---
title: Refuel LLM V2 API | Text Generation | ModelsLab
description: Advanced, highly accurate large language model for structured data extraction, classification, and enrichment—47B parameters, 16K context, excels in.
url: https://modelslab.com/models/refuel_ai/togethercomputer-refuel-llm-v2.md
canonical: https://modelslab.com/models/refuel_ai/togethercomputer-refuel-llm-v2.md
type: product
component: Playground/LLM/Index
generated_at: 2026-05-05T18:46:02.724094Z
---

Refuel LLM V2
---

 [LLMs.txt](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2/llms.txt) [.md](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2.md)

togethercomputer-Refuel-Llm-V2 refuel\_ai Closed Source Model $0.720000 / call

Refuel LLM V2
---

Choose a prompt below to get started or type your own message

 Explain quantum computing in simple terms

 Write a Python function to sort a list

 Create a marketing email for a SaaS product

 Compare REST vs GraphQL APIs

Send

### Refuel LLM V2

refuel\_ai togethercomputer-Refuel-Llm-V2

Copy model ID

PricingInput $0.72 / 1M tokens

Output $0.72 / 1M tokens

API EndpointsOpenAI Compatible

`https://modelslab.com/api/v7/llm/chat/completions`Endpoint

Anthropic Compatible

`https://modelslab.com/api/v7/llm/v1/messages`Messages

`https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens

`https://modelslab.com/api/v7/llm/v1/models`Models

Use with Claude Code

cURL Example

ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses.

Temperature0.7

Max Tokens1000

Top P0.9

Frequency Penalty0

Presence Penalty0

Model Info

Support

Related Models
---

Discover similar models you might be interested in

 [View all LLM Models](https://modelslab.com/models?feature=llmaster)

[QC](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-30B-A3B-Instruct)[Together AI](https://modelslab.com/models/together_ai)

 [Qwen3 Coder 30B A3b Instruct

Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-30B-A3B-Instruct)

[US](https://modelslab.com/models/open_router/upstage-solar-pro-3)[Open Router](https://modelslab.com/models/open_router)

 [Upstage: Solar Pro 3

Closed Source Model](https://modelslab.com/models/open_router/upstage-solar-pro-3)

[NN](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8)[Together AI](https://modelslab.com/models/together_ai)

 [Nvidia Nemotron 3 Super 120B A12b Fp8

Closed Source Model](https://modelslab.com/models/together_ai/nvidia-NVIDIA-Nemotron-3-Super-120B-A12B-FP8)

[OG](https://modelslab.com/models/open_router/openai-gpt-4-turbo-preview)[Open Router](https://modelslab.com/models/open_router)

 [OpenAI: GPT-4 Turbo Preview

Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4-turbo-preview)

[L4](https://modelslab.com/models/together_ai/meta-llama-Llama-4-Scout-17B-16E-Instruct)[Together AI](https://modelslab.com/models/together_ai)

 [Llama 4 Scout Instruct (17Bx16E)

Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Llama-4-Scout-17B-16E-Instruct)

[QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-122b-a10b)[Open Router](https://modelslab.com/models/open_router)

 [Qwen: Qwen3.5-122B-A10B

Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-122b-a10b)

[QN](https://modelslab.com/models/together_ai/Qwen-Qwen3-Next-80B-A3B-Thinking)[Together AI](https://modelslab.com/models/together_ai)

 [Qwen3 Next 80B A3b Thinking

Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-Next-80B-A3B-Thinking)

[M(](https://modelslab.com/models/mistral_ai/mistralai-Mistral-7B-Instruct-v0.1)[ModelsLab](https://modelslab.com/models/mistral_ai)

 [Mistral (7B) Instruct

Closed Source Model](https://modelslab.com/models/mistral_ai/mistralai-Mistral-7B-Instruct-v0.1)

[MM](https://modelslab.com/models/open_router/minimax-minimax-m2.1)[Open Router](https://modelslab.com/models/open_router)

 [MiniMax: MiniMax M2.1

Closed Source Model](https://modelslab.com/models/open_router/minimax-minimax-m2.1)

[AA](https://modelslab.com/models/open_router/arcee-ai-maestro-reasoning)[Open Router](https://modelslab.com/models/open_router)

 [Arcee AI: Maestro Reasoning

Closed Source Model](https://modelslab.com/models/open_router/arcee-ai-maestro-reasoning)

[ML](https://modelslab.com/models/open_router/meta-llama-llama-3.3-70b-instruct-free)[Open Router](https://modelslab.com/models/open_router)

 [Meta: Llama 3.3 70B Instruct (free)

Closed Source Model](https://modelslab.com/models/open_router/meta-llama-llama-3.3-70b-instruct-free)

[II](https://modelslab.com/models/open_router/inflection-inflection-3-pi)[Open Router](https://modelslab.com/models/open_router)

 [Inflection: Inflection 3 Pi

Closed Source Model](https://modelslab.com/models/open_router/inflection-inflection-3-pi)

[N3](https://modelslab.com/models/together_ai/nim-meta-llama-3.3-70b-instruct)[Together AI](https://modelslab.com/models/together_ai)

 [nim/meta/llama-3.3-70b-instruct

Closed Source Model](https://modelslab.com/models/together_ai/nim-meta-llama-3.3-70b-instruct)

[AA](https://modelslab.com/models/open_router/aion-labs-aion-1.0)[Open Router](https://modelslab.com/models/open_router)

 [AionLabs: Aion-1.0

Closed Source Model](https://modelslab.com/models/open_router/aion-labs-aion-1.0)

[QQ](https://modelslab.com/models/qwen/Qwen-QwQ-32B)[ModelsLab](https://modelslab.com/models/qwen)

 [Qwen QwQ-32B

Closed Source Model](https://modelslab.com/models/qwen/Qwen-QwQ-32B)

[NH](https://modelslab.com/models/open_router/nousresearch-hermes-4-70b)[Open Router](https://modelslab.com/models/open_router)

 [Nous: Hermes 4 70B

Closed Source Model](https://modelslab.com/models/open_router/nousresearch-hermes-4-70b)

[MM](https://modelslab.com/models/open_router/mistralai-mistral-small-2603)[Open Router](https://modelslab.com/models/open_router)

 [Mistral: Mistral Small 4

Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-small-2603)

[DR](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)[Together AI](https://modelslab.com/models/together_ai)

 [DeepSeek R1 Distill Qwen 14B

Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)

About Refuel LLM V2
---

Advanced, highly accurate large language model for structured data extraction, classification, and enrichment—47B parameters, 16K context, excels in finance, HR, and e-commerce with calibrated confidence scoring.

### Technical Specifications

Model IDtogethercomputer-Refuel-Llm-V2CategoryLLM ModelsTaskText GenerationPrice$0.720000 per million tokensAddedJuly 22, 2025

### Key Features

- Chat completion and multi-turn conversation API
- Streaming response with token-by-token output
- Function calling and tool use support
- System prompts and role-based messaging
- JSON mode and structured output

### Quick Start

Integrate Refuel LLM V2 into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started.

PythonJavaScriptcURLPHP

```
<code>import requests
import json

url = "https://modelslab.com/api/v7/llm/chat/completions"

headers = {
    "Content-Type": "application/json"
}

data = {
        "model_id": "togethercomputer-Refuel-Llm-V2",
        "messages": [
            {
                "role": "user",
                "content": "Hello!"
            }
        ],
        "max_tokens": 1000,
        "key": "YOUR_API_KEY"
    }

try:
    response = requests.post(url, headers=headers, json=data)
    response.raise_for_status()  # Raises an HTTPError for bad responses (4XX or 5XX)
    result = response.json()
    print("API Response:")
    print(json.dumps(result, indent=2))
except requests.exceptions.HTTPError as http_err:
    print(f"HTTP error occurred: {http_err} - {response.text}")
except Exception as err:
    print(f"Other error occurred: {err}")</code>
```

View the [full API documentation](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2/api) for SDKs, code examples in Python, JavaScript, and more.

### Pricing

Refuel LLM V2 API costs $0.720000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing)

### Use Cases

- AI chatbots and virtual assistants
- Code generation and developer tools
- Content writing and copywriting automation
- Data analysis, summarization, and extraction

[Learn more about Refuel LLM V2](https://modelslab.com/refuel-llm-v2) [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Refuel Ai](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing)

Refuel LLM V2 FAQ
---

### What is Refuel LLM V2?

Advanced, highly accurate large language model for structured data extraction, classification, and enrichment—47B parameters, 16K context, excels in finance, HR, and e-commerce with calibrated confidence scoring.

### How do I use the Refuel LLM V2 API?

You can integrate Refuel LLM V2 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "togethercomputer-Refuel-Llm-V2" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.

### How much does Refuel LLM V2 cost?

Refuel LLM V2 costs $0.720000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started.

### What is the Refuel LLM V2 model ID?

The model ID for Refuel LLM V2 is "togethercomputer-Refuel-Llm-V2". Use this ID in your API requests to specify this model.

### Does Refuel LLM V2 have a free tier?

Yes, ModelsLab offers a free tier that lets you try Refuel LLM V2 and other AI models. Sign up to get free API credits and start building immediately.

---

*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 - 2026-05-06*