Qwen3.6 27BOpen weights
Alibaba · released 2026-04-22
The official API price of Qwen3.6 27B is $0.6 per 1M input tokens and $3.6 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 29 providers sell it. The lowest is DevPass (LLM Gateway): $0.15 input, $1.35 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialqwen3.6-27b | $0.6 | $3.6 | — | Official | Official docs |
 DevPass (LLM Gateway)Lowestqwen3.6-27b | $0.15 | $1.35 | — | Lowest | Official docs |
LLLM Gatewaygreenference/ | $0.15 | $1.35 | — | Official docs | |
 ChutesQwen/ | $0.25 | $2 | $0.025 | Official docs | |
NNanoGPTqwen/ | $0.203 | $2.24 | $0.1015 | Official docs | |
NNanoGPTqwen/ | $0.203 | $2.24 | $0.1015 | Official docs | |
 EmpirioLabs AIqwen3-6-27b | $0.412564 | $2.475384 | $0.412564 | Official docs | |
MMerge Gatewayqwen/ | $0.4126 | $2.4754 | — | Official docs | |
OOfoxqwen/ | $0.43 | $2.57 | — | Official docs | |
 SiliconFlow (China)Qwen/ | $0.449804 | $2.698826 | — | Official docs | |
KKilo Gatewayqwen/ | $0.45 | $2.7 | — | Official docs | |
CCortecsqwen3.6-27b | $0.446 | $3.008 | — | Official docs |
20 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| SiliconFlowQwen/ | $0.3 | $3.2 | — | Official docs | |
AAbacusQwen/ | $0.32 | $3.2 | — | Official docs | |
Aai&qwen/ | $0.32 | $3.2 | $0.2 | Official docs | |
AAmbientqwen/ | $0.32 | $3.2 | $0.16 | Official docs | |
 Deep InfraQwen/ | $0.32 | $3.2 | — | Official docs | |
 OpenRouterqwen/ | $0.32 | $3.2 | — | Official docs | |
NNanoGPTTEE/ | $0.32 | $3.25 | $0.03 | Official docs | |
 Venice AIqwen3-6-27b | $0.325 | $3.25 | — | Official docs | |
 Hugging FaceQwen/ | $0.47 | $3.19 | — | Official docs | |
OOVHcloud AI Endpointsqwen3.6-27b | $0.47 | $3.19 | — | Official docs | |
 Novita AIqwen/ | $0.6 | $3.6 | — | Official docs | |
OOfoxbailian/ | $0.6 | $3.6 | — | Official docs | |
 Vercel AI Gatewayalibaba/ | $0.6 | $3.6 | — | Official docs | |
TThinking MachinesQwen/ | $1.86 | $5.595 | $0.372 | Official docs | |
SSTACKITDeprecatedQwen/ | $0.53 | $0.76 | — | Deprecated | Official docs |
 GroqDeprecatedqwen/ | $0.6 | $3 | $0.3 | Deprecated | Official docs |
SSyntheticDeprecatedhf: | $0.45 | $3.6 | $0.45 | Deprecated | Official docs |
IInferXQwen3.6-27B-FP8 | $0 | $0 | — | Official docs | |
PPendraqwen3.6: | $0 | $0 | — | Official docs | |
QQVACqwen3.6-27b | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Qwen vision-language model for visual reasoning, documents, and agent tasks
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 65.5K
- Input
- Text, Image, Video
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2026-04-22
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.