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: Hy3 ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Hy3 | deepinfra | $0.24 | $0.13 | $0.53 | 262K |
| Hy3 | edenai via DeepInfra | $0.24 | $0.13 | $0.53 | 262K |
| Hy3 | huggingface | $0.24 | $0.13 | $0.53 | 262K |
| Hy3 | edenai via Tencent Cloud | $0.24 | $0.13 | $0.53 | 256K |
| Hunyuan 3 | impossibl | $0.24 | $0.13 | $0.53 | 262K |
| Tencent: Hy3 | kilo | $0.24 | $0.13 | $0.53 | 262K |
| Tencent: Hy3 | openrouter | $0.24 | $0.13 | $0.53 | 262K |
| Hy3 | requesty via Tencent Cloud | $0.24 | $0.13 | $0.53 | 262K |
| Hy3 | siliconflow | $0.24 | $0.13 | $0.53 | — |
| Tencent: Hy3 | trustedrouter | $0.25 | $0.14 | $0.56 | 262K |
| Hy3 | novita | $0.26 | $0.14 | $0.58 | 262K |
| Hy3 | opencode-go | $0.26 | $0.14 | $0.58 | 256K |
| Tencent Hy3 | vercel | $0.26 | $0.14 | $0.58 | 262K |
| Hy3 | poe | $0.26 | $0.14 | $0.59 | 262K |
| Tencent: Hy3 | zenmux | $0.26 | $0.15 | $0.59 | 262K |
| Hy3 | kenari | $0.27 | $0.15 | $0.61 | 197K |
| Hy3 | aihubmix | $0.28 | $0.16 | $0.62 | 256K |
| Hy3 | orcarouter | $0.30 | $0.18 | $0.59 | 256K |
| Hy3 | aiml | $0.38 | $0.21 | $0.85 | — |
| Hy3 Free | opencode | Free | Free | Free | 190K |
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.