1{ 2 "chat": { 3 "llama3-8b-8192": { 4 "description": "LLaMA3 8b", 5 "inputTokens": 8192, 6 "inputTokenPrice": 0.05, 7 "outputTokens": 8192, 8 "outputTokenPrice": 0.08 9 }, 10 "llama3-70b-8192": { 11 "description": "LLaMA3 70b", 12 "inputTokens": 8192, 13 "inputTokenPrice": 0.59, 14 "outputTokens": 8192, 15 "outputTokenPrice": 0.79 16 }, 17 "llama2-70b-4096": { 18 "description": "LLaMA2 70b", 19 "inputTokens": 4096, 20 "inputTokenPrice": 0.7, 21 "outputTokens": 4096, 22 "outputTokenPrice": 0.8 23 }, 24 "mixtral-8x7b-32768": { 25 "description": "Mixtral 8x7b", 26 "inputTokens": 32768, 27 "inputTokenPrice": 0.24, 28 "outputTokens": 32768, 29 "outputTokenPrice": 0.24 30 }, 31 "gemma-7b-it": { 32 "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.", 33 "inputTokens": 8192, 34 "inputTokenPrice": 0.07, 35 "outputTokens": 8192, 36 "outputTokenPrice": 0.07 37 } 38 } 39}