Qwen
Qwen3.8 27B
Released 2026-08-14
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
You send / 1M
$0.039
tokens in
It replies / 1M
$1.25
tokens out
Memory
1M
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 |
|---|---|---|---|---|
| Tenstorrent · fp4 | $0.060 | $0.500 | 98% | Read |
| Near AI · fp8 | $0.040 | $1.35 | 100% | Read |
| Cerebras · fp16 | $0.990 | $1.49 | 100% | Read |
| DeepInfra · bf16 | $0.150 | $1.88 | 100% | Read |
| Ionstream · fp8 | $0.040 | $1.95 | 99% | Read |
| AkashML · fp8 | $0.225 | $1.98 | 100% | Read |
| Parasail · fp8 | $0.240 | $2.20 | 100% | Read |
| Reka · fp8 | $0.040 | $2.20 | 100% | Read |
| Modal | $0.040 | $2.30 | 100% | Read |
| Wafer · fp8 | $0.040 | $2.30 | 100% | Read |
| ModelRun · fp4 | $0.200 | $2.50 | 100% | Read |
| DekaLLM | $0.040 | $2.50 | 100% | Read |
| Mancer 2 · fp8 | $0.180 | $2.50 | 97% | Read |
| Phala | $0.200 | $2.50 | 98% | Read |
| Novita | $0.420 | $3.00 | 100% | Read |
| CoreWeave · fp8 | $0.400 | $3.00 | 100% | Read |
| Cloudflare | $0.450 | $3.20 | 100% | Read |
| Venice · fp8 | $0.450 | $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
- Repeated text is billed at $0.0039 per 1M (prompt caching)
- Intelligence score: 33.7 / 100 (Artificial Analysis)
Similar models
- GLM 5.3 FlashXZ.ai · $0.370 in / $1.25 out per 1M
- GPT-5.4 NanoOpenAI · $0.200 in / $1.25 out per 1M
- Qwen3.7 PlusQwen · $0.320 in / $1.28 out per 1M
- DeepSeek V4.1 Flash 1017DeepSeek · $0.300 in / $1.20 out per 1M
- Muse Glimmer 30BMeta · $0.300 in / $1.20 out per 1M
- Inkling SmallThinkingmachines · $0.450 in / $1.20 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 Zero Data Retention Long-Context AI ModelsTop No-Training Vision AI ModelsTop No-Training Vision Reasoning AI Models