[ { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "codellama/CodeLlama-34b-Instruct-hf", "model_name": "CodeLlama 34B Instruct Hf", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 1, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf", "model_id": "codellama/CodeLlama-70b-Instruct-hf", "model_name": "CodeLlama 70B Instruct Hf", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 1, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it", "model_id": "google/gemma-7b-it", "model_name": "Gemma 7B It", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "model_id": "HuggingFaceH4/zephyr-7b-beta", "model_name": "Zephyr 7B Beta", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "meta-llama/Llama-2-13b-chat-hf", "model_name": "Llama 2 13B Chat Hf", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 0.25, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "meta-llama/Llama-2-70b-chat-hf", "model_name": "Llama 2 70B Chat Hf", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 1, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "meta-llama/Llama-2-7b-chat-hf", "model_name": "Llama 2 7B Chat Hf", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct", "model_id": "meta-llama/Meta-Llama-3-70B-Instruct", "model_name": "Meta Llama 3 70B Instruct", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 1, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", "model_id": "mistralai/Mixtral-8x22B-Instruct-v0.1", "model_name": "Mixtral 8x22B Instruct V0.1", "provider_id": "anyscale", "provider_name": "Anyscale", "input_cost_per_million": 0.8999999999999999, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]