FlashGoogle · $0.750 in / $3.75 out per 1M
- Gemini 3.6 FlashGoogle · $0.750 in / $3.75 out per 1M
- Gemini Flash Latest~google · $0.750 in / $3.75 out per 1M
- Kimi K2.6Moonshot · $0.650 in / $3.41 out per 1M
- Sakana NamazuSakana · $0.950 in / $4.00 out per 1M
- GLM 5V TurboZ.ai · $1.20 in / $4.00 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Vision AI ModelsTop No-Training Vision Reasoning AI ModelsTop No-Training Vision Tool-Calling AI Models