Mistral Small token counter
Updated
In short: This counter runs Mistral AI's official Mistral Small 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 179.
tokens
| Model | Tokens | Chars per token | As input | As output |
|---|---|---|---|---|
| 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) | … | … | … | … |
| 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 | … | … | … | … |
| Ministral 3 3B Ministral 3 tokenizer (Tekken, Ministral 3 14B) Price: Ministral 3 3B at Amazon Bedrock, 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). Mistral Small and Ministral 3 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; Mistral Small and Ministral 3 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.
Other counters: DeepSeek · GLM · Qwen · Gemma · GPT · Llama 3 · Llama 4 · Kimi · Ministral 3 · 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
- Paste text into the box or pick a sample. The Mistral Small 3.1 tokenizer (Tekken) is preselected and downloads once (17 MB) when you start typing.
- The text appears split into tokens, a colour per token; tick "Show token IDs" to see the numbers.
- Compare the Mistral Small count with the other tokenizers in the table; load any of them for an exact count.
- Copy the link or download a CSV of the counts and costs.
About the Mistral Small tokenizer
The Mistral Small 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 12 of the 16 tokenizers we measured, 1 = fewest), 2,096 per 1,000 words of Python (rank 10 of 16) and 1,790 per 1,000 words of Modern Standard Arabic (rank 3 of 16). Its best showing here is Arabic MSA (rank 3 of 16); its weakest is Chinese (rank 13 of 16).
2 models in our price database use this tokenizer: Mistral Small 3.1 24B Instruct and Mistral-Small-24B-Instruct-2501. We hold 6 standard prices for them from 5 providers. The cheapest input price is $0.05 per 1M tokens, for Mistral-Small-24B-Instruct-2501 on DeepInfra (checked 2026-11-14). At that price 1,000 English words cost $0.000065 to send. Mistral Small models are not sold by BroadNet. That is less than BroadNet's cheapest chat model, Gemma 4 VL 26B, at $0.00013 for the same text.
| Tokenizer | Mistral Small 3.1 tokenizer (Tekken), a byte-level BPE |
|---|---|
| Source | mistralai/Mistral-Small-3.1-24B-Instruct-2503 (commit 68faf51) |
| Token IDs | 131,072, special tokens included |
| Models using it | 2: Mistral Small 3.1 24B Instruct and Mistral-Small-24B-Instruct-2501 |
| Cheapest input price | $0.05 per 1M tokens (Mistral-Small-24B-Instruct-2501, DeepInfra, checked 2026-11-14) |
| English prose | 130 tokens per 100 words (rank 12 of 16) |
| Arabic (MSA) | 179 tokens per 100 words (rank 3 of 16) |
| Python code | 210 tokens per 100 words (rank 10 of 16) |
| Download | 17 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 Mistral Small prompt cost?
input cost = tokens × input price per 1M ÷ 1,000,000
output cost = tokens × output price per 1M ÷ 1,000,000Worked example: "English Wikipedia: Water" in our dataset is 274 words. The Mistral Small 3.1 tokenizer (Tekken) splits it into 361 tokens. Sent to Mistral-Small-24B-Instruct-2501 on DeepInfra at $0.05 per 1M input tokens it costs $0.000018; the same number of tokens written as output at $0.08 per 1M costs $0.000029.
Questions
Which tokenizer does Mistral Small use?
A byte-level BPE with 131,072 token IDs, published as tokenizer.json in mistralai/Mistral-Small-3.1-24B-Instruct-2503. This page loads that file pinned to commit 68faf51, the commit our dataset measured.
Which models use the Mistral Small tokenizer?
Mistral Small 3.1 24B Instruct and Mistral-Small-24B-Instruct-2501. 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. Not covered: Mistral Small 3.2 24B Instruct (no tokenizer.json in the repo).
What is the cheapest Mistral Small API price per token?
Of the 6 standard prices we hold for Mistral Small models, the lowest input price is $0.05 per 1M tokens (output $0.08), for Mistral-Small-24B-Instruct-2501 on DeepInfra, 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 Mistral Small?
Modern Standard Arabic sentences take 1.27× the tokens of their English translations with this tokenizer (rank 3 of 16 on the same texts). Hindi takes 2.76× 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 Mistral Small tokenizer the same as Ministral 3?
No. On the 52 texts of our dataset they gave the same count on 30; in total Mistral Small needs 6.9% more tokens, and up to 54% on a single text. See the Ministral 3 counter.
Does the count include chat-template tokens?
No. For Mistral Small 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.