NVIDIA NIM

The NVIDIA provider connects promptfoo to NVIDIA's hosted inference API at https://integrate.api.nvidia.com/v1. The endpoint is OpenAI-compatible, so any model NVIDIA exposes through it can be used the same way you'd use OpenAI Chat Completions.

Setup

Set your API key as an environment variable:

export NVIDIA_API_KEY=your_api_key_here

Or add it to your .env file:

NVIDIA_API_KEY=your_api_key_here

Getting an API key

1. Sign in at build.nvidia.com (free developer account).
2. Open any model card (for example, Llama 3.3 70B Instruct).
3. Click Get API Key. The key starts with nvapi-.

NVIDIA's developer program currently grants a recurring allowance of free request credits per account, which is usually enough for prompt iteration and small evals before any paid usage is needed. Current credit limits and pricing are documented at build.nvidia.com; check there for what is in effect today rather than assuming the value listed in any blog post.

Configuration

Use the nvidia: prefix followed by the full model id as listed on the model card:

providers:
  - nvidia:meta/llama-3.3-70b-instruct
  - nvidia:qwen/qwen2.5-coder-32b-instruct
  - nvidia:nvidia/nemotron-3-super-120b-a12b

Standard OpenAI-compatible parameters are passed through:

providers:
  - id: nvidia:meta/llama-3.3-70b-instruct
    config:
      temperature: 0.7
      max_tokens: 1024
      top_p: 0.9
      stop: ['END']

To override the base URL (for example, when routing through a corporate proxy or to a self-hosted NIM):

providers:
  - id: nvidia:meta/llama-3.3-70b-instruct
    config:
      apiBaseUrl: https://your-proxy.example.com/nvidia/v1
      apiKeyEnvar: CUSTOM_NVIDIA_KEY

A few common models

The full list is on build.nvidia.com. Some commonly used ids:

Model	Provider format
Llama 3.3 70B Instruct	nvidia:meta/llama-3.3-70b-instruct
Llama 3.1 405B Instruct	nvidia:meta/llama-3.1-405b-instruct
Llama 3.2 90B Vision Instruct	nvidia:meta/llama-3.2-90b-vision-instruct
Nemotron 3 Super 120B A12B	nvidia:nvidia/nemotron-3-super-120b-a12b
Mistral Large 2 Instruct	nvidia:mistralai/mistral-large-2-instruct
Mixtral 8x22B Instruct	nvidia:mistralai/mixtral-8x22b-instruct-v0.1
Qwen 2.5 Coder 32B Instruct	nvidia:qwen/qwen2.5-coder-32b-instruct
DeepSeek R1	nvidia:deepseek-ai/deepseek-r1

Example

A minimal eval comparing two NIM-hosted models. Uses deterministic assertions so the example runs end-to-end with only NVIDIA_API_KEY configured — llm-rubric would otherwise fall back to promptfoo's default OpenAI grader and require a separate OPENAI_API_KEY.

promptfooconfig.yaml

providers:
  - id: nvidia:meta/llama-3.3-70b-instruct
    config:
      temperature: 0.2
      max_tokens: 256
  - id: nvidia:nvidia/nemotron-3-super-120b-a12b
    config:
      temperature: 1
      top_p: 0.95
      max_tokens: 1024
      passthrough:
        chat_template_kwargs:
          enable_thinking: false

prompts:
  - 'Summarise the following in one sentence: {{passage}}'

tests:
  - vars:
      passage: 'Photosynthesis is the process by which plants convert light energy into chemical energy stored in glucose.'
    assert:
      - type: icontains
        value: plants
      - type: icontains-any
        value: [light, energy, glucose]

The Nemotron configuration follows its model-specific sampling guidance and disables reasoning for this short summarization task. Additional request fields such as chat_template_kwargs go under config.passthrough. If you enable reasoning, increase max_tokens to leave room for both reasoning and the final answer; the hosted example uses 16384.

These examples use a model in NVIDIA's hosted chat catalog. Self-hosted NIM deployments can use their own served model identifiers.

If you want a model-graded assertion, point llm-rubric at a NIM-hosted grader so the example stays self-contained:

defaultTest:
  options:
    provider: nvidia:meta/llama-3.3-70b-instruct

Notes

• Cost calculation is not built in for NVIDIA models. NIM bills against credits rather than per-token public price lists for many models, and the actual cost depends on your account tier. Set both inputCost and outputCost on the provider config if you want to record an estimate in eval output.
• Tool calling and JSON-mode responses follow the same configuration as the OpenAI provider because the API surface is OpenAI-compatible. Streaming responses are not implemented by this provider.
• This provider supports NIM chat-completion models. Retrieval, embedding, reranking, and other NIM APIs require a provider that targets their corresponding endpoint.