Tokens for any listed model
Sample
Paste sample text or enter token counts; pick provider from the list.
What you get
Normalizes pricing when you split input vs output tokens.
AI Token Counter & API Cost Calculator
Paste text to estimate tokens (heuristic) and see input/output cost across every model in the live OpenRouter catalog — OpenAI, Anthropic (incl. Claude Fable 5.1), Google (incl. Gemini 3.8 Flash), DeepSeek, Z.ai GLM, Qwen, xAI Grok, MiniMax, and more. When OpenRouter adds a model, it shows up in this comparison table on refresh. Live model lists and $/1M rates load from OpenRouter’s public models API (https://openrouter.ai/api/v1/models), with TensorFeed and a local snapshot as fallbacks. New releases (for example Gemini 3.8 Flash or Claude Fable 5.1) appear automatically when OpenRouter lists them.
AI Token Counter & API Cost Calculator
Cost table: 22 models · Local registry · as of 2026-09-02 · refreshing…
Pricing data: OpenRouter models
Tokens
0
Words
0
Chars (no spaces)
0
Total Characters
0
How to Use This Tool
- Paste or type your text into the input area.
- View real-time token, word, and character estimates.
- Scan the cost table for every active live catalog model.
- Use provider-specific calculators for volume projections.
Features
- Real-time token estimate as you type
- All major providers from the OpenRouter models API
- Side-by-side input vs output cost columns
- Word and character counts alongside tokens
- Automatically includes newly published models
Example
Frequently Asked Questions
What is a token and why does it matter?
A token is a chunk of text an LLM processes as a unit. API pricing is usually per million tokens, so estimates help you budget and trim prompts.
Why might my API report a different token count?
This tool uses a fast word-based heuristic (~1.33 tokens/word). Production APIs use model-specific tokenizers (tiktoken, SentencePiece, etc.). Use it for planning, then verify with the provider tokenizer for billing-critical work.
How do new models appear in the table?
The table is fed by OpenRouter’s public models API (proxied through MyScripter). New entries appear after OpenRouter updates and our cache refreshes (about hourly).
Related Tools
GPT Token & API Cost Calculator
Calculate API costs for current OpenAI GPT models with live OpenRouter pricing.
Claude API Cost Estimator
Estimate costs for Claude Fable 5.1 and other current Anthropic models with live pricing.
Gemini Token & API Cost Calculator
Calculate costs for Gemini 3.8 Flash and other current Google models with live pricing.
Llama Self-Hosting Cost Estimator
Estimate GPU and cloud costs for self-hosting Llama models.
RAG vs Fine-Tuning Cost Comparison Calculator
Compare RAG and fine-tuning costs to find the optimal approach for your project.