Unleash the Power of LLMs: A Unified Interface with Just-Prompt

Tired of juggling multiple APIs for different Large Language Models (LLMs)? Just-Prompt offers a streamlined solution, providing a single, unified interface to access the power of OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama. Simplify your workflow and unlock the potential of cross-platform LLM interactions.

Why Choose Just-Prompt for Your LLM Needs?

Unified API: Interact with various LLMs using a single, consistent interface, saving you development time and effort. Say goodbye to managing individual provider SDKs!
Multi-Model Support: Run prompts across multiple LLMs simultaneously, allowing for comparative analysis or ensemble approaches. Supercharge your ability to perform A/B testing across LLM's.
Flexibility: Use text prompts directly or load them from files, adapting to your preferred workflow.
Easy Integration: Simple installation and configuration using environment variables.

Powerful Tools to Streamline Your LLM Interactions

Just-Prompt provides several handy tools to manage all major LLM providers. Here’s a breakdown:

prompt: Send a text prompt to one or more LLMs. Use this to quickly query different LLMs from your terminal.
- Parameters:
  - text: The prompt itself.
  - models_prefixed_by_provider (optional): Specify the models to use (e.g., openai:gpt-4o). If omitted, Just-Prompt uses your defined default models.
prompt_from_file: Load a prompt from a file and send it to multiple LLMs. Great for more sophisticated or repetitive workflows.
- Parameters:
  - file: Path to the file containing the prompt.
  - models_prefixed_by_provider (optional): Specify the models.
prompt_from_file_to_file: Read a prompt from a file, send it to LLMs, and save the responses to individual markdown files. This tool enables you to record the history of your prompts in organized files.
- Parameters:
  - file: Path to the prompt file.
  - models_prefixed_by_provider (optional): Specify the models.
  - output_dir (optional, default: "."): The directory where response files will be saved.
ceo_and_board: Simulate a board meeting by sending a prompt to multiple 'board member' LLMs and have a 'CEO' model make a decision based on their responses. The tool empowers users to harness the diverse insights of multiple specialized AI's to tackle complex, high-level strategic decisions.
- Parameters:
  - file: Path to the file containing the prompt describing the scenario.
  - models_prefixed_by_provider (optional): List of models acting as board members.
  - output_dir (optional, default: "."): Directory for saving responses and the CEO decision.
  - ceo_model (optional, default: "openai:o3"): The model to use as the CEO.
list_providers: Get a list of all available LLM providers.
- Parameters: None
list_models: List all available models for a specific provider.
- Parameters:
  - provider: The provider to query (e.g., 'openai' or 'o').

Provider Prefixes: Your Key to Model Selection

Each model needs to be prefixed with its provider's name. Use the short name for quicker referencing:

OpenAI: o or openai (e.g., o:gpt-4o-mini, openai:gpt-4o-mini)
Anthropic: a or anthropic (e.g., a:claude-3-5-haiku, anthropic:claude-3-5-haiku)
Google Gemini: g or gemini (e.g., g:gemini-2.5-pro-exp-03-25, gemini:gemini:gemini-2.5-pro-exp-03-25)
Groq: q or groq (e.g., q:llama-3.1-70b-versatile, groq:llama-3.1-70b-versatile)
DeepSeek: d or deepseek (e.g., d:deepseek-coder, deepseek:deepseek-coder)
Ollama: l or ollama (e.g., l:llama3.1, ollama:llama3.1)

Getting Started with Just-Prompt: Installation & Configuration

Clone the Repository:

git clone https://github.com/yourusername/just-prompt.git
cd just-prompt

Install Dependencies:
```
uv sync
```

Configure API Keys:

Create a .env file (copy from .env.sample).

Add your API keys to the .env file or export them in your shell:

OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
GEMINI_API_KEY=your_gemini_api_key_here
GROQ_API_KEY=your_groq_api_key_here
DEEPSEEK_API_KEY=your_deepseek_api_key_here
OLLAMA_HOST=http://localhost:11434

Advanced Features: Reasoning Effort, Thinking Tokens, and Thinking Budget

Just-Prompt allows you to fine-tune the reasoning process for certain models:

OpenAI: Control the reasoning effort for o-series models (e.g., o4-mini, o3) using suffixes like :low, :medium, or :high (e.g., openai:o4-mini:low).
Anthropic: Utilize thinking tokens with Claude models (e.g., claude-3-7-sonnet-20250219) using suffixes like :1k, :4k, or :8000 to enable more thorough thought processes (e.g. anthropic:claude-3-7-sonnet-20250219:4k).
Gemini: Leverage thinking budget with Gemini models (e.g., gemini-2.5-flash-preview-04-17) using suffixes like :1k, :4k, or :8000 to enable more thorough reasoning before providing a response (e.g. gemini:gemini-2.5-flash-preview-04-17:4k).

Unlock the Full Potential of Large Language Models Today!

Just-Prompt simplifies LLM interactions, empowering you to focus on innovation and insights. Start using Just-Prompt today.

Unleash the Power of LLMs: A Unified Interface with Just-Prompt

Why Choose Just-Prompt for Your LLM Needs?

Unified API: Interact with various LLMs using a single, consistent interface, saving you development time and effort. Say goodbye to managing individual provider SDKs!

Multi-Model Support: Run prompts across multiple LLMs simultaneously, allowing for comparative analysis or ensemble approaches. Supercharge your ability to perform A/B testing across LLM's.

Flexibility: Use text prompts directly or load them from files, adapting to your preferred workflow.

Easy Integration: Simple installation and configuration using environment variables.

Powerful Tools to Streamline Your LLM Interactions

Just-Prompt provides several handy tools to manage all major LLM providers. Here’s a breakdown:

prompt: Send a text prompt to one or more LLMs. Use this to quickly query different LLMs from your terminal.

Parameters:
- text: The prompt itself.
- models_prefixed_by_provider (optional): Specify the models to use (e.g., openai:gpt-4o). If omitted, Just-Prompt uses your defined default models.

prompt_from_file: Load a prompt from a file and send it to multiple LLMs. Great for more sophisticated or repetitive workflows.

Parameters:
- file: Path to the file containing the prompt.
- models_prefixed_by_provider (optional): Specify the models.

prompt_from_file_to_file: Read a prompt from a file, send it to LLMs, and save the responses to individual markdown files. This tool enables you to record the history of your prompts in organized files.

Parameters:
- file: Path to the prompt file.
- models_prefixed_by_provider (optional): Specify the models.
- output_dir (optional, default: "."): The directory where response files will be saved.

ceo_and_board: Simulate a board meeting by sending a prompt to multiple 'board member' LLMs and have a 'CEO' model make a decision based on their responses. The tool empowers users to harness the diverse insights of multiple specialized AI's to tackle complex, high-level strategic decisions.

Parameters:
- file: Path to the file containing the prompt describing the scenario.
- models_prefixed_by_provider (optional): List of models acting as board members.
- output_dir (optional, default: "."): Directory for saving responses and the CEO decision.
- ceo_model (optional, default: "openai:o3"): The model to use as the CEO.

list_providers: Get a list of all available LLM providers.

Parameters: None

list_models: List all available models for a specific provider.

Parameters:
- provider: The provider to query (e.g., 'openai' or 'o').

Provider Prefixes: Your Key to Model Selection

Each model needs to be prefixed with its provider's name. Use the short name for quicker referencing:

OpenAI: o or openai (e.g., o:gpt-4o-mini, openai:gpt-4o-mini)

Anthropic: a or anthropic (e.g., a:claude-3-5-haiku, anthropic:claude-3-5-haiku)

Google Gemini: g or gemini (e.g., g:gemini-2.5-pro-exp-03-25, gemini:gemini:gemini-2.5-pro-exp-03-25)

Groq: q or groq (e.g., q:llama-3.1-70b-versatile, groq:llama-3.1-70b-versatile)

DeepSeek: d or deepseek (e.g., d:deepseek-coder, deepseek:deepseek-coder)

Ollama: l or ollama (e.g., l:llama3.1, ollama:llama3.1)

Getting Started with Just-Prompt: Installation & Configuration

Clone the Repository:

git clone https://github.com/yourusername/just-prompt.git
cd just-prompt

Install Dependencies:

uv sync

Configure API Keys:

Create a .env file (copy from .env.sample).

Add your API keys to the .env file or export them in your shell:

OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
GEMINI_API_KEY=your_gemini_api_key_here
GROQ_API_KEY=your_groq_api_key_here
DEEPSEEK_API_KEY=your_deepseek_api_key_here
OLLAMA_HOST=http://localhost:11434

Advanced Features: Reasoning Effort, Thinking Tokens, and Thinking Budget

Just-Prompt allows you to fine-tune the reasoning process for certain models:

OpenAI: Control the reasoning effort for o-series models (e.g., o4-mini, o3) using suffixes like :low, :medium, or :high (e.g., openai:o4-mini:low).

Anthropic: Utilize thinking tokens with Claude models (e.g., claude-3-7-sonnet-20250219) using suffixes like :1k, :4k, or :8000 to enable more thorough thought processes (e.g. anthropic:claude-3-7-sonnet-20250219:4k).

Gemini: Leverage thinking budget with Gemini models (e.g., gemini-2.5-flash-preview-04-17) using suffixes like :1k, :4k, or :8000 to enable more thorough reasoning before providing a response (e.g. gemini:gemini-2.5-flash-preview-04-17:4k).