AI Rate CardTools: 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: Gemma 3 12B IT ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Google: Gemma 3 12B | kilo | $0.064 | $0.04 | $0.12 | 131K |
| Google Gemma 3 12B | helicone | $0.07 | $0.05 | $0.10 | 131K |
| Gemma 3 12B IT | jiekou | $0.07 | $0.05 | $0.10 | — |
| Gemma 3 12B IT | novita | $0.07 | $0.05 | $0.10 | 131K |
| Google: Gemma 3 12B | trustedrouter | $0.07385 | $0.05275 | $0.11 | 131K |
| Gemma 3 12B IT | deepinfra | $0.08 | $0.05 | $0.15 | 131K |
| Gemma 3 12B IT | edenai via DeepInfra | $0.08 | $0.05 | $0.15 | 131K |
| Google: Gemma 3 12B IT | fastrouter | $0.08 | $0.05 | $0.15 | 131K |
| Gemma 3 12B IT | huggingface | $0.08 | $0.05 | $0.15 | 131K |
| Google: Gemma 3 12B | openrouter | $0.08 | $0.05 | $0.15 | 131K |
| Gemma 3 12B IT | aiml | $0.08464 | $0.0529 | $0.16 | — |
| Gemma 3 12B IT | amazon-bedrock | $0.15 | $0.09 | $0.29 | — |
| Gemma 3 12B IT | edenai via Amazon Bedrock | $0.15 | $0.09 | $0.29 | 128K |
| Gemma 3 12B It | aihubmix | $0.24 | $0.20 | $0.20 | — |
| Gemma 3 12B IT | edenai via Databricks | $0.25 | $0.15 | $0.50 | 128K |
| Gemma 3 12B It | aihubmix | $0.36 | $0.20 | $0.80 | — |
| Gemma 3 12B IT | cloudflare-workers-ai | $0.46 | $0.34 | $0.56 | — |
| Gemma 3 12B IT | nvidia | Free | Free | Free | 131K |
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.