Question 1

Which tokenizer does Mistral use?

Accepted Answer

Mistral uses its own tokenizer, which is not publicly available to run in a browser. This counter estimates counts with OpenAI's cl100k_base encoding, which is typically within roughly 10 to 20 percent of the real count for English text.

Question 2

Are these Mistral token counts exact or estimated?

Accepted Answer

Estimated. Mistral has not released its tokenizer for browser use, so this tool approximates counts with OpenAI's cl100k_base encoding. Estimates are usually close for English text but can drift for code, JSON, and non-English languages. Estimated counts are marked with a tilde (~).

Question 3

How is Mistral API cost calculated?

Accepted Answer

Cost equals tokens divided by one million, multiplied by the model's per-million-token rate. Each Mistral model has separate input and output rates, and this page shows both: what your text would cost as a prompt (input) and what the same number of tokens would cost as a response (output).

Question 4

Why do token counts matter for Mistral API costs?

Accepted Answer

Mistral bills API usage per token, not per word or character. A token is roughly 4 characters or about three quarters of a word in English. Knowing the token count of your prompts lets you predict spend, stay inside context windows, and compare Mistral models like Voxtral TTS, Mistral Large 4 and Mistral Large 3 before you commit.

Model	Tokens	Input Cost	Output Cost
Voxtral TTS	—	—	—
Mistral Large 4	—	—	—
Mistral Large 3	—	—	—
Mistral Medium 3.5	—	—	—
Mistral Small 4	—	—	—
Codestral	—	—	—
Ministral 3 8B	—	—	—
Ministral 3 14B	—	—	—

Model	Input /1M	Output /1M	Context
Voxtral TTS	$16.00	<$0.0001	128K
Mistral Large 4	$0.680	$2.09	1.0M
Mistral Large 3	$0.500	$1.50	262K
Mistral Medium 3.5	$1.50	$7.50	256K
Mistral Small 4	$0.150	$0.600	256K
Codestral	$0.300	$0.900	256K
Ministral 3 8B	$0.150	$0.150	262K
Ministral 3 14B	$0.200	$0.200	262K

Mistral Token Counter

Mistral Model Pricing

Frequently Asked Questions

Related Tools