BroadRouter

Ministral 3 token counter

Updated

In short: This counter runs Mistral AI's official Ministral 3 tokenizer.json in your browser, pinned to the same commit as our tokenizer dataset. It has 131,072 token IDs and is a 17 MB download. English prose takes about 130 tokens per 100 words, Modern Standard Arabic about 176.

Free, no sign-up, runs in your browser: nothing you type is sent anywhere.

Try:

… tokens

Tokens and cost of this text per model
ModelTokensChars per tokenAs inputAs output
Ministral 3 3B
Ministral 3 tokenizer (Tekken, Ministral 3 14B)
Price: Ministral 3 3B at Amazon Bedrock, cheapest listed input price (not BroadNet)
…………
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash tokenizer
…………
GLM 5.3
GLM 5.3 tokenizer
…………
Qwen3.8 27B
Qwen3.8 27B tokenizer
…………
Gemma 4 VL 26B
Gemma 4 tokenizer (Google base model)
…………
GPT (o200k)
OpenAI o200k_base
…………
Mistral-Small-24B-Instruct-2501
Mistral Small 3.1 tokenizer (Tekken)
Price: Mistral-Small-24B-Instruct-2501 at DeepInfra, cheapest listed input price (not BroadNet)
…………

Cost = tokens × the model's published price per 1M input or output tokens. GPT is shown for reference only (no BroadNet price). Ministral 3 and Mistral Small models are not sold by BroadNet: their rows use the cheapest standard input price we hold for a model with that tokenizer, read from the provider's own pricing page. Sources and check dates are in the real cost by language dataset. The chat-format option adds template tokens only for the DeepSeek, GLM, Qwen, Gemma and GPT rows; Ministral 3 and Mistral Small rows count your text alone. Measured ratios for every tokenizer are in the tokenizer efficiency dataset. Rows marked ≈ are estimates from measured characters per token until you load that tokenizer; loading downloads its tokenizer.json from Hugging Face once and keeps it in your browser cache.

Create an account ($5 starting credit)

Other counters: DeepSeek · GLM · Qwen · Gemma · GPT · Llama 3 · Llama 4 · Kimi · Mistral Small · gpt-oss · Phi-4 · Gemma 3 · MiniMax · Nemotron 3 · Qwen3 · all models. BroadNet prices synced 2026-11-14.

Report a wrong price or number (email to info@broadnet.ai, with this page's link and your inputs filled in).

How it works

  1. Paste text into the box or pick a sample. The Ministral 3 tokenizer (Tekken, Ministral 3 14B) is preselected and downloads once (17 MB) when you start typing.
  2. The text appears split into tokens, a colour per token; tick "Show token IDs" to see the numbers.
  3. Compare the Ministral 3 count with the other tokenizers in the table; load any of them for an exact count.
  4. Copy the link or download a CSV of the counts and costs.

About the Ministral 3 tokenizer

The Ministral 3 tokenizer is a byte-level BPE. It has 131,072 token IDs, 1,000 of them added or special tokens such as chat-format markers. Text is split into words, punctuation and numbers first, then merged byte by byte. Numbers are split into single digits, so 2026 is four tokens.

On the open texts of our tokenizer efficiency dataset it needs 1,302 tokens per 1,000 English words (rank 13 of the 16 tokenizers we measured, 1 = fewest), 2,096 per 1,000 words of Python (rank 11 of 16) and 1,760 per 1,000 words of Modern Standard Arabic (rank 1 of 16). Its best showing here is Arabic MSA (rank 1 of 16); its weakest is Chinese (rank 14 of 16).

4 models in our price database use this tokenizer: Ministral 3 14B, Ministral 3 8B, Ministral 3 3B and Devstral 2 123B. We hold 8 standard prices for them from 3 providers. The cheapest input price is $0.10 per 1M tokens, for Ministral 3 3B on Amazon Bedrock (checked 2026-11-14). At that price 1,000 English words cost $0.00013 to send. Ministral 3 models are not sold by BroadNet. BroadNet's cheapest chat model, Gemma 4 VL 26B, costs about the same for this text.

Ministral 3 tokenizer facts
TokenizerMinistral 3 tokenizer (Tekken, Ministral 3 14B), a byte-level BPE
Sourcemistralai/Ministral-3-14B-Instruct-2512 (commit 29439f8)
Token IDs131,072, special tokens included
Models using it4: Ministral 3 14B, Ministral 3 8B, Ministral 3 3B and Devstral 2 123B
Cheapest input price$0.10 per 1M tokens (Ministral 3 3B, Amazon Bedrock, checked 2026-11-14)
English prose130 tokens per 100 words (rank 13 of 16)
Arabic (MSA)176 tokens per 100 words (rank 1 of 16)
Python code210 tokens per 100 words (rank 11 of 16)
Download17 MB, once; then cached in your browser

Tokens per 100 words measured on the open texts of our dataset with all 16 tokenizers (2026-11-15); rank 1 = fewest tokens on the same texts. Model mapping checked 2026-11-15. Third-party prices are standard-tier prices from each provider's own page; BroadNet prices come from its pricing.json.

How much does a Ministral 3 prompt cost?

input cost  = tokens × input price per 1M  ÷ 1,000,000
output cost = tokens × output price per 1M ÷ 1,000,000

Worked example: "English Wikipedia: Water" in our dataset is 274 words. The Ministral 3 tokenizer (Tekken, Ministral 3 14B) splits it into 361 tokens. Sent to Ministral 3 3B on Amazon Bedrock at $0.10 per 1M input tokens it costs $0.000036; the same number of tokens written as output at $0.10 per 1M costs $0.000036.

Questions

Which tokenizer does Ministral 3 use?

A byte-level BPE with 131,072 token IDs, published as tokenizer.json in mistralai/Ministral-3-14B-Instruct-2512. This page loads that file pinned to commit 29439f8, the commit our dataset measured.

Which models use the Ministral 3 tokenizer?

Ministral 3 14B, Ministral 3 8B, Ministral 3 3B and Devstral 2 123B. Each was checked against the model's own Hugging Face repo on 2026-11-15: same tokenizer file, or the same vocabulary and rules with identical counts on every dataset text.

What is the cheapest Ministral 3 API price per token?

Of the 8 standard prices we hold for Ministral 3 models, the lowest input price is $0.10 per 1M tokens (output $0.10), for Ministral 3 3B on Amazon Bedrock, read from the provider's pricing page on 2026-11-14. Promotional prices are not ranked. Prices differ by model size and provider: each model's price page lists every provider we hold.

How many tokens does Arabic take with Ministral 3?

Modern Standard Arabic sentences take 1.25× the tokens of their English translations with this tokenizer (rank 1 of 16 on the same texts). Hindi takes 1.80× and Chinese 1.42×. Measured on parallel sentences in our open dataset (2026-11-15). Paste your own text above, or use the Arabic token counter.

Is the Ministral 3 tokenizer the same as Mistral Small?

No. On the 52 texts of our dataset they gave the same count on 30; in total Ministral 3 needs 6.4% fewer tokens, and up to 35% on a single text. See the Mistral Small counter.

Does the count include chat-template tokens?

No. For Ministral 3 this page counts your text only, as our dataset does. A chat request also adds the chat template's role markers and special tokens, so the billed prompt is a little longer than your text. Read usage.prompt_tokens on a real response to see the exact figure.

Go deeper

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity