Skip to content
LLMs
Qwen logo

Qwen: Qwen3.6 35B A3B

by Qwen

Qwen: Qwen3.6 35B A3B is a large language model from Qwen. It costs $0.100 per million input tokens and $0.900 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weightsimage inputvideo input
Input / 1M tokens
$0.100
Output / 1M tokens
$0.900
Cached input / 1M
$0.050

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

11 hosts serve Qwen3.6 35B A3B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen3.6 35B A3B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DarkbloomCheapestfp4$0.050$0.700262K-99.8%
AkashMLfp8$0.100$0.900262K-99.8%
DeepInfrafp8$0.100$0.950262K-99.0%
DekaLLM$0.100$1.00262K-99.9%
Venicefp8$0.100$1.00256K-99.9%
Io Netfp8$0.133$0.941262K-93.5%
Parasailfp8$0.150$1.00262K-99.8%
AtlasCloudfp8$0.186$1.11262K-99.3%
Phala$0.200$1.27262K-99.7%
CoreWeavefp8$0.250$1.25262K-100.0%
SiliconFlowfp8$0.240$1.80262K-97.6%

The spread between Darkbloom and SiliconFlow is 3.0× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
18.8
Coding index
41.9
Agentic index
15.0

About 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...

Specifications

Qwen: Qwen3.6 35B A3B specifications
Model IDqwen/qwen3.6-35b-a3b
ProviderQwen
Context window262K tokens
Max output236K tokens
Input modalitiestext, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - Qwen/Qwen3.6-35B-A3B
ReleasedApril 27, 2026

Cheaper alternatives

Models that cost less than Qwen3.6 35B A3B while keeping at least half its context window and every input modality it supports.

GLM 5.3 Flash

$0.150 in · $0.500 out

1.3× cheaper

Qwen3.8 Flash

$0.150 in · $0.470 out

1.3× cheaper

MiMo-V2.5

$0.140 in · $0.280 out

1.7× cheaper

Seed-2.0-Mini

$0.100 in · $0.400 out

1.7× cheaper

Gemini 2.5 Flash Lite

$0.100 in · $0.400 out

1.7× cheaper

Frequently asked

How much does Qwen: Qwen3.6 35B A3B cost?

$0.100 per million input tokens and $0.900 per million output tokens. Cached input reads cost $0.050 per million tokens.

What is the context window of Qwen: Qwen3.6 35B A3B?

262K tokens, with up to 236K tokens of output per request.

Which provider serves Qwen: Qwen3.6 35B A3B cheapest?

Darkbloom at $0.050 per million input tokens - 3.0× cheaper than SiliconFlow, the most expensive of the 11 hosts serving it.

Confirm against the source: Qwen official pricing.