---
title: Refuel LLM V2 Small — Data Tasks LLM | ModelsLab
description: Run Refuel LLM V2 Small for classification, extraction, and data cleaning. Generate structured outputs fast via API. Try it now.
url: https://modelslab.com/refuel-llm-v2-small
canonical: https://modelslab.com/refuel-llm-v2-small
type: website
component: Seo/ModelPage
generated_at: 2026-04-15T02:01:41.071914Z
---

Available now on ModelsLab · Language Model

Refuel LLM V2 Small
Data Tasks Mastered
---

[Try Refuel LLM V2 Small](/models/refuel_ai/togethercomputer-Refuel-Llm-V2-Small) [API Documentation](https://docs.modelslab.com)

Extract. Classify. Clean.
---

8B Parameters

### Llama3 Base Optimized

Refuel LLM V2 Small uses Llama3-8B base for data labeling, enrichment, and cleaning tasks.

79.67% Accuracy

### Beats GPT-3.5 Turbo

Outperforms Claude-3-Sonnet and GPT-3.5-Turbo on 2750+ data structuring benchmarks.

8K Context

### Handles Long Inputs

Supports 8K max input length for classification, extraction, and entity resolution.

Examples

See what Refuel LLM V2 Small can create
---

Copy any prompt below and try it yourself in the [playground](/models/refuel_ai/togethercomputer-Refuel-Llm-V2-Small).

Invoice Extraction

“Extract structured fields from this invoice text: date, amount, vendor, items list. Input: Invoice dated 2023-10-01 from Acme Corp, total $1500, items: widgets x10 $100 each, gadgets x5 $200 each. Output as JSON.”

Sentiment Classify

“Classify sentiment of customer review as positive, negative, neutral with confidence score. Input: Product arrived fast but quality poor. Output JSON: {sentiment: negative, confidence: 0.85}.”

Entity Resolution

“Resolve entities in email: names, organizations, dates. Input: Meeting with John Doe from Google on Friday 2023-10-06. Output JSON list of resolved entities.”

Data Cleaning

“Clean and standardize addresses from messy list. Input: 123 Main St, NY; 456 broadway nyc. Output standardized JSON array.”

For Developers

A few lines of code.
Data extraction. One call.
---

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

- **Serverless:** scales to zero, scales to millions
- **Pay per token,** no minimums
- **Python and JavaScript SDKs,** plus REST API

[API Documentation ](https://docs.modelslab.com)

PythonJavaScriptcURL

Copy

```
<code>import requests

response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())</code>
```

FAQ

Common questions about Refuel LLM V2 Small
---

[Read the docs ](https://docs.modelslab.com)

### What is Refuel LLM V2 Small?

### How does Refuel LLM V2 Small API work?

### Is Refuel LLM V2 Small model better than GPT-3.5?

### What tasks suits Refuel LLM V2 Small?

### Refuel LLM V2 Small alternative to Claude?

### Where to access refuel llm v2 small model?

Ready to create?
---

Start generating with Refuel LLM V2 Small on ModelsLab.

[Try Refuel LLM V2 Small](/models/refuel_ai/togethercomputer-Refuel-Llm-V2-Small) [API Documentation](https://docs.modelslab.com)

---

*This markdown version is optimized for AI agents and LLMs.*

**Links:**
- [Website](https://modelslab.com)
- [API Documentation](https://docs.modelslab.com)
- [Blog](https://modelslab.com/blog)

---
*Generated by ModelsLab - 2026-04-15*