BroadRouter

gpt-oss token counter

Updated

In short: This counter runs OpenAI's official gpt-oss tokenizer.json in your browser, pinned to the same commit as our tokenizer dataset. It has 200,019 token IDs and is a 28 MB download. English prose takes about 127 tokens per 100 words, Modern Standard Arabic about 189.

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
OpenAI GPT OSS 120B
gpt-oss tokenizer (o200k_harmony)
Price: OpenAI GPT OSS 120B at CoreWeave Forge, 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). gpt-oss 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; gpt-oss 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 · 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 gpt-oss tokenizer (o200k_harmony) is preselected and downloads once (28 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 gpt-oss 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 gpt-oss tokenizer

The gpt-oss tokenizer is a byte-level BPE. It has 200,019 token IDs, 21 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 groups of up to three digits, so 2026 is two tokens.

On the open texts of our tokenizer efficiency dataset it needs 1,269 tokens per 1,000 English words (rank 4 of the 16 tokenizers we measured, 1 = fewest), 2,025 per 1,000 words of Python (rank 6 of 16) and 1,885 per 1,000 words of Modern Standard Arabic (rank 7 of 16). Its best showing here is JSON (rank 3 of 16); its weakest is Chinese (rank 11 of 16).

4 models in our price database use this tokenizer: OpenAI GPT OSS 120B, GPT OSS 20B, GPT OSS Safeguard 120B and GPT OSS Safeguard 20B. We hold 35 standard prices for them from 21 providers. The cheapest input price is $0.03 per 1M tokens, for OpenAI GPT OSS 120B on CoreWeave Forge (checked 2026-11-15). At that price 1,000 English words cost $0.000038 to send. gpt-oss 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.

gpt-oss tokenizer facts
Tokenizergpt-oss tokenizer (o200k_harmony), a byte-level BPE
Sourceopenai/gpt-oss-120b (commit b5c939d)
Token IDs200,019 (199,998 in the base vocabulary)
Models using it4: OpenAI GPT OSS 120B, GPT OSS 20B, GPT OSS Safeguard 120B and GPT OSS Safeguard 20B
Cheapest input price$0.03 per 1M tokens (OpenAI GPT OSS 120B, CoreWeave Forge, checked 2026-11-15)
English prose127 tokens per 100 words (rank 4 of 16)
Arabic (MSA)189 tokens per 100 words (rank 7 of 16)
Python code203 tokens per 100 words (rank 6 of 16)
Download28 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 gpt-oss 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 gpt-oss tokenizer (o200k_harmony) splits it into 355 tokens. Sent to OpenAI GPT OSS 120B on CoreWeave Forge at $0.03 per 1M input tokens it costs $0.000011; the same number of tokens written as output at $0.17 per 1M costs $0.000060.

Questions

Which tokenizer does gpt-oss use?

A byte-level BPE with 200,019 token IDs, published as tokenizer.json in openai/gpt-oss-120b. This page loads that file pinned to commit b5c939d, the commit our dataset measured.

Which models use the gpt-oss tokenizer?

OpenAI GPT OSS 120B, GPT OSS 20B, GPT OSS Safeguard 120B and GPT OSS Safeguard 20B. 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 gpt-oss API price per token?

Of the 35 standard prices we hold for gpt-oss models, the lowest input price is $0.03 per 1M tokens (output $0.17), for OpenAI GPT OSS 120B on CoreWeave Forge, read from the provider's pricing page on 2026-11-15. 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 gpt-oss?

Modern Standard Arabic sentences take 1.38× the tokens of their English translations with this tokenizer (rank 7 of 16 on the same texts). Hindi takes 1.58× and Chinese 1.26×. Measured on parallel sentences in our open dataset (2026-11-15). Paste your own text above, or use the Arabic token counter.

Is the gpt-oss tokenizer the same as GPT (o200k)?

They gave identical counts on all 52 texts of our dataset, but they are separate tokenizers with different special tokens, so text that contains control markers can count differently. Load both in the table above to compare your own text. GPT (o200k) has its own counter.

Does the count include chat-template tokens?

No. For gpt-oss 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