indoxrouter 0.1.2__py3-none-any.whl → 0.1.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (36) hide show
  1. indoxrouter-0.1.3.dist-info/METADATA +188 -0
  2. indoxrouter-0.1.3.dist-info/RECORD +4 -0
  3. indoxrouter-0.1.3.dist-info/top_level.txt +1 -0
  4. indoxRouter/__init__.py +0 -83
  5. indoxRouter/client.py +0 -632
  6. indoxRouter/client_resourses/__init__.py +0 -20
  7. indoxRouter/client_resourses/base.py +0 -67
  8. indoxRouter/client_resourses/chat.py +0 -144
  9. indoxRouter/client_resourses/completion.py +0 -138
  10. indoxRouter/client_resourses/embedding.py +0 -83
  11. indoxRouter/client_resourses/image.py +0 -116
  12. indoxRouter/client_resourses/models.py +0 -114
  13. indoxRouter/config.py +0 -151
  14. indoxRouter/constants/__init__.py +0 -81
  15. indoxRouter/exceptions/__init__.py +0 -70
  16. indoxRouter/models/__init__.py +0 -111
  17. indoxRouter/providers/__init__.py +0 -108
  18. indoxRouter/providers/ai21labs.json +0 -128
  19. indoxRouter/providers/base_provider.py +0 -101
  20. indoxRouter/providers/claude.json +0 -164
  21. indoxRouter/providers/cohere.json +0 -116
  22. indoxRouter/providers/databricks.json +0 -110
  23. indoxRouter/providers/deepseek.json +0 -110
  24. indoxRouter/providers/google.json +0 -128
  25. indoxRouter/providers/meta.json +0 -128
  26. indoxRouter/providers/mistral.json +0 -146
  27. indoxRouter/providers/nvidia.json +0 -110
  28. indoxRouter/providers/openai.json +0 -308
  29. indoxRouter/providers/openai.py +0 -521
  30. indoxRouter/providers/qwen.json +0 -110
  31. indoxRouter/utils/__init__.py +0 -240
  32. indoxrouter-0.1.2.dist-info/LICENSE +0 -21
  33. indoxrouter-0.1.2.dist-info/METADATA +0 -259
  34. indoxrouter-0.1.2.dist-info/RECORD +0 -33
  35. indoxrouter-0.1.2.dist-info/top_level.txt +0 -1
  36. {indoxrouter-0.1.2.dist-info → indoxrouter-0.1.3.dist-info}/WHEEL +0 -0
@@ -1,128 +0,0 @@
1
- [
2
- {
3
- "number": "1",
4
- "modelName": "gemini-1.5-pro",
5
- "name": "Gemini 1.5 Pro",
6
- "type": "Text Generation",
7
- "inputPricePer1KTokens": 0.0025,
8
- "outputPricePer1KTokens": 0.0075,
9
- "description": "Gemini 1.5 Pro is Google's advanced multimodal model with strong reasoning and creative capabilities. Supports text, images, audio, video inputs, and offers extensive context handling.",
10
- "contextWindows": "1M Tokens",
11
- "recommended": true,
12
- "commercial": true,
13
- "pricey": false,
14
- "output": "8192 Tokens",
15
- "comments": "Google's primary model with massive context window and multimodal capabilities.",
16
- "companyModelName": "Google : Gemini 1.5 Pro",
17
- "promptTemplate": "User: %1\nModel: %2",
18
- "systemPrompt": ""
19
- },
20
- {
21
- "number": "2",
22
- "modelName": "gemini-1.5-flash",
23
- "name": "Gemini 1.5 Flash",
24
- "type": "Text Generation",
25
- "inputPricePer1KTokens": 0.0005,
26
- "outputPricePer1KTokens": 0.0015,
27
- "description": "Gemini 1.5 Flash is designed for efficiency while maintaining strong capabilities. Ideal for applications requiring quick responses and cost effectiveness.",
28
- "contextWindows": "1M Tokens",
29
- "recommended": true,
30
- "commercial": true,
31
- "pricey": false,
32
- "output": "8192 Tokens",
33
- "comments": "Fast and affordable model with large context window.",
34
- "companyModelName": "Google : Gemini 1.5 Flash",
35
- "promptTemplate": "User: %1\nModel: %2",
36
- "systemPrompt": ""
37
- },
38
- {
39
- "number": "3",
40
- "modelName": "gemini-1.5-ultra",
41
- "name": "Gemini 1.5 Ultra",
42
- "type": "Text Generation",
43
- "inputPricePer1KTokens": 0.01,
44
- "outputPricePer1KTokens": 0.03,
45
- "description": "Gemini 1.5 Ultra is Google's most powerful model, offering superior reasoning, problem-solving, and creative capabilities. Best for complex enterprise applications requiring top-tier performance.",
46
- "contextWindows": "1M Tokens",
47
- "recommended": true,
48
- "commercial": true,
49
- "pricey": true,
50
- "output": "8192 Tokens",
51
- "comments": "Google's most capable model for demanding enterprise applications.",
52
- "companyModelName": "Google : Gemini 1.5 Ultra",
53
- "promptTemplate": "User: %1\nModel: %2",
54
- "systemPrompt": ""
55
- },
56
- {
57
- "number": "4",
58
- "modelName": "gemini-1.0-pro",
59
- "name": "Gemini 1.0 Pro",
60
- "type": "Text Generation",
61
- "inputPricePer1KTokens": 0.0025,
62
- "outputPricePer1KTokens": 0.0075,
63
- "description": "Gemini 1.0 Pro is Google's previous generation model. Offers good general capabilities for text and image inputs but with a smaller context window than 1.5 models.",
64
- "contextWindows": "32k Tokens",
65
- "recommended": false,
66
- "commercial": true,
67
- "pricey": false,
68
- "output": "8192 Tokens",
69
- "comments": "Previous generation model, recommended to upgrade to 1.5 series.",
70
- "companyModelName": "Google : Gemini 1.0 Pro",
71
- "promptTemplate": "User: %1\nModel: %2",
72
- "systemPrompt": ""
73
- },
74
- {
75
- "number": "5",
76
- "modelName": "gemini-1.0-ultra",
77
- "name": "Gemini 1.0 Ultra",
78
- "type": "Text Generation",
79
- "inputPricePer1KTokens": 0.01,
80
- "outputPricePer1KTokens": 0.03,
81
- "description": "Gemini 1.0 Ultra was Google's previous flagship model. Strong capabilities but superseded by the 1.5 series which offers larger context windows and improved performance.",
82
- "contextWindows": "32k Tokens",
83
- "recommended": false,
84
- "commercial": true,
85
- "pricey": true,
86
- "output": "8192 Tokens",
87
- "comments": "Previous generation flagship model, now replaced by 1.5 Ultra.",
88
- "companyModelName": "Google : Gemini 1.0 Ultra",
89
- "promptTemplate": "User: %1\nModel: %2",
90
- "systemPrompt": ""
91
- },
92
- {
93
- "number": "6",
94
- "modelName": "text-embedding-gecko",
95
- "name": "Text Embedding Gecko",
96
- "type": "Embedding",
97
- "inputPricePer1KTokens": 0.0001,
98
- "outputPricePer1KTokens": 0.0,
99
- "description": "Google's text embedding model optimized for transforming text into vector representations. Suitable for search, classification, and clustering applications.",
100
- "contextWindows": "2048 Tokens",
101
- "recommended": true,
102
- "commercial": true,
103
- "pricey": false,
104
- "output": "N/A",
105
- "comments": "Efficient embedding model for semantic applications.",
106
- "companyModelName": "Google : Text Embedding Gecko",
107
- "promptTemplate": "",
108
- "systemPrompt": ""
109
- },
110
- {
111
- "number": "7",
112
- "modelName": "text-embedding-004",
113
- "name": "Text Embedding 004",
114
- "type": "Embedding",
115
- "inputPricePer1KTokens": 0.0002,
116
- "outputPricePer1KTokens": 0.0,
117
- "description": "Google's advanced embedding model offering improved performance over Gecko. Creates high-quality vector representations for enhanced semantic understanding.",
118
- "contextWindows": "8192 Tokens",
119
- "recommended": true,
120
- "commercial": true,
121
- "pricey": false,
122
- "output": "N/A",
123
- "comments": "Enhanced embedding model with larger context window.",
124
- "companyModelName": "Google : Text Embedding 004",
125
- "promptTemplate": "",
126
- "systemPrompt": ""
127
- }
128
- ]
@@ -1,128 +0,0 @@
1
- [
2
- {
3
- "number": "1",
4
- "modelName": "llama-3-70b-instruct",
5
- "name": "Llama 3 70B Instruct",
6
- "type": "Text Generation",
7
- "inputPricePer1KTokens": 0.002,
8
- "outputPricePer1KTokens": 0.006,
9
- "description": "Llama 3 70B Instruct is Meta's largest and most capable instruction-tuned model. Best for complex reasoning, code generation, and creative tasks requiring high-quality outputs.",
10
- "contextWindows": "128k Tokens",
11
- "recommended": true,
12
- "commercial": true,
13
- "pricey": false,
14
- "output": "4096 Tokens",
15
- "comments": "Meta's flagship model with best overall performance.",
16
- "companyModelName": "Meta AI : Llama 3 70B Instruct",
17
- "promptTemplate": "<|system|>\n%system\n<|user|>\n%1<|assistant|>\n%2",
18
- "systemPrompt": "You are a helpful assistant."
19
- },
20
- {
21
- "number": "2",
22
- "modelName": "llama-3-8b-instruct",
23
- "name": "Llama 3 8B Instruct",
24
- "type": "Text Generation",
25
- "inputPricePer1KTokens": 0.0004,
26
- "outputPricePer1KTokens": 0.0012,
27
- "description": "Llama 3 8B Instruct is Meta's compact model optimized for efficiency and responsiveness. Good balance of capabilities and performance for less complex tasks.",
28
- "contextWindows": "128k Tokens",
29
- "recommended": true,
30
- "commercial": true,
31
- "pricey": false,
32
- "output": "4096 Tokens",
33
- "comments": "Efficient model with strong performance for its size.",
34
- "companyModelName": "Meta AI : Llama 3 8B Instruct",
35
- "promptTemplate": "<|system|>\n%system\n<|user|>\n%1<|assistant|>\n%2",
36
- "systemPrompt": "You are a helpful assistant."
37
- },
38
- {
39
- "number": "3",
40
- "modelName": "llama-3-70b",
41
- "name": "Llama 3 70B",
42
- "type": "Text Generation",
43
- "inputPricePer1KTokens": 0.0017,
44
- "outputPricePer1KTokens": 0.0051,
45
- "description": "Base (non-instruct) version of Llama 3 70B. Provides the raw capabilities without specific instruction tuning. Suitable for fine-tuning for specialized applications.",
46
- "contextWindows": "128k Tokens",
47
- "recommended": false,
48
- "commercial": true,
49
- "pricey": false,
50
- "output": "4096 Tokens",
51
- "comments": "Base model variant best for custom fine-tuning.",
52
- "companyModelName": "Meta AI : Llama 3 70B",
53
- "promptTemplate": "",
54
- "systemPrompt": ""
55
- },
56
- {
57
- "number": "4",
58
- "modelName": "llama-3-8b",
59
- "name": "Llama 3 8B",
60
- "type": "Text Generation",
61
- "inputPricePer1KTokens": 0.00035,
62
- "outputPricePer1KTokens": 0.00105,
63
- "description": "Base (non-instruct) version of Llama 3 8B. Compact model ideal for fine-tuning for specialized tasks where efficiency is important.",
64
- "contextWindows": "128k Tokens",
65
- "recommended": false,
66
- "commercial": true,
67
- "pricey": false,
68
- "output": "4096 Tokens",
69
- "comments": "Smaller base model variant for efficient custom applications.",
70
- "companyModelName": "Meta AI : Llama 3 8B",
71
- "promptTemplate": "",
72
- "systemPrompt": ""
73
- },
74
- {
75
- "number": "5",
76
- "modelName": "llama-2-70b-chat",
77
- "name": "Llama 2 70B Chat",
78
- "type": "Text Generation",
79
- "inputPricePer1KTokens": 0.0015,
80
- "outputPricePer1KTokens": 0.0045,
81
- "description": "Llama 2 70B Chat is Meta's previous generation large conversational model. Still capable but superseded by Llama 3 models with improved capabilities.",
82
- "contextWindows": "4k Tokens",
83
- "recommended": false,
84
- "commercial": true,
85
- "pricey": false,
86
- "output": "4096 Tokens",
87
- "comments": "Previous generation model with smaller context window.",
88
- "companyModelName": "Meta AI : Llama 2 70B Chat",
89
- "promptTemplate": "<s>[INST] %1 [/INST] %2",
90
- "systemPrompt": ""
91
- },
92
- {
93
- "number": "6",
94
- "modelName": "llama-2-13b-chat",
95
- "name": "Llama 2 13B Chat",
96
- "type": "Text Generation",
97
- "inputPricePer1KTokens": 0.0007,
98
- "outputPricePer1KTokens": 0.0021,
99
- "description": "Medium-sized conversational model from the Llama 2 series. More efficient than the 70B variant but with reduced capabilities.",
100
- "contextWindows": "4k Tokens",
101
- "recommended": false,
102
- "commercial": true,
103
- "pricey": false,
104
- "output": "4096 Tokens",
105
- "comments": "Mid-tier previous generation model.",
106
- "companyModelName": "Meta AI : Llama 2 13B Chat",
107
- "promptTemplate": "<s>[INST] %1 [/INST] %2",
108
- "systemPrompt": ""
109
- },
110
- {
111
- "number": "7",
112
- "modelName": "llama-2-7b-chat",
113
- "name": "Llama 2 7B Chat",
114
- "type": "Text Generation",
115
- "inputPricePer1KTokens": 0.0003,
116
- "outputPricePer1KTokens": 0.0009,
117
- "description": "Smallest conversational model in the Llama 2 series. Designed for efficiency and speed with reduced capabilities.",
118
- "contextWindows": "4k Tokens",
119
- "recommended": false,
120
- "commercial": true,
121
- "pricey": false,
122
- "output": "4096 Tokens",
123
- "comments": "Smallest previous generation model, now superseded by Llama 3 8B.",
124
- "companyModelName": "Meta AI : Llama 2 7B Chat",
125
- "promptTemplate": "<s>[INST] %1 [/INST] %2",
126
- "systemPrompt": ""
127
- }
128
- ]
@@ -1,146 +0,0 @@
1
- [
2
- {
3
- "number": "1",
4
- "modelName": "mistral-large-2407",
5
- "name": "Mistral Large (2407)",
6
- "type": "Text Generation",
7
- "inputPricePer1KTokens": 0.0075,
8
- "outputPricePer1KTokens": 0.0225,
9
- "description": "Mistral Large is Mistral AI's most powerful model, optimized for complex reasoning, coding, and creative generation tasks. It offers advanced capabilities with strong performance across a wide range of use cases.",
10
- "contextWindows": "128k Tokens",
11
- "recommended": true,
12
- "commercial": true,
13
- "pricey": true,
14
- "output": "8192 Tokens",
15
- "comments": "Mistral's flagship model with strongest overall capabilities.",
16
- "companyModelName": "Mistral AI : Mistral Large (2407)",
17
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
18
- "systemPrompt": ""
19
- },
20
- {
21
- "number": "2",
22
- "modelName": "mistral-medium-2407",
23
- "name": "Mistral Medium (2407)",
24
- "type": "Text Generation",
25
- "inputPricePer1KTokens": 0.0027,
26
- "outputPricePer1KTokens": 0.0081,
27
- "description": "Mistral Medium balances performance and cost efficiency. Designed for general-purpose applications requiring strong reasoning and text generation with good overall quality.",
28
- "contextWindows": "128k Tokens",
29
- "recommended": true,
30
- "commercial": true,
31
- "pricey": false,
32
- "output": "8192 Tokens",
33
- "comments": "Well-balanced model for most production use cases.",
34
- "companyModelName": "Mistral AI : Mistral Medium (2407)",
35
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
36
- "systemPrompt": ""
37
- },
38
- {
39
- "number": "3",
40
- "modelName": "mistral-small-2402",
41
- "name": "Mistral Small (2402)",
42
- "type": "Text Generation",
43
- "inputPricePer1KTokens": 0.0002,
44
- "outputPricePer1KTokens": 0.0006,
45
- "description": "Mistral Small is optimized for high throughput and efficiency. Offers good performance for simpler tasks at a very competitive price point, making it suitable for cost-sensitive applications.",
46
- "contextWindows": "128k Tokens",
47
- "recommended": true,
48
- "commercial": true,
49
- "pricey": false,
50
- "output": "8192 Tokens",
51
- "comments": "Excellent price-performance ratio for everyday tasks.",
52
- "companyModelName": "Mistral AI : Mistral Small (2402)",
53
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
54
- "systemPrompt": ""
55
- },
56
- {
57
- "number": "4",
58
- "modelName": "open-mistral-7b",
59
- "name": "Open Mistral 7B",
60
- "type": "Text Generation",
61
- "inputPricePer1KTokens": 0.00015,
62
- "outputPricePer1KTokens": 0.00045,
63
- "description": "Open Mistral 7B is an open-weight model offering good performance for basic text generation tasks. Cost-effective for simple applications or when budget constraints are important.",
64
- "contextWindows": "32k Tokens",
65
- "recommended": false,
66
- "commercial": true,
67
- "pricey": false,
68
- "output": "8192 Tokens",
69
- "comments": "Entry-level model, good for simple tasks and prototyping.",
70
- "companyModelName": "Mistral AI : Open Mistral 7B",
71
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
72
- "systemPrompt": ""
73
- },
74
- {
75
- "number": "5",
76
- "modelName": "open-mixtral-8x7b",
77
- "name": "Open Mixtral 8x7B",
78
- "type": "Text Generation",
79
- "inputPricePer1KTokens": 0.0004,
80
- "outputPricePer1KTokens": 0.0012,
81
- "description": "Open Mixtral 8x7B is a mixture-of-experts model with significantly improved capabilities over the 7B model. Offers strong performance for various tasks at a competitive price point.",
82
- "contextWindows": "32k Tokens",
83
- "recommended": true,
84
- "commercial": true,
85
- "pricey": false,
86
- "output": "8192 Tokens",
87
- "comments": "Strong open-weight model with mixture-of-experts architecture.",
88
- "companyModelName": "Mistral AI : Open Mixtral 8x7B",
89
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
90
- "systemPrompt": ""
91
- },
92
- {
93
- "number": "6",
94
- "modelName": "mistral-embed",
95
- "name": "Mistral Embed",
96
- "type": "Embedding",
97
- "inputPricePer1KTokens": 0.0001,
98
- "outputPricePer1KTokens": 0.0,
99
- "description": "Mistral Embed is an embedding model that transforms text into high-quality vector representations. Suitable for semantic search, clustering, and other NLP applications requiring text embeddings.",
100
- "contextWindows": "8k Tokens",
101
- "recommended": true,
102
- "commercial": true,
103
- "pricey": false,
104
- "output": "N/A",
105
- "comments": "Efficient embedding model for semantic search and retrieval applications.",
106
- "companyModelName": "Mistral AI : Mistral Embed",
107
- "promptTemplate": "",
108
- "systemPrompt": ""
109
- },
110
- {
111
- "number": "7",
112
- "modelName": "mistral-large-2402",
113
- "name": "Mistral Large (2402)",
114
- "type": "Text Generation",
115
- "inputPricePer1KTokens": 0.006,
116
- "outputPricePer1KTokens": 0.018,
117
- "description": "Previous version of Mistral Large. Still offers strong capabilities across reasoning, writing, and coding tasks, but has been superseded by the 2407 version.",
118
- "contextWindows": "32k Tokens",
119
- "recommended": false,
120
- "commercial": true,
121
- "pricey": true,
122
- "output": "8192 Tokens",
123
- "comments": "Previous generation flagship model.",
124
- "companyModelName": "Mistral AI : Mistral Large (2402)",
125
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
126
- "systemPrompt": ""
127
- },
128
- {
129
- "number": "8",
130
- "modelName": "mistral-medium-2312",
131
- "name": "Mistral Medium (2312)",
132
- "type": "Text Generation",
133
- "inputPricePer1KTokens": 0.0024,
134
- "outputPricePer1KTokens": 0.0072,
135
- "description": "Earlier version of Mistral Medium. Provides decent general-purpose capabilities with good efficiency, but newer versions offer improved performance.",
136
- "contextWindows": "32k Tokens",
137
- "recommended": false,
138
- "commercial": true,
139
- "pricey": false,
140
- "output": "8192 Tokens",
141
- "comments": "Previous generation medium model.",
142
- "companyModelName": "Mistral AI : Mistral Medium (2312)",
143
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
144
- "systemPrompt": ""
145
- }
146
- ]
@@ -1,110 +0,0 @@
1
- [
2
- {
3
- "number": "1",
4
- "modelName": "nvidia-tensorrt-llm-mixtral-8x7b-instruct",
5
- "name": "TensorRT-LLM Mixtral 8x7B Instruct",
6
- "type": "Text Generation",
7
- "inputPricePer1KTokens": 0.0005,
8
- "outputPricePer1KTokens": 0.0015,
9
- "description": "NVIDIA's optimized version of Mixtral 8x7B Instruct, accelerated with TensorRT-LLM for high throughput and low latency.",
10
- "contextWindows": "32k Tokens",
11
- "recommended": true,
12
- "commercial": true,
13
- "pricey": false,
14
- "output": "4096 Tokens",
15
- "comments": "Optimized for enterprise deployment on NVIDIA hardware.",
16
- "companyModelName": "NVIDIA : TensorRT-LLM Mixtral 8x7B Instruct",
17
- "promptTemplate": "<s>[INST] %1 [/INST] %2 </s>",
18
- "systemPrompt": ""
19
- },
20
- {
21
- "number": "2",
22
- "modelName": "nvidia-nemotron-4-340b-instruct",
23
- "name": "Nemotron-4 340B Instruct",
24
- "type": "Text Generation",
25
- "inputPricePer1KTokens": 0.003,
26
- "outputPricePer1KTokens": 0.009,
27
- "description": "NVIDIA's largest instruction-tuned model with 340B parameters, designed for advanced reasoning and complex tasks.",
28
- "contextWindows": "128k Tokens",
29
- "recommended": true,
30
- "commercial": true,
31
- "pricey": true,
32
- "output": "8192 Tokens",
33
- "comments": "State-of-the-art model for complex enterprise applications.",
34
- "companyModelName": "NVIDIA : Nemotron-4 340B Instruct",
35
- "promptTemplate": "<|user|>\n%1<|assistant|>\n%2",
36
- "systemPrompt": ""
37
- },
38
- {
39
- "number": "3",
40
- "modelName": "nvidia-nemotron-4-340b-base",
41
- "name": "Nemotron-4 340B Base",
42
- "type": "Text Generation",
43
- "inputPricePer1KTokens": 0.002,
44
- "outputPricePer1KTokens": 0.006,
45
- "description": "Base version of NVIDIA's 340B parameter model for custom fine-tuning and specialized applications.",
46
- "contextWindows": "128k Tokens",
47
- "recommended": false,
48
- "commercial": true,
49
- "pricey": true,
50
- "output": "8192 Tokens",
51
- "comments": "Suitable for custom fine-tuning on enterprise data.",
52
- "companyModelName": "NVIDIA : Nemotron-4 340B Base",
53
- "promptTemplate": "<|user|>\n%1<|assistant|>\n%2",
54
- "systemPrompt": ""
55
- },
56
- {
57
- "number": "4",
58
- "modelName": "nvidia-aicc-llama3-70b",
59
- "name": "AI Compute Cloud Llama 3 70B",
60
- "type": "Text Generation",
61
- "inputPricePer1KTokens": 0.0015,
62
- "outputPricePer1KTokens": 0.0045,
63
- "description": "NVIDIA AI Compute Cloud optimized version of Llama 3 70B, tuned for enterprise deployment.",
64
- "contextWindows": "128k Tokens",
65
- "recommended": true,
66
- "commercial": true,
67
- "pricey": false,
68
- "output": "4096 Tokens",
69
- "comments": "High-performance model with NVIDIA acceleration.",
70
- "companyModelName": "NVIDIA : AI Compute Cloud Llama 3 70B",
71
- "promptTemplate": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n%2<|eot_id|>",
72
- "systemPrompt": ""
73
- },
74
- {
75
- "number": "5",
76
- "modelName": "nvidia-nemo-sirius-8b",
77
- "name": "NeMo Sirius 8B",
78
- "type": "Text Generation",
79
- "inputPricePer1KTokens": 0.0002,
80
- "outputPricePer1KTokens": 0.0006,
81
- "description": "Compact and efficient model from NVIDIA's NeMo framework, optimized for edge and on-premise deployment.",
82
- "contextWindows": "16k Tokens",
83
- "recommended": true,
84
- "commercial": true,
85
- "pricey": false,
86
- "output": "4096 Tokens",
87
- "comments": "Excellent for on-premise and edge computing use cases.",
88
- "companyModelName": "NVIDIA : NeMo Sirius 8B",
89
- "promptTemplate": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>",
90
- "systemPrompt": ""
91
- },
92
- {
93
- "number": "6",
94
- "modelName": "nvidia-picasso-vision",
95
- "name": "Picasso Vision",
96
- "type": "Text and Vision",
97
- "inputPricePer1KTokens": 0.0025,
98
- "outputPricePer1KTokens": 0.0075,
99
- "description": "NVIDIA's multimodal model capable of understanding and reasoning about images and text together.",
100
- "contextWindows": "32k Tokens",
101
- "recommended": true,
102
- "commercial": true,
103
- "pricey": false,
104
- "output": "4096 Tokens",
105
- "comments": "Advanced vision capabilities for enterprise applications.",
106
- "companyModelName": "NVIDIA : Picasso Vision",
107
- "promptTemplate": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>",
108
- "systemPrompt": ""
109
- }
110
- ]