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: Phi-4 ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Microsoft: Phi 4 | kilo | $0.0784 | $0.056 | $0.11 | 16K |
| Phi-4 | requesty via DeepInfra | $0.0784 | $0.056 | $0.11 | 16K |
| Phi-4 | deepinfra | $0.098 | $0.07 | $0.14 | 16K |
| Phi-4 | edenai via DeepInfra | $0.098 | $0.07 | $0.14 | 16K |
| Microsoft: Phi 4 | fastrouter | $0.098 | $0.07 | $0.14 | 16K |
| Phi-4 | huggingface | $0.098 | $0.07 | $0.14 | 16K |
| Microsoft: Phi 4 | openrouter | $0.098 | $0.07 | $0.14 | 16K |
| Phi-4 | trustedrouter via DeepInfra | $0.10 | $0.07385 | $0.15 | — |
| Phi-4 | azure | $0.23 | $0.12 | $0.50 | 128K |
| Phi-4 | impossibl | $0.23 | $0.12 | $0.50 | 16K |
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.