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: Qwen3.7 Max ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Qwen3.7 Max | novita | $2.00 | $1.25 | $3.75 | 1M |
| Qwen3.7 Max | orcarouter | $2.00 | $1.25 | $3.75 | 1M |
| Qwen3.7 Max | trustedrouter | $2.11 | $1.32 | $3.96 | 1M |
| Qwen: Qwen3.7 Max | kilo | $2.36 | $1.48 | $4.42 | 1M |
| Qwen: Qwen3.7 Max | openrouter | $2.36 | $1.48 | $4.42 | 1M |
| Qwen 3.7 Max | standardcompute | $2.36 | $1.48 | $4.42 | 1M |
| Qwen3.7 Max | togetherai | $2.40 | $1.50 | $4.50 | — |
| Qwen3.7 Max | edenai via Alibaba Cloud | $2.60 | $1.62 | $4.88 | 1M |
| Qwen3.7 Max | empiriolabs | $2.64 | $1.65 | $4.95 | 984K |
| Qwen3.7 Max | aihubmix | $2.70 | $1.69 | $5.07 | 1M |
| Qwen3.7 Max | ofox | $2.74 | $1.71 | $5.14 | 1.1M |
| Qwen3.7 Max | moark | $2.88 | $1.80 | $5.40 | — |
| Qwen3.7 Max | aiml | $3.20 | $2.00 | $6.00 | — |
| Qwen3.7 Max | cometapi | $3.20 | $2.00 | $6.00 | — |
| Qwen3.7 Max | abacus | $4.00 | $2.50 | $7.50 | 1M |
| Qwen3.7 Max | deepinfra | $4.00 | $2.50 | $7.50 | 256K |
| Qwen3.7 Max | edenai via DeepInfra | $4.00 | $2.50 | $7.50 | 256K |
| Qwen3.7 Max | empiriolabs | $4.00 | $2.50 | $7.50 | 984K |
| Qwen: Qwen3.7 Max | fastrouter | $4.00 | $2.50 | $7.50 | 256K |
| Qwen3.7-Max | hyper | $4.00 | $2.50 | $7.50 | 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.