What models does Nscale support through this promptfoo integration?

Nscale supports a broad catalog including text models like OpenAI's gpt-oss-120b/20b, Qwen 3 variants, Meta's Llama 3.3-70b and Llama 4-scout, DeepSeek R1 distilled models, Mistral's devstral-small and mixtral-8x22b, an embedding model (Qwen3-Embedding-8B), and text-to-image models (FLUX.1-schnell, Stable Diffusion XL, and SDXL-Lightning).

How do I set up and run the Nscale provider example?

Sign up at Nscale, generate a service token from account settings, set it as the `NSCALE_SERVICE_TOKEN` environment variable or in a `.env` file, then scaffold with `npx promptfoo@latest init --example provider-nscale`. Run text evaluation with `promptfoo eval` and image evaluation with `promptfoo eval -c image-promptfooconfig.yaml`.

What are the pricing and performance benefits of Nscale?

Nscale offers highly competitive pricing starting from $0.01 input / $0.03 output per 1M tokens for text generation and $0.0008 per megapixel for image generation, with zero rate limits, no cold starts, and claimed savings of up to 80% versus other providers.

When should I use this Nscale example?

Use this example when you want to evaluate Nscale-hosted text or text-to-image models for quality and reasoning before adopting Nscale as your inference provider, particularly if you have bursty or unpredictable traffic where cost and latency consistency matter.

Prompt Chain

Evaluate Nscale Inference API Models

Name: Provider Nscale
Availability: OnlineOnly
Author: Promptfoo

Promptfoo example evaluating Nscale's low-cost text and image models, with zero rate limits and no cold starts.

Copy chain

Works with nscale

Promptfoo

Own this? Claim it

Spark score

out of 100

Updated today

Source checked Sep 20, 2026

Version 0.123.1

Models

qwen 2 5llama 3

Add to Favorites

Why it matters

Leverage promptfoo to benchmark and evaluate the performance of Nscale Serverless Inference API models. Ensure cost-effective and high-performance AI inference.

Outcomes

What it gets done

Integrate with Nscale Serverless Inference API

Evaluate model performance and cost-effectiveness

Automate AI inference testing

Identify optimal AI models for specific tasks

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-nscale | 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

Navigate to account settings

Go to Service Tokens section

Generate and set service token

Overview

Provider Nscale

A promptfoo example evaluating Nscale's Serverless Inference models - text reasoning/creativity comparison and image-generation comparison - across its OpenAI, Qwen, Llama, DeepSeek, and Mistral model catalog. Use to compare Nscale's model quality and pricing before switching providers. Not usable without an Nscale account and service token.

What it does

This promptfoo example evaluates models on Nscale's Serverless Inference API, positioned as cost-effective, high-performance inference with zero rate limits and no cold starts. It ships two configs: promptfooconfig.yaml compares two Nscale text models on reasoning and creative-writing tasks, reporting accuracy, creativity, and response-quality metrics; image-promptfooconfig.yaml compares Nscale's image-generation models across landscapes, futuristic scenes, portraits, and abstract art prompts.

npx promptfoo@latest init --example provider-nscale
cd provider-nscale

Nscale's catalog spans OpenAI's open-weight gpt-oss-120b and gpt-oss-20b, several Qwen 3 sizes (Qwen3-235B-A22B, Qwen3-235B-A22B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-14B, Qwen3-32B) plus Qwen 2.5 Coder variants and QwQ-32B, Meta's Llama-3.3-70B-Instruct and Llama-3.1-8B-Instruct alongside the multimodal Llama-4-Scout-17B-16E-Instruct (image-text-to-text), DeepSeek R1 Distill models on both Llama and Qwen bases, and Mistral's Devstral-Small-2505 and Mixtral-8x22B-Instruct-v0.1. It also offers a Qwen3-Embedding-8B embedding model and three text-to-image models: FLUX.1-schnell, stable-diffusion-xl-base-1.0, and SDXL-Lightning.

When to use - and when NOT to

Use it to compare Nscale's text or image model quality and cost before committing - Nscale advertises up to 80% cost savings versus other providers, with text pricing starting around $0.01 input / $0.03 output per 1M tokens and image pricing from $0.0008 per megapixel, plus zero rate limits and no cold starts on requests. Rates are subject to change, so check Nscale's own pricing page for current numbers rather than treating these as fixed. It is not useful without an Nscale account, since the example requires an NSCALE_SERVICE_TOKEN.

Inputs and outputs

Authentication takes four steps: sign up for an account at Nscale, navigate to account settings, open the "Service Tokens" section, and generate a token - set as an NSCALE_SERVICE_TOKEN environment variable or added to .env. Run promptfoo eval for the text-model comparison, which evaluates two popular Nscale models on their ability to solve reasoning problems and generate creative content, or promptfoo eval -c image-promptfooconfig.yaml for the image-model comparison. Output for the text run is a comparison of how each model handles different task types, with metrics on accuracy, creativity, and response quality; output for the image run is generated images from each model side by side across the tested prompt categories.

Integrations

Calls Nscale's Serverless Inference API directly through promptfoo's Nscale provider - no other provider is required to run either example.

Who it's for

Teams evaluating a lower-cost inference provider for text or image generation who want to see Nscale's actual model outputs and pricing before switching from a more expensive provider.

Source README

provider-nscale (Nscale Example (Cost-Effective AI Inference))

This example demonstrates how to use the Nscale provider with promptfoo to evaluate Nscale Serverless Inference API models, which offer cost-effective, high-performance AI inference with zero rate limits.

You can run this example with:

npx promptfoo@latest init --example provider-nscale
cd provider-nscale

Prerequisites

Authentication Setup

Sign up for an account at Nscale
Navigate to your account settings
Go to "Service Tokens" section
Generate a service token and set it as an environment variable:

export NSCALE_SERVICE_TOKEN="your-service-token-here"

Alternatively, you can add it to your .env file:

NSCALE_SERVICE_TOKEN=your-service-token-here

Example Configuration

This repository contains an example configuration demonstrating Nscale's capabilities:

Basic Model Evaluation (`promptfooconfig.yaml`)

This configuration evaluates two popular Nscale models on their ability to solve reasoning problems and generate creative content.

promptfoo eval

Expected output: You'll see a comparison of how each model handles different types of tasks, with metrics on accuracy, creativity, and response quality.

Image Generation Evaluation (`image-promptfooconfig.yaml`)

This configuration compares Nscale's image generation models on various prompts to evaluate their quality and consistency.

promptfoo eval -c image-promptfooconfig.yaml

Expected output: You'll see generated images from different models (Flux.1 Schnell, SDXL Lightning, Stable Diffusion XL) for comparison across various image types including landscapes, futuristic scenes, portraits, and abstract art.

Model Capabilities

Nscale supports many popular models with competitive pricing:

Text Generation Models:

openai/gpt-oss-120b - OpenAI's 120B open-weight model
openai/gpt-oss-20b - OpenAI's 20B model
Qwen/Qwen3-235B-A22B - Qwen 3 235B model
Qwen/Qwen3-235B-A22B-Instruct-2507 - Qwen 3 235B Instruct 2507
Qwen/Qwen3-4B-Thinking-2507 - Qwen 3 4B Thinking 2507
Qwen/Qwen3-8B - Qwen 3 8B model
Qwen/Qwen3-14B - Qwen 3 14B model
Qwen/Qwen3-32B - Qwen 3 32B model
Qwen/Qwen2.5-Coder-3B-Instruct - Qwen 2.5 Coder 3B Instruct
Qwen/Qwen2.5-Coder-7B-Instruct - Qwen 2.5 Coder 7B Instruct
Qwen/Qwen2.5-Coder-32B-Instruct - Qwen 2.5 Coder 32B Instruct
Qwen/QwQ-32B - Qwen QwQ 32B model
meta-llama/Llama-3.3-70B-Instruct - Meta's Llama 3.3 70B model
meta-llama/Llama-3.1-8B-Instruct - Meta's Llama 3.1 8B model
meta-llama/Llama-4-Scout-17B-16E-Instruct - Llama 4 Scout 17B model (Image-Text-to-Text)
deepseek-ai/DeepSeek-R1-Distill-Llama-70B - DeepSeek R1 Distill Llama 70B
deepseek-ai/DeepSeek-R1-Distill-Llama-8B - DeepSeek R1 Distill Llama 8B
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B - DeepSeek R1 Distill Qwen 1.5B
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B - DeepSeek R1 Distill Qwen 7B
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B - DeepSeek R1 Distill Qwen 14B
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B - DeepSeek R1 Distill Qwen 32B
mistralai/Devstral-Small-2505 - Mistral's Devstral Small model
mistralai/Mixtral-8x22B-Instruct-v0.1 - Mixtral 8x22B Instruct

Embedding Models:

Qwen/Qwen3-Embedding-8B - Qwen 3 8B Embedding model

Text-to-Image Models:

black-forest-labs/FLUX.1-schnell - Flux.1 Schnell image generation model
stabilityai/stable-diffusion-xl-base-1.0 - Stable Diffusion XL 1.0
ByteDance/SDXL-Lightning - SDXL Lightning

Pricing & Usage

Nscale offers highly competitive pricing with up to 80% cost savings compared to other providers:

Text Generation: Starting from $0.01 input / $0.03 output per 1M tokens
Image Generation: Starting from $0.0008 per mega-pixel
Zero rate limits and no cold starts

Check the official pricing page for the most current rates.

Learn More

FAQ

Common questions

Discussion