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-3.3-70B-Instruct ×

ModelProviderYour cost/mo, $Input, $Output, $Context
Llama-3.3-70B-Instructrequesty via DeepInfra$0.13$0.08$0.26131K
Llama3.3-70Bmeganova$0.16$0.10$0.30131K
Llama 3.3 70B Turbodeepinfra$0.16$0.10$0.32131K
Llama-3.3-70B-Instructedenai via DeepInfra$0.16$0.10$0.32131K
Meta: Llama 3.3 70B Instruct Turbofastrouter$0.16$0.10$0.32131K
Meta: Llama 3.3 70B Instructkilo$0.16$0.10$0.32131K
Meta: Llama 3.3 70B Instructopenrouter$0.16$0.10$0.32131K
Meta Llama 3.3 70B Instructhelicone$0.21$0.13$0.39128K
Llama-3.3-70B-Instructjiekou$0.21$0.13$0.39—
Llama-3.3-70B-Instructhuggingface$0.22$0.14$0.40131K
Llama-3.3-70B-Instructnovita$0.22$0.14$0.4012K
Meta: Llama 3.3 70B Instructtrustedrouter$0.23$0.14$0.42131K
Llama-3.3-70B-Instructdeepinfra$0.31$0.23$0.40131K
Llama-3.3-70B-Instructedenai via FlexAI$0.32$0.22$0.50131K
Llama 3.3 70Baihubmix$0.72$0.60$0.6066K
Meta: Llama 3.3 70B Instructio-net$0.74$0.58$0.77128K
Llama 3.3 70B Instruct fp8 Fastcloudflare-workers-ai$0.74$0.29$2.2524K
Llama-3.3-70B-Instructedenai via Databricks$0.80$0.50$1.50128K
Llama 3.3 70B Instructaihubmix$0.84$0.60$1.20131K
Llama-3.3-70B-Instructedenai via Arkanecloud$0.84$0.70$0.70128K

All 31 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.