Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

Qwen3.5-35B-A3B

A month of tokens

  • Qwen3.5-35B-A3B$42.25

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

Qwen3.5-35B-A3B
Input per 1M$0.163
Output per 1M$1.3
Cached inputn/a
Batch in / outn/a
Blended (3:1)$0.447
Context262K
Routes7
ReleasedFeb 25, 2026
Leadersboard scoren/a

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

Qwen3.5-35B-A3B

Way to buyIn / out per 1M
Darkbloom
fp4, cheapest
$0.08 / $0.75-45% vs list
DeepInfra
fp8 · cached $0.05
$0.14 / $1-21% vs list
Parasail
fp8 · cached $0.05
$0.15 / $1-19% vs list
Qwen (Alibaba) API
The lab's own API
$0.163 / $1.3List price
Venice
Default region · cached $0.156
$0.313 / $1.25+22% vs list
AtlasCloud
fp8 · cached $0.225
$0.225 / $1.8+38% vs list
SiliconFlow
fp8 · cached $0.15
$0.24 / $1.8+41% vs list

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.