Qwen model page

Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

TextVisionVideoStructured outputTool callingReasoning
Provider In / 1M
$0.05
Provider Out / 1M
$0.70
Context
262K
UAI Status
Pending sync

Availability on UAI

A public fallback landing page for a model that is not in the live UAI catalog yet.

Provider
Qwen

Pulled from the provider's public model page

Context window
262K tokens

Public model metadata

UAI status
Pending sync

This route exists now, but the model is not active in /v1/models yet

Pricing source
Provider public page

UAI pricing will appear automatically once the catalog row is synced

This page is available for direct linking and discovery, but the row is not active in the live UAI catalog yet. Until it is synced, /v1/models may not list it and requests for qwen/qwen3.6-35b-a3b can fail validation.

Why use this model through UAI

The same model route, but with one account, one balance, and one API shape.

Reasoning workloads

Use Qwen3.6 35B A3B for multi-step prompts, planning, and deeper analysis while keeping the same OpenAI-compatible UAI endpoint.

Multimodal prompts

The synced capabilities for this row indicate image or vision support, so you can route multimodal requests through the same UAI account and billing flow.

Agent integrations

Tool and function-style parameters stay available through the same UAI request surface, so agent stacks do not need a separate provider integration.

Pricing and source data

Public metadata until the live UAI catalog row is synced.

UAI catalog status
Pending sync
Qwen input / 1M
$0.05
Qwen output / 1M
$0.70
Context window
262,144
Supported params
reasoning, include_reasoning, temperature, top_p, top_k, frequency_penalty

Once this row is synced into UAI, this page will automatically switch from public fallback metadata to live UAI pricing, request validation, and app links.

How to use it on UAI

This public page exists already, but the callable catalog row is still pending sync.

Create a UAI key in API Keys, then use /v1/models or the public models catalog to see which rows are active right now.

Requests for qwen/qwen3.6-35b-a3b may fail until the live UAI catalog sync includes this row. This page stays up now so the URL can still be shared, indexed, and linked from rankings.

Related models

Other active rows to compare without leaving the public catalog.

qwen
Qwen: Qwen3.7 Flash
qwen/qwen3.7-flash
Input / 1M$0.04
Context1M tokens
qwen
Qwen 3 30B
qwen3:30b
Input / 1M$0.00
ContextContext pending
qwen
Qwen3.6 35B A3B (Lenovo)
shared-local/up_lenovo_rtx8000_ollama/qwen3.6:35b-a3b
Input / 1M$0.00
Context33K tokens