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 Large 3 ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| Mistral Large 3 | aihubmix | $0.80 | $0.50 | $1.50 | 256K |
| Mistral Large 3 | amazon-bedrock | $0.80 | $0.50 | $1.50 | — |
| Mistral Large 3 | edenai via Amazon Bedrock | $0.80 | $0.50 | $1.50 | 256K |
| Mistral Large 3 | edenai via Azure | $0.80 | $0.50 | $1.50 | 256K |
| Mistral Large 3 | impossibl | $0.80 | $0.50 | $1.50 | 128K |
| Mistral: Mistral Large 3 2512 | kilo | $0.80 | $0.50 | $1.50 | 262K |
| Mistral Large 3 | ollama-cloud | $0.80 | $0.50 | $1.50 | — |
| Mistral Large 3 | ollama | $0.80 | $0.50 | $1.50 | — |
| Mistral: Mistral Large 3 2512 | openrouter | $0.80 | $0.50 | $1.50 | 262K |
| Mistral Large 3 | vercel | $0.80 | $0.50 | $1.50 | 262K |
| Mistral: Mistral Large 3 | zenmux | $0.80 | $0.50 | $1.50 | 256K |
| Mistral Large 3 | trustedrouter | $0.84 | $0.53 | $1.58 | — |
| Mistral Large 3 | edenai via Azure | $0.88 | $0.55 | $1.65 | 256K |
| Mistral Large 3 | cortecs | $0.98 | $0.61 | $1.84 | 256K |
| Mistral Large 3 | ibm-watsonx | $1.02 | $0.64 | $1.91 | — |
| mistral-large-2512 | 302ai | $1.76 | $1.10 | $3.30 | 128K |
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.