Question 1

How much does Devstral cost?

Accepted Answer

Devstral costs $0.4 per 1 million input tokens and $2 per 1 million output tokens. This pricing is set by Mistral.

Question 2

What tokenizer does Devstral use?

Accepted Answer

Devstral uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.

Question 3

What is Devstral's context window?

Accepted Answer

Devstral supports a context window of 256K tokens (256,000 tokens). The maximum output length is 33K tokens.

Question 4

How does Devstral compare to other models?

Accepted Answer

You can compare Devstral's pricing and capabilities against other LLMs in the comparison table above, or visit the full pricing page for a side-by-side view of all models.

Question 5

How do I count tokens for Devstral?

Accepted Answer

Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Devstral using the cl100k_base tokenizer.

Model	Input / 1M	Output / 1M	Context	Max Output
Devstral	$0.4	$2	256K	33K
Mistral Large 3	$0.5	$1.5	262K	8K
GPT-5 Mini	$0.25	$2	400K	16K
Qwen 3.5 27B	$0.3	$2.4	128K	33K

Devstral Token Counter & Pricing

Count Tokens

Pricing Details

Compare Devstral with Similar Models

Frequently Asked Questions

Related Models