1{
2    "chat": {
3        "llama3.2:3b": {
4            "description": "Meta's Llama 3.2 model with 3 billion parameters.",
5            "inputTokens": 8192,
6            "inputTokenPrice": 0,
7            "outputTokens": 8192,
8            "outputTokenPrice": 0
9        },
10        "llama3.2:1b": {
11            "description": "Meta's Llama 3.2 model with 1 billion parameters.",
12            "inputTokens": 8192,
13            "inputTokenPrice": 0,
14            "outputTokens": 8192,
15            "outputTokenPrice": 0
16        },
17        "llama3.1:405b": {
18            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 405 billion parameters.",
19            "inputTokens": 8192,
20            "inputTokenPrice": 0,
21            "outputTokens": 8192,
22            "outputTokenPrice": 0
23        },
24        "llama3.1:70b": {
25            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 70 billion parameters.",
26            "inputTokens": 8192,
27            "inputTokenPrice": 0,
28            "outputTokens": 8192,
29            "outputTokenPrice": 0
30        },
31        "llama3.1:8b": {
32            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 8 billion parameters.",
33            "inputTokens": 8192,
34            "inputTokenPrice": 0,
35            "outputTokens": 8192,
36            "outputTokenPrice": 0
37        },
38        "gemma2:27b": {
39            "description": "Google Gemma 2 is a high-performing and efficient model. 27 billion parameters.",
40            "inputTokens": 4096,
41            "inputTokenPrice": 0,
42            "outputTokens": 4096,
43            "outputTokenPrice": 0
44        },
45        "gemma2:9b": {
46            "description": "Google Gemma 2 is a high-performing and efficient model. 9 billion parameters.",
47            "inputTokens": 4096,
48            "inputTokenPrice": 0,
49            "outputTokens": 4096,
50            "outputTokenPrice": 0
51        },
52        "gemma2:2b": {
53            "description": "Google Gemma 2 is a high-performing and efficient model. 2 billion parameters.",
54            "inputTokens": 4096,
55            "inputTokenPrice": 0,
56            "outputTokens": 4096,
57            "outputTokenPrice": 0
58        },
59        "qwen2.5:72b": {
60            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 72 billion parameters.",
61            "inputTokens": 128000,
62            "inputTokenPrice": 0,
63            "outputTokens": 8192,
64            "outputTokenPrice": 0
65        },
66        "qwen2.5:32b": {
67            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 32 billion parameters.",
68            "inputTokens": 128000,
69            "inputTokenPrice": 0,
70            "outputTokens": 8192,
71            "outputTokenPrice": 0
72        },
73        "qwen2.5:14b": {
74            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 14 billion parameters.",
75            "inputTokens": 128000,
76            "inputTokenPrice": 0,
77            "outputTokens": 8192,
78            "outputTokenPrice": 0
79        },
80        "qwen2.5:7b": {
81            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 7 billion parameters.",
82            "inputTokens": 128000,
83            "inputTokenPrice": 0,
84            "outputTokens": 8192,
85            "outputTokenPrice": 0
86        },
87        "qwen2.5:3b": {
88            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 3 billion parameters.",
89            "inputTokens": 128000,
90            "inputTokenPrice": 0,
91            "outputTokens": 8192,
92            "outputTokenPrice": 0
93        },
94        "qwen2.5:1.5b": {
95            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 1.5 billion parameters.",
96            "inputTokens": 128000,
97            "inputTokenPrice": 0,
98            "outputTokens": 8192,
99            "outputTokenPrice": 0
100        },
101        "qwen2.5:0.5b": {
102            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 0.5 billion parameters.",
103            "inputTokens": 128000,
104            "inputTokenPrice": 0,
105            "outputTokens": 8192,
106            "outputTokenPrice": 0
107        }
108    },
109    "embedding": {
110        "nomic-embed-text": {
111            "description": "A high-performing open embedding model with a large token context window.",
112            "inputTokens": 8192,
113            "inputTokenPrice": 0,
114            "dimensions": 768
115        },
116        "mxbai-embed-large": {
117            "description": "State-of-the-art large embedding model from mixedbread.ai",
118            "inputTokens": 512,
119            "inputTokenPrice": 0,
120            "dimensions": 1024
121        },
122        "all-minilm": {
123            "description": "The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective.",
124            "inputTokens": 256,
125            "inputTokenPrice": 0,
126            "dimensions": 384
127        },
128        "bge-large": {
129            "description": "Embedding model from BAAI mapping texts to vectors.",
130            "inputTokens": 512,
131            "inputTokenPrice": 0,
132            "dimensions": 1024
133        }
134    }
135}
136