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: Nano Banana 2.1 ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Nano Banana 2.1 | cometapi | $2.40 | $1.20 | $6.00 | — |
| Nano Banana 2.1 | iteracompute | $2.40 | $1.20 | $6.00 | — |
| Nano Banana 2.1 | abacus | $3.00 | $1.50 | $7.50 | 66K |
| Gemini Nano Banana 2.1 | aihubmix | $3.00 | $1.50 | $7.50 | 66K |
| Google: Nano Banana 2.1 (Gemini Nano Banana 2.1) | fastrouter | $3.00 | $1.50 | $7.50 | 131K |
| Google: Nano Banana 2.1 | kilo | $3.00 | $1.50 | $7.50 | 66K |
| Nano Banana 2.1 | ofox | $3.00 | $1.50 | $7.50 | — |
| Gemini Nano Banana 2.1 | vercel | $3.00 | $0.0336 / image | $7.50 | 131K |
| Nano Banana 2.1 | zenmux | $3.00 | $1.50 | $7.50 | — |
| Nano Banana 2.1 | aiml | $7.50 | $1.50 | $30.00 | — |
| Nano Banana 2.1 | edenai via Google | $7.50 | $1.50 | $30.00 | 66K |
| Nano Banana 2.1 | edenai via Google Vertex AI | $7.50 | $0.0336 / image | $30.00 | — |
| Nano Banana 2.1 | google-vertex | $7.50 | $1.50 | $30.00 | — |
| Nano Banana 2.1 | $7.50 | $1.50 | $30.00 | 131K | |
| gemini nano banana 2.1 | jiekou | $7.50 | $1.50 | $30.00 | — |
| Google: Nano Banana 2.1 | openrouter | $7.50 | $1.50 | $30.00 | 66K |
| Nano Banana 2.1 | poe | $7.58 | $1.52 | $30.30 | — |
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.