> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Promptfoo

> Run Promptfoo evals against TokenLab models

## Overview

Promptfoo can evaluate TokenLab through its OpenAI-compatible chat and Responses providers.

<Note>
  **Type**: Evaluation Framework

  **Primary Paths**: OpenAI-compatible chat completions and Responses

  **Support Confidence**: Supported path
</Note>

## Environment

```bash theme={null}
export TOKENLAB_API_KEY="sk-your-tokenlab-key"
```

## Example Config

```yaml theme={null}
description: TokenLab provider example

prompts:
  - 'Answer in one concise paragraph: {{question}}'

providers:
  - id: openai:chat:gpt-5.4-mini
    label: tokenlab-chat-gpt-5.4-mini
    config:
      apiBaseUrl: https://api.tokenlab.sh/v1
      apiKey: '{{env.TOKENLAB_API_KEY}}'
  - id: openai:responses:gpt-5.5
    label: tokenlab-responses-gpt-5.5
    config:
      apiBaseUrl: https://api.tokenlab.sh/v1
      apiKey: '{{env.TOKENLAB_API_KEY}}'

tests:
  - vars:
      question: What are two practical ways to evaluate an LLM gateway?
    assert:
      - type: contains-any
        value:
          - latency
          - reliability
          - cost
          - quality
```

## Run

```bash theme={null}
promptfoo eval
```

Use chat providers for broad compatibility. Use Responses providers when the eval specifically depends on Responses behavior.