Skip to content

Compare model prices

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

Llama 3.1 8B Instruct

A month of tokens

  • Llama 3.1 8B Instruct$2.80

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

Side by side

Llama 3.1 8B Instruct
Input per 1M$0.02
Output per 1M$0.04
Cached inputn/a
Batch in / outn/a
Blended (3:1)$0.025
Context131K
Routes5
ReleasedJul 23, 2024
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

Llama 3.1 8B Instruct

Way to buyIn / out per 1M
DeepInfra
fp8
$0.02 / $0.04Same as list
Novita AI
fp8
$0.02 / $0.05+10% vs list
Groq
Default region · cached $0.025
$0.05 / $0.08+130% vs list
Cloudflare Workers AI
fp8
$0.152 / $0.287+643% vs list
CoreWeave
bf16 · cached $0.22
$0.22 / $0.22+780% 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.