API Reference

Complete reference for using the AICR API Server.

Overview

The AICR API Server provides HTTP REST access to recipe generation and bundle creation for GPU-accelerated infrastructure. Use the API for programmatic access to configuration recommendations and deployment artifacts.

Version numbers in the sample requests and responses below (server version, chart versions, driver versions) are illustrative. The authoritative, current versions are in the Component Catalog and the Container Images BOM.

┌──────────────┐      ┌──────────────┐
│ GET /recipe  │─────▶│   Recipe     │
└──────────────┘      └──────────────┘
        │
        ▼
┌──────────────┐      ┌──────────────┐
│ POST /bundle │─────▶│  bundles.zip │
└──────────────┘      └──────────────┘

API vs CLI

Use the API for remote recipe generation and bundle creation
Use the CLI for local operations, snapshot capture, and ConfigMap integration

Feature	API	CLI
Recipe generation	✅ GET /v1/recipe	✅ `aicr recipe`
Value query	✅ GET /v1/query	✅ `aicr query`
Bundle creation	✅ POST /v1/bundle	✅ `aicr bundle`
Snapshot capture	❌ Use CLI	✅ `aicr snapshot`
ConfigMap I/O	❌ Use CLI	✅ `cm://` URIs
Agent deployment	❌ Use CLI	✅ `aicr snapshot`

Base URL

Local development (example):

http://localhost:8080

Start the local server:

docker pull ghcr.io/nvidia/aicrd:latest
docker run -p 8080:8080 ghcr.io/nvidia/aicrd:latest

Quick Start

Get a Recipe

Generate an optimized configuration recipe for your environment:

# GET: Basic recipe for H100 on EKS (query parameters)
curl "http://localhost:8080/v1/recipe?accelerator=h100&service=eks"

# GET: Training workload on Ubuntu
curl "http://localhost:8080/v1/recipe?accelerator=h100&service=eks&intent=training&os=ubuntu"

# POST: Recipe from criteria file (YAML body)
curl -X POST "http://localhost:8080/v1/recipe" \
  -H "Content-Type: application/x-yaml" \
  -d 'kind: RecipeCriteria
apiVersion: aicr.run/v1alpha2
metadata:
  name: my-config
spec:
  service: eks
  accelerator: h100
  intent: training'

# Save recipe to file
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" -o recipe.json

Generate Bundles

Create deployment bundles from a recipe:

# Pipe recipe directly to bundle endpoint.
# The POST body must be a fully-hydrated RecipeResult; piping GET /v1/recipe
# output (as below) supplies one. Do not hand-author a partial body.
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" | \
  curl -X POST "http://localhost:8080/v1/bundle" \
    -H "Content-Type: application/json" -d @- -o bundles.zip

# Extract the bundles
unzip bundles.zip -d ./bundles

Endpoints

GET /

Service information and available routes.

curl "http://localhost:8080/"

Response:

{
  "service": "aicrd",
  "version": "v0.14.0",
  "routes": ["/v1/recipe", "/v1/query", "/v1/bundle"]
}

GET /v1/recipe

Generate an optimized configuration recipe based on environment parameters.

Query Parameters:

Parameter	Type	Default	Description
`service`	string	any	K8s service: `eks`, `gke`, `aks`, `oke`, `ocp`, `kind`, `lke`, `bcm`, `any`
`accelerator`	string	any	GPU type: `h100`, `h200`, `gb200`, `b200`, `a100`, `l40`, `l40s`, `rtx-pro-6000`, `any`
`gpu`	string	any	Alias for `accelerator`
`intent`	string	any	Workload: `training`, `inference`, `any`
`os`	string	any	Node OS: `ubuntu`, `rhel`, `cos`, `amazonlinux`, `ol`, `talos`, `any`
`platform`	string	any	Platform/framework: `dynamo`, `kubeflow`, `nim`, `runai`, `slurm`, `any`
`nodes`	integer	0	GPU node count (0 = any)

Examples:

# Minimal request
curl "http://localhost:8080/v1/recipe"

# Specify accelerator
curl "http://localhost:8080/v1/recipe?accelerator=h100"

# Full specification
curl "http://localhost:8080/v1/recipe?service=eks&accelerator=h100&intent=training&os=ubuntu&nodes=8"

# Using gpu alias
curl "http://localhost:8080/v1/recipe?gpu=gb200&service=gke"

# Pretty print with jq
curl -s "http://localhost:8080/v1/recipe?accelerator=h100" | jq '.'

POST /v1/recipe

Generate an optimized configuration recipe from a criteria file body. This endpoint provides an alternative to query parameters, accepting a Kubernetes-style RecipeCriteria resource in the request body.

Content Types:

application/json - JSON format
application/x-yaml - YAML format

Request Body:

The request body must be a RecipeCriteria resource:

kind: RecipeCriteria
apiVersion: aicr.run/v1alpha2
metadata:
  name: my-criteria
spec:
  service: eks
  accelerator: gb200
  os: ubuntu
  intent: training
  platform: kubeflow
  nodes: 8

Examples:

# POST with YAML body
curl -X POST "http://localhost:8080/v1/recipe" \
  -H "Content-Type: application/x-yaml" \
  -d 'kind: RecipeCriteria
apiVersion: aicr.run/v1alpha2
metadata:
  name: training-config
spec:
  service: eks
  accelerator: h100
  intent: training'

# POST with JSON body
curl -X POST "http://localhost:8080/v1/recipe" \
  -H "Content-Type: application/json" \
  -d '{
    "kind": "RecipeCriteria",
    "apiVersion": "aicr.run/v1alpha2",
    "metadata": {"name": "training-config"},
    "spec": {
      "service": "eks",
      "accelerator": "h100",
      "intent": "training"
    }
  }'

# POST with criteria file
curl -X POST "http://localhost:8080/v1/recipe" \
  -H "Content-Type: application/yaml" \
  -d @criteria.yaml

# Pretty print response
curl -s -X POST "http://localhost:8080/v1/recipe" \
  -H "Content-Type: application/json" \
  -d '{"kind":"RecipeCriteria","apiVersion":"aicr.run/v1alpha2","spec":{"service":"eks","accelerator":"h100"}}' \
  | jq '.'

Error Responses:

400 Bad Request - Invalid criteria format, missing required fields, or invalid enum values
405 Method Not Allowed - Only GET and POST are supported

Response:

{
  "apiVersion": "aicr.run/v1alpha2",
  "kind": "RecipeResult",
  "metadata": {
    "version": "v0.14.0",
    "appliedOverlays": [
      "base",
      "eks",
      "eks-training",
      "gb200-eks-training"
    ],
    "excludedOverlays": [
      {
        "name": "h100-eks-ubuntu-training",
        "reason": "mixin-constraint-failed"
      }
    ],
    "constraintWarnings": [
      {
        "overlay": "h100-eks-ubuntu-training",
        "constraint": "OS.sysctl./proc/sys/kernel/osrelease",
        "expected": ">= 6.8",
        "actual": "5.15.0",
        "reason": "mixin-constraint-failed: expected >= 6.8, got 5.15.0"
      }
    ]
  },
  "criteria": {
    "service": "eks",
    "accelerator": "gb200",
    "intent": "training",
    "os": "any",
    "platform": "any"
  },
  "constraints": [
    {
      "name": "GPU.driver.version",
      "value": "580.82.07"
    },
    {
      "name": "GPU.driver.cudaVersion",
      "value": "13.1"
    }
  ],
  "componentRefs": [
    {
      "name": "gpu-operator",
      "type": "Helm",
      "chart": "gpu-operator",
      "source": "https://helm.ngc.nvidia.com/nvidia",
      "version": "v25.3.3"
    },
    {
      "name": "network-operator",
      "type": "Helm",
      "chart": "network-operator",
      "source": "https://helm.ngc.nvidia.com/nvidia",
      "version": "v25.4.0"
    }
  ],
  "deploymentOrder": [
    "gpu-operator",
    "network-operator"
  ]
}

metadata.excludedOverlays is optional. When present, each entry includes the overlay name and a machine-readable reason such as constraint-failed or mixin-constraint-failed.

GET /v1/query

Query a specific value from a fully hydrated recipe. Resolves a recipe from criteria (same parameters as GET /v1/recipe), merges all base, overlay, and inline overrides, then returns the value at the given selector path.

Query Parameters:

All GET /v1/recipe parameters are supported, plus:

Parameter	Type	Required	Description
`selector`	string	Yes	Dot-delimited path to the value to extract (e.g. `components.gpu-operator.values.driver.version`). Empty string returns the entire hydrated recipe.

Response:

Scalar values (string, number, bool) are returned as plain JSON values
Complex values (maps, lists) are returned as JSON objects/arrays

Examples:

# Get a specific Helm value
curl -s "http://localhost:8080/v1/query?service=eks&accelerator=h100&intent=training&selector=components.gpu-operator.values.driver.version"

# Get deployment order
curl -s "http://localhost:8080/v1/query?service=eks&accelerator=h100&intent=training&selector=deploymentOrder" | jq '.'

# Get a component subtree
curl -s "http://localhost:8080/v1/query?service=eks&accelerator=h100&selector=components.gpu-operator.values.driver" | jq '.'

POST /v1/query

Alternative to GET /v1/query that accepts the criteria and selector in the request body. The body is a QueryRequest with a criteria object (same fields as the RecipeCriteria spec) and a selector string.

Content Types:

application/json - JSON format
application/x-yaml - YAML format

Request Body:

criteria:
  service: eks
  accelerator: h100
  intent: training
selector: "components.gpu-operator.values.driver.version"

Examples:

curl -X POST "http://localhost:8080/v1/query" \
  -H "Content-Type: application/json" \
  -d '{
    "criteria": {"service": "eks", "accelerator": "h100", "intent": "training"},
    "selector": "components.gpu-operator.values.driver.version"
  }'

The response format matches GET /v1/query: scalar values are returned as plain JSON values; maps and lists are returned as JSON objects/arrays.

POST /v1/bundle

Generate deployment bundles from a recipe.

Query Parameters:

Parameter	Type	Default	Description
`bundlers`	string	(all)	Comma-delimited list of bundler types to execute. Not currently honored — all bundlers run regardless (#1531).
`set`	string[]		Value overrides (format: `bundler:path.to.field=value`). Repeat for multiple.
`dynamic`	string[]		Declare value paths as install-time parameters (format: `component:path.to.field`). Repeat for multiple. Supported with `deployer=helm`, `deployer=argocd-helm`, `deployer=flux`, and `deployer=helmfile`.
`system-node-selector`	string[]		Node selectors for system components (format: `key=value`). Repeat for multiple.
`system-node-toleration`	string[]		Tolerations for system components (format: `key=value:effect`). Repeat for multiple.
`accelerated-node-selector`	string[]		Node selectors for GPU nodes (format: `key=value`). Repeat for multiple.
`accelerated-node-toleration`	string[]		Tolerations for GPU nodes (format: `key=value:effect`). Repeat for multiple.
`nodes`	int	0	Estimated number of GPU nodes (0 = unset). Written to Helm value paths declared in the registry under `nodeScheduling.nodeCountPaths`.
`vendor-charts`	bool	false	Pull upstream Helm chart bytes into the bundle at bundle time so the artifact is fully self-contained and air-gap deployable. Each vendored chart is recorded in `provenance.yaml` with name, version, source URL, and SHA256. Trades the upstream CVE-yank fail-loud signal for offline deployability — see the CLI reference's "Vendoring Charts for Air-Gap" section for the full tradeoff. Requires the `helm` binary on the API server's `$PATH` and registry credentials configured for any private upstream repos (`HELM_REPOSITORY_USERNAME`/`HELM_REPOSITORY_PASSWORD` for HTTP(S); docker config for OCI). If prerequisites are missing the request fails with a structured error code (`SERVICE_UNAVAILABLE` / HTTP 503 for missing helm, `UNAUTHORIZED` / HTTP 401 for credentials).
`deployer`	string	helm	Deployment method: `helm`, `argocd`, `argocd-helm`, `flux`, or `helmfile`
`repo`	string		Git repository URL for GitOps deployments (used with `deployer=argocd` and `deployer=flux`; ignored by `deployer=argocd-helm`)
`app-name`	string		Parent Argo Application name (default: `aicr-stack` for `deployer=argocd-helm`, `nvidia-stack` for `deployer=argocd`). Must be a DNS-1123 subdomain. Required when deploying multiple non-overlapping AICR bundles to the same Argo CD namespace so the parent Applications do not collide. For `deployer=argocd-helm`, the value is the chart default and can still be overridden at install time via `helm install --set appName=...`. Rejected with HTTP 400 on other deployers.

Request Body:

The request body is the recipe (RecipeResult) directly. No wrapper object needed.

Components

These are the recipe components in recipes/registry.yaml. (The bundlers query parameter that would select a subset is currently ignored — all run regardless, #1531.) The registry is the authoritative source — see the component catalog for the full, current list with detailed descriptions. The table below is illustrative of commonly used components:

Component	Description
`agentgateway`	Kubernetes Gateway API implementation for AI/ML inference (InferencePool routing)
`agentgateway-crds`	Kubernetes Gateway API CRDs for AI/ML inference (Gateway API + Inference Extension)
`aws-ebs-csi-driver`	Amazon EBS CSI driver (EKS)
`aws-efa`	AWS Elastic Fabric Adapter device plugin (EKS)
`cert-manager`	TLS certificate management
`dynamo-platform`	NVIDIA Dynamo inference serving platform
`gatekeeper`	OPA Gatekeeper policy controller
`gke-nccl-tcpxo`	NCCL TCPxO network plugin for optimized collective communication (GKE)
`gpu-operator`	NVIDIA GPU Operator — driver and runtime lifecycle
`gpu-operator-ocp`	GPU Operator variant for OpenShift (OCP)
`gpu-operator-ocp-olm`	GPU Operator for OpenShift via Operator Lifecycle Manager (OLM)
`grove`	Dynamo pod lifecycle management
`k8s-ephemeral-storage-metrics`	Ephemeral storage usage metrics
`k8s-nim-operator`	NVIDIA NIM Operator for inference microservice deployments
`kai-scheduler`	DRA-aware gang scheduler with topology-aware placement
`kube-prometheus-stack`	Prometheus, Grafana, Alertmanager monitoring stack
`kubeflow-trainer`	Kubeflow Training Operator for distributed training
`kueue`	Kubernetes-native job queuing for batch and AI workloads
`network-operator`	NVIDIA Network Operator — RDMA, SR-IOV, host networking
`network-operator-ocp`	Network Operator variant for OpenShift (OCP)
`network-operator-ocp-olm`	Network Operator for OpenShift via Operator Lifecycle Manager (OLM)
`nfd`	Node Feature Discovery — labels nodes with hardware features; publishes per-node `NodeResourceTopology` CRDs on production GPU recipes
`nfd-ocp`	Node Feature Discovery variant for OpenShift (OCP)
`nfd-ocp-olm`	Node Feature Discovery for OpenShift via Operator Lifecycle Manager (OLM)
`nodewright-customizations`	Environment-specific node tuning profiles
`nodewright-operator`	OS-level node tuning and kernel configuration
`nvidia-dra-driver-gpu`	Dynamic Resource Allocation driver for GPUs
`nvsentinel`	GPU health monitoring and automated remediation
`prometheus-adapter`	Custom metrics for HPA scaling
`prometheus-operator-crds`	CRDs for the prometheus-operator (`Alertmanager`, `Prometheus`, `ServiceMonitor`, etc.)
`slinky-slurm`	Slinky-managed Slurm cluster instance (Controller, LoginSet, NodeSet, RestApi); reconciled by `slinky-slurm-operator`
`slinky-slurm-operator`	SchedMD Slinky Slurm operator and admission webhook
`slinky-slurm-operator-crds`	CRDs for the SchedMD Slinky Slurm operator (`slinky.slurm.net`)

Examples:

Note: The POST body must be a fully-hydrated RecipeResult — the server adopts the body as-is and does not hydrate registry defaults, so a hand-authored partial body (missing namespace, valuesFile, overrides, dependencyRefs) yields empty values and namespaces in the generated bundle. Obtain a complete body from aicr recipe ... --format json --output - (the CLI defaults to YAML, but POST /v1/bundle JSON-decodes its body) or GET /v1/recipe and pass it unchanged. The inline bodies below are elided for brevity (only a few component fields shown) — use a generated RecipeResult, not these literals.

The bundlers query parameter is not currently honored — all bundlers run regardless (#1531). There is no supported way to bundle a subset via the API today: hand-trimming componentRefs is unsafe (it silently drops required dependencies and breaks deployers like Helmfile on dangling dependencyRefs). Bundle the full hydrated result.

# Basic: pipe recipe to bundle
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" | \
  curl -X POST "http://localhost:8080/v1/bundle" \
    -H "Content-Type: application/json" -d @- -o bundles.zip

# Advanced: with value overrides and Argo CD deployer
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" | \
  curl -X POST "http://localhost:8080/v1/bundle?deployer=argocd&repo=https://github.com/my-org/my-gitops-repo.git&set=gpuoperator:gds.enabled=true" \
    -H "Content-Type: application/json" -d @- -o bundles.zip

# With node scheduling for system and GPU nodes
# (recipe.json must be a fully-hydrated RecipeResult, e.g. from GET /v1/recipe)
curl -X POST "http://localhost:8080/v1/bundle?system-node-selector=nodeGroup=system&system-node-toleration=dedicated=system:NoSchedule&accelerated-node-selector=nvidia.com/gpu.present=true&accelerated-node-toleration=nvidia.com/gpu=present:NoSchedule" \
  -H "Content-Type: application/json" \
  -d @recipe.json \
  -o bundles.zip

# Generate bundles from a saved (fully-hydrated) recipe
curl -X POST "http://localhost:8080/v1/bundle" \
  -H "Content-Type: application/json" \
  -d @recipe.json \
  -o bundles.zip

# Elided literal body (NOT complete — use a generated RecipeResult instead)
curl -X POST "http://localhost:8080/v1/bundle" \
  -H "Content-Type: application/json" \
  -d '{
    "apiVersion": "aicr.run/v1alpha2",
    "kind": "RecipeResult",
    "componentRefs": [
      {"name": "gpu-operator", "type": "Helm", "chart": "gpu-operator", "source": "https://helm.ngc.nvidia.com/nvidia", "version": "v26.3.2", "namespace": "gpu-operator", "valuesFile": "components/gpu-operator/values.yaml"},
      {"name": "network-operator", "type": "Helm", "chart": "network-operator", "source": "https://helm.ngc.nvidia.com/nvidia", "version": "26.1.1", "namespace": "nvidia-network-operator", "valuesFile": "components/network-operator/values.yaml"}
    ],
    "deploymentOrder": ["gpu-operator", "network-operator"]
  }' \
  -o bundles.zip

Response Headers:

Header	Description	Example
`Content-Type`	Always `application/zip`	`application/zip`
`Content-Disposition`	Download filename	`attachment; filename="bundles.zip"`
`X-Bundle-Files`	Total files in archive	`10`
`X-Bundle-Size`	Uncompressed size (bytes)	`45678`
`X-Bundle-Duration`	Generation time	`1.234s`

Bundle Structure

bundles.zip
├── deploy.sh                    # root automation script (executable)
├── README.md                    # root deployment guide
├── checksums.txt                # SHA256 checksums (always set for /v1/bundle)
├── recipe.yaml                  # canonical post-resolution recipe (helm deployer)
├── 001-<component>/             # per-component folder (NNN-prefixed)
│   ├── install.sh               # component install script
│   ├── values.yaml              # static Helm values
│   ├── cluster-values.yaml      # per-cluster dynamic values
│   └── upstream.env             # CHART/REPO/VERSION (upstream-helm only)
└── 002-<component>/
    ├── install.sh
    ├── values.yaml
    └── cluster-values.yaml

Checksums are root-level only; component folders carry install.sh at their root (no scripts/ subdirectory), and no uninstall.sh/undeploy.sh is generated.

GET /health

Service health check (liveness probe).

curl "http://localhost:8080/health"

Response:

{
  "status": "healthy",
  "timestamp": "2026-01-11T10:30:00Z"
}

GET /ready

Service readiness check (readiness probe).

curl "http://localhost:8080/ready"

Response:

{
  "status": "ready",
  "timestamp": "2026-01-11T10:30:00Z"
}

GET /metrics

Prometheus metrics endpoint.

curl "http://localhost:8080/metrics"

Key Metrics:

Metric	Type	Description
`aicr_http_requests_total`	counter	Total HTTP requests by method, path, status
`aicr_http_request_duration_seconds`	histogram	Request latency distribution
`aicr_http_requests_in_flight`	gauge	Current concurrent requests
`aicr_rate_limit_rejects_total`	counter	Rate limit rejections

Complete Workflow Example

Fetch a recipe and generate bundles in one workflow:

#!/bin/bash

# Step 1: Get recipe for H100 on EKS for training
echo "Fetching recipe..."
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks&intent=training" \
  -o recipe.json

# Display recipe summary
echo "Recipe components:"
jq -r '.componentRefs[] | "  - \(.name): \(.version)"' recipe.json

# Step 2: Generate bundles from recipe (pipe directly)
# recipe.json is the fully-hydrated RecipeResult fetched in Step 1.
echo "Generating bundles..."
curl -s -X POST "http://localhost:8080/v1/bundle" \
  -H "Content-Type: application/json" \
  -d @recipe.json \
  -o bundles.zip

# Alternative: one-liner without intermediate file
# curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" | \
#   curl -X POST "http://localhost:8080/v1/bundle" \
#     -H "Content-Type: application/json" -d @- -o bundles.zip

# Step 3: Extract and verify
echo "Extracting bundles..."
unzip -q bundles.zip -d ./deployment

# Verify checksums (checksums.txt is at the bundle root, not per-component)
echo "Verifying checksums..."
cd deployment
sha256sum -c checksums.txt

# Step 4: Deploy (example)
echo "Bundle ready for deployment:"
ls -la

Error Handling

Error Response Format

{
  "code": "ERROR_CODE",
  "message": "Human-readable error description",
  "details": { ... },
  "requestId": "550e8400-e29b-41d4-a716-446655440000",
  "timestamp": "2026-01-11T10:30:00Z",
  "retryable": true
}

Error Codes

Code	HTTP Status	Description	Retryable
`INVALID_REQUEST`	400	Invalid query parameters, request body, or disallowed criteria value	No
`UNAUTHORIZED`	401	Authentication or authorization failure	No
`NOT_FOUND`	404	Selector path not found in the resolved configuration	No
`METHOD_NOT_ALLOWED`	405	Wrong HTTP method	No
`CONFLICT`	409	Resource state conflict (e.g., already exists or version mismatch)	No
`RATE_LIMIT_EXCEEDED`	429	Too many requests	Yes
`INTERNAL`	500	Server error	Yes
`SERVICE_UNAVAILABLE`	503	Server temporarily unavailable	Yes
`TIMEOUT`	504	Operation exceeded its time limit	Yes

INVALID_REQUEST is not always 400: POST /v1/query and POST /v1/recipe return it with HTTP 413 Request Entity Too Large when the request body exceeds the server's body-size limit (MaxRecipePOSTBytes).

Handling Rate Limits

# Check rate limit headers
curl -I "http://localhost:8080/v1/recipe?accelerator=h100"

# Response headers:
# X-RateLimit-Limit: 100
# X-RateLimit-Remaining: 95
# X-RateLimit-Reset: 1736589000

When rate limited (HTTP 429), use the Retry-After header:

# Retry with backoff
response=$(curl -s -w "%{http_code}" "http://localhost:8080/v1/recipe?accelerator=h100")
if [ "${response: -3}" = "429" ]; then
  retry_after=$(curl -sI "http://localhost:8080/v1/recipe" | grep -i "Retry-After" | awk '{print $2}')
  echo "Rate limited. Retrying after ${retry_after}s..."
  sleep "$retry_after"
fi

Rate Limiting

Limit: 100 requests per second (a single process-global token bucket shared across all clients, not per-IP)
Burst: 200 requests
Headers: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset
429 Response: Includes Retry-After header

Criteria Allowlists

The API server can be configured to restrict which criteria values are allowed. This enables operators to limit the API to specific accelerators, services, intents, or OS types.

Configuration

Allowlists are configured via environment variables when starting the server:

Environment Variable	Description	Example
`AICR_ALLOWED_ACCELERATORS`	Comma-separated list of allowed GPU types	`h100,l40`
`AICR_ALLOWED_SERVICES`	Comma-separated list of allowed K8s services	`eks,gke`
`AICR_ALLOWED_INTENTS`	Comma-separated list of allowed workload intents	`training`
`AICR_ALLOWED_OS`	Comma-separated list of allowed OS types	`ubuntu,rhel`

Behavior:

If an environment variable is not set, all values for that criteria are allowed
If an environment variable is set, only the specified values are permitted
The any value is always allowed regardless of allowlist configuration
Allowlists apply to both /v1/recipe and /v1/bundle endpoints

Example Configuration

# Start server allowing only H100 and L40 GPUs on EKS
docker run -p 8080:8080 \
  -e AICR_ALLOWED_ACCELERATORS=h100,l40 \
  -e AICR_ALLOWED_SERVICES=eks \
  ghcr.io/nvidia/aicrd:latest

Error Response

When a disallowed criteria value is requested:

curl "http://localhost:8080/v1/recipe?accelerator=gb200&service=eks"

Response (HTTP 400):

{
  "code": "INVALID_REQUEST",
  "message": "accelerator type not allowed",
  "details": {
    "requested": "gb200",
    "allowed": ["h100", "l40"]
  },
  "requestId": "550e8400-e29b-41d4-a716-446655440000",
  "timestamp": "2026-01-27T10:30:00Z",
  "retryable": false
}

CLI Behavior

The CLI (aicr) is not affected by allowlists. Allowlists only apply to the API server, allowing operators to restrict API access while maintaining full CLI functionality for administrative tasks.

Programming Language Examples

Python

import requests
import zipfile
import io

BASE_URL = "http://localhost:8080"

# Get recipe
params = {
    "accelerator": "h100",
    "service": "eks",
    "intent": "training",
    "os": "ubuntu"
}

resp = requests.get(f"{BASE_URL}/v1/recipe", params=params)
resp.raise_for_status()
recipe = resp.json()

print(f"Recipe has {len(recipe['componentRefs'])} components")

# Generate bundles — the (fully-hydrated) recipe is the request body.
resp = requests.post(
    f"{BASE_URL}/v1/bundle",
    json=recipe,
)
resp.raise_for_status()

# Extract zip
with zipfile.ZipFile(io.BytesIO(resp.content)) as zf:
    zf.extractall("./deployment")
    print(f"Extracted {len(zf.namelist())} files")

Go

package main

import (
    "encoding/json"
    "fmt"
    "io"
    "net/http"
    "net/url"
    "os"
)

func main() {
    baseURL := "http://localhost:8080"

    // Get recipe
    params := url.Values{}
    params.Add("accelerator", "h100")
    params.Add("service", "eks")
    
    resp, err := http.Get(baseURL + "/v1/recipe?" + params.Encode())
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()

    var recipe map[string]interface{}
    json.NewDecoder(resp.Body).Decode(&recipe)
    
    fmt.Printf("Got recipe with %d components\n", 
        len(recipe["componentRefs"].([]interface{})))
}

JavaScript/Node.js

const BASE_URL = "http://localhost:8080";

async function main() {
    // Get recipe
    const params = new URLSearchParams({
        accelerator: "h100",
        service: "eks",
        intent: "training"
    });
    
    const recipeResp = await fetch(`${BASE_URL}/v1/recipe?${params}`);
    const recipe = await recipeResp.json();
    
    console.log(`Recipe has ${recipe.componentRefs.length} components`);
    
    // Generate bundles — the (fully-hydrated) recipe is the request body.
    const bundleResp = await fetch(`${BASE_URL}/v1/bundle`, {
        method: "POST",
        headers: { "Content-Type": "application/json" },
        body: JSON.stringify(recipe),
    });
    
    // Save zip
    const buffer = await bundleResp.arrayBuffer();
    require("fs").writeFileSync("bundles.zip", Buffer.from(buffer));
    console.log("Bundles saved to bundles.zip");
}

main();

Shell Script (Batch Processing)

#!/bin/bash
# Generate recipes for multiple environments

environments=(
  "os=ubuntu&accelerator=h100&service=eks"
  "os=ubuntu&accelerator=gb200&service=gke"
  "os=rhel&accelerator=a100&service=aks"
)

for env in "${environments[@]}"; do
  echo "Fetching recipe for: $env"

  curl -s "http://localhost:8080/v1/recipe?${env}" \
    | jq -r '.componentRefs[] | "\(.name): \(.version)"'

  echo ""
done

OpenAPI Specification

The full OpenAPI 3.1 specification is available at: api/aicr/v1/server.yaml

Generate client SDKs:

# Download spec
curl https://raw.githubusercontent.com/NVIDIA/aicr/main/api/aicr/v1/server.yaml \
  -o openapi.yaml

# Generate Python client
openapi-generator-cli generate -i openapi.yaml -g python -o ./python-client

# Generate Go client
openapi-generator-cli generate -i openapi.yaml -g go -o ./go-client

# Generate TypeScript client
openapi-generator-cli generate -i openapi.yaml -g typescript-fetch -o ./ts-client

Troubleshooting

Common Issues

"Invalid accelerator type" error:

# Use valid values: h100, h200, gb200, b200, a100, l40, l40s, rtx-pro-6000, any
curl "http://localhost:8080/v1/recipe?accelerator=h100"

"Recipe is required" error:

# The body IS the RecipeResult itself — not wrapped in a {"recipe": ...} field.
# Pass a fully-hydrated RecipeResult (e.g. from GET /v1/recipe) directly:
curl -s "http://localhost:8080/v1/recipe?accelerator=h100&service=eks" | \
  curl -X POST "http://localhost:8080/v1/bundle" \
    -H "Content-Type: application/json" -d @- -o bundles.zip

Empty zip file:

# Check recipe has componentRefs
curl -s "http://localhost:8080/v1/recipe?accelerator=h100" | jq '.componentRefs'

Connection refused (local):

# Start local server first
make server

Uh oh!

FilesExpand file tree

api-reference.md

Latest commit

History

api-reference.md

File metadata and controls

API Reference

Overview

API vs CLI

Base URL

Quick Start

Get a Recipe

Generate Bundles

Endpoints

GET /

GET /v1/recipe

POST /v1/recipe

GET /v1/query

POST /v1/query

POST /v1/bundle

Components

Bundle Structure

GET /health

GET /ready

GET /metrics

Complete Workflow Example

Error Handling

Error Response Format

Error Codes

Handling Rate Limits

Rate Limiting

Criteria Allowlists

Configuration

Example Configuration

Error Response

CLI Behavior

Programming Language Examples

Python

Go

JavaScript/Node.js

Shell Script (Batch Processing)

OpenAPI Specification

Troubleshooting

Common Issues

See Also