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