xref: /plugin/aichat/Model/OpenAI/models.json (revision 42b2c6e864def16df42600c2885e21d4d148fd0c) 
1{
2    "chat": {
3        "gpt-3.5-turbo": {
4            "description": "GPT-3.5 Turbo is a variant of GPT-3.5 that is optimized for speed and can generate responses in a fraction of the time.",
5            "inputTokens": 16385,
6            "inputTokenPrice": 1.5,
7            "outputTokens": 4096,
8            "outputTokenPrice": 2
9        },
10        "gpt-4": {
11            "description": "GPT-4 is the latest version of OpenAI's Generative Pre-trained Transformer (GPT) language model. It is capable of generating human-like text and can be used for a wide range of natural language processing tasks.",
12            "inputTokens": 8192,
13            "inputTokenPrice": 30,
14            "outputTokens": 4096,
15            "outputTokenPrice": 60
16        },
17        "gpt-4-turbo": {
18            "description": "GPT-4 Turbo is a variant of GPT-4 that is optimized for speed and can generate responses in a fraction of the time.",
19            "inputTokens": 128000,
20            "inputTokenPrice": 10,
21            "outputTokens": 4096,
22            "outputTokenPrice": 30
23        },
24        "gpt-4o": {
25            "description": "GPT-4o has the same high intelligence as GPT-4 Turbo but is much more efficient",
26            "inputTokens": 128000,
27            "inputTokenPrice": 2.5,
28            "outputTokens": 16384,
29            "outputTokenPrice": 10
30        },
31        "gpt-4o-mini": {
32            "description": "",
33            "inputTokens": 128000,
34            "inputTokenPrice": 0.15,
35            "outputTokens": 16384,
36            "outputTokenPrice": 0.6
37        },
38        "gpt-4-32k": {
39            "description": "",
40            "inputTokens": 32768,
41            "inputTokenPrice": 60,
42            "outputTokens": 4096,
43            "outputTokenPrice": 120
44        },
45        "gpt-3.5-turbo-16k": {
46            "description": "",
47            "inputTokens": 16385,
48            "inputTokenPrice": 3,
49            "outputTokens": 4096,
50            "outputTokenPrice": 4
51        },
52        "o1-mini": {
53            "description": "",
54            "inputTokens": 128000,
55            "inputTokenPrice": 1.1,
56            "outputTokens": 65536,
57            "outputTokenPrice": 4.4
58        },
59        "chatgpt-4o-latest": {
60            "description": "",
61            "inputTokens": 128000,
62            "inputTokenPrice": 5,
63            "outputTokens": 4096,
64            "outputTokenPrice": 15
65        },
66        "o1": {
67            "description": "",
68            "inputTokens": 200000,
69            "inputTokenPrice": 15,
70            "outputTokens": 100000,
71            "outputTokenPrice": 60
72        },
73        "o3-mini": {
74            "description": "",
75            "inputTokens": 200000,
76            "inputTokenPrice": 1.1,
77            "outputTokens": 100000,
78            "outputTokenPrice": 4.4
79        }
80    },
81    "embedding": {
82        "text-embedding-ada-002": {
83            "description": "Most capable 2nd generation embedding model",
84            "inputTokens": 8191,
85            "inputTokenPrice": 0.1,
86            "dimensions": 1536
87        },
88        "text-embedding-3-small": {
89            "description": "Increased performance over 2nd generation ada embedding model",
90            "inputTokens": 8191,
91            "inputTokenPrice": 0.02,
92            "dimensions": 1536
93        },
94        "text-embedding-3-large": {
95            "description": "Most capable embedding model for both english and non-english tasks",
96            "inputTokens": 8191,
97            "inputTokenPrice": 0.13,
98            "dimensions": 3072
99        },
100        "text-embedding-ada-002-v2": {
101            "description": "",
102            "inputTokens": 8191,
103            "inputTokenPrice": 0.1,
104            "dimensions": 1536
105        }
106    }
107}