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: DeepSeek-V3 ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| DeepSeek-V3 | requesty via DeepInfra | $0.40 | $0.26 | $0.71 | 128K |
| deepseek-ai/DeepSeek-V3 | siliconflow | $0.45 | $0.25 | $1.00 | 164K |
| DeepSeek V3 | helicone | $0.47 | $0.27 | $1.00 | 128K |
| deepseek-ai/DeepSeek-V3 | trustedrouter | $0.49 | $0.30 | $0.94 | 164K |
| DeepSeek V3 | aihubmix | $0.49 | $0.27 | $1.09 | — |
| DeepSeek-V3 | deepinfra | $0.50 | $0.32 | $0.89 | 164K |
| DeepSeek-V3 | edenai via DeepInfra | $0.50 | $0.32 | $0.89 | 164K |
| DeepSeek: DeepSeek V3 | fastrouter | $0.50 | $0.32 | $0.89 | 164K |
| DeepSeek-V3 | huggingface | $0.50 | $0.32 | $0.89 | 164K |
| DeepSeek-V3 | aiml | $0.55 | $0.31 | $1.21 | — |
| DeepSeek-V3.1 | amazon-bedrock | $0.92 | $0.58 | $1.68 | 164K |
| DeepSeek-V3 | edenai via Amazon Bedrock | $0.92 | $0.58 | $1.68 | 128K |
| DeepSeek-V3 | novita | $1.07 | $0.89 | $0.89 | 64K |
| DeepSeek-V3 | togetherai | $1.50 | $1.25 | $1.25 | 131K |
| DeepSeek-V3 | poe | $0.50 | $0.27 | $1.13 | 164K |
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.