---
title: LiquidAI: LFM2.5 1.2B Thinking (free) | Text Generation | ModelsLab
description: Open-weight reasoning model with 1.2B parameters, runs on-device under 1GB RAM, excels at math and logic tasks—free to download and deploy across Apple.
url: https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/liquid/liquid-lfm-2.5-1.2b-thinking-free/api.md
canonical: https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/liquid/liquid-lfm-2.5-1.2b-thinking-free/api.md
type: product
component: Playground/LLM/Index
generated_at: 2026-05-13T10:32:58.962654Z
---

LiquidAI: LFM2.5-1.2B-Thinking (free)
---

 [LLMs.txt](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/liquid-lfm-2.5-1.2b-thinking-free/llms.txt) [.md](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/liquid/liquid-lfm-2.5-1.2b-thinking-free.md)

liquid-lfm-2.5-1.2b-thinking-free liquid Closed Source Model

LiquidAI: LFM2.5-1.2B-Thinking (free)
---

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

### LiquidAI: LFM2.5-1.2B-Thinking (free)

liquid liquid-lfm-2.5-1.2b-thinking-free

Copy model ID

PricingInput $0.00 / 1M tokens

Output $0.00 / 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-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster)

[AC](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-sonnet-latest)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Anthropic Claude Sonnet Latest

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-sonnet-latest)

[QP](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3.6-Plus)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Qwen3.6 Plus

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3.6-Plus)

[SS](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/stepfun-step-3.5-flash)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [StepFun: Step 3.5 Flash

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/stepfun-step-3.5-flash)

[DR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek)

 [DeepSeek R1 Distill Qwen 14B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-14B)

[N3](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nim-meta-llama-3.2-90b-vision-instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [nim/meta/llama-3.2-90b-vision-instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/nim-meta-llama-3.2-90b-vision-instruct)

[DR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-r1-distill-llama-70b)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [DeepSeek: R1 Distill Llama 70B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-r1-distill-llama-70b)

[G4](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/zai-org-GLM-4.5V)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [GLM 4.5V

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/zai-org-GLM-4.5V)

[QC](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-Coder-30B-A3B-Instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Qwen3 Coder 30B A3b Instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-Coder-30B-A3B-Instruct)

[GN](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/google-gemini-3-pro-image-preview)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/google-gemini-3-pro-image-preview)

[GG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/google-gemini-2.5-flash-lite)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Google: Gemini 2.5 Flash Lite

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/google-gemini-2.5-flash-lite)

[Q0](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-0.6B)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Qwen3 0.6B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen3-0.6B)

[XG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/x-ai-grok-4-fast)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [xAI: Grok 4 Fast

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/x-ai-grok-4-fast)

[G3](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/google-gemma-3-1b-it)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Gemma 3 1b it

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/google-gemma-3-1b-it)

[QV](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen2.5-VL-72B-Instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai)

 [Qwen2.5-VL (72B) Instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen2.5-VL-72B-Instruct)

[MM](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/mistralai-mixtral-8x22b-instruct)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [Mistral: Mixtral 8x22B Instruct

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/mistralai-mixtral-8x22b-instruct)

[OO](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3-deep-research)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [OpenAI: o3 Deep Research

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3-deep-research)

[DR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek)

 [DeepSeek R1 Distill Qwen 1.5B

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/deepseek/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B)

[OG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-gpt-4-0314)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router)

 [OpenAI: GPT-4 (older v0314)

Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-gpt-4-0314)

About LiquidAI: LFM2.5-1.2B-Thinking (Free)
---

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

### Technical Specifications

Model IDliquid-lfm-2.5-1.2b-thinking-freeCategoryLLM ModelsTaskText GenerationAddedFebruary 20, 2026

### 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 LiquidAI: LFM2.5-1.2B-Thinking (Free) into your application with a single API call. Get your API key from the [pricing page](https://modelslab-frontend-v2-927501783998.us-east4.run.app/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": "liquid-lfm-2.5-1.2b-thinking-free",
        "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-frontend-v2-927501783998.us-east4.run.app/models/liquid/liquid-lfm-2.5-1.2b-thinking-free/api) for SDKs, code examples in Python, JavaScript, and more.

### 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 LiquidAI: LFM2.5-1.2B-Thinking (Free)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/liquidai-lfm25-12b-thinking-free) [Browse LLM Models](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster) [More from Liquid](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [View Pricing](https://modelslab-frontend-v2-927501783998.us-east4.run.app/pricing)

LiquidAI: LFM2.5-1.2B-Thinking (Free) FAQ
---

### What is LiquidAI: LFM2.5-1.2B-Thinking (Free)?

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

### How do I use the LiquidAI: LFM2.5-1.2B-Thinking (Free) API?

You can integrate LiquidAI: LFM2.5-1.2B-Thinking (Free) into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "liquid-lfm-2.5-1.2b-thinking-free" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.

### What is the LiquidAI: LFM2.5-1.2B-Thinking (Free) model ID?

The model ID for LiquidAI: LFM2.5-1.2B-Thinking (Free) is "liquid-lfm-2.5-1.2b-thinking-free". Use this ID in your API requests to specify this model.

### Does LiquidAI: LFM2.5-1.2B-Thinking (Free) have a free tier?

Yes, ModelsLab offers a free tier that lets you try LiquidAI: LFM2.5-1.2B-Thinking (Free) 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 - 2026-05-13*