Skip to content

Compare model prices

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

Qwen3.8 27B

A month of tokens

  • Qwen3.8 27B$93.50

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

Side by side

Qwen3.8 27B
Input per 1M$0.425
Output per 1M$2.55
Cached input$0.085
Batch in / outn/a
Blended (3:1)$0.956
Context1M
Routes16
ReleasedAug 14, 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

Qwen3.8 27B

Way to buyIn / out per 1M
Darkbloom
fp4, cheapest
$0.1 / $1.8-45% vs list
DeepInfra
bf16 · cached $0.037
$0.15 / $1.88-39% vs list
Phala
Default region · cached $0.042
$0.199 / $2.08-30% vs list
DekaLLM
Default region · cached $0.05
$0.1 / $2.5-27% vs list
Chutes
fp8 · cached $0.024
$0.24 / $2.2-24% vs list
Parasail
fp8 · cached $0.05
$0.24 / $2.2-24% vs list
AkashML
fp8 · cached $0.05
$0.25 / $2.2-23% vs list
Mancer 2
fp8
$0.2 / $2.5-19% vs list
Ionstream
fp8 · cached $0.1
$0.28 / $2.55-11% vs list
Qwen (Alibaba) API
The lab's own API · cached $0.085
$0.425 / $2.55List price
CoreWeave
fp8 · cached $0.15
$0.4 / $3+10% vs list
Novita AI
Default region · cached $0.085
$0.42 / $3+11% vs list
Cloudflare Workers AI
Default region · cached $0.05
$0.45 / $3.2+19% vs list
Venice
fp8
$0.45 / $3.2+19% vs list
Wafer
Default region · cached $0.087
$0.097 / $4.4+23% vs list
Reka
fp8 · cached $0.089
$0.098 / $4.4+23% 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.