Qwen 3.5 122B A10BChat
Qwen's 122B/10B-active multimodal MoE, balancing stronger quality with efficient inference.
1 rail262K ctx$0.005typical$0.44 → $2.88 /MTok
Models
Qwen 3.6 27B
Qwen's compact multimodal reasoning model on a cost-efficient DeepInfra rail with ultra-fast Groq failover.
- Modalities
- textimagetext
- Price
- $0.75 / $3.84/M tok
- Context
- 131K
- Max output
- 16K
- Providers
- 2
Playground
Providers
| Provider | Role | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | Primary | 131K | $0.75 / $3.84/MToksame price, any rail | 4.5s | 4.5s | 100% |
| ggroqNo trainingNo training on your data. Zero-retention available | Fallback | 131K | 197ms | 197ms | 100% |
Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.008/req
- Input
- $0.75/M tok
- Cached input
- $0.21/M tok
- Output
- $3.84/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
qwen-3.6-27b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-3.6-27b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Qwen 3.6 27B?
Qwen's compact multimodal reasoning model on a cost-efficient DeepInfra rail with ultra-fast Groq failover.
How much does Qwen 3.6 27B cost?
Qwen 3.6 27B costs $0.75/M input tokens and $3.84/M output tokens.
What inputs and outputs does Qwen 3.6 27B support?
Qwen 3.6 27B accepts text and image and returns text.
How do I call Qwen 3.6 27B?
POST /api/v1/chat/completions with `"model": "qwen-3.6-27b"`.
What other Qwen models are on NinjaChat?
Qwen 3.5 122B A10B, Qwen 3.5 27B, Qwen 3.5 397B A17B, 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, QwQ 32B.