Skip to content
Vinkius

Keywords AI Connector for AI agents.

11 live capabilities

Monitor LLM costs and performance metrics in real time.

Live agent request Keywords AI / Connector

Waiting for input…

AI Agent

Why people use Keywords AI

Keywords AI LLM Cost Management for Developers

Keywords AI puts all that data into a single place. Your agent can pull your credit balance, check request logs, and summarize your usage stats in seconds. You get a clear picture of your AI spend without the manual headache.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • Visual Studio Code
  • Windsurf

What Vinkius changes

You get a unified dashboard for all your LLM costs and performance metrics.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

  1. Real-world use case 01

    Budget Audit

    A manager asks the agent to summarize the total cost for a specific model last week to see if it fits the department budget.

  2. Real-world use case 02

    Latency Check

    A developer wants to see if a new model is slower than the old one and compares their performance metrics side by side.

  3. Real-world use case 03

    Team Management

    An admin needs to see who has been active on the platform to audit access and manage team permissions.

Complete set · 11capabilities

The complete Keywords AI capability set.

These are the exact actions your AI can choose when you ask it to work with Keywords AI.

Capability set01 / 03

01—04

4 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 01 Capability

    Get analytics

    Pull up your analytics dashboard to see high-level trends. It's perfect for getting a quick snapshot of your performance.

  2. 02 Capability

    Get credits

    Check your current credit balance instantly. This helps you stay on top of your budget without leaving your workspace.

  3. 03 Capability

    Get request

    Get the specific details of a single API call. It's useful for debugging a weird response or checking a specific token count.

  4. 04 Capability

    Get user

    Retrieve specific details about a team member. Use this when you need to verify a user's identity or permissions.

Capability set02 / 03

05—08

4 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 05 Capability

    List alerts

    Review your current monitoring thresholds and alerts. This lets you see what's being tracked and what triggers a notification.

  2. 06 Capability

    List users

    See a list of everyone on your team who has access. It makes managing your team's permissions much faster.

  3. 07 Capability

    Get usage stats

    Pull your overall usage statistics for a broader view of your activity. This helps you see how much you're actually using your resources.

  4. 08 Capability

    List models

    Browse the full catalog of available LLM models. It helps you see what options you have for your next project.

Capability set03 / 03

09—11

3 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 09 Capability

    List requests by model

    Filter your request logs by a specific model. This is the best way to see how one specific model is performing compared to others.

  2. 10 Capability

    List requests

    Pull a full list of your API request logs. Use this to audit every interaction your AI agent has made with the gateway.

  3. 11 Capability

    Check keywordsai status

    Use this to see if your connection to the platform is active. It's the quickest way to verify your API is reachable.

Set up in minutes

One URL. Then ask Keywords AI to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Keywords AI from the conversation.

Choose your client

Live preview
Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP
https://edge.vinkius.com/vk_preview_R4VkEIrwLVvP7dLw0Fdy9vfjO7WqxWYeI2hDwlBU/mcp
  1. Step 01

    Open Connectors

    In Claude Web or Claude Desktop, open Settings and choose Connectors.

  2. Step 02

    Add the URL

    Choose Add custom connector, name it Keywords AI, and paste the URL above.

  3. Step 03

    Turn it on in chat

    Select +, open Connectors, and enable Keywords AI for the conversation.

Where the request belongs

Work Keywords AI can move forward.

Built around the request

This is for AI ops engineers who are tired of manual cost tracking and product managers who need to justify AI spend to their leadership.

01

AI Ops Engineer

Uses this to set up automated alerts and monitor production latency across different LLM providers.

02

Product Manager

Uses this to pull cost trends and performance data to decide which models to use for new features.

03

DevOps Lead

Uses this to manage team permissions and audit API request logs for security and budget control.

Build the capability set

Add more capabilities.

Each Connector adds new actions and data without changing how you work.

Browse Connectors
Portkey logo
01 10 capabilities

Portkey

AI gateway observability: monitor logs, costs, and manage LLM configurations via agents.

View Connector
LiteLLM (LLM Proxy & Spend Tracking) logo
02 10 capabilities

LiteLLM (LLM Proxy & Spend Tracking)

Manage your LLM gateway via LiteLLM. generate API keys, track spending, and orchestrate model fallback paths.

View Connector
Helicone (LLM Observability) logo
03 10 capabilities

Helicone (LLM Observability)

Monitor LLM usage via Helicone. track requests, analyze costs, measure latency, and manage prompts.

View Connector
LangSmith logo
04 3 capabilities

LangSmith

Observability and evaluation platform for LLM applications. monitor traces, debug agent runs, and track performance metrics across your AI stack.

View Connector
Anthropic logo
05 8 capabilities

Anthropic

Interact with Claude models via the Anthropic Messages API. send prompts, manage batches, and monitor rate limits directly.

View Connector
LLM API Cost Calculator logo
06 4 capabilities

LLM API Cost Calculator

Estimate and compare the financial impact of LLM usage across different providers.

View Connector

Bring your own AI

Change the model, client or framework. Keep Keywords AI connected.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • VS Code
  • Windsurf
  • ZCode
  • Cline
  • Zed
  • Continue
  • Kiro
  • Roo Code
  • Zencoder
  • Goose
  • Void
  • Augment Code
  • Amp
  • Qodo
  • Tabnine
  • Pieces
  • Sourcegraph Cody
  • JetBrains
  • Warp
  • Amazon Q
  • Antigravity
  • BoltAI
  • Raycast
  • Jan
  • LM Studio
  • AnythingLLM
  • Open WebUI
  • Msty
  • Cherry Studio
  • LibreChat
  • TypingMind
  • Chorus
  • 5ire
  • n8n
  • LangChain
  • LlamaIndex
  • CrewAI
  • Vercel AI SDK

Before you connect

Questions about Keywords AI.

The practical details behind the request, access and result.

How does Keywords AI help me save money on LLM APIs?

It tracks your spending across all providers in one place, making it easy to spot high-cost models and prevent budget overages.

Can I use Keywords AI to see my team's usage?

Yes, you can list all team users and see their activity to manage permissions and monitor how your team is interacting with models.

What kind of analytics can I get with Keywords AI?

You can see cost trends, latency metrics, and error rates for all your requests across different providers.

Can Keywords AI alert me when I'm running low on credits?

Yes, it lets you review and set up monitoring thresholds for your usage so you can get notified before you run out.

Does Keywords AI support multiple model providers?

It works as a unified gateway to track any LLM provider you connect to the platform, giving you a single view of your entire stack.

How do I check if my API connection is working?

You can ask your agent to verify the connection status instantly to ensure your gateway is reachable and active.

Can my AI track LLM costs?

Yes. get_credits shows your balance, get_usage_stats breaks down costs by model and time period.

Can I filter request logs by model?

Yes. list_requests_by_model returns only requests made to a specific LLM.

What analytics are available?

get_analytics provides cost trends, latency percentiles, error rates, and token usage over time.

One connection away

Give your agent a direct line to Keywords AI.

Connect Keywords AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available