Qwen
Qwen3.5-35B-A3B
Released 2026-02-25
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
You send / 1M
$0.140
tokens in
It replies / 1M
$1.00
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0007
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 | $0.140 | $1.00 | 99% | Read |
| Parasail · fp8 | $0.150 | $1.00 | 100% | Read |
| Venice | $0.150 | $1.00 | 100% | Read |
| SiliconFlow · fp8 | $0.240 | $1.80 | 94% | 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: 82K tokens
- Repeated text is billed at $0.050 per 1M (prompt caching)
- Intelligence score: 19.3 / 100 (Artificial Analysis)
Similar models
- Qwen3 VL 30B A3B ThinkingQwen · $0.290 in / $1.00 out per 1M
- Qwen3.6 35B A3BQwen · $0.100 in / $0.900 out per 1M
- GLM 4.6VZ.ai · $0.300 in / $0.900 out per 1M
- Qwen3.6 FlashQwen · $0.188 in / $1.13 out per 1M
- MiMo-V2.6-ProXiaomi · $0.435 in / $0.870 out per 1M
- Step 3.7 FlashStepfun · $0.200 in / $1.15 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap 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 Cheap AI ModelsTop No-Training Cheap Vision AI Models