Weekly spend check
Dan Fletcher, ML lead at BigCo, asked what Runpod cost last week. Memtro split spend in USD by day and by pod, and named the running pods with their hourly cost.
Runpod + Memtro
Which GPU pods are running, and what are they costing us?
Runpod shows you your pods with GPU, image, status, hourly cost and live utilisation. It reads serverless endpoints with their workers and request metrics, network volumes, GPU types with prices, and spend by day, pod or endpoint. When asked and granted, it can create, start, stop, restart, change or terminate a pod. It can also rescale or delete a serverless endpoint, and create, grow or delete a network volume. Creating or starting a pod starts hourly billing. Memtro never reads environment variables, secrets, SSH keys or registry credentials.
In Memtro
What you can do with Runpod in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Runpod tool, reads what it needs, and answers with the source cited.
What it does
- 01Lists pods with status, GPU type, image, hourly cost in USD and data centre.
- 02Reads one pod's live GPU, CPU and memory utilisation, ports, disks and mounted volumes.
- 03Reads serverless endpoints, their workers and request metrics, network volumes, GPU prices and spend in USD.
- 04When asked and granted, creates or starts a pod, which starts hourly billing, or stops, restarts or changes one.
- 05When asked and granted, terminates a pod or deletes an endpoint or network volume, all permanently.
- 06When asked and granted, rescales a serverless endpoint, or creates, renames or grows a network volume, which is billed for its size.
Acts when asked
When you ask it to
These tools change something in Runpod. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
- 01Create a pod (starts hourly GPU or CPU billing)
- 02Start a stopped pod (resumes billing)
- 03Stop a running pod (keeps its disk)
- 04Restart a running pod's container
- 05Terminate a pod (permanent)
- 06Rename a pod, change its image, disk, ports or lock
- 07Rescale or change a serverless endpoint
- 08Delete a serverless endpoint (permanent)
- 09Create a network volume (billed storage)
- 10Rename or grow a network volume
- 11Delete a network volume (permanent)
In practice
Ask it like you would a colleague
Once Runpod is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Runpod + MemtroWhich pods are running and what do they cost per hour?
What did we spend on Runpod last month?
How busy is the GPU on the training pod?
How many requests failed on the inference endpoint today?
What does an H100 cost per hour on secure cloud?
Stopping an idle pod
Maya Okafor at Acme Ltd saw an idle training pod and asked Memtro to stop it. With the action granted, Memtro stopped it, so compute billing ended while its disk was kept.
Teams
Where it fits
The teams that lean on Runpod most, a question each of them asks, and what they connect beside it.
- EngineeringKeep decisions from evaporatingEngineer, Tech lead, On call, New joiner“Who owns the billing migration, and what did we decide about retries?”Used alongside GitHub, Linear, Jira, Confluence, Slack and 5 more.
- ProductHear what customers actually ask forProduct manager, Researcher, Designer, Head of product“Which customers asked for SSO this quarter, and what is their combined ARR?”Used alongside Help Scout, HubSpot, Linear, Jira, Slack and 6 more.
- Agent buildersMemory and tools for the agents you buildSolo builder, Platform team, Automation engineer, Whoever signs it off“Search memtro for what we know about Acme before drafting the proposal”Used alongside GitHub, Linear and Slack.
Better together
Works with
A record in Runpod is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
- Work managementRunpod with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementRunpod with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementRunpod with LinearIssues, projects and teams, synced hourly into memory.
- SupportRunpod with Help ScoutAI that reads your support conversations and cross-references the customer everywhere else.
- SupportRunpod with ZendeskEvery ticket, reply and internal note, ready to be asked about.
- SupportRunpod with IntercomCustomer conversations and the people behind them, in your company memory.
- Documents and wikisRunpod with NotionSearch pages and query databases, and write to them when you ask.
- Documents and wikisRunpod with Google DriveSearch Drive and read Docs, Sheets and Slides as text, and write a Doc when you ask.
- Documents and wikisRunpod with ConfluenceSearch and read wiki pages, and write them when you ask.
Also in Engineering and operations
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- GitHub
- AWS CloudWatch
- Sentry
- ServiceNow
- Okta
- Twilio
- AWS CloudTrail
- GitLab
- Bitbucket
- Vercel
- PagerDuty
- Datadog
- Grafana
- incident.io
- Azure DevOps
- CircleCI
- Cloudflare
- LaunchDarkly
- New Relic
- Rollbar
- Snyk
- Better Stack
- Buildkite
- DigitalOcean
- Heroku
- Netlify
- SonarQube Cloud
- Statuspage
UptimeRobot- Axiom
- BugSnag
- Checkly
- Hetzner Cloud
Honeycomb- Pingdom
- Render
- Statsig
- Sumo Logic
- Supabase
- HCP Terraform
- Vultr
- Airbrake
- Codecov
Cronitor- Dynatrace
FireHydrant- Fly.io
- Honeybadger
- Akamai Linode
- Octopus Deploy
- Pulumi
- Rootly
- Semgrep
- Splunk
StatusCake- Tailscale
- Argo CD
- authentik
- Coolify
- Gitea
GlitchTip
GLPI- Jenkins
Langfuse
LibreNMS- n8n
NetBox- Portainer
- Prefect
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone- OpenAI (usage and cost)
- Anthropic (usage and cost)
- Algolia
- Flagsmith
- Unleash
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert- KnowBe4
JumpCloud
ConfigCat- Railway
- Fastly
- Postman
- Make
- Braintrust
- OpenRouter
- ElevenLabs
Split- Scaleway
Aikido Security- AssemblyAI
Astronomer- Bamboo
- Baseten
- Bitrise
- Bitwarden
- BrowserStack
- bunny.net
- Cachet
- Checkmk
- Civo
- Cloudsmith
- Codacy
- Codemagic
Comet Opik- Coralogix
CrowdStrike Falcon- Dagster+
- DeepSource
Detectify- Docker Hub
Domotz- Grafana OnCall
- Harness
- Hugging Face
- Instatus
- Koyeb
- Lambda Cloud
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary- Mezmo
NinjaOne- Nomad
Northflank- Oh Dear
- OVHcloud
Portkey- Probely (Snyk API & Web)
PromptLayer- Proxmox VE
PRTG Network Monitor- Qase
Raygun
Retell AI- Retool
- SecurityScorecard
- Semaphore CI
Shodan- SigNoz
- Socket
Spike.sh
Squadcast- SwaggerHub
- TeamCity
Tenable- Together AI
- Travis CI
UpGuard
Uptime.com
Vanta- Vapi
- Windmill
Zenduty- OpsLevel
Cortex- Auth0
- Clerk
WorkOS
Kandji
Automox
Huntress- HackerOne
SimpleMDM- AppSignal
Healthchecks.io
Rapid7 InsightVM- 1Password Events
- JFrog Artifactory
- Sauce Labs
Zenhub- Deepgram
- Replicate
Setup
How to connect
Connect withAPI key
- 1
In the Runpod console open Settings, then API Keys, and create a key. Choose Read Only for reads, or All for actions. It is shown once.
- 2
In Memtro open Connections → Runpod and paste the API key.
- 3
A key made inside a team acts for that team. An administrator grants the pod, endpoint and volume actions by name.
- 4
Ask: which pods are running and what do they cost per hour?
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Runpod tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Runpod?+
Only when you ask, and only what it has been granted: create a pod (starts hourly GPU or CPU billing); start a stopped pod (resumes billing); stop a running pod (keeps its disk); restart a running pod's container; terminate a pod (permanent); rename a pod, change its image, disk, ports or lock; rescale or change a serverless endpoint; delete a serverless endpoint (permanent); create a network volume (billed storage); rename or grow a network volume; delete a network volume (permanent). Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
Who can use a Runpod connection?+
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Does Memtro store my Runpod data?+
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
How do I connect Runpod?+
API key. In the Runpod console open Settings, then API Keys, and create a key. Choose Read Only for reads, or All for actions. It is shown once.
Connect Runpod in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.