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: Mistral Nemo ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Mistral-Nemo-Instruct-2407 | meganova | $0.028 | $0.02 | $0.04 | 131K |
| Mistral Nemo | edenai via FlexAI | $0.029 | $0.023 | $0.03 | 131K |
| Mistral Nemo | deepinfra | $0.035 | $0.029 | $0.03 | 131K |
| Mistral Nemo | edenai via DeepInfra | $0.035 | $0.029 | $0.03 | 131K |
| Mistral: Mistral Nemo | fastrouter | $0.035 | $0.029 | $0.03 | 131K |
| Mistral: Mistral Nemo | openrouter | $0.035 | $0.029 | $0.03 | 131K |
| Mistral Nemo 12B | vercel | $0.035 | $0.029 | $0.03 | 131K |
| mistralai/Mistral-Nemo-Instruct-2407 | trustedrouter | $0.03692 | $0.0306 | $0.03165 | 131K |
| Mistral Nemo Instruct 2407 TEE | chutes | $0.04406 | $0.0245 | $0.0978 | 131K |
| Mistral: Mistral Nemo Instruct 2407 | io-net | $0.06875 | $0.05675 | $0.06 | 128K |
| Mistral Nemo | jiekou | $0.074 | $0.04 | $0.17 | — |
| Mistral Nemo | edenai via OVHcloud | $0.17 | $0.14 | $0.14 | 66K |
| Mistral Nemo | ovhcloud | $0.17 | $0.14 | $0.14 | 66K |
| Mistral Nemo | cortecs | $0.17 | $0.15 | $0.15 | 118K |
| Mistral: Mistral Nemo | kilo | $0.18 | $0.15 | $0.15 | 131K |
| Mistral Nemo | aiml | $0.19 | $0.16 | $0.18 | — |
| Mistral Nemo | requesty via Novita AI | $0.20 | $0.17 | $0.17 | 131K |
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.