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-3.1-8B-Instruct ×

ModelProviderYour cost/mo, $Input, $Output, $Context
Llama 3.1 8B Instruct (free)aihubmix$0.024$0.02$0.02—
Meta Llama 3.1 8B Instruct Turbohelicone$0.026$0.02$0.03128K
Llama-3.1-8B-Instructdeepinfra$0.028$0.02$0.04131K
Meta: Llama 3.1 8B Instruct Turbofastrouter$0.028$0.02$0.04131K
Meta: Llama 3.1 8B Instructkilo$0.028$0.02$0.04131K
Llama-3.1-8B-Instructtrustedrouter via DeepInfra$0.02954$0.0211$0.0422—
Llama-3.1-8B-Instructdeepinfra$0.03$0.02$0.05131K
Llama-3.1-8B-Instructedenai via DeepInfra$0.03$0.02$0.05131K
Llama-3.1-8B-Instructedenai via FlexAI$0.03$0.02$0.05131K
Meta Llama 3.1 8B Instructhelicone$0.03$0.02$0.0516K
Llama-3.1-8B-Instructhuggingface$0.03$0.02$0.05131K
Llama-3.1-8B-Instructjiekou$0.03$0.02$0.05—
Llama-3.1-8B-Instructnovita$0.03$0.02$0.0516K
Llama-3.1-8B-Instructrequesty via DeepInfra$0.03$0.02$0.05131K
Meta: Llama 3.1 8B Instructtrustedrouter$0.03165$0.0211$0.05275131K
Meta Llama 3.1 8B Instructtrustedrouter$0.03376$0.0211$0.0633128K
Meta Llama 3.1 8B Instanthelicone$0.066$0.05$0.08131K
Meta: Llama 3.1 8B Instructopenrouter$0.066$0.05$0.08131K
Llama-3.1-8B-Instructcloudflare-workers-ai$0.18$0.12$0.27—
Llama-3.1-8B-Instructedenai via Arkanecloud$0.18$0.15$0.15131K

All 28 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.