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 Scout 17B Instruct ×

ModelProviderYour cost/mo, $Input, $Output, $Context
Meta: Llama 4 Scoutkilo$0.13$0.08$0.241.3M
Meta Llama 4 Scout 17B 16Ehelicone$0.14$0.08$0.30131K
Llama 4 Scout 17Bdeepinfra$0.16$0.10$0.30328K
Llama 4 Scout 17B Instructedenai via DeepInfra$0.16$0.10$0.30328K
Meta: LLaMA 4 Scout 17B 16E Instructfastrouter$0.16$0.10$0.3033K
Llama 4 Scout 17B Instructhuggingface$0.16$0.10$0.30890K
Meta: Llama 4 Scoutopenrouter$0.16$0.10$0.301.3M
Meta: Llama 4 Scout Instructzenmux$0.16$0.08$0.40131K
Llama 4 Scout Instructtrustedrouter$0.17$0.11$0.32131K
Llama 4 Scout 17B Instructjiekou$0.20$0.10$0.50—
Llama 4 Scoutaihubmix$0.24$0.20$0.20131K
Llama 4 Scout 17B Instructnovita$0.30$0.18$0.59131K
Llama 4 Scout 17B Instructamazon-bedrock$0.30$0.17$0.66—
Llama 4 Scout 17B Instruct (US)amazon-bedrock$0.30$0.17$0.66—
Llama 4 Scout 17B Instructvercel$0.30$0.17$0.66128K
Llama 4 Scout 17B 16E Instructazure$0.36$0.20$0.78128K
Llama 4 Scout 17B Instructaiml$0.39$0.23$0.77—
Llama 4 Scout 17B Instructgoogle-vertex$0.39$0.25$0.70—
Llama 4 Scout 17B 16E Instructcloudflare-workers-ai$0.44$0.27$0.85131K
Llama 4 Scout 17B Instructedenai via Cloudflare$0.44$0.27$0.85131K

All 20 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.