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: Qwen2.5-VL 72B Instruct ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Qwen2.5 VL 72B Instruct | aihubmix | $0.60 | $0.50 | $0.50 | — |
| Qwen2.5-VL 72B Instruct | jiekou | $0.96 | $0.80 | $0.80 | — |
| Qwen: Qwen2.5 VL 72B Instruct | kilo | $1.00 | $0.80 | $1.00 | 128K |
| Qwen: Qwen2.5 VL 72B Instruct | openrouter | $1.00 | $0.80 | $1.00 | 128K |
| Qwen2.5-VL 72B Instruct | trustedrouter via Parasail | $1.05 | $0.84 | $1.05 | — |
| Qwen2.5-VL 72B Instruct | edenai via OVHcloud | $1.21 | $1.01 | $1.01 | 33K |
| Qwen2.5-VL 72B Instruct | huggingface | $1.21 | $1.01 | $1.01 | 33K |
| Qwen2.5-VL 72B Instruct | ovhcloud | $1.21 | $1.01 | $1.01 | 33K |
| Qwen2.5-VL 72B Instruct | cortecs | $1.22 | $1.02 | $1.02 | 32K |
| Qwen 2.5 VL 72B Instruct | qiniu-ai | $3.71 | $2.32 | $6.96 | 128K |
| Qwen2.5 VL 72B Instruct | aihubmix | $3.84 | $2.40 | $7.20 | — |
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.