Qwen
Qwen3.6 27B
Released 2026-04-27
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
You send / 1M
$0.450
tokens in
It replies / 1M
$2.70
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0019
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 |
|---|---|---|---|---|
| Reka | $0.200 | $3.00 | 99% | Read |
| SiliconFlow · fp8 | $0.300 | $3.20 | 84% | Read |
| DeepInfra · fp8 | $0.320 | $3.20 | 97% | Read |
| Phala | $0.320 | $3.25 | 92% | Read |
| Venice · fp8 | $0.325 | $3.25 | 98% | 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: 66K tokens
- Intelligence score: 21.4 / 100 (Artificial Analysis)
Similar models
- Step 5 PreviewStepfun · $1.00 in / $2.70 out per 1M
- Qwen3.5-27BQwen · $0.260 in / $2.60 out per 1M
- Moondream 3 PreviewMoondream · $0.300 in / $2.50 out per 1M
- Moondream 3.1Moondream · $0.300 in / $2.50 out per 1M
- Seed 2.1 TurboBytedance Seed · $0.500 in / $2.50 out per 1M
- Gemini 3.5 Flash LiteGoogle · $0.300 in / $2.50 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