Calculadora de tokens gratuita
Usa este contador de tokens para contar tokens localmente para prompts, documentos, código, JSON y mensajes de chat, y luego estima el costo de la API en los principales proveedores.
Pieces appear as the local tokenizer reads your text.
Paste text to turn the pricing table into exact estimated costs for your prompt.
A token calculator, sometimes called a token counter, estimates how much text an LLM will process before you send a request. Tokens are the units used for context limits and API billing, so the count matters for prompts, documents, code, JSON, and chat transcripts. Token-Calculator.net runs the browser calculator locally, shows word and character counts alongside tokens, and turns the same count into estimated input, cached-input, and output costs for major model providers.
Use it when you need to check whether a prompt fits a context window, compare model cost before an API call, trim repeated instructions, or explain usage to a product or finance team.
Estimate token count before a user prompt, system prompt, or multi-turn chat goes to an LLM.
Paste policy text, research notes, transcripts, or long-form content to judge request size.
Measure structured data, code snippets, logs, and payloads that often use tokens differently from prose.
Use one token count to compare OpenAI, Claude, and Gemini pricing before choosing a model.
The main calculator works for general LLM planning. These focused guides explain provider and conversion-specific cases without changing how the browser calculator works.
Compare input, cache-read, and output pricing across major LLM providers. Long-context tiers are applied automatically. Estimates use standard paid text rates and exclude cache writes and storage, Batch, Flex, Priority, tools, and media charges.
| Model | Provider | Context | Current rate / 1M tokens | Estimated cost | Pricing tier |
|---|---|---|---|---|---|
| GPT-6 Astra | OpenAI | 1,050K / 128K | Input $10 Cache read $1 Output $50 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $20, cache read $2, output $75. Access is rolling out. Check availability for your API account. |
| GPT-5.6 Sol | OpenAI | 1,050K / 128K | Input $4 Cache read $0.4 Output $20 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $8, cache read $0.8, output $30. Promotional Standard rates, guaranteed at least through Nov 21, 2026. |
| GPT-5.6 Terra | OpenAI | 1,050K / 128K | Input $2 Cache read $0.2 Output $12 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $4, cache read $0.4, output $18. |
| GPT-5.6 Luna | OpenAI | 1,050K / 128K | Input $0.2 Cache read $0.02 Output $1.2 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $0.4, cache read $0.04, output $1.8. |
| GPT-5.5 | OpenAI | 1,050K / 128K | Input $5 Cache read $0.5 Output $30 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $10, cache read $1, output $45. |
| GPT-5.5 Pro | OpenAI | 1,050K / 128K | Input $30 Cache read Not offered Output $180 | Input $0.0000 Cache read Not offered Output $0.0000 | Standard Long context after 272K input: input $60, cache read Not offered, output $270. |
| GPT-5.4 | OpenAI | 1,050K / 128K | Input $2.5 Cache read $0.25 Output $15 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 272K input: input $5, cache read $0.5, output $22.5. |
| GPT-5.4 Mini | OpenAI | 400K / 128K | Input $0.75 Cache read $0.075 Output $4.5 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| GPT-5.4 Nano | OpenAI | 400K / 128K | Input $0.2 Cache read $0.02 Output $1.25 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| GPT-5.4 Pro | OpenAI | 1,050K / 128K | Input $30 Cache read Not offered Output $180 | Input $0.0000 Cache read Not offered Output $0.0000 | Standard Long context after 272K input: input $60, cache read Not offered, output $270. |
| Claude Fable 5.1 | Anthropic | 1M / 128K | Input $10 Cache read $0.25 Output $50 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Mythos 5.1 (limited availability) | Anthropic | 1M / 128K | Input $10 Cache read $0.25 Output $50 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Fable 5 | Anthropic | 1M / 128K | Input $10 Cache read $1 Output $50 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Sonnet 5 | Anthropic | 1M / 128K | Input $2 Cache read $0.2 Output $10 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Mythos 5 (limited availability) | Anthropic | 1M / 128K | Input $10 Cache read $1 Output $50 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Opus 5 | Anthropic | 1M / 128K | Input $5 Cache read $0.5 Output $25 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Opus 4.8 | Anthropic | 1M / 128K | Input $5 Cache read $0.5 Output $25 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Sonnet 4.6 | Anthropic | 1M / 128K | Input $3 Cache read $0.3 Output $15 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Claude Haiku 4.5 | Anthropic | 200K / 64K | Input $1 Cache read $0.1 Output $5 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
| Gemini 3.8 Flash | 1,048K / 65K | Input $0.75 Cache read $0.075 Output $3.75 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Promotional Standard rates through Dec 31, 2026. Rates double on Jan 1, 2027. | |
| Gemini 3.7 Flash | 1,048K / 65K | Input $0.75 Cache read $0.075 Output $3.75 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Promotional Standard rates through Dec 31, 2026. Rates double on Jan 1, 2027. | |
| Gemini 3.6 Flash | 1,048K / 65K | Input $0.75 Cache read $0.075 Output $3.75 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Promotional Standard rates through Dec 31, 2026. Rates double on Jan 1, 2027. | |
| Gemini 3.5 Flash | 1,048K / 65K | Input $1.5 Cache read $0.15 Output $9 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard | |
| Gemini 3.5 Flash-Lite | 1,048K / 65K | Input $0.3 Cache read $0.03 Output $2.5 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard | |
| Gemini 3.1 Pro Preview | 1,048K / 65K | Input $2 Cache read $0.2 Output $12 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 200K input: input $4, cache read $0.4, output $18. | |
| Gemini 3.1 Flash-Lite | 1,048K / 65K | Input $0.25 Cache read $0.025 Output $1.5 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard | |
| Gemini 2.5 Pro | 1,048K / 65K | Input $1.25 Cache read $0.125 Output $10 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard Long context after 200K input: input $2.5, cache read $0.25, output $15. | |
| Gemini 2.5 Flash | 1,048K / 65K | Input $0.3 Cache read $0.03 Output $2.5 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard | |
| Gemini 2.5 Flash-Lite | 1,048K / 65K | Input $0.1 Cache read $0.01 Output $0.4 | Input $0.0000 Cache read $0.0000 Output $0.0000 | Standard |
Quick answers for token counts, local browser processing, model price comparisons, and prompt planning.
These guides explain AI tokens, tokenization, word-to-token ratios, cached input pricing, context windows, and prompt optimization without crowding the calculator page.
Use the paid Token-Calculator.net API for metered token, character, and word counts with key-based access. The browser calculator remains free; API access requires an active subscription.
Una calculadora de tokens cuenta las unidades de texto que un modelo de lenguaje procesa antes de una solicitud. Esta herramienta cuenta tokens, palabras y caracteres localmente en tu navegador y estima el costo de la API a partir de ese conteo.
No. La calculadora funciona por completo en tu navegador: el texto que pegas nunca sale de tu dispositivo.
Sí. La calculadora está pensada para planificar prompts de los principales modelos y combina el conteo de tokens con referencias de precios de OpenAI, Anthropic Claude y Google Gemini.
En inglés, 1.000 palabras suelen ser entre 1.300 y 1.500 tokens, pero la proporción cambia según el idioma, la puntuación, el código y el formato. Pega tu texto exacto para una estimación precisa.
Sí, la calculadora del navegador es completamente gratuita. Solo los planes de acceso a la API tienen costo.
Es lo mismo: un contador de tokens de IA mide cuántos tokens contiene un texto para modelos como ChatGPT, Claude o Gemini. Esta página funciona como contador y como calculadora de costos.