Model prices / Alibaba / Qwen3.6 35B-A3B
Qwen3.6 35B-A3BOpen weights
Alibaba · released 2026-04-17
The official API price of Qwen3.6 35B-A3B is $0.375 per 1M input tokens and $2.25 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 65.5K output tokens per request. 40 providers sell it. The lowest is engy: $0.045 input, $0.3 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| AlibabaOfficialqwen3.6-35b-a3b | $0.375 | $2.25 | — | Official | Official docs |
EengyLowestqwen3.6-35b-a3b | $0.045 | $0.3 | $0.015 | Lowest | Official docs |
BBoundlessqwen3.6 | $0.04 | $0.35 | $0.02 | Official docs | |
 EmpirioLabs AIqwen3-6-35b-a3b | $0.07 | $0.42 | $0.035 | Official docs | |
ZZenifraalibaba/ | $0.19 | $0.48 | — | Official docs | |
SSaladCloud AI Gatewayqwen3.6-35b-a3b | $0.09 | $0.6 | — | Official docs | |
NNanoGPTqwen/ | $0.112 | $0.8 | $0.056 | Official docs | |
NNanoGPTqwen/ | $0.112 | $0.8 | $0.056 | Official docs | |
NNeuralwattqwen3.6-35b-flex | $0.1885 | $0.7475 | $0.01885 | Official docs | |
 CoreWeaveQwen/ | $0.1 | $0.89 | $0.035 | Official docs | |
KKilo Gatewayqwen/ | $0.1 | $0.9 | $0.025 | Official docs | |
 OpenRouterqwen/ | $0.1 | $0.9 | $0.025 | Official docs |
36 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Deep InfraQwen/ | $0.1 | $0.95 | $0.1 | Official docs | |
 Hugging FaceQwen/ | $0.15 | $0.95 | — | Official docs | |
 Venice AIqwen3-6-35b-a3b | $0.1 | $1 | — | Official docs | |
AAmbientqwen/ | $0.15 | $1 | $0.15 | Official docs | |
UUmans AIumans-flash | $0.15 | $1 | $0.05 | Official docs | |
NNEAR AI CloudQwen/ | $0.17 | $1.1 | $0.056 | Official docs | |
NNeuralwattqwen3.6-35b | $0.29 | $1.15 | $0.029 | Official docs | |
NNeuralwattqwen3.6-35b-fast | $0.29 | $1.15 | $0.029 | Official docs | |
NNanoGPTTEE/ | $0.2 | $1.27 | $0.056 | Official docs | |
EevrocQwen/ | $0.345 | $1.38 | — | Official docs | |
 DevPass (LLM Gateway)qwen3.6-35b-a3b | $0.248 | $1.485 | — | Official docs | |
LLLM Gatewaynovita/ | $0.248 | $1.485 | — | Official docs | |
MMerge Gatewayqwen/ | $0.248 | $1.485 | $0.0496 | Official docs | |
 Novita AIqwen/ | $0.248 | $1.485 | — | Official docs | |
OOpperqwen3.6-35b-a3b | $0.248 | $1.485 | — | Official docs | |
OOrcaRouterqwen/ | $0.248 | $1.485 | — | Official docs | |
 AIHubMixqwen3.6-35b-a3b | $0.254 | $1.524 | — | Official docs | |
TThinking MachinesQwen/ | $0.45 | $1.335 | $0.09 | Official docs | |
TThinking MachinesQwen/ | $0.45 | $1.335 | $0.09 | Official docs | |
 SiliconFlow (China)Qwen/ | $0.269005 | $1.614033 | — | Official docs | |
CCortecsqwen3.6-35b-a3b | $0.279 | $1.671 | — | Official docs | |
SScalewayBetaqwen3.6-35b-a3b | $0.280375 | $1.68225 | — | Beta | Official docs |
3302.AIqwen3.6-35b-a3b | $0.28 | $1.7 | — | Official docs | |
| SiliconFlowQwen/ | $0.24 | $1.8 | $0.15 | Official docs | |
 GreenPTqwen3.6-35b-a3b | $0.342 | $2.052 | — | Official docs | |
LLLM Gatewayalibaba/ | $0.375 | $2.25 | — | Official docs | |
 Vercel AI Gatewayalibaba/ | $0.375 | $2.25 | — | Official docs | |
LLLMTRqwen3-6-35b | $5 | $10 | — | Official docs | |
AAKI.IODeprecatedqwen3.6-35b | $0.168225 | $0.56075 | — | Deprecated | Official docs |
HHetznerBetaQwen/ | $0 | $0 | $0 | Beta | Official docs |
IInferXQwen3.6-35B-A3B-FP8 | $0 | $0 | — | Official docs | |
IInferXQwen3.6-35B-A3B-fp8-no-thinking | $0 | $0 | — | Official docs | |
NNaNqwen3.6 | $0 | $0 | — | Official docs | |
QQVACqwen3.6-35b-a3b | $0 | $0 | — | Official docs | |
UUmans AI Coding Planumans-flash | $0 | $0 | $0 | Official docs | |
UUmans AI Coding Planumans-qwen3.6-35b-a3b | $0 | $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
Open multimodal Qwen MoE for local agents that need vision, audio, and code
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
- 2025-04
- Open weights
- Yes
- Released
- 2026-04-17
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.