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 | Context | Price · in / out |
|---|---|---|
| ggroqNo trainingNo training on your data. Zero-retention available | 32K | $0.44 / $0.74/MTok |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.003/req
- Input
- $0.44/M tok
- Cached input
- $0.18/M tok
- Output
- $0.74/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
qwq-32b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwq-32b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingresponse_format
FAQ
What is QwQ 32B?
Alibaba's reasoning-focused open model, strong at math.
How much does QwQ 32B cost?
QwQ 32B costs $0.44/M input tokens and $0.74/M output tokens.
What inputs and outputs does QwQ 32B support?
QwQ 32B accepts text and returns text.
How do I call QwQ 32B?
POST /api/v1/chat/completions with `"model": "qwq-32b"`.
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 27B, Qwen 3.8 Max, Qwen3 Next 80B A3B.