BroadRouter

GPT token counter

Updated

In short: This counter uses o200k_base, the encoding OpenAI's tiktoken uses for GPT-4o, GPT-4.1, the o-series and GPT-5 models, via the gpt-tokenizer library. It has 200,019 token IDs. The table puts the same text through DeepSeek, Qwen, GLM and Gemma tokenizers for comparison.

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
GPT (o200k)
OpenAI o200k_base
…………
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)
…………

Cost = tokens × the model's published price per 1M input or output tokens. GPT is shown for reference only (no BroadNet price). 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 · Llama 3 · Llama 4 · Kimi · Mistral Small · Ministral 3 · gpt-oss · Phi-4 · Gemma 3 · MiniMax · Nemotron 3 · Qwen3 · all models. 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 OpenAI o200k_base is preselected and downloads once (1.1 MB) when you start.
  2. The text appears split into tokens, a colour per token; tick "Show token IDs" to see the numbers.
  3. Tick "Chat format" to include the system prompt and chat-template tokens a request adds.
  4. Compare the table with the other models and copy the link or download CSV.

About the GPT tokenizer

o200k_base is a byte-level BPE encoding with 199,998 merge ranks plus special tokens. It replaced cl100k_base (GPT-4 and GPT-3.5) and is far better on non-English text. The counter uses gpt-tokenizer, which we checked gives the same token IDs as OpenAI's tiktoken on every sample on this page.

BroadNet does not sell GPT models, so this page shows no GPT price. It is here so you can see how a GPT-based estimate compares with the tokenizer of the open model you may move to: on our Modern Standard Arabic texts o200k needs 189 tokens per 100 words against 222 for DeepSeek V4.1 Flash.

GPT tokenizer facts
TokenizerOpenAI o200k_base
Sourceo200k_base via gpt-tokenizer
Token IDs200,019 (199,998 in the base vocabulary)
English prose127 tokens per 100 words (rank 1 of 5)
Arabic189 tokens per 100 words (rank 2 of 5)
Python code203 tokens per 100 words (rank 2 of 5)
Download1.1 MB, once; then cached in your browser

Tokens per 100 words measured on the open texts of our dataset with every tokenizer (2026-11-15; Arabic = Modern Standard Arabic); rank 1 = fewest tokens. All counts: tokenizer efficiency dataset. On Arabic the most compact was Qwen, on code GLM. Full table on the token counter.

Questions

Which GPT models use o200k_base?

GPT-4o, GPT-4o mini, GPT-4.1, the o1, o3 and o4 reasoning models and the GPT-5 family, according to the model maps in tiktoken and gpt-tokenizer. GPT-4 and GPT-3.5 Turbo used the older cl100k_base.

Does this count match OpenAI's tokenizer?

For plain text, yes: we checked gpt-tokenizer against tiktoken on every sample here and the token IDs were identical. For chat requests OpenAI does not publish its exact format; the counter adds the cookbook rule of about 4 tokens per message plus 3 for the reply.

Can I use a GPT token count to estimate DeepSeek or Qwen costs?

Only roughly. On English the counts are close, but on our dataset texts they differ by up to 33% against Qwen and more on Arabic and Hindi against some models. Load the real tokenizers in the table to see the exact gap for your text.

How many words is 1,000 GPT tokens?

About 787.402 English words by our measurement (1183 words = 1501 tokens). Other languages and code differ; see the tokens to words converter.

What is the cheapest BroadNet model for my text?

Load all tokenizers in the table: the input and output columns price your exact text on each BroadNet model. For a whole workload, use the LLM API cost calculator.

Go deeper

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity