AI Rate Card

Tools: pick a model by cost

Find the cheapest offer for your monthly workload, count the tokens of a prompt, convert price units.

Cost picker

How many tokens a month you send to the model (input) and get back (output), in millions. For example, a chatbot with 1,000 conversations a day is about 10 M input and 2 M output. Don't know your numbers? Count them below in the token estimator.

Model: Llama 4 Maverick 17B Instruct ×

ModelProviderYour cost/mo, $Input, $Output, $Context
Llama 4 Maverickaihubmix$0.24$0.20$0.201M
Meta Llama 4 Maverick 17B 128Ehelicone$0.27$0.15$0.60131K
Meta: Llama 4 Maverickkilo$0.32$0.19$0.65524K
Meta: Llama 4 Maverickopenrouter$0.32$0.19$0.65524K
Llama 4 Maverick 17B Instructjiekou$0.34$0.17$0.85—
Llama 4 Maverick 17B FP8deepinfra$0.36$0.20$0.801M
Llama 4 Maverick 17B Instructedenai via DeepInfra$0.36$0.20$0.801M
Llama 4 Maverick 17B Instructrequesty via Novita AI$0.37$0.20$0.851M
Llama 4 Maverick 17B Instructdigitalocean$0.42$0.25$0.87—
Llama 4 Maverick 17B Instructamazon-bedrock$0.43$0.24$0.97—
Llama 4 Maverick 17B Instruct (US)amazon-bedrock$0.43$0.24$0.97—
Meta-Llama: Llama 4 Maverick 17B 128E Instruct FP8io-net$0.43$0.27$0.83430K
Llama 4 Maverick 17B Instructvercel$0.43$0.24$0.97128K
Llama 4 Maverick 17B Instructpoe$0.44$0.24$0.98128K
Llama 4 Maverick 17B Instructhuggingface$0.44$0.27$0.851M
Llama 4 Maverick 17B Instructnovita$0.44$0.27$0.851M
Meta: Llama 4 Mavericktrustedrouter$0.45$0.26$0.92128K
Llama 4 Maverick Instructtrustedrouter$0.46$0.28$0.871M
Llama 4 Maverick 17B Instructgoogle-vertex$0.58$0.35$1.15—
Llama 4 Maverick 17B Instructibm-watsonx$0.67$0.37$1.48—

All 23 in Models

Token estimator

Don't know your workload in tokens? Paste an example of your prompt, say how many such requests you make a month and how long an answer is: you get the monthly workload. The button puts it into the picker above and shows the offers.

Price units

Providers quote per token, per 1K or per 1M tokens: the same price in all three.

AI picker

Describe the task in your own words - what the model must do, how fast, the budget, the region - and get a short list of models and providers with the reasons.

Coming soon.