1{
2 "name": "Azure OpenAI",
3 "id": "azure",
4 "type": "azure",
5 "api_key": "$AZURE_OPENAI_API_KEY",
6 "api_endpoint": "$AZURE_OPENAI_API_ENDPOINT",
7 "default_large_model_id": "o4-mini",
8 "default_small_model_id": "gpt-4o",
9 "models": [
10 {
11 "id": "codex-mini-latest",
12 "model": "Codex Mini",
13 "cost_per_1m_in": 1.5,
14 "cost_per_1m_out": 6,
15 "cost_per_1m_in_cached": 0,
16 "cost_per_1m_out_cached": 0.375,
17 "context_window": 200000,
18 "default_max_tokens": 100000,
19 "can_reason": false,
20 "supports_attachments": true
21 },
22 {
23 "id": "o4-mini",
24 "model": "o4 Mini",
25 "cost_per_1m_in": 1.1,
26 "cost_per_1m_out": 4.4,
27 "cost_per_1m_in_cached": 0,
28 "cost_per_1m_out_cached": 0.275,
29 "context_window": 200000,
30 "default_max_tokens": 100000,
31 "can_reason": false,
32 "supports_attachments": true
33 },
34 {
35 "id": "o3",
36 "model": "o3",
37 "cost_per_1m_in": 2,
38 "cost_per_1m_out": 8,
39 "cost_per_1m_in_cached": 0,
40 "cost_per_1m_out_cached": 0.5,
41 "context_window": 200000,
42 "default_max_tokens": 100000,
43 "can_reason": false,
44 "supports_attachments": true
45 },
46 {
47 "id": "o3-pro",
48 "model": "o3 Pro",
49 "cost_per_1m_in": 20,
50 "cost_per_1m_out": 80,
51 "cost_per_1m_in_cached": 0,
52 "cost_per_1m_out_cached": 0,
53 "context_window": 200000,
54 "default_max_tokens": 100000,
55 "can_reason": false,
56 "supports_attachments": true
57 },
58 {
59 "id": "gpt-4.1",
60 "model": "GPT-4.1",
61 "cost_per_1m_in": 2,
62 "cost_per_1m_out": 8,
63 "cost_per_1m_in_cached": 0,
64 "cost_per_1m_out_cached": 0.5,
65 "context_window": 1047576,
66 "default_max_tokens": 32768,
67 "can_reason": false,
68 "supports_attachments": true
69 },
70 {
71 "id": "gpt-4.1-mini",
72 "model": "GPT-4.1 Mini",
73 "cost_per_1m_in": 0.39999999999999997,
74 "cost_per_1m_out": 1.5999999999999999,
75 "cost_per_1m_in_cached": 0,
76 "cost_per_1m_out_cached": 0.09999999999999999,
77 "context_window": 1047576,
78 "default_max_tokens": 32768,
79 "can_reason": false,
80 "supports_attachments": true
81 },
82 {
83 "id": "gpt-4.1-nano",
84 "model": "GPT-4.1 Nano",
85 "cost_per_1m_in": 0.09999999999999999,
86 "cost_per_1m_out": 0.39999999999999997,
87 "cost_per_1m_in_cached": 0,
88 "cost_per_1m_out_cached": 0.024999999999999998,
89 "context_window": 1047576,
90 "default_max_tokens": 32768,
91 "can_reason": false,
92 "supports_attachments": true
93 },
94 {
95 "id": "gpt-4.5-preview",
96 "model": "GPT-4.5 (Preview)",
97 "cost_per_1m_in": 75,
98 "cost_per_1m_out": 150,
99 "cost_per_1m_in_cached": 0,
100 "cost_per_1m_out_cached": 37.5,
101 "context_window": 128000,
102 "default_max_tokens": 16384,
103 "can_reason": false,
104 "supports_attachments": true
105 },
106 {
107 "id": "o3-mini",
108 "model": "o3 Mini",
109 "cost_per_1m_in": 1.1,
110 "cost_per_1m_out": 4.4,
111 "cost_per_1m_in_cached": 0,
112 "cost_per_1m_out_cached": 0.55,
113 "context_window": 200000,
114 "default_max_tokens": 100000,
115 "can_reason": false,
116 "supports_attachments": false
117 },
118 {
119 "id": "gpt-4o",
120 "model": "GPT-4o",
121 "cost_per_1m_in": 2.5,
122 "cost_per_1m_out": 10,
123 "cost_per_1m_in_cached": 0,
124 "cost_per_1m_out_cached": 1.25,
125 "context_window": 128000,
126 "default_max_tokens": 16384,
127 "can_reason": false,
128 "supports_attachments": true
129 },
130 {
131 "id": "gpt-4o-mini",
132 "model": "GPT-4o-mini",
133 "cost_per_1m_in": 0.15,
134 "cost_per_1m_out": 0.6,
135 "cost_per_1m_in_cached": 0,
136 "cost_per_1m_out_cached": 0.075,
137 "context_window": 128000,
138 "default_max_tokens": 16384,
139 "can_reason": false,
140 "reasoning_effort": "",
141 "supports_attachments": true
142 }
143 ]
144}