Compteur de tokens IA — Outil en ligne gratuit
Compte les tokens pour GPT-4, Claude, Gemini — avec estimation de coût
Compte les tokens GPT-4, GPT-3.5, Claude et Gemini. Estime les coûts API. 100 % local — illimité, privé. Sans inscription.
💰 Coût estimate
📚 En savoir plus
Free GPT / Claude / Gemini token counter with cost estimates
Outilolis AI Token Counter counts tokens for every major AI model: GPT-4o, GPT-4, GPT-3.5, Claude 3 Opus/Sonnet/Haiku, Gemini Pro/Flash. Live cost estimates for input and output tokens. 100% client-side — your prompts never leave your browser.
How to use this tool
- 1
Paste your text or prompt
Any text — prompts, documents, code, JSON payloads.
- 2
Pick the AI model
GPT-4, GPT-3.5, Claude 3, Gemini — each uses different tokenizers.
- 3
Read token count + cost
Live token count for the chosen model, plus estimated input/output API costs.
Token rules of thumb
- English: ~1 token per 0.75 words (~4 characters per token)
- Code: more tokens per character due to special symbols
- Nonn-English: ~1.5-3× more tokens (especially CJK languages)
- JSON: 20-40% overhead from brackets and quotes
- Numbers: each digit is often a token
Current API pricing (2026, per 1M tokens)
| Model | Input | Output | Context |
|---|---|---|---|
| GPT-4o | $2.50 | $10.00 | 128K |
| GPT-4 Turbo | $10.00 | $30.00 | 128K |
| GPT-3.5 Turbo | $0.50 | $1.50 | 16K |
| Claude 3 Opus | $15.00 | $75.00 | 200K |
| Claude 3.5 Sonnet | $3.00 | $15.00 | 200K |
| Claude 3 Haiku | $0.25 | $1.25 | 200K |
| Gemini 1.5 Pro | $1.25 | $5.00 | 1M+ |
| Gemini 1.5 Flash | $0.075 | $0.30 | 1M |
Prixs are reference as of our . Always verify on the provider's official pricing page before budgeting.
Frequently Asked Questions
What is a token?
Why do different models count differently?
cl100k_base. GPT-3.5 and embeddings use similar. Claude uses its own tokenizer (similar counts, slightly different). Gemini uses Google's SentencePiece-based tokenizer (~1.3× GPT counts on average).Is this 100% accurate for GPT?
gpt-tokenizer library that mirrors OpenAI's cl100k_base encoding. Matches tokens exactly.Is Claude count accurate?
count_tokens API endpoint.Why are my prompts expensive?
Is my text uploaded?
À retenir
- AI Token Counter is a free, browser-based developer tool — count tokens for gpt-4, claude, gemini — with cost estimates.
- Non signup, no downloads, no file uploads. Outils run in your browser; the few that need an outside service say so on the page.
- Works on desktop, tablet, and mobile. Install as a PWA for offline access.
How to Use AI Token Counter
- Open the tool: Launch AI Token Counter on Outilolis — no account or download needed.
- Enter your data: Paste text, enter values, or select a file directly in your browser.
- Get instant results: Everything is processed locally — results appear immediately.
- Copy or download: Save your output or share it. Bookmark for quick access next time.
AI Token Counter — Quick Facts
- Prix
- Gratuit — sans limites, sans filigrane, sans paywall
- Confidentialité
- Traité dans votre navigateur. Les outils qui ont besoin d’un service externe l’indiquent sur la page. Les visites sont comptabilisées (Google Analytics).
- Plateforme
- Tout navigateur moderne — desktop, tablette ou mobile
- Catégorie
- Développeur Outils on Outilolis
- Hors ligne
- Works offline after first visit (Progressive Web App)
| Caractéristique | Détails |
|---|---|
| Outil | AI Token Counter |
| Catégorie | Développeur |
| Inscription requise | Non |
| Téléversement de fichier | Aucun — traité dans le navigateur |
| Compatible mobile | Entièrement adaptatif |
| Coût | Gratuit pour toujours |
Why Use AI Token Counter?
You should try AI Token Counter for a quick, private way to count tokens for gpt-4, claude, gemini — with cost estimates. Processing happens in your browser and files are never uploaded; the few tools that need an outside service say so on the page.
On the other hand, dedicated APIs or desktop tools suit batch processing better. They also handle server-side automation. For everyday tasks, browser tools offer the best speed, privacy, and convenience.