Qwen3.6 35B A3B

Native vision-language MoE model with hybrid linear attention and sparse mixture-of-experts, improved agentic coding, math/code reasoning, and spatial intelligence.

qwen3.6-35b-a3b
STABLEGet StartedView uptime
262,144 context
Released April 29, 2026
Starting at $0.25/M input tokens
Starting at $1.48/M output tokens
Streaming
Vision
Tools
Reasoning
JSON Output
No ratings yetSign in to rate

Select Provider

All Providers for Qwen3.6 35B A3B

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Alibaba Cloud
Context: 262.1k
Input
$0.248
/M tokens
Cache Read
/M tokens
Output
$1.485
/M tokens
+ $0.010 per search
Get Started
NovitaAI
Context: 262.1k
Input
$0.248
/M tokens
Cache Read
/M tokens
Output
$1.485
/M tokens
Get Started

Frequently asked questions

What is Qwen3.6 35B A3B?

Native vision-language MoE model with hybrid linear attention and sparse mixture-of-experts, improved agentic coding, math/code reasoning, and spatial intelligence. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Qwen3.6 35B A3B cost?

Pricing for Qwen3.6 35B A3B on LLM Gateway starts at $0.25 per million input tokens and $1.48 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Qwen3.6 35B A3B?

Qwen3.6 35B A3B supports a context window of up to 262,144 tokens on its largest provider deployment.

Which providers serve Qwen3.6 35B A3B?

Qwen3.6 35B A3B is served by Alibaba Cloud, NovitaAI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Qwen3.6 35B A3B support tool calling and structured outputs?

Yes. Qwen3.6 35B A3B supports both tool (function) calling and structured JSON outputs through LLM Gateway.

When was Qwen3.6 35B A3B released?

Qwen3.6 35B A3B was released on April 29, 2026.