{ "chat": { "llama3-8b-8192": { "description": "LLaMA3 8b", "inputTokens": 8192, "inputTokenPrice": 0.05, "outputTokens": 8192, "outputTokenPrice": 0.08 }, "llama3-70b-8192": { "description": "LLaMA3 70b", "inputTokens": 8192, "inputTokenPrice": 0.59, "outputTokens": 8192, "outputTokenPrice": 0.79 }, "llama2-70b-4096": { "description": "LLaMA2 70b", "inputTokens": 4096, "inputTokenPrice": 0.7, "outputTokens": 4096, "outputTokenPrice": 0.8 }, "mixtral-8x7b-32768": { "description": "Mixtral 8x7b", "inputTokens": 32768, "inputTokenPrice": 0.24, "outputTokens": 32768, "outputTokenPrice": 0.24 }, "gemma-7b-it": { "description": "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.", "inputTokens": 8192, "inputTokenPrice": 0.07, "outputTokens": 8192, "outputTokenPrice": 0.07 } } }