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: Nemotron 3 Ultra 550B A55B ×

ModelProviderYour cost/mo, $Input, $Output, $Context
nemotron-3-ultraollama-cloud$0.70$0.10$3.00262K
Nemotron 3 Ultra 550B A55Bollama$0.70$0.10$3.00—
Nemotron 3 Ultra 550B A55Brequesty via Doubleword$0.74$0.37$1.87262K
NVIDIA: Nemotron 3 Ultrakilo$0.75$0.40$1.76262K
Nemotron 3 Ultra 550B A55Bdeepinfra$0.94$0.50$2.20—
Nemotron 3 Ultra 550B A55Bedenai via DeepInfra$0.94$0.50$2.20262K
NVIDIA: Nemotron 3 Ultra 550B A55Bfastrouter$0.94$0.50$2.20262K
NVIDIA: Nemotron 3 Ultratrustedrouter$0.98$0.53$2.27262K
Nemotron 3 Ultra 550B A55Bbaseten$1.08$0.60$2.40—
Nemotron 3 Ultra 550B A55Bfireworks-ai$1.08$0.60$2.40—
Nemotron 3 Ultra 550B A55Bimpossibl$1.08$0.60$2.40262K
NVIDIA: Nemotron 3 Ultraopenrouter$1.08$0.60$2.40262K
Nemotron 3 Ultravercel$1.08$0.60$2.401M
Nemotron 3 Ultra 550B A55Bdigitalocean$1.24$0.90$1.70—
Nemotron 3 Ultra 550B A55Bedenai via Arkanecloud$1.30$0.60$3.50512K
Nemotron 3 Ultra 550B A55Btrustedrouter via Digitalocean Gradient AI$1.31$0.95$1.79—
Nemotron 3 Ultra 550B A55Btogetherai$1.32$0.60$3.60512K
Nemotron 3 Ultra 550B A55Baiml$1.40$0.63$3.81—
Nemotron 3 Ultra 550B A55Bkenari$1.49$0.66$4.141M
Nemotron 3 Ultra 550B A55Bedenai via Nebius$1.60$1.00$3.001M

All 29 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.