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: Hy4 preview ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Hy4 preview | kenari | $1.12 | $0.66 | $2.32 | 1M |
| Tencent: Hy4 Preview | fastrouter | $1.27 | $0.79 | $2.38 | 1M |
| Hy4 preview | deepinfra | $1.33 | $0.83 | $2.50 | — |
| Hy4 preview | edenai via DeepInfra | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | edenai via Tencent Cloud | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | huggingface | $1.33 | $0.83 | $2.50 | 1M |
| Hunyuan 4 Preview | impossibl | $1.33 | $0.83 | $2.50 | 1M |
| Tencent: Hy4 Preview | io-net | $1.33 | $0.83 | $2.50 | 262K |
| Tencent: Hy4 preview | kilo | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | novita | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | opencode-go | $1.33 | $0.83 | $2.50 | 1M |
| Tencent: Hy4 preview | openrouter | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | requesty via Tencent Cloud | $1.33 | $0.83 | $2.50 | 1M |
| Tencent Hy4 Preview | vercel | $1.33 | $0.83 | $2.50 | 1M |
| Hy4 preview | zenmux | $1.33 | $0.83 | $2.50 | — |
| Hy4 Preview | aihubmix | $1.35 | $0.84 | $2.54 | 1M |
| Tencent: Hy4 preview | trustedrouter | $1.41 | $0.88 | $2.64 | 1M |
| Hy4 preview | aiml | $1.41 | $0.88 | $2.65 | — |
| Hy4 preview | poe | $1.35 | $0.84 | $2.53 | — |
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.