Skip to content

Compare model prices

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

Qwen3.8 2.4T A95B

A month of tokens

  • Qwen3.8 2.4T A95B$320.00

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

Side by side

Qwen3.8 2.4T A95B
Input per 1M$2
Output per 1M$6
Cached input$0.25
Batch in / outn/a
Blended (3:1)$3
Context1M
Routes7
ReleasedAug 12, 2026
Leadersboard score5 (#27)

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper

Every route

Qwen3.8 2.4T A95B

Way to buyIn / out per 1M
Qwen (Alibaba) API
The lab's own API · cached $0.25
$2 / $6List price
DeepInfra
fp4 · cached $0.2
$2 / $6Same as list
Modal
Default region · cached $0.25
$2 / $6Same as list
Novita AI
Default region · cached $0.25
$2 / $6Same as list
SiliconFlow
fp8 · cached $0.25
$2 / $6Same as list
Together AI
Default region · cached $0.25
$2 / $6Same as list
Venice
Default region · cached $0.25
$2 / $6Same as list

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.