NEWPromptev MCP Server — One URL. Every tool, every agent, your team’s knowledge. Connect Claude Code, Cursor, or any MCP client.

No seats. No plans.
Pay per credit.

Bring your own LLM keys. We manage infrastructure, memory, sessions, context ingestion, auto-indexing, embedding, retrieval, tools, and governance — no RAG overhead, no pipeline to build. Every feature is included from the first day — you buy credits when you need them, and nothing else.

You bring: LLM keys
We handle: Everything else
SOC 2 Type II Certified

1 credit = 1 AI action. Most queries use 2–5 credits. Ingestion: 1 credit/page for documents & PDFs, 1 credit/slide for presentations, 1 credit/MB for spreadsheets & data files. See full breakdown ↓

Start free
Everything the platform does. No credit card.
$0
2,500 credits to start — worth $12.50
Get Started Free
  • 2,500 credits, once, on sign-up
  • Enough to connect a source, ingest a real document and hold a genuine conversation
  • Every feature — nothing is held back
  • Single sign-on, approvals and audit included
  • Your own model keys
Enterprise
A custom deployment, and people to call.
Let’s talk
Sized to your estate, not to a seat count · [email protected]
Contact us →
  • Deployment in your own cloud account, or fully on your premises
  • Onboarding and support
  • An annual licence rather than metered credits
  • The route for data that must stay in one jurisdiction
  • Buys a place to run and people to call — not features

Last updated: July 4, 2026

Every workspace includes

✓ RBAC✓ Context Graph✓ Collaboration✓ All Integrations✓ All Deployments✓ Unlimited Agents✓ Custom Tools✓ Agent Portal✓ Cross-Session Memory

Start building now.

No credit card required · 2,500 credits free to start · No subscription

How credits work

Transparent, predictable pricing. You know exactly what you're paying for.

Agent & query credits

💬

Base request = 1 credit

Every request uses Promptev’s orchestration, logging, and streaming infrastructure. Your LLM keys, our platform.

🔍

Context retrieval = +1 credit

Semantic search across your Context Packs — semantic search. Base + context = 2 credits.

🔗

Context Graph query = +5 credits

Graph-based retrieval with entity linking and relationship traversal. Base + graph = 6 credits.

🔧

Each tool call = +1 credit

Agent calls Jira, Slack, Gmail, SharePoint — 1 credit per tool, additive.

Ingestion credits

📄

PDFs = 1 credit per page

A 10-page PDF costs 10 credits. Includes text extraction, structured data processing, and OCR for scanned pages. Charged once per sync.

🖼️

Images = 1 credit

Each image (JPEG, PNG, TIFF, etc.) counts as 1 page. Includes text extraction and structured data processing.

📝

Documents (DOCX) = 1 credit per page

Word documents charged per page, just like PDFs. A 12-page report = 12 credits. Includes text extraction, image processing, and structured data.

📊

Presentations (PPTX) = 1 credit per slide

PowerPoint files charged per slide. A 17-slide deck = 17 credits. Includes text extraction, chart/image processing, and structured data.

📁

Spreadsheets & other files = 1 credit per MB

Excel, CSV, code files, text — charged by file size (minimum 1 credit). A 3 MB spreadsheet = 3 credits. A 200 KB CSV = 1 credit.

🕸️

Context Graph = +1 credit per 8 chunks + 1 per topic cluster

Entity extraction, relationship mapping, and topic clustering. Only applies to graph-mode packs — semantic packs skip this.

Example

🧮

1 query + context + 3 tools = 5 credits

Base (1) + context retrieval (1) + Jira (1) + Slack (1) + email (1) = 5 total.

📚

20-page PDF + 17-slide PPTX + 12-page DOCX + 2 images = 51 credits

PDF (20) + PPTX slides (17) + DOCX pages (12) + images (2) = 51 total. All processing included. Embedding always free.

Playground testing counts towards credits. Every request — chat, playground, API, scheduled, webhook — uses credits. Embedding is always free.

Security in every workspace

🔒
AES-256 at rest
🔐
TLS 1.3 in transit
🔑
BYOK — your keys
🛡️
SOC 2 Type II
🚫
Zero model training

The cost of not using Promptev

What companies typically spend to get what Promptev gives you out of the box.

$5,000+/ mo
vs
$0/ mo

Junior ops / AI engineer

Building and maintaining RAG pipelines, integrations, prompt management, and context retrieval — one person, full-time. Promptev starts free.

$2,000+/ mo
vs
$0/ mo

Vector DB + infra

Pinecone, Weaviate, or pgvector hosting + embedding pipelines + monitoring. Included in Promptev, for everyone.

3–6 monthsto ship
vs
10 minto deploy

Time to production

Building context pipelines, tool orchestration, auth, and governance from scratch — or just connecting your data and going live.

Frequently asked questions

Every AI request = 1 credit. Context retrieval adds +1 credit (or +5 for Context Graph). Each tool call = +1 credit. File ingestion: 1 credit per page for PDFs & documents, 1 credit per slide for presentations, 1 credit for images, 1 credit per MB for spreadsheets & data files. Example: query + context + 3 tools = 5 credits. Embedding is always free.

No. There are no plans to hold anything back behind. Roles and permissions, the context graph, every integration, single sign-on, approvals, the audit trail, unlimited projects and agents — all of it is in every workspace, including one that has never paid. The only thing you buy is credits. Enterprise buys a custom deployment, onboarding and support — a place to run and people to call, not features.

Everything except the LLM. We handle infrastructure, memory, sessions, context ingestion, auto-indexing, embedding, document processing, retrieval, tool orchestration, and governance — no RAG pipelines to build or maintain. Embedding is always free. Just bring your own LLM keys and we take care of the rest.

We notify at 80% and 100%. We never cut off agents mid-conversation.

Yes. Every request uses credits — playground, chatbot, API, scheduled, or webhook. No separate test mode. Only embedding is free.

Bring Your Own Keys. Connect your LLM provider (OpenAI, Claude, Gemini, Mistral). Encrypted with AES-256. Promptev handles context, retrieval, OCR, tools, and governance — you control the models.

Never. Your data is your source of truth — it’s routed to your model, which you bring. We never train on it, store it for third parties, or share it. Encrypted at rest (AES-256) and in transit (TLS 1.3). Your data powers your agents — and nothing else. See our Privacy Policy.

Yes. Special pricing for early-stage startups and nonprofits. Contact us.

Not sure which plan?
Let's figure it out together.

Our team can help scope your use case and recommend the right tier.

No credit card required · 2,500 credits free to start · No subscription

2,500 free credits · No card required · No subscription