BroadRouter

MiniMax token counter

Updated

In short: This counter runs MiniMax's official MiniMax tokenizer.json in your browser, pinned to the same commit as our tokenizer dataset. It has 200,061 token IDs and is a 3.1 MB download. English prose takes about 125 tokens per 100 words, Modern Standard Arabic about 183.

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
MiniMax M3.1 Flash
MiniMax M3 tokenizer
Price: MiniMax M3.1 Flash at DigitalOcean, 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
…………

Cost = tokens × the model's published price per 1M input or output tokens. GPT is shown for reference only (no BroadNet price). MiniMax models are not sold by BroadNet: its row uses 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; MiniMax row counts 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 · Ministral 3 · gpt-oss · Phi-4 · Gemma 3 · 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 MiniMax M3 tokenizer is preselected and downloads once (3.1 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 MiniMax 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 MiniMax tokenizer

The MiniMax tokenizer is a byte-level BPE. It has 200,061 token IDs, 61 of them added or special tokens such as chat-format markers, and applies NFC Unicode normalisation before splitting. Text is split into words, punctuation and numbers first, then merged byte by byte. Numbers are split into groups of up to three digits, so 2026 is two tokens.

On the open texts of our tokenizer efficiency dataset it needs 1,245 tokens per 1,000 English words (rank 1 of the 16 tokenizers we measured, 1 = fewest), 2,061 per 1,000 words of Python (rank 9 of 16) and 1,828 per 1,000 words of Modern Standard Arabic (rank 4 of 16). Its best showing here is English (rank 1 of 16); its weakest is Hindi (rank 13 of 16).

5 models in our price database use this tokenizer: MiniMax M3, MiniMax M3.1 Flash, MiniMax M2.5, Minimax M2.1 and MiniMax M2. We hold 32 standard prices for them from 16 providers. The cheapest input price is $0.15 per 1M tokens, for MiniMax M3.1 Flash on DigitalOcean (checked 2026-11-14). At that price 1,000 English words cost $0.00019 to send. MiniMax models are not sold by BroadNet. BroadNet's cheapest chat model, Gemma 4 VL 26B, costs $0.00013 for the same text.

MiniMax tokenizer facts
TokenizerMiniMax M3 tokenizer, a byte-level BPE
SourceMiniMaxAI/MiniMax-M3 (commit d95e30c)
Token IDs200,061 (200,000 in the base vocabulary)
Models using it5: MiniMax M3, MiniMax M3.1 Flash, MiniMax M2.5, Minimax M2.1 and MiniMax M2
Cheapest input price$0.15 per 1M tokens (MiniMax M3.1 Flash, DigitalOcean, checked 2026-11-14)
English prose125 tokens per 100 words (rank 1 of 16)
Arabic (MSA)183 tokens per 100 words (rank 4 of 16)
Python code206 tokens per 100 words (rank 9 of 16)
Download3.1 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 MiniMax 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 MiniMax M3 tokenizer splits it into 346 tokens. Sent to MiniMax M3.1 Flash on DigitalOcean at $0.15 per 1M input tokens it costs $0.000052; the same number of tokens written as output at $0.60 per 1M costs $0.00021.

Questions

Which tokenizer does MiniMax use?

A byte-level BPE with 200,061 token IDs, published as tokenizer.json in MiniMaxAI/MiniMax-M3. This page loads that file pinned to commit d95e30c, the commit our dataset measured.

Which models use the MiniMax tokenizer?

MiniMax M3, MiniMax M3.1 Flash, MiniMax M2.5, Minimax M2.1 and MiniMax M2. 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 MiniMax API price per token?

Of the 32 standard prices we hold for MiniMax models, the lowest input price is $0.15 per 1M tokens (output $0.60), for MiniMax M3.1 Flash on DigitalOcean, 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 MiniMax?

Modern Standard Arabic sentences take 1.36× the tokens of their English translations with this tokenizer (rank 4 of 16 on the same texts). Hindi takes 2.94× and Chinese 0.92×. Measured on parallel sentences in our open dataset (2026-11-15). Paste your own text above, or use the Arabic token counter.

Is the MiniMax tokenizer the same as Kimi?

No. On the 52 texts of our dataset they gave the same count on 4; in total MiniMax needs 13.1% fewer tokens, and up to 83% on a single text. See the Kimi counter.

Does the count include chat-template tokens?

No. For MiniMax 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