wyreup
PRO Wyreup PRO

Hosted-AI tools. Pay only for what you run.

Every tool that runs in your browser stays free. PRO adds the AI tools that need real servers — transcription, OCR, translation (100+ languages), text-to-speech, image generation, long-context PDF Q&A, structured-JSON extraction, content safety, and more. Tools chain together so one tool's output feeds the next. Most cost 1–2 credits a run; failed runs refund automatically.

Packs from $5  ·  or $8/mo  ·  credits never expire

See pricing ↓

Simple credit pricing

Buy a pack once — credits never expire — or subscribe monthly. Most tools cost 1–2 credits, so a starter pack covers roughly 220 images generated or analyzed, 220 grammar fixes, 110 PDF Q&A runs, 110 text-to-speech outputs, or 70 transcriptions.

Starter
220
credits
$5
Best value
480
credits
$10
Power
1000
credits
$20
Monthly
440
credits / month
$8/mo

Pack credits never expire. The monthly plan grants 440 credits each cycle into the same balance — the best per-credit rate — and you can cancel anytime. Payment is handled by Lemon Squeezy; we never see your card.

What PRO unlocks

30 hosted-AI tools, grouped by what they cost to run. Each shows its credit cost before you run it.

1 credit per run

  • Analyze Chart Reads a chart, graph, or diagram image and explains the data and main trend in plain text.
  • Ask About Image Ask a question about an image and get an answer from a hosted vision model.
  • Content Safety Hosted Llama Guard classifier — flags text containing violence, sexual content, hate speech, self-harm, harassment, and 9 other categories. Useful for moderators, parents, and anyone shipping user-generated content.
  • Cron From Text AI-generated cron expressions for schedules the free heuristic engine cannot parse. A hosted LLM handles arbitrary, open-ended phrasings.
  • Describe Image Generates a concise description / alt-text for an image using a hosted vision model. Output is plain text.
  • Detect Objects Detects and locates objects in an image, returning labels, confidence scores, and bounding boxes as JSON.
  • Extract JSON Hosted Llama-4 Scout pulls structured JSON out of any text — receipts, emails, contracts, log lines. Describe the fields you want and get back a valid object. Major chain unlock: feeds anything downstream that needs structured input.
  • Fix Grammar Hosted LLM cleans up grammar, spelling, and punctuation while preserving your voice. Returns the corrected text only — no commentary, no explanation.
  • Generate Image Hosted Flux Schnell — turns a text prompt into a 1024×1024 JPEG in seconds. Pair it with Background Remove or Upscale to take the result further.
  • Named Entity Recognition Hosted LLM named-entity extraction — pulls people, organisations, places, dates, and money references with much better recall than browser models on long-form text.
  • OCR High-quality text extraction from images and scans, powered by a hosted vision model. Output is plain text — chains into translate, summarize, and other text tools.
  • Read Handwriting Transcribes handwritten text from an image using a hosted vision model. Output is plain text.
  • Regex From Text AI-generated regular expressions for descriptions the free heuristic engine cannot match. A hosted LLM handles arbitrary, open-ended phrasings.
  • Rewrite Tone Hosted fast LLM rewrites your text in a chosen tone — formal, casual, kid-friendly, concise, professional, or friendly. Useful for email drafts, customer replies, and turning a rough note into something you can send.
  • Sentiment Hosted LLM sentiment classification — handles sarcasm, mixed tone, and domain language the in-browser heuristic misses. Returns positive / negative / neutral.
  • Translate (100+ languages) Hosted M2M-100 — direct translation across 100+ language pairs without going through a chat LLM. Faster and cheaper than the Llama-class Translate for straight-shot translation.
  • Translate to Indic Languages Hosted IndicTrans2 — purpose-built English-to-Indic translation across Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Punjabi, Malayalam, Kannada, Urdu, and Assamese. Higher fidelity for these languages than a general LLM.

2 credits per run

  • Ask a Long PDF Hosted Llama 4 Scout with a 10M-token context window — for textbooks, court transcripts, large contracts, and books that exceed the standard Ask-a-PDF tool. Extracts text in your browser then sends to the long-context model.
  • Ask a PDF Extracts a PDF’s text in your browser, then answers a question about it with a hosted LLM.
  • Redact PII Hosted LLM strips personal data — names, emails, phones, addresses, SSNs, card-shaped numbers — replacing each with [REDACTED]. Catches free-form mentions ("met Joe at Acme HQ in March") that pattern-based redaction misses.
  • Summarize Higher-quality summarization powered by a hosted Llama-class model. Pairs well with transcribe-pro for "audio → notes" flows.
  • Summarize PDF Extracts a PDF’s text in your browser, then summarizes it with a hosted LLM.
  • Text to Speech Hosted neural TTS — turns text into a natural-sounding MP3 in seconds. Chain it after Summarize, Translate, OCR, or Redact to get audio out of any tool that produces text.
  • Translate Hosted Llama-class translation. Higher quality than browser-only models — particularly for less common language pairs.
  • Translate Image Text Extracts text from an image and translates it. Photograph a sign or document, get the translation.

3 credits per run

  • Background Remove Hosted large RMBG model — cleaner edges on hair, glass, and fine detail than the in-browser version. Output is a transparent PNG.
  • Deep Analysis Hosted DeepSeek R1 reasoning model — reads your document and answers a specific question with explicit step-by-step reasoning. Suited to contracts, legal text, code review, and root-cause analysis from logs.
  • Transcribe Audio Hosted Whisper-large-v3 transcription — higher accuracy and better with noisy or accented speech than the free in-browser version.
  • Upscale Hosted Real-ESRGAN upscale, 2× or 4×. Sharper edges, better fine detail than the in-browser variant — and faster on large inputs since the GPU does the heavy lifting.

5 credits per run

  • Transcribe & Translate Transcribes an audio file and translates the transcript in one step.

How it works

  1. 01 Sign up

    One field, instant — you're signed in right away. No password.

  2. 02 Add credits

    Pick a pack or the monthly plan. Lemon Squeezy handles payment; we never see your card.

  3. 03 Run any PRO tool

    Each shows its credit cost up front. Credits deduct on success; failed runs refund automatically.

Built to be fair

Free stays free

Every in-browser tool — compression, PDF, image, audio, code & data helpers — stays free. No account, no upload, no tracking.

Failed runs auto-refund

If a hosted-AI tool errors, the credits return to your balance automatically. No ticket, no waiting.

Same privacy posture

Inputs and outputs aren't kept after a PRO run — only which tool ran, for your own history.

One key, everywhere

Browser, CLI, and AI agents draw from the same balance with the same key.

Don't want a hosted tier at all?

Wyreup is MIT-licensed. Run @wyreup/core entirely on your own infrastructure. PRO exists because hosted-AI inference has a real per-call cost — not because the free tools are limited.