Skip to content

Compare model prices

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

Gemma 4 26B A4B

A month of tokens

  • Gemma 4 26B A4B$8.60

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

Side by side

Gemma 4 26B A4B
Input per 1M$0.042
Output per 1M$0.22
Cached inputn/a
Batch in / outn/a
Blended (3:1)$0.086
Context262K
Routes12
ReleasedApr 3, 2026
Leadersboard scoren/a

On the price map

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

Every route

Gemma 4 26B A4B

Way to buyIn / out per 1M
Darkbloom
Default region
$0.042 / $0.22Same as list
DekaLLM
bf16
$0.06 / $0.33+47% vs list
DeepInfra
fp8
$0.07 / $0.34+59% vs list
NextBit
bf16 · cached $0.05
$0.09 / $0.3+65% vs list
Cloudflare Workers AI
Default region
$0.1 / $0.3+73% vs list
CoreWeave
bf16 · cached $0.05
$0.1 / $0.3+73% vs list
Makora
Default region · cached $0.034
$0.1 / $0.34+85% vs list
Novita AI
bf16
$0.13 / $0.4+128% vs list
Parasail
bf16 · cached $0.05
$0.13 / $0.4+128% vs list
Venice
bf16 · cached $0.05
$0.13 / $0.4+128% vs list
SiliconFlow
fp8 · cached $0.05
$0.14 / $0.4+137% vs list
Google Vertex AI
global
$0.15 / $0.6+203% vs 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.