Skip to contents

Process request using OpenRouter API

Source: R/process_openrouter.R
process_openrouter.Rd

This function processes annotation requests using the OpenRouter API, which provides access to various LLM models including OpenAI, Anthropic, Meta, and Google models. OpenRouter also offers free models with the :free suffix (e.g., 'meta-llama/llama-4-maverick:free').

Usage

process_openrouter(prompt, model, api_key)

Arguments

prompt

Character string containing the prompt to send to the API

model

Character string specifying the model to use (e.g., 'openai/gpt-4o' or 'meta-llama/llama-4-maverick:free')

api_key

Character string containing the OpenRouter API key

Value

Character vector containing the model's response

Details

For free models, use the :free suffix in the model name. For example:

  • 'meta-llama/llama-4-maverick:free' - Meta Llama 4 Maverick (free)

  • 'nvidia/llama-3.1-nemotron-ultra-253b-v1:free' - NVIDIA Nemotron Ultra 253B (free)

  • 'deepseek/deepseek-chat-v3-0324:free' - DeepSeek Chat v3 (free)

  • 'microsoft/mai-ds-r1:free' - Microsoft MAI-DS-R1 (free)

Free models don't consume credits but may have limitations compared to paid models.