Qwen
Qwen3.5-122B-A10B
Released 2026-02-25
The Qwen3.5 122B-A10B 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. In terms of...
You send / 1M
$0.260
tokens in
It replies / 1M
$2.08
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0014
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 |
|---|---|---|---|---|
| SiliconFlow · fp8 | $0.260 | $2.08 | 97% | Read |
| Novita · bf16 | $0.400 | $3.20 | 100% | 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: 17.7 / 100 (Artificial Analysis)
Similar models
- Grok Build 0.1xAI · $1.00 in / $2.00 out per 1M
- MiMo-V2.5Xiaomi · $0.400 in / $2.00 out per 1M
- Seed-2.0-LiteBytedance Seed · $0.250 in / $2.00 out per 1M
- Seed 1.6Bytedance Seed · $0.250 in / $2.00 out per 1M
- GPT-5.1-Codex-MiniOpenAI · $0.250 in / $2.00 out per 1M
- GPT-5 Image MiniOpenAI · $2.50 in / $2.00 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