MONTHLY BUDGET
What will this workflow cost?
Move the sliders to estimate a month of real usage on Claude Sonnet 5.
Estimated monthly spend$7.37
REAL TOKENIZER · 23 MODELS
Know what your
prompt costs.
Count tokens with a real BPE tokenizer in your browser, compare 23 major models, and plan API spend before you ship.
GBuilt for clear decisions — not confusing dashboards.
REGISTRY SNAPSHOT
23 models.
11 providers.
THE CALCULATOR
Start with the text.
Nothing leaves your browser
COUNTING MODE
TRY A SAMPLE
COMPARE MODELS
Same prompt. Different math.
Switch models above or click a card to make it your active calculator.
MORE THAN A COUNTER
Plan the work, not just the prompt.
Small tools that turn a one-off count into a repeat workflow.
PROMPT HEALTH
Is this prompt doing too much?
A quick local check for repetition, context weight, and likely cleanup opportunities.
98/ 100
prompt health
prompt health
- Reasonable prompt size
- Clear section structure
- Local-only analysis
FILE COUNTER
Count a document in seconds.
Drop a .txt, .md, .json, .csv, .py, .js, or .ts file. It stays in your browser.
THE LIVING REGISTRY
More models, less guesswork.
Reference pricing snapshot · verify provider billing before production use.
AnthropicFlagship
Claude Fable 5Fable 5 · 1M contextINPUT / 1M$10.00OUTPUT / 1M$50.00CACHED / 1M$1.00
AnthropicFlagship
Claude Mythos 5Mythos 5 · 1M contextINPUT / 1M$10.00OUTPUT / 1M$50.00CACHED / 1M$1.00
AnthropicFlagship
Claude Opus 5Opus 5 · 1M contextINPUT / 1M$5.00OUTPUT / 1M$25.00CACHED / 1M$0.5000
AnthropicBalanced
Claude Sonnet 5Sonnet 5 · 1M contextINPUT / 1M$2.00OUTPUT / 1M$10.00CACHED / 1M$0.2000
AnthropicFast
Claude Haiku 4.5Haiku 4.5 · 200K contextINPUT / 1M$1.00OUTPUT / 1M$5.00CACHED / 1M$0.1000
OpenAIFlagship
GPT-5.6 SolGPT-5.6 · 1.05M contextINPUT / 1M$5.00OUTPUT / 1M$30.00CACHED / 1M$0.5000
OpenAIBalanced
GPT-5.6 TerraGPT-5.6 · 1.05M contextINPUT / 1M$2.00OUTPUT / 1M$12.00CACHED / 1M$0.2000
OpenAIFast
GPT-5.6 LunaGPT-5.6 · 1.05M contextINPUT / 1M$0.2000OUTPUT / 1M$1.20CACHED / 1M$0.0200
GoogleFlagship
Gemini 3.1 Pro PreviewGemini 3.1 · 1.05M contextINPUT / 1M$2.00OUTPUT / 1M$12.00CACHED / 1M$0.2000
GoogleFast
Gemini 3.6 FlashGemini 3.6 · 1.05M contextINPUT / 1M$0.7500OUTPUT / 1M$3.75CACHED / 1M$0.0750
GoogleFast
Gemini 3.7 FlashGemini 3.7 · 1.05M contextINPUT / 1M$0.7500OUTPUT / 1M$3.75CACHED / 1M$0.0750
GoogleFast
Gemini 3.5 Flash-LiteGemini 3.5 · 1.05M contextINPUT / 1M$0.3000OUTPUT / 1M$2.50CACHED / 1M$0.0300
xAIFlagship
Grok 4.6Grok 4.6 · 500K contextINPUT / 1M$2.00OUTPUT / 1M$6.00CACHED / 1M$0.5000
xAIBalanced
Grok 4.5Grok 4.5 · 500K contextINPUT / 1M$2.00OUTPUT / 1M$6.00CACHED / 1M$0.3000
MoonshotBalanced
Kimi K3Kimi K3 · 1.05M contextINPUT / 1M$3.00OUTPUT / 1M$15.00CACHED / 1M$0.3000
MoonshotFast
Kimi K2.7 CodeKimi K2.7 · 262K contextINPUT / 1M$0.9500OUTPUT / 1M$4.00CACHED / 1M$0.1900
DeepSeekBalanced
DeepSeek V4 ProDeepSeek V4 · 1.05M contextINPUT / 1M$0.4350OUTPUT / 1M$0.8700CACHED / 1M$0.0036
DeepSeekFast
DeepSeek V4 FlashDeepSeek V4 · 1.05M contextINPUT / 1M$0.1400OUTPUT / 1M$0.2800CACHED / 1M$0.0028
AlibabaFlagship
Qwen 3.8 MaxQwen 3.8 · 1M contextINPUT / 1M$2.00OUTPUT / 1M$6.00CACHED / 1M$0.2500
MetaOpen
Llama 4 MaverickLlama 4 · 1M contextINPUT / 1M$0.2000OUTPUT / 1M$0.8000CACHED / 1M—
MistralOpen
Mistral Large 3Mistral Large · 262K contextINPUT / 1M$0.5000OUTPUT / 1M$1.50CACHED / 1M$0.0500
CohereBalanced
Command ACommand A · 256K contextINPUT / 1M$2.50OUTPUT / 1M$10.00CACHED / 1M—
PerplexityBalanced
Sonar ProSonar · 200K contextINPUT / 1M$3.00OUTPUT / 1M$15.00CACHED / 1M—
FROM THE PROMPTCOSTLAB BLOG
Learn, then calculate.
The calculator stays focused. Tutorials, comparisons, and model updates live in their own searchable publication.
Model guidesClaude Fable 5 token limits, pricing, and context fit
A plain-English guide to planning prompts for Anthropic's flagship family, including thinking-token billing and cache pricing.
Read article →
Token basicsWhy the same prompt has different token counts
Tokenizers explained without the textbook: vocabulary, chunks, and hidden request overhead.
Read article →
RegistryThe 2026 model registry: what changed this month
A living update log for major model families, context windows, and pricing snapshots.
Read article →LEARN THE BASICS
Useful answers,
zero jargon.
PromptCostLab is designed for someone who wants a trustworthy answer before they need a full course on tokenization.
Why do models disagree on token count?
Every provider uses its own tokenizer and request formatting. The same sentence can be a different number of tokens on Claude, GPT, Gemini, or Kimi. That is why PromptCostLab labels its counts: exact for OpenAI models, close approximation elsewhere.
Does my prompt leave this browser?
Never. The tokenizer runs on your device — the same o200k vocabulary OpenAI models use, downloaded once as a static script. Connected exact counting for structured messages, tools, files, and images may come later, and only if you choose to send data to a provider.
Can I add new models and blog posts?
Yes. The registry and journal are intentionally data-driven: add a model record or article record, and the filters, cards, and comparison surfaces update with it.