AI Token Cost Calculator
Estimate token costs using only provider-sourced rates approved for this calculator. Sources checked:
Need the broader, unverified-for-this-calculator price list? Browse the API price table. Comparing metered APIs with your own hardware or a rented GPU? Run the local AI vs API calculator.
How do I use the AI token cost calculator?
- Enter expected input tokens — roughly 0.75 words or 4 characters per token. A 2,000-word prompt is ~2,700 tokens.
- Enter expected output tokens — model responses are usually 200–2,000 tokens unless you explicitly set
max_tokens. - Set monthly request volume — multiplies the single-request cost to estimate monthly spend.
- Compare rows — the approved models appear first by recommendation; switch to lowest-cost sorting whenever price is the priority.
- Click a model to open the official pricing source and check its current rate.
Methodology
The displayed subset was checked against official API pricing pages on 2026-10-08. Each result shows its source and check date. The provider page is authoritative if pricing changes. The formula for a single request is:
cost = (input_tokens / 1,000,000 * input_rate) + (output_tokens / 1,000,000 * output_rate)
When the cached-input slider is above 0%, the input portion splits into cached and non-cached fractions, each multiplied by the respective rate. Models without a published cached rate use the standard input rate for both.
Only Data-approved rate rows are used in estimates. Models and rate tiers without verified row-level provenance are excluded.
Frequently asked questions about AI token costs
How do I calculate AI API costs?
Multiply input tokens by the input rate and output tokens by the output rate, divide each by 1,000,000, then add the two amounts. This calculator also lets you estimate cached-input savings when a verified cached rate is available.
Which API models are included?
This calculator currently shows 8 Data-verified models: seven Mistral models and Claude Haiku 4.5. Other models are temporarily excluded until their exact rates have row-level official-source verification. The full API pricing table is separate and is not a list of verified calculator rows.
What is the cheapest verified model shown?
Among the 8 verified rows, Ministral 3 3B has the lowest listed output rate at $0.10 per million output tokens. Check the model's source link for current provider pricing before purchasing.
Are input and output tokens priced the same?
Not always. Each model row uses its separately verified input and output rates. Cached input has its own rate where the provider publishes one.
How accurate is this calculator?
The 8 displayed rate rows were checked against official provider pages on 2026-10-08. Each row links to its source and shows the check date. Provider pages remain authoritative, and rates may change after that date.