What is the Provider Atlascloud prompt chain used for?

It's an example configuration for evaluating multiple model families hosted on Atlas Cloud through a single OpenAI-compatible API key, supporting prompt and model evaluation workflows with standard generation parameters and assertion-based testing.

How do I reference Atlas Cloud models in the provider configuration?

Models are referenced using the format `atlascloud: `, such as `atlascloud:deepseek-ai/DeepSeek-V3-0324` or `atlascloud:qwen/qwen3-32b`.

Can I route Atlas Cloud requests through a custom gateway or proxy?

Yes, you can set `apiBaseUrl` (e.g., `https://proxy.example.com/atlas/v1`) and `apiKeyEnvar` (e.g., `MY_ATLASCLOUD_TOKEN`) on the provider config to route requests through an alternate endpoint with different credentials.

Prompt Chain

Evaluate prompts across Atlas Cloud model families

Name: Provider Atlascloud
Availability: OnlineOnly
Author: Promptfoo

Promptfoo example evaluating prompts against Atlas Cloud's deepseek-v3 model, including routing through a custom gateway.

Copy chain

Works with atlascloudopenai

Promptfoo

Own this? Claim it

Spark score

out of 100

Updated 10 days ago

Source checked Sep 10, 2026

Version 0.123.0

Models

deepseek v3 qwen 2 5

Add to Favorites

Why it matters

Enable developers to systematically test and compare prompt performance across multiple LLM families hosted on Atlas Cloud using a unified OpenAI-compatible API, ensuring consistent quality before production deployment.

Outcomes

What it gets done

Configure multiple Atlas Cloud-hosted chat models for side-by-side evaluation

Run deterministic and rubric-based assertions against prompt outputs

Compare generation parameters across DeepSeek, Qwen, and other model families

Set up custom gateway endpoints with flexible API key management

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/pfoo-provider-atlascloud | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Steps

Steps in the chain

Create Atlas Cloud API key

Set environment variable

Initialize promptfoo with Atlas Cloud example

Navigate to project directory

Run evaluation

Overview

Provider Atlascloud

This promptfoo example configures Atlas Cloud's deepseek-v3 model as an evaluation provider, with deterministic assertions and an optional custom gateway routing setup. Use it as a starting template for evaluating prompts against Atlas Cloud-hosted models with promptfoo.

What it does

This promptfoo example configures Atlas Cloud as an LLM provider, running chat evaluations against Atlas Cloud's deepseek-v3 model with generation parameters and deterministic assertions on the responses.

When to use - and when NOT to

Use it as a starting template when you want to evaluate prompts against models hosted on Atlas Cloud through promptfoo, including via a custom gateway or proxy URL. It is specific to Atlas Cloud's provider syntax; swap the model ID to use a different model from Atlas Cloud's library, or use a different promptfoo example for other providers.

Inputs and outputs

Input is an ATLASCLOUD_API_KEY environment variable and the bundled promptfooconfig.yaml; running npx promptfoo eval -c promptfooconfig.yaml produces evaluation results scored against the config's assertions. The provider syntax atlascloud:deepseek-v3 selects the model, and an optional config.apiBaseUrl/apiKeyEnvar block routes requests through a custom gateway with a different API key variable.

Integrations

Atlas Cloud, via its chat API, and promptfoo's eval framework; the example doubles as a template for routing Atlas Cloud requests through a custom proxy.

Who it's for

Developers evaluating prompts or comparing outputs against Atlas Cloud-hosted models with promptfoo, or teams needing a working example for a gateway-fronted Atlas Cloud setup.

Source README

provider-atlascloud (Atlas Cloud Example)

This directory contains an example configuration for using Atlas Cloud with promptfoo.

The example uses the deepseek-v3 chat model ID from Atlas Cloud's first-model guide. Choose other models using the exact IDs and supported options in Atlas Cloud's model library.

Prerequisites

Create an Atlas Cloud API key from the Atlas Cloud docs.

Set the environment variable:

export ATLASCLOUD_API_KEY=your_api_key_here

Quick Start

npx promptfoo@latest init --example provider-atlascloud
cd provider-atlascloud
npx promptfoo eval -c promptfooconfig.yaml

Example Config

The included promptfooconfig.yaml demonstrates:

Atlas Cloud chat requests with generation parameters
Deterministic assertions on the responses

Provider Syntax

providers:
  - id: atlascloud:deepseek-v3

Custom Gateway Example

providers:
  - id: atlascloud:deepseek-v3
    config:
      apiBaseUrl: https://proxy.example.com/atlas/v1
      apiKeyEnvar: MY_ATLASCLOUD_TOKEN