Skip to content

Compare model prices

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

gpt-oss-120bGPT-6 Luna

A month of tokens

  • gpt-oss-120b$6.40
  • GPT-6 Luna$20.00

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

Side by side

gpt-oss-120bGPT-6 Luna
Input per 1M$0.03$0.1
Output per 1M$0.17$0.5
Cached input$0.03$0.01
Batch in / outn/a$0.05 / $0.25
Blended (3:1)$0.065$0.2
Context131K1.05M
Routes267
ReleasedAug 5, 2025Sep 22, 2026
Leadersboard scoren/an/a

On the price map

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

Every route

gpt-oss-120b

Way to buyIn / out per 1M
AkashML
bf16 · cached $0.03
$0.03 / $0.17Same as list
CoreWeave
fp4 · cached $0.03
$0.03 / $0.17Same as list
DekaLLM
bf16
$0.03 / $0.18+4% vs list
DeepInfra
bf16
$0.037 / $0.17+8% vs list
Crusoe
bf16 · cached $0.05
$0.05 / $0.25+54% vs list
Novita AI
fp4
$0.05 / $0.25+54% vs list
Mancer 2
fp8
$0.05 / $0.3+73% vs list
DigitalOcean
Default region · cached $0.012
$0.06 / $0.42+131% vs list
Google Vertex AI
global
$0.09 / $0.36+142% vs list
Baseten
fp4 · cached $0.1
$0.1 / $0.5+208% vs list
AWS Bedrock
Default region
$0.15 / $0.6+304% vs list
AWS Bedrock
eu-west-1
$0.15 / $0.6+304% vs list
Databricks Mosaic AI Gateway + Foundation Model APIs
From the platform pricing page
$0.15 / $0.6+304% vs list
DeepInfra
turbo, bf16
$0.15 / $0.6+304% vs list
Groq
Default region · cached $0.075
$0.15 / $0.6+304% vs list
Nebius
fp4
$0.15 / $0.6+304% vs list
OCI Generative AI
From the platform pricing page
$0.15 / $0.6+304% vs list
Phala
Default region
$0.15 / $0.6+304% vs list
SiliconFlow
fp8 · cached $0.075
$0.15 / $0.6+304% vs list
Together AI
Default region
$0.15 / $0.6+304% vs list
Parasail
fp4 · cached $0.055
$0.1 / $0.75+304% vs list
IBM watsonx.ai
From the platform pricing page
$0.159 / $0.636+328% vs list
Mara
Default region
$0.15 / $0.75+362% vs list
SambaNova
Default region
$0.14 / $0.95+427% vs list
DeepInfra
fp8
$0.2 / $0.95+496% vs list
Cerebras
fp16 · cached $0.35
$0.35 / $0.75+592% vs list

GPT-6 Luna

Way to buyIn / out per 1M
OpenAI
flex, cheapest · cached $0.005
$0.05 / $0.25-50% vs list
OpenAI API
The lab's own API · cached $0.01
$0.1 / $0.5List price
Azure AI Foundry
Default region · cached $0.01
$0.1 / $0.5Same as list
AWS Bedrock
us-east-1 · cached $0.011
$0.11 / $0.55+10% vs list
Azure AI Foundry
eu · cached $0.011
$0.11 / $0.55+10% vs list
Azure AI Foundry
us · cached $0.011
$0.11 / $0.55+10% vs list
OpenAI
fast · cached $0.02
$0.2 / $1+100% 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.