Loading...
Paste text to instantly count tokens, words, and characters for GPT, Claude, Gemini, and Grok models
Compare context windows, max output lengths, and API pricing across all major LLM providers.
| Model | Provider | Context Window | Max Output | Price (Input / Output per 1M tokens) |
|---|---|---|---|---|
| GPT-5.6 Sol | OpenAI | 1.05M tokens | 128K tokens | $5.00 / $30.00 |
| GPT-5.6 Terra | OpenAI | 1.05M tokens | 128K tokens | $2.50 / $15.00 |
| GPT-5.6 Luna | OpenAI | 1.05M tokens | 128K tokens | $1.00 / $6.00 |
| GPT-5.5 | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| GPT-5.5 Pro | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| GPT-5.4 | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| GPT-5.4 Pro | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| GPT-5.4 mini | OpenAI | 1M tokens | 16,384 tokens | See openai.com/pricing |
| GPT-5.4 nano | OpenAI | 1M tokens | 16,384 tokens | See openai.com/pricing |
| GPT-5 mini | OpenAI | 1M tokens | 16,384 tokens | See openai.com/pricing |
| GPT-5 nano | OpenAI | 1M tokens | 16,384 tokens | See openai.com/pricing |
| GPT-5 | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| GPT-4.1 | OpenAI | 1M tokens | 32,768 tokens | See openai.com/pricing |
| Claude Opus 4.8 | Anthropic | 1M tokens | 32,000 tokens | $5.00 / $25.00 |
| Claude Sonnet 4.6 | Anthropic | 1M tokens | 8,192 tokens | $3.00 / $15.00 |
| Claude Haiku 4.5 | Anthropic | 200K tokens | 8,192 tokens | $0.80 / $4.00 |
| Gemini 3.1 Pro | 1M tokens | 64,000 tokens | $2.00 / $12.00 | |
| Gemini 3 Flash | 1M tokens | 65,535 tokens | $0.50 / $3.00 | |
| Gemini 3.1 Flash-Lite | 1M tokens | 65,536 tokens | $0.25 / $1.50 | |
| Grok 4.5 | xAI | 500K tokens (API) | Bounded by context | $2.00 / $6.00 |
| Grok 4.3 | xAI | 1M tokens | Bounded by context | $1.25 / $2.50 |
| Grok 4.20 | xAI | 2M tokens (API); 128K Grok web UI | Bounded by context | $1.25 / $2.50 |
| Grok Build 0.1 | xAI | 256K tokens | Bounded by context | $1.00 / $2.00 |
Prices from official provider pricing pages as of March 2026. Some prices shown as "See pricing page" due to frequent updates - check openai.com/pricing, docs.anthropic.com/pricing, ai.google.dev/pricing, and docs.x.ai/pricing for latest rates. Note: GPT-4o, o3, o4-mini, and earlier models were retired in February 2026; GPT-5.6 (Sol, Terra, Luna), GPT-5.5, and GPT-5.4 are the current frontier OpenAI models. xAI Grok rates (the new Grok 4.5 at $2.00 / $6.00 with $0.50 cached input and a 500K context; Grok 4.3 and Grok 4.20 at $1.25 / $2.50, Grok Build 0.1 at $1.00 / $2.00 per 1M input/output tokens, plus $0.20 cached input) were verified July 2026 from docs.x.ai; xAI does not publish a separate max-output cap, so Grok output is bounded only by the model's context window. Token estimates use average ratios (~0.75 tokens/word for OpenAI/Google/xAI, ~0.80 for Anthropic).
Approximately 750 tokens for OpenAI, Google, and xAI models (GPT-5.6 Sol, GPT-5.5, GPT-5.4, Gemini 3.1 Pro, Grok 4.3) and 800 tokens for Anthropic models (Claude). The exact count varies based on word length, punctuation, and special characters.
GPT-5.6 (Sol, Terra, and Luna) supports a 1.05 million token context window, and GPT-5.5, GPT-5.4, Claude Opus 4.8, Gemini 3.1 Pro, and xAI's Grok 4.3 all support 1 million tokens, while xAI's Grok 4.20 supports 2 million via the API (the Grok web UI caps the working window near 128K on the free tier). 1 million tokens is roughly equivalent to 750,000 words or a 1,500-page book.
ChatGPT has a fixed context window. When your conversation exceeds the token limit, older messages are dropped. Use AI Toolbox (formerly ChatGPT Toolbox) to search and export important conversations before they're lost.
Be concise in prompts, avoid repeating context, use system instructions for persistent rules, and break long tasks into separate conversations. AI Toolbox's Prompt Library helps you save optimized prompts for reuse on ChatGPT, Gemini, Claude, and Grok.
This tool provides estimates based on average token-per-word ratios. For exact counts, use OpenAI's tiktoken library (Python), the Anthropic tokenizer API, or xAI's tokenize-text endpoint for Grok. Our estimates are within 5-10% of actual counts for English text.
Every AI Toolbox module, one payment
Modules unlocked
AI Toolbox is a browser extension that adds folders, search, and export inside each AI. This unlocks all four modules, it is not an AI subscription. You keep using your own ChatGPT, Gemini, Claude, and Grok accounts.
14-day money-back guarantee. Pay once, own it forever.
Compare all plansAdd folders, search, export, and prompt management to ChatGPT - free to start.