# NVIDIA Integration via LowCodeAPI
**Last Updated**: February 10, 2026
## Overview
NVIDIA NIM (NVIDIA Inference Microservices) provides access to top open-source AI models through a unified API. Compatible with OpenAI API specification.
**Categories:**
- {'id': 'inference-cloud', 'name': 'Inference Cloud'}
## Base Endpoint
https://api.lowcodeapi.com/nvidia
**Important**: Always include the provider name in the URL path after `api.lowcodeapi.com/`
## Authentication
**Type:** TOKEN
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/llm-apis
## URL Format (Important)
LowCodeAPI supports two URL formats. **Always try the New Format first**, then fall back to Old Format if needed.
### New Format (Priority)
- Path parameters stay in the URL path
- Do NOT include path parameters as query parameters
- Example: `https://api.lowcodeapi.com/{provider}/resource/{id}?api_token=XXX`
### Old Format (Fallback)
- Path parameters become query parameters
- Example: `https://api.lowcodeapi.com/{provider}/resource/id?id={id}&api_token=XXX`
### Decision Flow for AI Agents
1. Always use **New Format** first - keep path parameters in the URL path
2. If you get a 404 or error, try **Old Format** with sanitized path
3. Log which format worked for future requests to this provider
## API Categories
## Common Endpoints
### Create chat completion
**Method:** POST
**LowCodeAPI Path:** /v1/chat/completions
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/chat/completions?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/chat/completions?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| frequency_penalty | number | |
| logit_bias | object | |
| logprobs | boolean | |
| max_tokens | number | |
| messages | array | |
| model | string | |
| n | number | |
| presence_penalty | number | |
| response_format | object | |
| seed | number | |
| stop | array | |
| stream | boolean | |
| temperature | number | |
| top_logprobs | number | |
| top_p | number | |
| user | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/chat/completions?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/llm-apis
### List models
**Method:** GET
**LowCodeAPI Path:** /v1/models
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/models?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/models?api_token=YOUR_API_TOKEN
**Example Request (New Format):**
```bash
curl -X GET 'https://api.lowcodeapi.com/nvidia/v1/models?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/llm-apis
### Create embedding
**Method:** POST
**LowCodeAPI Path:** /v1/embeddings
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/embeddings?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/embeddings?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| dimensions | number | |
| encoding_format | string | |
| input | array | |
| input_type | string | |
| model | string | |
| truncate | string | |
| user | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/embeddings?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/retrieval-apis
### Create ranking
**Method:** POST
**LowCodeAPI Path:** /v1/ranking
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/ranking?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/ranking?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| model | string | |
| passages | array | |
| query | object | |
| truncate | string | |
| user | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/ranking?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.nvidia.com/nim/nemo-retriever/text-reranking/latest/reference.html
### Run DINOv2 inference
**Method:** POST
**LowCodeAPI Path:** /v1/cv/nvidia/nv-dinov2
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-dinov2?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-dinov2?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| embedding_type | string | |
| image | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-dinov2?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/nvidia-nv-dinov2
### Run Grounding DINO inference
**Method:** POST
**LowCodeAPI Path:** /v1/cv/nvidia/nv-grounding-dino
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-grounding-dino?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-grounding-dino?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| box_threshold | number | |
| image | string | |
| prompt | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/nv-grounding-dino?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/nvidia-nv-grounding-dino
### Run Ocrdnet inference
**Method:** POST
**LowCodeAPI Path:** /v1/cv/nvidia/ocdrnet
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/ocdrnet?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/ocdrnet?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| image | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/ocdrnet?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/nvidia-ocdrnet
### Run retail object detection
**Method:** POST
**LowCodeAPI Path:** /v1/cv/nvidia/retail-object-detection
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/retail-object-detection?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/retail-object-detection?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| image | string | |
| num_detections | number | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/retail-object-detection?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/nvidia-retail-object-detection
### Run Visual ChangeNet inference
**Method:** POST
**LowCodeAPI Path:** /v1/cv/nvidia/visual-changenet
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/visual-changenet?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/visual-changenet?api_token=YOUR_API_TOKEN
**Request Body:**
| Field | Type | Description |
|-------|------|-------------|
| image_a | string | |
| image_b | string | |
**Example Request (New Format):**
```bash
curl -X POST 'https://api.lowcodeapi.com/nvidia/v1/cv/nvidia/visual-changenet?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/nim/reference/nvidia-visual-changenet
### Get inference status
**Method:** GET
**LowCodeAPI Path:** /v1/v2/nvcf/pexec/status/{requestId}
**New Format URL:**
https://api.lowcodeapi.com/nvidia/v1/v2/nvcf/pexec/status/{requestId}?api_token=YOUR_API_TOKEN
**Old Format URL:**
https://api.lowcodeapi.com/nvidia/v1/v2/nvcf/pexec/status/requestid?requestId={requestId}&api_token=YOUR_API_TOKEN
**Path Parameters:**
| Parameter | Type | Description |
|-----------|------|-------------|
| requestId | string | |
**Example Request (New Format):**
```bash
curl -X GET 'https://api.lowcodeapi.com/nvidia/v1/v2/nvcf/pexec/status/{requestId}?api_token=YOUR_API_TOKEN'
```
**Official Documentation:** https://docs.api.nvidia.com/cloud-functions/reference/statuspolling
## Usage Examples
### Example 1: Basic Chat Completion
Creating a simple text completion or chat message:
```bash
# Create a chat completion - no path parameters needed
curl -X POST "https://api.lowcodeapi.com/nvidia/v1/chat/completions?api_token=YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "your-model-name",
"messages": [
{"role": "user", "content": "Hello, how can you help me?"}
]
}'
# Response includes generated content
```
### Example 2: Text Generation with Path Parameters
Generating text with specific model settings:
```bash
# Generate content using a specific model
curl -X POST "https://api.lowcodeapi.com/nvidia/v1/models/generate?api_token=YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Write a short poem about technology",
"max_tokens": 100
}'
# Or if the provider uses model in the path:
curl -X POST "https://api.lowcodeapi.com/nvidia/v1/models/{MODEL_ID}:generateContent?api_token=YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"contents": [{"parts": [{"text": "Write a short story"}]}]
}'
```
### Example 3: List Available Models
```bash
# Get list of available models
curl -X GET "https://api.lowcodeapi.com/nvidia/v1/models?api_token=YOUR_API_TOKEN"
```
## Error Handling
LowCodeAPI returns standard HTTP status codes. Common errors:
| Status Code | Description |
|-------------|-------------|
| 200 | Success - Request completed successfully |
| 400 | Bad Request - Invalid parameters or request body |
| 401 | Unauthorized - Invalid or missing API token |
| 403 | Forbidden - Insufficient permissions |
| 404 | Not Found - Endpoint or resource doesn't exist |
| 429 | Too Many Requests - Rate limit exceeded |
| 500 | Server Error - Provider API error |
All error responses include error details:
```json
{
"data": {
"error": {
"message": "Error description",
"code": "ERROR_CODE"
}
}
}
```
## Complete Endpoint Reference
| Endpoint | Method | Category |
|----------|--------|----------|
| Create chat completion | POST | Chat |
| List models | GET | Models |
| Create embedding | POST | Embeddings |
| Create ranking | POST | Reranking |
| Run DINOv2 inference | POST | Visual Models |
| Run Grounding DINO inference | POST | Visual Models |
| Run Ocrdnet inference | POST | Visual Models |
| Run retail object detection | POST | Visual Models |
| Run Visual ChangeNet inference | POST | Visual Models |
| Get inference status | GET | Visual Models |
| Run NeVA 22B inference | POST | Multimodal |
| Run VILA inference | POST | Multimodal |
| Run Llama 3.1 Nemotron Nano VL 8B inference | POST | Multimodal |
| Run Parabricks Universal Variant Calling | POST | Healthcare |
| Run Parabricks fq2bam sequence alignment | POST | Healthcare |
| Generate molecules with GenMol | POST | Healthcare |
| Generate synthetic CT images with MAISI | POST | Healthcare |
| Generate molecules with MolMIM | POST | Healthcare |
| Run VISTA-3D medical imaging segmentation | POST | Healthcare |
| Run CorrDiff weather downscaling | POST | Climate Simulation |
| Run FourCastNet global weather forecasting | POST | Climate Simulation |
| Submit cuOpt routing problem | POST | Route Optimization |
## API Definition Endpoints
You can fetch the complete API specification for this provider:
**New Format (OpenAPI spec):**
```bash
curl 'https://backend.lowcodeapi.com/nvidia/openapi'
```
**Old Format (API definition):**
```bash
curl 'https://backend.lowcodeapi.com/nvidia/definition'
```
## Response Format
All responses are wrapped in a `data` key:
```json
{
"data": {
// Actual response from provider (object or array)
}
}
```