> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo-helix/_mcp/server.

# Inference Gateway


## API Docs

- Inference Gateway [Model Inference Proxy GET](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/gateway-proxy-get.md)
- Inference Gateway [Model Inference Proxy POST](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/gateway-proxy-post.md)
- Inference Gateway [Model Inference Proxy PUT](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/gateway-proxy-put.md)
- Inference Gateway [Model Inference Proxy DELETE](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/gateway-proxy-delete.md)
- Inference Gateway [Model Inference Proxy PATCH](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/gateway-proxy-patch.md)
- Inference Gateway [OpenAI List Models](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-list-models.md)
- Inference Gateway [OpenAI Get Model](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-get-model.md)
- Inference Gateway [OpenAI Inference Proxy GET](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-get.md)
- Inference Gateway [OpenAI Inference Proxy POST](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-post.md)
- Inference Gateway [OpenAI Inference Proxy PUT](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-put.md)
- Inference Gateway [OpenAI Inference Proxy DELETE](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-delete.md)
- Inference Gateway [OpenAI Inference Proxy PATCH](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openai-proxy-patch.md)
- Inference Gateway [Provider Inference Proxy GET](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-proxy-get.md)
- Inference Gateway [Provider Inference Proxy POST](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-proxy-post.md)
- Inference Gateway [Provider Inference Proxy PUT](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-proxy-put.md)
- Inference Gateway [Provider Inference Proxy DELETE](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-proxy-delete.md)
- Inference Gateway [Provider Inference Proxy PATCH](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-proxy-patch.md)
- Inference Gateway [Check Provider Readiness](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/provider-ready.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openapi.json)
- [OpenAPI YAML](https://docs.nvidia.com/nemo-helix/latest/documentation/reference/api-reference/inference-gateway/openapi.yaml)