--- title: Runpod API Integration on Truto slug: runpod category: Application Development canonical: "https://truto.one/integrations/detail/runpod/" --- # Runpod API Integration on Truto **Category:** Application Development **Status:** Generally available ## MCP-ready AI tools Truto exposes 58 tools for Runpod that AI agents can call directly. - **list_all_runpod_openapi_jsons** — Get the OpenAPI 3.0 specification for the runpod API. Returns the complete API specification as an opaque JSON document; the source provides no enumerable field-level schema (example payload is an empty object), and the response structure follows the OpenAPI 3.0 standard. - **list_all_runpod_docs** — Get the interactive RunPod API documentation page. Returns an HTML page rendering the OpenAPI schema UI — this endpoint serves a text/html response rather than structured JSON data, so no enumerable fields are available. - **list_all_runpod_pods** — List runpod Pods with optional filters. Returns: env, gpu, id, image, interruptible, locked, machine, name, ports. Supports filtering by computeType, desiredStatus, gpuTypeId, dataCenterId, imageName, and more. - **create_a_runpod_pod** — Create a new runpod Pod and optionally deploy it. Returns: env, gpu, id, image, interruptible, locked, machine, machineId, name, ports, templateId, imageName. - **get_single_runpod_pod_by_id** — Get a single runpod Pod by id. Returns: env, gpu, id, image, interruptible, locked, machine, name, ports. Required: id. - **update_a_runpod_pod_by_id** — Update a runpod Pod by id, potentially triggering a reset. Returns: env, gpu, id, image, interruptible, locked, machine, machineId, name, ports, templateId, imageName. Required: id. - **delete_a_runpod_pod_by_id** — Delete a runpod Pod by id. Returns an empty 204 response on success. Required: id. - **runpod_pods_start** — Start or resume a runpod Pod. Returns: id, desiredStatus. Required: pod_id. - **runpod_pods_stop** — Stop a running runpod Pod. Returns: id, desiredStatus. Required: pod_id. - **runpod_pods_reset** — Reset a runpod Pod. Returns: id, desiredStatus. Required: pod_id. - **create_a_runpod_pod_update** — Update a runpod pod by pod_id (synonym for PATCH /pods/{podId}). Returns the updated pod object including id, imageName, env, machineId, machine details, and desiredStatus. Required: pod_id. - **create_a_runpod_pod_restart** — Restart a runpod Pod by its pod_id. Returns an empty 204 response on success. Required: pod_id. - **list_all_runpod_endpoints** — List all RunPod serverless endpoints. Returns: createdAt, env, id, name, template, version, workers. - **create_a_runpod_endpoint** — Create a new RunPod serverless endpoint. Returns: allowedCudaVersions, computeType, createdAt, dataCenterIds, env, executionTimeoutMs, gpuCount, gpuTypeIds, id, idleTimeout, instanceIds, minCudaVersion, name, networkVolumeId, networkVolumeIds, scalerType, scalerValue, template, templateId, userId, version, workers, workersMax, workersMin, gpuIds, locations, flashBootType, pods. - **get_single_runpod_endpoint_by_id** — Get a single RunPod serverless endpoint by id. Returns: createdAt, env, id, name, template, version, workers. Required: id. - **update_a_runpod_endpoint_by_id** — Update an existing RunPod serverless endpoint by id. Returns: createdAt, env, id, name, template, templateId, version, workers, workersMax, gpuIds. Required: id. - **delete_a_runpod_endpoint_by_id** — Delete a RunPod serverless endpoint by id. Returns an empty 204 response on success. Required: id. - **create_a_runpod_endpoint_update** — Update a RunPod endpoint by ID (synonym for PATCH /endpoints/{endpointId}). Returns the updated endpoint object including id, name, gpuIds, templateId, workersMax, workersMin, scalerType, scalerValue, idleTimeout, locations, networkVolumeId, and flashBootType. Required: endpoint_id. - **list_all_runpod_templates** — List Runpod templates. Returns: category, earned, env, id, name, ports, readme. Optionally broaden results to include endpoint-bound templates, community public templates, or official Runpod templates using the filter parameters. - **create_a_runpod_template** — Create a new Runpod template. Returns: category, earned, env, id, imageName, name, ports, readme. Required: imageName, name. - **get_single_runpod_template_by_id** — Get a single Runpod template by id. Returns: category, earned, env, id, name, ports, readme. Required: id. - **update_a_runpod_template_by_id** — Update a Runpod template by id. Returns: category, earned, env, id, name, ports, readme. Required: id. - **delete_a_runpod_template_by_id** — Delete a Runpod template by id. Returns an empty 204 response on success. Required: id. - **create_a_runpod_template_update** — Update a RunPod template by template_id (synonym for PATCH /templates/{templateId}). Returns the updated template object including id, imageName, name, and env. Required: template_id. - **list_all_runpod_networkvolumes** — List all runpod network volumes. Returns: id, name, size, dataCenterId. - **create_a_runpod_networkvolume** — Create a new runpod network volume. Returns: dataCenterId, id, name, size. Required: name. - **get_single_runpod_networkvolume_by_id** — Get a single runpod network volume by id. Returns: dataCenterId, id, name, size. Required: id. - **update_a_runpod_networkvolume_by_id** — Update a runpod network volume by id. Returns: dataCenterId, id, name, size. Required: id. - **delete_a_runpod_networkvolume_by_id** — Delete a runpod network volume by id. Returns an empty 204 response on success. Required: id. - **create_a_runpod_networkvolume_update** — Update a runpod network volume. Acts as a synonym for PATCH on the network volume resource. Returns the updated network volume including its id and name. Required: network_volume_id. - **list_all_runpod_containerregistryauths** — List all container registry auths in runpod. Returns: id, name, created_at, updated_at. - **create_a_runpod_containerregistryauth** — Create a new container registry auth in runpod. Returns: id, name, created_at, updated_at. - **get_single_runpod_containerregistryauth_by_id** — Get a single runpod container registry auth by id. Returns: id, name, created_at, updated_at. Required: id. - **delete_a_runpod_containerregistryauth_by_id** — Delete a runpod container registry auth by id. Returns an empty 204 response on success. Required: id. - **list_all_runpod_billing_pods** — Retrieve runpod pod billing history aggregated into configurable time buckets. Returns a BillingRecords collection; the record-level field schema is defined by the BillingRecords type in the runpod REST API reference and is not enumerated in the available source documentation. Optionally filter by gpuTypeId or podId and control aggregation granularity via bucketSize and grouping. - **list_all_runpod_billing_endpoints** — Retrieve Runpod Serverless endpoint billing history aggregated into time buckets. Returns billing record objects grouped by the chosen field; the field-level response shape is not enumerated in the available source documentation. All query parameters are optional. - **list_all_runpod_billing_networkvolumes** — List runpod network volume billing history aggregated into configurable time buckets. Returns billing records for the requested time range (response field details are not enumerated in the API docs). Optional: bucketSize (defaults to day), startTime, endTime. - **create_a_runpod_pod_start** — Start (resume) a stopped runpod Pod via the podResume mutation. Returns: id, desiredStatus, imageName, data. Required: pod_id. Optionally supply gpuCount and allowedCudaVersions to control GPU allocation and CUDA version filtering when the Pod resumes. - **create_a_runpod_pod_stop** — Stop a runpod Pod by pod_id, releasing the GPU while preserving volume data. Returns: id, desiredStatus, data. Required: pod_id. - **create_a_runpod_pod_reset** — Reset a runpod Pod, stopping and restarting it in place. Returns the pod's id and desiredStatus reflecting the result of the reset operation. Required: pod_id. - **list_all_runpod_network_volumes** — List all runpod network volumes available to your account — persistent storage units attachable to pods and serverless endpoints. Returns: id, name, size, dataCenterId, attributes, data. - **get_single_runpod_network_volume_by_id** — Get a single runpod network volume by id. Returns: dataCenterId, id, name, size, attributes, data. Required: id. - **create_a_runpod_network_volume** — Create a new runpod network volume for persistent storage attachable to pods and serverless endpoints. Returns: dataCenterId, id, name, size, attributes, data. - **update_a_runpod_network_volume_by_id** — Update an existing runpod network volume by id. Returns: dataCenterId, id, name, size, attributes, data. Required: id. - **delete_a_runpod_network_volume_by_id** — Delete a runpod network volume by id. Returns an empty 204 response on success. Required: id. - **list_all_runpod_container_registry_auths** — List all container registry auth credentials saved in runpod for connecting to private Docker registries. Returns: id, name. - **get_single_runpod_container_registry_auth_by_id** — Get a single runpod container registry auth credential by id. Returns: id, name. Required: id. - **create_a_runpod_container_registry_auth** — Create a new container registry auth credential in runpod to enable pulling from a private Docker registry. Returns: id, name, data. - **delete_a_runpod_container_registry_auth_by_id** — Delete a runpod container registry auth credential by id. Returns an empty 204 response on success. Required: id. - **list_all_runpod_billing_network_volumes** — List runpod network volumes with associated billing information. Returns: amount, time. No required parameters. - **create_a_runpod_serverless_sync_job** — Submit a synchronous job to a runpod serverless endpoint and wait for completion before returning the result. Returns: id, status. Required: endpoint_id and input. Default wait time is 90 seconds, adjustable via the wait query parameter (1000–300000 ms); results are retained for 1 minute after completion. - **create_a_runpod_serverless_async_job** — Submit an asynchronous job to a RunPod serverless endpoint. The job processes in the background; retrieve its result via the /status endpoint. Results are available for 30 minutes after completion. Returns: id, status. Required: endpoint_id, input. - **get_single_runpod_serverless_job_status_by_id** — Get the status of a runpod serverless job by job and endpoint ID. Returns: id, status. Required: endpoint_id, id. - **get_single_runpod_serverless_job_stream_by_id** — Get the accumulated streaming output chunks for a runpod serverless job by job id. Returns an array of stream chunk objects, each containing output (with text, input_tokens, output_tokens) and metrics (with stream_index, scenario, gpu_kv_cache_usage, running, pending, and throughput stats). Required: endpoint_id, id. - **create_a_runpod_serverless_job_cancellation** — Cancel a runpod serverless job that is currently queued or running. Returns: id, status. Required: endpoint_id, job_id. - **create_a_runpod_serverless_job_retry** — Retry a failed or timed-out RunPod serverless job by requeuing it with its original input parameters and the same job ID, discarding any previous output. Returns: id, status. Required: endpoint_id, job_id. Only works for jobs whose current status is FAILED or TIMED_OUT; expired jobs (async results older than 30 minutes) cannot be retried. - **create_a_runpod_serverless_queue_purge** — Purge all pending jobs from the queue of a runpod serverless endpoint. Returns: removed, status. Required: endpoint_id. - **get_single_runpod_serverless_endpoint_health_by_id** — Get the operational health status of a runpod serverless endpoint. Returns: jobs, workers. Required: endpoint_id. ## How it works 1. **Link your customer's Runpod account.** Use Truto's frontend SDK; we handle every OAuth and API key flow so you don't need to create the OAuth app. 2. **Authentication is automatic.** Truto refreshes tokens, stores credentials securely, and injects them into every API request. 3. **Call Truto's API to reach Runpod.** The Proxy API is a 1-to-1 mapping of the Runpod API. 4. **Get a unified response format.** Every response uses a single shape, with cursor-based pagination and data in the `result` field. ## Use cases - **Embed GPU-powered inference in your SaaS** — Let your customers connect their own Runpod account so your product can route AI inference jobs to their serverless endpoints. You ship generative features without owning GPU infrastructure or absorbing inference costs. - **Offer BYOC GPU provisioning for AI workspaces** — MLOps and developer platforms can let users one-click provision GPU Pods on their own Runpod account, with templates pre-configured for training, fine-tuning, or notebook environments. - **Automate batch AI job orchestration** — Workflow and automation platforms can queue thousands of async inference jobs against a user's Runpod serverless endpoint, stream results back, and handle retries and cancellations programmatically. - **Surface GPU spend in FinOps dashboards** — Cloud cost observability tools can pull granular Pod, endpoint, and network volume billing data from each connected Runpod account to flag idle workers and attribute inference costs to teams. - **Manage scheduled Pod lifecycles to cut idle spend** — Cost-control and scheduling tools can programmatically start, stop, and reset user Pods on a schedule — for example, spinning training Pods up overnight and stopping them by morning. ## What you can build - **Sync and async serverless job submission** — Submit inference payloads to a user's Runpod endpoint with sync or async semantics, then poll status or cancel and retry stalled jobs. - **Token and metric streaming UI** — Stream accumulated output chunks and hardware telemetry from in-flight serverless jobs to power real-time generation UIs in your product. - **One-click GPU Pod provisioning** — Create, update, start, stop, reset, and delete Pods from a user's Runpod account using saved templates with specific GPU types and container images. - **Serverless endpoint deployment and autoscaling controls** — Programmatically create and update endpoints with configurable GPU IDs, flashboot, and min/max worker bounds so users can deploy models from inside your product. - **Template and network volume management** — Create and manage Pod templates and network volumes to standardize environments and mount model weights into newly provisioned GPU workloads. - **GPU billing and endpoint health dashboards** — Pull billing records for Pods, endpoints, and network volumes plus endpoint health metrics to power cost attribution, idle-worker alerts, and usage analytics. ## FAQs ### How do end users authenticate their Runpod account? Runpod uses API key authentication. Through Truto, your end users supply a Runpod API key during the connection flow, and Truto stores and injects it on every request — your app never handles the raw credential. ### Which Runpod resources can we manage through this integration? You can manage Pods, Serverless Endpoints, Templates, Network Volumes, and Container Registry Auths, plus submit and control Serverless Jobs (sync, async, status, stream, retry, cancel, queue purge) and read billing data for Pods, Endpoints, and Network Volumes. ### Can we stream tokens from a running inference job? Yes. The serverless job stream endpoint returns accumulated output chunks and hardware metrics for an in-progress job, which you can relay to your end-user's UI as the job progresses. ### Is there a unified API for Runpod on Truto? Not currently. Runpod is exposed as a passthrough integration with first-class tools for each resource, so you get typed access to Runpod-native concepts like Pods, Endpoints, and Serverless Jobs without a normalization layer. ### How do we control GPU costs on behalf of users? You can stop or reset Pods to halt billing, configure endpoint autoscaling with workersMin/workersMax, and read billing endpoints to detect idle workers or endpoints with active capacity but no queued jobs. ### How does Truto handle Runpod rate limits and errors? Truto proxies Runpod's native rate limits and surfaces error responses directly. You can implement retries on transient failures, and for serverless jobs Runpod itself exposes retry and cancellation actions you can call through Truto.