Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

Join

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

Join

⚡｜serverless

⛅｜pods

🔧｜api-opensource

📡｜instant-clusters

🗂｜hub

Paul

10/8/2025

How to get the IP address of a running pod via API

EDIT: I see someone else asked something similar more than 30 days ago, with no answer. Hopefully I can get one this time! I'm writing a tool to manage pods to run LLMs, which I will then access from VSCode. Much of it is working...

Solution:

response: ``` [ { "adjustedCostPerHr": 0.69,...

Message Not Public

Peter Lebiedzinski

10/1/2025

Is the `cost` accurate in Public Endpoint?

I am using the Public Endpoints API to generate images with: https://console.runpod.io/hub/playground/image/qwen-image-t2i According to the docs, the pricing is $0.02/Mega-pixel. In the API response from generating the image, it provides a cost value in the JSON data, and it always seems to be 0.02, regardless of the input image dimensions I'm using. Is this accurate? The billing/pricing isn't transparent in most of the Public Endpoints, and I'd like confirmation before I'm able to deploy anything....

red_wolf

7/30/2025

Configuring endpoints via API if publishing via Github integration

It seems that there's no way to create / update endpoints via the API, unless you host the images on a docker registry. Are there plans to extend API support to endpoints that are published from a github branch? I want to have my full endpoint configuration and deployment via codel but this doesn't seem to be possible using the github integration, as opposed to deploying from a container registry. ...

RukshanJS

7/25/2025

How to run locally

I know about the test_input.json and can run the worker as a standalone program which works fine. But we have a nextjs frontend and want to test locally an api call to the runpod server/worker (rather than cloud runpod api) Could not figure out a way how to do this. Can someone please help. Thank you...

7/24/2025

Missing 12.9 cuda version in Create pod API

Hi, I'm trying to create a pod with APIs with vllm 0.9.2 on A40/A6000 in EU-SE1 how can I force it to be created on an host with cuda 12.9? vllm 0.9.0+ requires cuda 12.8+ but the hosts with a40 there have a mix of 12.4, 12.7 and 12.9. If I don't set a cuda version it work when I'm lucky to get an host with 12.9 otherwise it won't work. Is it possible to get the cuda version 12.9 added to the API options to create a new pod ?...

John lanser

7/23/2025

Restart api not working

I was trying out the restart api but it seems to be not working, even though it returns 200 response but the pod is not restarted. https://docs.runpod.io/api-reference/pods/POST/pods/podId/restart...

Taha

7/6/2025

401 when attempting to call the create pod endpoint

I get a 401 when I try creating a pod through the REST API. Is anything wrong with my request? ```curl curl -X POST https://rest.runpod.io/v1/pods \ -H "Authorization: Bearer $RUNPOD_API_KEY" ...

Solution:

You need a api key with "all" permission

Message Not Public

R1ckyH

7/1/2025

runpod python api create_pod params

since the runpod have a place of template, which include image_name, should the image name be a must if want to create a pod when we having template?

Phobos

6/22/2025

Pod information endpoint doesn't return the public ip (empty string)

This endpoint returns the public ip as an empty string, even though a public ip has been allocated: curl -s -X GET https://rest.runpod.io/v1/pods/$RUNPOD_POD_ID ...

コスチャ

6/16/2025

GpuAvailability is empty for pods

I'm trying to request info about GPUs availabilty via gql https://graphql-spec.runpod.io/#definition-GpuAvailability but there are empty/null responses only. What's the correct way to request it? `query gpuTypes { gpuTypes { id...

Myron

6/14/2025

REST Api GPU util

In the graphQL API we can pull the Pods' gpuUtilPercent I'm not seeing the same value on the REST api however. Is this going to get added or am I overlooking something?...

Eugene_Swanley

6/9/2025

Manage API keys

Hello, Is there any way to manage API keys via the API — for example, to automatically generate a new key for every pod I create?...

Eugene_Swanley

6/5/2025

Empty machine information in Pod

I’m using the REST API to retrieve information about running pods and noticed that the API returns an empty machine field in the responses to both find pod and list pods requests. Is this expected behavior? If so, is there another way to obtain machine details? Also, is there any way to fetch current pod utilization — similar to what’s shown in the UI?...

Eugene_Swanley

6/2/2025

GraphQL Introspection or Schema download

Hello, I would like to implement provisioner for pod and will work the control API. As I see there is REST interface and GraphQL. I wanted to use graphql but it's hard to write queries without the generated code. Can you enable the introspeciton on server or provider a way to download the schema, so I'll be able to generate client code?...

YayL

6/1/2025

Unexpected status code: 401

After having played around a bit with the runpodctl I have now run into an issue where I am unable to perform any real commands because I get status code 401 everytime. I have generating a new API key, to no avail. I should also note that I, perhaps stupidly, made some changes to the code to allow for a globalNetwork flag and I changed the version name in order to more easily make sure that those running my bash script have this patched version. I quickly realized that this caused issues and I r...

zoob

5/29/2025

Billing Info

on the GET https://rest.runpod.io/v1/billing/pods?grouping=gpuTypeId there is a property time in response. but as i receive it, for every billing record time value always shows 00:00:00 - it shows only date, in fact was this designed this way? can i somehow get the time too?(in addition to date)...

zoob

5/27/2025

runpod api questions about gpu type availability and gpu count

- how can i get precise information about availability of some gpu type for pod creating on demand? - is stockStatus value from LowestPrice type of graphql api representing availability status of some specific gpu to create pod with? my workflow is: graphql gpuTypes query -> passing to POST https://rest.runpod.io/v1/pods request body gpu count from my local ui(not more than maxGpuCountCommunityCloud i parsed for specific gpu type) and gpu type id...

コスチャ

5/23/2025

Retrieve public templates via REST API

Is there a way to fetch the public templates (the ones listed on https://www.runpod.io/console/explore)? The /templates endpoint only returns the templates I’ve created.

jojje

5/8/2025

Access pod logs via API

Can someone please explain how to access the pod logs via the API? Seems only the web console has access, and the only thing preventing this from being added to runpodctlis being able to access hapi.runpod.net/v1/pod/<pod-id>/logs resource. See: https://github.com/runpod/runpodctl/issues/29...

Vikas

5/6/2025

curl: (7) Failed to connect to 64.247.206.102 port 8000 after 41 ms: Couldn't connect to server

My application is listening on port 8000 on the pod with the above-mentioned public ip address, but when i curl that from a server outside the runpod using this command: curl -X POST http://64.247.206.102:8000 -H "Content-Type: application/json" -d '{"prompt": "Test prompt" , "max_tokens": 50}' ...

Gaming

Programming

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!