xref: /plugin/aichat/Model/Gemini/models.json (revision b971544330dac8e132930c58cba9d7442ef90031) 
1{
2    "chat": {
3        "gemini-2.5-flash": {
4            "description": "https:\/\/ai.google.dev\/pricing",
5            "inputTokens": 1048576,
6            "inputTokenPrice": 0.3,
7            "outputTokens": 65535,
8            "outputTokenPrice": 2.5
9        },
10        "gemini-2.5-pro": {
11            "description": "https:\/\/ai.google.dev\/pricing",
12            "inputTokens": 1048576,
13            "inputTokenPrice": 1.25,
14            "outputTokens": 65535,
15            "outputTokenPrice": 10
16        },
17        "gemini-2.0-flash": {
18            "description": "https:\/\/ai.google.dev\/pricing#2_0flash",
19            "inputTokens": 1048576,
20            "inputTokenPrice": 0.1,
21            "outputTokens": 8192,
22            "outputTokenPrice": 0.4
23        },
24        "gemini-2.0-flash-lite": {
25            "description": "https:\/\/ai.google.dev\/gemini-api\/docs\/pricing#gemini-2.0-flash-lite",
26            "inputTokens": 1048576,
27            "inputTokenPrice": 0.08,
28            "outputTokens": 8192,
29            "outputTokenPrice": 0.3
30        },
31        "gemini-1.5-pro": {
32            "description": "https:\/\/ai.google.dev\/pricing",
33            "inputTokens": 2097152,
34            "inputTokenPrice": 3.5,
35            "outputTokens": 8192,
36            "outputTokenPrice": 10.5
37        },
38        "gemini-1.5-pro-latest": {
39            "description": "https:\/\/ai.google.dev\/pricing",
40            "inputTokens": 1048576,
41            "inputTokenPrice": 3.5,
42            "outputTokens": 8192,
43            "outputTokenPrice": 1.05
44        },
45        "gemini-gemma-2-27b-it": {
46            "description": "https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/learn\/models#foundation_models",
47            "inputTokens": 8192,
48            "inputTokenPrice": 0.35,
49            "outputTokens": 8192,
50            "outputTokenPrice": 1.05
51        },
52        "gemini-gemma-2-9b-it": {
53            "description": "https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/learn\/models#foundation_models",
54            "inputTokens": 8192,
55            "inputTokenPrice": 0.35,
56            "outputTokens": 8192,
57            "outputTokenPrice": 1.05
58        },
59        "gemma-3-27b-it": {
60            "description": "https:\/\/aistudio.google.com",
61            "inputTokens": 131072,
62            "inputTokenPrice": 0,
63            "outputTokens": 8192,
64            "outputTokenPrice": 0
65        },
66        "gemini-2.5-flash-lite": {
67            "description": "https:\/\/ai.google.dev\/gemini-api\/docs\/models#gemini-2.5-flash-lite",
68            "inputTokens": 1048576,
69            "inputTokenPrice": 0.1,
70            "outputTokens": 65535,
71            "outputTokenPrice": 0.4
72        },
73        "gemini-flash-latest": {
74            "description": "https:\/\/developers.googleblog.com\/en\/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release\/",
75            "inputTokens": 1048576,
76            "inputTokenPrice": 0.3,
77            "outputTokens": 65535,
78            "outputTokenPrice": 2.5
79        },
80        "gemini-flash-lite-latest": {
81            "description": "https:\/\/developers.googleblog.com\/en\/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release\/",
82            "inputTokens": 1048576,
83            "inputTokenPrice": 0.1,
84            "outputTokens": 65535,
85            "outputTokenPrice": 0.4
86        },
87        "gemini-2.5-flash-native-audio-latest": {
88            "description": "https:\/\/ai.google.dev\/pricing",
89            "inputTokens": 1048576,
90            "inputTokenPrice": 0.3,
91            "outputTokens": 8192,
92            "outputTokenPrice": 2.5
93        },
94        "gemini-pro-latest": {
95            "description": "https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/pricing",
96            "inputTokens": 1048576,
97            "inputTokenPrice": 1.25,
98            "outputTokens": 65535,
99            "outputTokenPrice": 10
100        }
101    },
102    "embedding": {
103        "text-embedding-004": {
104            "description": "Achieves a stronger retrieval performance and outperforms existing models with comparable dimensions, on the standard MTEB embedding benchmarks",
105            "inputTokens": 2048,
106            "inputTokenPrice": 0.00625,
107            "dimensions": 768
108        },
109        "embedding-001": {
110            "description": "Older embedding model",
111            "inputTokens": 2048,
112            "inputTokenPrice": 0.00625,
113            "dimensions": 768
114        },
115        "gemini-1.5-flash": {
116            "description": "https:\/\/ai.google.dev\/gemini-api\/docs\/embeddings#multimodal",
117            "inputTokens": 8192,
118            "inputTokenPrice": 0.08,
119            "dimensions": 1536
120        }
121    }
122}