AI tools

See how much of a model context window your text uses. Compare GPT-4o, Claude, and Gemini token limits.

Test prompt templates with variables. Enter {{placeholders}} and preview the filled prompt instantly.

Estimate embedding API costs for OpenAI, Cohere, and Voyage. Enter token count and see per-request pricing.

Calculate RAG chunk count from token total, chunk size, and overlap. Plan vector indexing splits in your browser.

Compare LLM API costs across OpenAI, Claude, and Gemini for the same token counts. Free browser calculator.

Extract JSON from LLM responses. Parse fenced code blocks and inline objects from pasted model output.

Estimate how many tokens an image costs a vision model from its dimensions, so a batch of screenshots does not surprise you on the bill.

Infer a JSON Schema from a sample document, giving you types, required fields and nested structures as a draft to tighten by hand.

Fix the damage pasted Markdown picks up: smart quotes, non-breaking spaces, inconsistent list markers and headings stuck to the paragraph above.

Put two prompts side by side and see exactly which words changed, so you know what you actually varied before blaming the model for the difference.

Track a prompt across revisions and see what each edit changed, which is the only way to attribute an output shift to the edit that caused it.

Paste the JSON or Markdown a model handed back with its stray prose, code fences and trailing commas, and get a clean, indented block out.