ScalewaySkip to loginSkip to main contentSkip to footer section
Home PricingModel-as-a-service

Model-as-a-service

Serve Generative AI models and pay for a dedicated infrastructure or for millions of tokens

Generative APIs

Serve the latest AI models via API, pay by million token

NameProviderTasksInput tokensOutput tokens
qwen3-235b-a22b-instruct-2507QwenChat€0.75 /million tokens€2.25 /million tokensOrder
gpt-oss-120bOpenAIChat€0.15 /million tokens€0.60 /million tokensOrder
gemma-3-27b-itGoogleChat and Vision€0.25 /million tokens€0.50 /million tokensOrder
voxtral-small-24b-2507MistralAudio transcription and Chat€0.15 /million tokens€0.35 /million tokensOrder
mistral-small-3.2-24b-instruct-2506MistralChat and Vision€0.15 /million tokens€0.35 /million tokensOrder
llama-3.3-70b-instructMetaChat€0.90 /million tokens€0.90 /million tokensOrder
deepseek-r1-distill-llama-70bDeepseekChat€0.90 /million tokens€0.90 /million tokensOrder
bge-multilingual-gemma2BAAIEmbeddings€0.10 /million tokensFree /million tokensOrder
pixtral-12b-2409MistralChat and Vision€0.20 /million tokens€0.20 /million tokensOrder
qwen3-coder-30b-a3b-instructQwenChat€0.20 /million tokens€0.80 /million tokensOrder
mistral-nemo-instruct-2407MistralChat€0.20 /million tokens€0.20 /million tokensOrder
llama-3.1-8b-instructMetaChat€0.20 /million tokens€0.20 /million tokensOrder
mistral-small-3.1-24b-instruct-2503MistralChat and Vision€0.15 /million tokens€0.35 /million tokensOrder
qwen2.5-coder-32b-instructQwenChat€0.90 /million tokens€0.90 /million tokensOrder
llama-3.1-70b-instructMetaChat€0.90 /million tokens€0.90 /million tokensOrder
devstral-small-2505MistralChat€0.15 /million tokens€0.35 /million tokensOrder
Legal notice

Prices before tax.
You benefit from a free tier on the first 1,000,000 tokens. You'll be charged from token number 1,000,001.

Managed Inference

Deploy your managed AI infrastructure with dedicated GPUs and optimized models. You are charged for usage of the GPU type you choose. Billing only starts once the model is deployed

ModelGPUPriceApprox. per month
llama-3.1-8b-instructL4-1-24G€0.93/hour~€679/month
L40S-1-48G€1.72/hour~€1256/month
H100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
llama-3.3-70b-instructH100-2-80G€6.68/hour~€4876/month
llama-3.1-70b-instructH100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
llama-3.1-nemotron-70b-instructH100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
mistral-7b-instruct-v0.3L4-1-24G€0.93/hour~€679/month
L40S-1-48G€1.72/hour~€1256/month
H100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
mixtral-8x7b-instruct-v0.1H100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
mistral-nemo-instruct-2407L40S-1-48G€1.72/hour~€1256/month
H100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
pixtral-12b-2409L40S-1-48G€1.72/hour~€1256/month
H100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
molmo-72b-0924H100-2-80G€6.68/hour~€4876/month
qwen2.5-coder-32b-instructH100-1-80G€3.40/hour~€2482/month
H100-2-80G€6.68/hour~€4876/month
bge-multilingual-gemma2L4-1-24G€0.93/hour~€679/month
L40S-1-48G€1.72/hour~€1256/month
sentence-t5-xxlL4-1-24G€0.93/hour~€679/month
Legal notice

Prices before tax

Go to product pageCreate your account