qwen Open weights Vision Reasoning

Qwen3.6 35B A3B pricing & benchmarks

Released Apr 27, 2026 · served by 8 providers · ranked #51 by intelligence in our index

Input / 1M tokens$0.100
Output / 1M tokens$1.00
Context window262K
Cached input
Intelligence index31.6
Coding index41.9
Agentic index21.4
1M in + 300K out$0.40

What Qwen3.6 35B A3B is

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...

Providers and prices for Qwen3.6 35B A3B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Venicecheapest $0.100 $1.00 256K fp8 98.1%
AkashML $0.140 $1.00 262K fp8 99.8%
Parasail $0.150 $1.00 262K fp8 98.8%
AtlasCloud $0.186 $1.11 262K fp8 99.5%
CoreWeave $0.250 $1.25 262K fp8 99.5%
Phala $0.200 $1.27 262K 98.3%
SiliconFlow $0.200 $1.60 262K fp8 98.9%
Io Net $0.285 $2.40 262K fp8 99.9%

Cheaper models in the same class

Models scoring within 4 points of Qwen3.6 35B A3B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Qwen3.6 35B A3B API cost?

$0.100 per 1M input tokens and $1.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.40.

Is Qwen3.6 35B A3B free?

No. It is a paid model starting at $0.100 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3.6 35B A3B?

Venice at $0.100 input / $1.00 output per 1M tokens (fp8 quantization).

Can I self-host Qwen3.6 35B A3B?

Yes — weights are published as Qwen/Qwen3.6-35B-A3B on Hugging Face, so you can run it on your own hardware.