Token calculator
Calculate exactly how many tokens your text uses and what each model charges for it. Exact counts for GPT and OpenAI, clearly labeled estimates elsewhere.
Token count uses the exact GPT (o200k) tokenizer. Counted in your browser, never uploaded.
| Model | Tokens | Per request | Monthly | Context |
|---|---|---|---|---|
| Qwen3.8 Max | 0 est. | $0.003 | $3.00 | 0.1% |
| DeepSeek V4 Flashcheapest | 0 est. | $0.00014 | $0.14 | 0.1% |
| Claude Opus 5 | 0 est. | $0.013 | $12.50 | 0.1% |
Token counts vary by tokenizer and model; non-OpenAI counts are estimates. Cost is an estimate and provider pricing can change. See each model's source on the pricing page.
What is a token?
A token is the unit a model reads and bills on, roughly 4 characters or 0.75 words of English. Words are not tokens: "cat" is one token, but "unbelievable" can be three, and punctuation, spaces and emoji all count. That is why a token calculator, not a word count, tells you the real size and cost of a request.
Why token counts differ between providers
Each AI provider uses its own tokenizer, which splits text into pieces differently. OpenAI uses BPE (byte-pair encoding), while other providers have their own variants. The same sentence can produce a different token count depending on the model, which is why per-provider estimates matter when planning API costs.
FAQ
Is a token the same as a word?
No. On average one token is about 0.75 words of English, but common words are one token while rare or long words split into several. Code and non-English text use more tokens per word.
Which tokenizer does this use?
GPT and OpenAI models are counted with the exact o200k BPE tokenizer in your browser. Other providers are shown as clearly labeled estimates, since their tokenizers are not available client-side.
Does punctuation count as tokens?
Yes. Every comma, period, bracket and space contributes to the token count. Heavily punctuated text like JSON or code costs more tokens than plain prose of the same word count.
How do I reduce my token count?
Remove unnecessary whitespace and filler words, shorten system prompts, use abbreviations where clear, and avoid repeating context the model already has. Each token saved reduces both cost and latency.
Current model pricing
| Model | Provider | Input | Cached | Output | Context | Verified |
|---|---|---|---|---|---|---|
| Qwen3.8 Max | Alibaba | $2 | $0.25 | $6 | 1 000k | 2026-08-03 |
| Claude Haiku 4.5 (latest) | Anthropic | $1 | $0.1 | $5 | 200k | 2025-10-15 |
| Claude Opus 4.8 | Anthropic | $5 | $0.5 | $25 | 1 000k | 2026-05-28 |
| Claude Sonnet 4.6 | Anthropic | $3 | $0.3 | $15 | 1 000k | 2026-03-13 |
| DeepSeek Chat | DeepSeek | $0.14 | $0.0028 | $0.28 | 1 000k | 2026-02-28 |
| Gemini 2.5 Flash | $0.3 | $0.03 | $2.5 | 1 048,576k | 2025-06-17 | |
| Gemini 3.5 Flash | $1.5 | $0.15 | $9 | 1 048,576k | 2026-05-19 | |
| Mistral Medium (latest) | Mistral | $1.5 | n/a | $7.5 | 262,144k | 2026-04-29 |
| Kimi K3 | Moonshot AI | $3 | $0.3 | $15 | 1 048,576k | 2026-07-16 |
| GPT-4.1 mini | OpenAI | $0.4 | $0.1 | $1.6 | 1 047,576k | 2025-04-14 |
| GPT-4o | OpenAI | $2.5 | $1.25 | $10 | 128k | 2024-08-06 |
| GPT-5.5 | OpenAI | $5 | $0.5 | $30 | 1 050k | 2026-04-23 |
| Grok 4.5 | xAI | $2 | $0.3 | $6 | 500k | 2026-07-08 |
| GLM-5.2 | Zhipu AI | $1.4 | $0.26 | $4.4 | 1 000k | 2026-06-13 |
Prices per 1M tokens (USD). Each model links to its official source. Seed values pending re-verification. See the methodology.