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: Inkling ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Inkling | deepinfra | $1.76 | $0.95 | $4.05 | 524K |
| Inkling | edenai via DeepInfra | $1.76 | $0.95 | $4.05 | 524K |
| Inkling | huggingface | $1.76 | $0.95 | $4.05 | 1M |
| Inkling | baseten | $1.81 | $1.00 | $4.05 | — |
| Inkling | fireworks-ai | $1.81 | $1.00 | $4.05 | — |
| Thinking Machines: Inkling | kilo | $1.81 | $1.00 | $4.05 | 524K |
| Thinking Machines: Inkling | openrouter | $1.81 | $1.00 | $4.05 | 524K |
| Inkling | togetherai | $1.81 | $1.00 | $4.05 | — |
| Inkling | vercel | $1.81 | $1.00 | $4.05 | 256K |
| Inkling | poe | $1.83 | $1.01 | $4.09 | 256K |
| Thinking Machines: Inkling | trustedrouter | $1.91 | $1.05 | $4.27 | 524K |
| Inkling | aiml | $1.91 | $1.06 | $4.28 | — |
| Inkling | hyper | $1.97 | $1.09 | $4.41 | 1M |
| Inkling | modal | $2.20 | $1.20 | $5.00 | — |
| Inkling | impossibl | $2.81 | $1.87 | $4.68 | 66K |
| Inkling | requesty via Thinkingmachines | $2.81 | $1.87 | $4.68 | 66K |
| Tinker Inkling | abacus | $5.61 | $3.74 | $9.36 | 262K |
| Inkling 256K | impossibl | $5.61 | $3.74 | $9.36 | 262K |
| Thinking Machines: Inkling (free) | openrouter | Free | Free | Free | 1M |
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.