Qwen 3.6 35B A3BChat
Qwen's sparse 35B/3B-active multimodal model for efficient coding and agents.
3.4sp50100%up1 rail262K ctx$0.002typical$0.25 → $1.14 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | Primary | 1M | $0.60 / $3.84/MToksame price, any rail | 874ms | 874ms | 100% |
| ggmicloudNo trainingNo training on your data | Fallback | 1M | — | — | — |
Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.007/req
- Input
- $0.60/M tok
- Cached input
- $0.20/M tok
- Output
- $3.84/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
qwen-3.8-27b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-3.8-27b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Qwen 3.8 27B?
Qwen's efficient 27B model on independently operated DeepInfra and GMI rails.
How much does Qwen 3.8 27B cost?
Qwen 3.8 27B costs $0.60/M input tokens and $3.84/M output tokens.
What inputs and outputs does Qwen 3.8 27B support?
Qwen 3.8 27B accepts text and returns text.
How do I call Qwen 3.8 27B?
POST /api/v1/chat/completions with `"model": "qwen-3.8-27b"`.
What other Qwen models are on NinjaChat?
Qwen 3.6 35B A3B, Qwen 3.7 Plus, Qwen 3.8 2.4T A95B, Qwen 3.8 Max, Qwen3 Next 80B A3B, QwQ 32B.