model-library 0.1.6__py3-none-any.whl → 0.1.8__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.
- model_library/base/base.py +237 -62
- model_library/base/delegate_only.py +86 -9
- model_library/base/input.py +10 -7
- model_library/base/output.py +48 -0
- model_library/base/utils.py +56 -7
- model_library/config/alibaba_models.yaml +44 -57
- model_library/config/all_models.json +253 -126
- model_library/config/kimi_models.yaml +30 -3
- model_library/config/openai_models.yaml +15 -23
- model_library/config/zai_models.yaml +24 -3
- model_library/exceptions.py +14 -77
- model_library/logging.py +6 -2
- model_library/providers/ai21labs.py +30 -14
- model_library/providers/alibaba.py +17 -8
- model_library/providers/amazon.py +119 -64
- model_library/providers/anthropic.py +184 -104
- model_library/providers/azure.py +22 -10
- model_library/providers/cohere.py +7 -7
- model_library/providers/deepseek.py +8 -8
- model_library/providers/fireworks.py +7 -8
- model_library/providers/google/batch.py +17 -13
- model_library/providers/google/google.py +130 -73
- model_library/providers/inception.py +7 -7
- model_library/providers/kimi.py +18 -8
- model_library/providers/minimax.py +30 -13
- model_library/providers/mistral.py +61 -35
- model_library/providers/openai.py +219 -93
- model_library/providers/openrouter.py +34 -0
- model_library/providers/perplexity.py +7 -7
- model_library/providers/together.py +7 -8
- model_library/providers/vals.py +16 -9
- model_library/providers/xai.py +157 -144
- model_library/providers/zai.py +38 -8
- model_library/register_models.py +4 -2
- model_library/registry_utils.py +39 -15
- model_library/retriers/__init__.py +0 -0
- model_library/retriers/backoff.py +73 -0
- model_library/retriers/base.py +225 -0
- model_library/retriers/token.py +427 -0
- model_library/retriers/utils.py +11 -0
- model_library/settings.py +1 -1
- model_library/utils.py +13 -35
- {model_library-0.1.6.dist-info → model_library-0.1.8.dist-info}/METADATA +4 -3
- model_library-0.1.8.dist-info/RECORD +70 -0
- {model_library-0.1.6.dist-info → model_library-0.1.8.dist-info}/WHEEL +1 -1
- model_library-0.1.6.dist-info/RECORD +0 -64
- {model_library-0.1.6.dist-info → model_library-0.1.8.dist-info}/licenses/LICENSE +0 -0
- {model_library-0.1.6.dist-info → model_library-0.1.8.dist-info}/top_level.txt +0 -0
|
@@ -1,4 +1,184 @@
|
|
|
1
1
|
{
|
|
2
|
+
"kimi/kimi-k2.5-thinking": {
|
|
3
|
+
"company": "Moonshot AI",
|
|
4
|
+
"label": "Kimi K2.5",
|
|
5
|
+
"description": null,
|
|
6
|
+
"release_date": "2026-01-26",
|
|
7
|
+
"open_source": true,
|
|
8
|
+
"documentation_url": "https://platform.moonshot.ai/docs",
|
|
9
|
+
"properties": {
|
|
10
|
+
"context_window": 262144,
|
|
11
|
+
"max_tokens": 128000,
|
|
12
|
+
"training_cutoff": null,
|
|
13
|
+
"reasoning_model": true
|
|
14
|
+
},
|
|
15
|
+
"supports": {
|
|
16
|
+
"images": true,
|
|
17
|
+
"files": false,
|
|
18
|
+
"temperature": false,
|
|
19
|
+
"tools": true
|
|
20
|
+
},
|
|
21
|
+
"metadata": {
|
|
22
|
+
"deprecated": false,
|
|
23
|
+
"available_for_everyone": true,
|
|
24
|
+
"available_as_evaluator": false,
|
|
25
|
+
"ignored_for_cost": false
|
|
26
|
+
},
|
|
27
|
+
"provider_properties": {},
|
|
28
|
+
"costs_per_million_token": {
|
|
29
|
+
"input": 0.6,
|
|
30
|
+
"output": 3.0,
|
|
31
|
+
"cache": {
|
|
32
|
+
"read": 0.1,
|
|
33
|
+
"write_markup": 1.0
|
|
34
|
+
}
|
|
35
|
+
},
|
|
36
|
+
"alternative_keys": [],
|
|
37
|
+
"default_parameters": {
|
|
38
|
+
"temperature": 1.0,
|
|
39
|
+
"top_p": 0.95
|
|
40
|
+
},
|
|
41
|
+
"provider_endpoint": "kimi-k2.5",
|
|
42
|
+
"provider_name": "kimi",
|
|
43
|
+
"full_key": "kimi/kimi-k2.5-thinking",
|
|
44
|
+
"slug": "kimi_kimi-k2.5-thinking"
|
|
45
|
+
},
|
|
46
|
+
"kimi/kimi-k2.5": {
|
|
47
|
+
"company": "Moonshot AI",
|
|
48
|
+
"label": "Kimi K2.5",
|
|
49
|
+
"description": null,
|
|
50
|
+
"release_date": "2026-01-26",
|
|
51
|
+
"open_source": true,
|
|
52
|
+
"documentation_url": "https://platform.moonshot.ai/docs",
|
|
53
|
+
"properties": {
|
|
54
|
+
"context_window": 262144,
|
|
55
|
+
"max_tokens": 128000,
|
|
56
|
+
"training_cutoff": null,
|
|
57
|
+
"reasoning_model": false
|
|
58
|
+
},
|
|
59
|
+
"supports": {
|
|
60
|
+
"images": true,
|
|
61
|
+
"files": false,
|
|
62
|
+
"temperature": false,
|
|
63
|
+
"tools": true
|
|
64
|
+
},
|
|
65
|
+
"metadata": {
|
|
66
|
+
"deprecated": false,
|
|
67
|
+
"available_for_everyone": true,
|
|
68
|
+
"available_as_evaluator": false,
|
|
69
|
+
"ignored_for_cost": false
|
|
70
|
+
},
|
|
71
|
+
"provider_properties": {},
|
|
72
|
+
"costs_per_million_token": {
|
|
73
|
+
"input": 0.6,
|
|
74
|
+
"output": 3.0,
|
|
75
|
+
"cache": {
|
|
76
|
+
"read": 0.1,
|
|
77
|
+
"write_markup": 1.0
|
|
78
|
+
}
|
|
79
|
+
},
|
|
80
|
+
"alternative_keys": [
|
|
81
|
+
{
|
|
82
|
+
"kimi/kimi-k2.5-thinking": {
|
|
83
|
+
"properties": {
|
|
84
|
+
"reasoning_model": true
|
|
85
|
+
},
|
|
86
|
+
"default_parameters": {
|
|
87
|
+
"temperature": 1.0
|
|
88
|
+
}
|
|
89
|
+
}
|
|
90
|
+
}
|
|
91
|
+
],
|
|
92
|
+
"default_parameters": {
|
|
93
|
+
"temperature": 0.6,
|
|
94
|
+
"top_p": 0.95
|
|
95
|
+
},
|
|
96
|
+
"provider_endpoint": "kimi-k2.5",
|
|
97
|
+
"provider_name": "kimi",
|
|
98
|
+
"full_key": "kimi/kimi-k2.5",
|
|
99
|
+
"slug": "kimi_kimi-k2.5"
|
|
100
|
+
},
|
|
101
|
+
"alibaba/qwen3-max-2026-01-23": {
|
|
102
|
+
"company": "Alibaba",
|
|
103
|
+
"label": "Qwen 3 Max Thinking",
|
|
104
|
+
"description": "Qwen 3 Max with enhanced reasoning capabilities",
|
|
105
|
+
"release_date": "2026-01-23",
|
|
106
|
+
"open_source": false,
|
|
107
|
+
"properties": {
|
|
108
|
+
"context_window": 256000,
|
|
109
|
+
"max_tokens": 32000,
|
|
110
|
+
"training_cutoff": null,
|
|
111
|
+
"reasoning_model": true
|
|
112
|
+
},
|
|
113
|
+
"supports": {
|
|
114
|
+
"images": false,
|
|
115
|
+
"temperature": true,
|
|
116
|
+
"tools": true
|
|
117
|
+
},
|
|
118
|
+
"metadata": {
|
|
119
|
+
"deprecated": false,
|
|
120
|
+
"available_for_everyone": false,
|
|
121
|
+
"available_as_evaluator": false,
|
|
122
|
+
"ignored_for_cost": false
|
|
123
|
+
},
|
|
124
|
+
"provider_properties": {},
|
|
125
|
+
"costs_per_million_token": {},
|
|
126
|
+
"alternative_keys": [],
|
|
127
|
+
"default_parameters": {
|
|
128
|
+
"temperature": 0.7
|
|
129
|
+
},
|
|
130
|
+
"provider_endpoint": "qwen3-max-2026-01-23",
|
|
131
|
+
"provider_name": "alibaba",
|
|
132
|
+
"full_key": "alibaba/qwen3-max-2026-01-23",
|
|
133
|
+
"slug": "alibaba_qwen3-max-2026-01-23"
|
|
134
|
+
},
|
|
135
|
+
"zai/glm-4.7-flashx": {
|
|
136
|
+
"company": "zAI",
|
|
137
|
+
"label": "GLM 4.7 Flash",
|
|
138
|
+
"description": "z.AI lightweight fast model",
|
|
139
|
+
"release_date": "2026-01-19",
|
|
140
|
+
"open_source": true,
|
|
141
|
+
"documentation_url": "https://docs.z.ai/",
|
|
142
|
+
"properties": {
|
|
143
|
+
"context_window": 200000,
|
|
144
|
+
"max_tokens": 128000,
|
|
145
|
+
"training_cutoff": null,
|
|
146
|
+
"reasoning_model": true
|
|
147
|
+
},
|
|
148
|
+
"supports": {
|
|
149
|
+
"images": false,
|
|
150
|
+
"files": false,
|
|
151
|
+
"temperature": true,
|
|
152
|
+
"tools": true
|
|
153
|
+
},
|
|
154
|
+
"metadata": {
|
|
155
|
+
"deprecated": false,
|
|
156
|
+
"available_for_everyone": true,
|
|
157
|
+
"available_as_evaluator": false,
|
|
158
|
+
"ignored_for_cost": false
|
|
159
|
+
},
|
|
160
|
+
"provider_properties": {
|
|
161
|
+
"clear_thinking": false
|
|
162
|
+
},
|
|
163
|
+
"costs_per_million_token": {
|
|
164
|
+
"input": 0.07,
|
|
165
|
+
"output": 0.4,
|
|
166
|
+
"cache": {
|
|
167
|
+
"read": 0.01,
|
|
168
|
+
"read_discount": 1.0,
|
|
169
|
+
"write_markup": 1.0
|
|
170
|
+
}
|
|
171
|
+
},
|
|
172
|
+
"alternative_keys": [],
|
|
173
|
+
"default_parameters": {
|
|
174
|
+
"temperature": 1.0,
|
|
175
|
+
"top_p": 0.95
|
|
176
|
+
},
|
|
177
|
+
"provider_endpoint": "glm-4.7-flashx",
|
|
178
|
+
"provider_name": "zai",
|
|
179
|
+
"full_key": "zai/glm-4.7-flashx",
|
|
180
|
+
"slug": "zai_glm-4.7-flashx"
|
|
181
|
+
},
|
|
2
182
|
"minimax/MiniMax-M2.1": {
|
|
3
183
|
"company": "MiniMax",
|
|
4
184
|
"label": "MiniMax-M2.1",
|
|
@@ -229,6 +409,54 @@
|
|
|
229
409
|
"full_key": "openai/gpt-5.2-pro",
|
|
230
410
|
"slug": "openai_gpt-5.2-pro"
|
|
231
411
|
},
|
|
412
|
+
"openai/gpt-5.2-codex": {
|
|
413
|
+
"company": "OpenAI",
|
|
414
|
+
"label": "GPT 5.2 Codex",
|
|
415
|
+
"description": "GPT 5.2 optimized for code",
|
|
416
|
+
"release_date": "2025-12-11",
|
|
417
|
+
"open_source": false,
|
|
418
|
+
"documentation_url": "https://platform.openai.com/docs/models/gpt-5.2-codex",
|
|
419
|
+
"properties": {
|
|
420
|
+
"context_window": 400000,
|
|
421
|
+
"max_tokens": 128000,
|
|
422
|
+
"training_cutoff": "2024-09",
|
|
423
|
+
"reasoning_model": true
|
|
424
|
+
},
|
|
425
|
+
"supports": {
|
|
426
|
+
"images": true,
|
|
427
|
+
"files": true,
|
|
428
|
+
"batch": true,
|
|
429
|
+
"temperature": false,
|
|
430
|
+
"tools": true
|
|
431
|
+
},
|
|
432
|
+
"metadata": {
|
|
433
|
+
"deprecated": false,
|
|
434
|
+
"available_for_everyone": false,
|
|
435
|
+
"available_as_evaluator": false,
|
|
436
|
+
"ignored_for_cost": false
|
|
437
|
+
},
|
|
438
|
+
"provider_properties": {},
|
|
439
|
+
"costs_per_million_token": {
|
|
440
|
+
"input": 1.75,
|
|
441
|
+
"output": 14.0,
|
|
442
|
+
"cache": {
|
|
443
|
+
"read": 0.175,
|
|
444
|
+
"write_markup": 1.0
|
|
445
|
+
},
|
|
446
|
+
"batch": {
|
|
447
|
+
"input_discount": 0.5,
|
|
448
|
+
"output_discount": 0.5
|
|
449
|
+
}
|
|
450
|
+
},
|
|
451
|
+
"alternative_keys": [],
|
|
452
|
+
"default_parameters": {
|
|
453
|
+
"reasoning_effort": "high"
|
|
454
|
+
},
|
|
455
|
+
"provider_endpoint": "gpt-5.2-codex",
|
|
456
|
+
"provider_name": "openai",
|
|
457
|
+
"full_key": "openai/gpt-5.2-codex",
|
|
458
|
+
"slug": "openai_gpt-5.2-codex"
|
|
459
|
+
},
|
|
232
460
|
"openai/gpt-5.2-2025-12-11": {
|
|
233
461
|
"company": "OpenAI",
|
|
234
462
|
"label": "GPT 5.2",
|
|
@@ -408,7 +636,7 @@
|
|
|
408
636
|
"openai/gpt-5.1-codex-max": {
|
|
409
637
|
"company": "OpenAI",
|
|
410
638
|
"label": "GPT 5.1 Codex Max",
|
|
411
|
-
"description": "
|
|
639
|
+
"description": "GPT 5.1 optimized for code",
|
|
412
640
|
"release_date": "2025-12-04",
|
|
413
641
|
"open_source": false,
|
|
414
642
|
"documentation_url": "",
|
|
@@ -921,7 +1149,7 @@
|
|
|
921
1149
|
"openai/gpt-5.1-codex": {
|
|
922
1150
|
"company": "OpenAI",
|
|
923
1151
|
"label": "GPT 5.1 Codex",
|
|
924
|
-
"description": "
|
|
1152
|
+
"description": "GPT 5.1 optimized for code",
|
|
925
1153
|
"release_date": "2025-11-13",
|
|
926
1154
|
"open_source": false,
|
|
927
1155
|
"documentation_url": "https://platform.openai.com/docs/models/gpt-5.1-codex",
|
|
@@ -1015,7 +1243,7 @@
|
|
|
1015
1243
|
"slug": "openai_gpt-5.1-2025-11-13"
|
|
1016
1244
|
},
|
|
1017
1245
|
"kimi/kimi-k2-thinking": {
|
|
1018
|
-
"company": "
|
|
1246
|
+
"company": "Moonshot AI",
|
|
1019
1247
|
"label": "Kimi K2 Thinking",
|
|
1020
1248
|
"description": null,
|
|
1021
1249
|
"release_date": "2025-11-06",
|
|
@@ -1025,7 +1253,7 @@
|
|
|
1025
1253
|
"context_window": 256000,
|
|
1026
1254
|
"max_tokens": 32000,
|
|
1027
1255
|
"training_cutoff": null,
|
|
1028
|
-
"reasoning_model":
|
|
1256
|
+
"reasoning_model": false
|
|
1029
1257
|
},
|
|
1030
1258
|
"supports": {
|
|
1031
1259
|
"images": false,
|
|
@@ -1058,7 +1286,7 @@
|
|
|
1058
1286
|
}
|
|
1059
1287
|
],
|
|
1060
1288
|
"default_parameters": {
|
|
1061
|
-
"temperature":
|
|
1289
|
+
"temperature": 0.6
|
|
1062
1290
|
},
|
|
1063
1291
|
"provider_endpoint": "kimi-k2-thinking",
|
|
1064
1292
|
"provider_name": "kimi",
|
|
@@ -1102,7 +1330,7 @@
|
|
|
1102
1330
|
"slug": "inception_mercury"
|
|
1103
1331
|
},
|
|
1104
1332
|
"fireworks/kimi-k2-thinking": {
|
|
1105
|
-
"company": "
|
|
1333
|
+
"company": "Moonshot AI",
|
|
1106
1334
|
"label": "Kimi K2 Thinking",
|
|
1107
1335
|
"description": null,
|
|
1108
1336
|
"release_date": "2025-11-06",
|
|
@@ -1112,7 +1340,7 @@
|
|
|
1112
1340
|
"context_window": 256000,
|
|
1113
1341
|
"max_tokens": 32000,
|
|
1114
1342
|
"training_cutoff": null,
|
|
1115
|
-
"reasoning_model":
|
|
1343
|
+
"reasoning_model": false
|
|
1116
1344
|
},
|
|
1117
1345
|
"supports": {
|
|
1118
1346
|
"images": false,
|
|
@@ -1136,7 +1364,7 @@
|
|
|
1136
1364
|
},
|
|
1137
1365
|
"alternative_keys": [],
|
|
1138
1366
|
"default_parameters": {
|
|
1139
|
-
"temperature":
|
|
1367
|
+
"temperature": 0.6
|
|
1140
1368
|
},
|
|
1141
1369
|
"provider_endpoint": "kimi-k2-thinking",
|
|
1142
1370
|
"provider_name": "fireworks",
|
|
@@ -1939,7 +2167,7 @@
|
|
|
1939
2167
|
"temperature": true
|
|
1940
2168
|
},
|
|
1941
2169
|
"metadata": {
|
|
1942
|
-
"deprecated":
|
|
2170
|
+
"deprecated": true,
|
|
1943
2171
|
"available_for_everyone": false,
|
|
1944
2172
|
"available_as_evaluator": false,
|
|
1945
2173
|
"ignored_for_cost": false
|
|
@@ -1982,10 +2210,7 @@
|
|
|
1982
2210
|
"ignored_for_cost": false
|
|
1983
2211
|
},
|
|
1984
2212
|
"provider_properties": {},
|
|
1985
|
-
"costs_per_million_token": {
|
|
1986
|
-
"input": 1.2,
|
|
1987
|
-
"output": 6.0
|
|
1988
|
-
},
|
|
2213
|
+
"costs_per_million_token": {},
|
|
1989
2214
|
"alternative_keys": [],
|
|
1990
2215
|
"default_parameters": {
|
|
1991
2216
|
"temperature": 0.7
|
|
@@ -2019,19 +2244,7 @@
|
|
|
2019
2244
|
"ignored_for_cost": false
|
|
2020
2245
|
},
|
|
2021
2246
|
"provider_properties": {},
|
|
2022
|
-
"costs_per_million_token": {
|
|
2023
|
-
"input": 1.2,
|
|
2024
|
-
"output": 6.0,
|
|
2025
|
-
"cache": {
|
|
2026
|
-
"read_discount": 0.8,
|
|
2027
|
-
"write_markup": 1.0
|
|
2028
|
-
},
|
|
2029
|
-
"context": {
|
|
2030
|
-
"threshold": 32000.0,
|
|
2031
|
-
"input": 2.4,
|
|
2032
|
-
"output": 12.0
|
|
2033
|
-
}
|
|
2034
|
-
},
|
|
2247
|
+
"costs_per_million_token": {},
|
|
2035
2248
|
"alternative_keys": [],
|
|
2036
2249
|
"default_parameters": {
|
|
2037
2250
|
"temperature": 0.7
|
|
@@ -2383,8 +2596,8 @@
|
|
|
2383
2596
|
"properties": {
|
|
2384
2597
|
"context_window": 262144,
|
|
2385
2598
|
"max_tokens": 65536,
|
|
2386
|
-
"training_cutoff":
|
|
2387
|
-
"reasoning_model":
|
|
2599
|
+
"training_cutoff": null,
|
|
2600
|
+
"reasoning_model": true
|
|
2388
2601
|
},
|
|
2389
2602
|
"supports": {
|
|
2390
2603
|
"images": false,
|
|
@@ -2398,10 +2611,7 @@
|
|
|
2398
2611
|
"ignored_for_cost": false
|
|
2399
2612
|
},
|
|
2400
2613
|
"provider_properties": {},
|
|
2401
|
-
"costs_per_million_token": {
|
|
2402
|
-
"input": 1.2,
|
|
2403
|
-
"output": 6.0
|
|
2404
|
-
},
|
|
2614
|
+
"costs_per_million_token": {},
|
|
2405
2615
|
"alternative_keys": [],
|
|
2406
2616
|
"default_parameters": {
|
|
2407
2617
|
"temperature": 0.7
|
|
@@ -3305,9 +3515,14 @@
|
|
|
3305
3515
|
},
|
|
3306
3516
|
"alternative_keys": [
|
|
3307
3517
|
{
|
|
3308
|
-
"
|
|
3309
|
-
"
|
|
3310
|
-
|
|
3518
|
+
"fireworks/glm-4p5": {
|
|
3519
|
+
"metadata": {
|
|
3520
|
+
"deprecated": true
|
|
3521
|
+
},
|
|
3522
|
+
"costs_per_million_token": {
|
|
3523
|
+
"input": 0.55,
|
|
3524
|
+
"output": 2.19
|
|
3525
|
+
}
|
|
3311
3526
|
}
|
|
3312
3527
|
}
|
|
3313
3528
|
],
|
|
@@ -3385,15 +3600,15 @@
|
|
|
3385
3600
|
"tools": true
|
|
3386
3601
|
},
|
|
3387
3602
|
"metadata": {
|
|
3388
|
-
"deprecated":
|
|
3603
|
+
"deprecated": true,
|
|
3389
3604
|
"available_for_everyone": true,
|
|
3390
3605
|
"available_as_evaluator": false,
|
|
3391
3606
|
"ignored_for_cost": false
|
|
3392
3607
|
},
|
|
3393
3608
|
"provider_properties": {},
|
|
3394
3609
|
"costs_per_million_token": {
|
|
3395
|
-
"input": 0.
|
|
3396
|
-
"output": 2.
|
|
3610
|
+
"input": 0.55,
|
|
3611
|
+
"output": 2.19,
|
|
3397
3612
|
"cache": {
|
|
3398
3613
|
"read": 0.11,
|
|
3399
3614
|
"read_discount": 1.0,
|
|
@@ -12286,94 +12501,6 @@
|
|
|
12286
12501
|
"full_key": "azure/gpt-4-turbo-2024-04-09",
|
|
12287
12502
|
"slug": "azure_gpt-4-turbo-2024-04-09"
|
|
12288
12503
|
},
|
|
12289
|
-
"databricks/dbrx-instruct": {
|
|
12290
|
-
"company": "Databricks",
|
|
12291
|
-
"label": "DBRX Instruct",
|
|
12292
|
-
"description": "Databricks Instruct model.",
|
|
12293
|
-
"release_date": "2024-03-27",
|
|
12294
|
-
"open_source": false,
|
|
12295
|
-
"properties": {
|
|
12296
|
-
"context_window": 32768,
|
|
12297
|
-
"max_tokens": 4096,
|
|
12298
|
-
"training_cutoff": "2023-12",
|
|
12299
|
-
"reasoning_model": false
|
|
12300
|
-
},
|
|
12301
|
-
"supports": {
|
|
12302
|
-
"images": false,
|
|
12303
|
-
"files": false,
|
|
12304
|
-
"batch": true,
|
|
12305
|
-
"temperature": true,
|
|
12306
|
-
"tools": true
|
|
12307
|
-
},
|
|
12308
|
-
"metadata": {
|
|
12309
|
-
"deprecated": true,
|
|
12310
|
-
"available_for_everyone": false,
|
|
12311
|
-
"available_as_evaluator": false,
|
|
12312
|
-
"ignored_for_cost": false
|
|
12313
|
-
},
|
|
12314
|
-
"provider_properties": {},
|
|
12315
|
-
"costs_per_million_token": {
|
|
12316
|
-
"input": 2.25,
|
|
12317
|
-
"output": 6.75,
|
|
12318
|
-
"batch": {
|
|
12319
|
-
"input_discount": 0.5,
|
|
12320
|
-
"output_discount": 0.5
|
|
12321
|
-
}
|
|
12322
|
-
},
|
|
12323
|
-
"alternative_keys": [],
|
|
12324
|
-
"default_parameters": {
|
|
12325
|
-
"reasoning_effort": "high"
|
|
12326
|
-
},
|
|
12327
|
-
"provider_endpoint": "databricks-dbrx-instruct",
|
|
12328
|
-
"provider_name": "databricks",
|
|
12329
|
-
"full_key": "databricks/dbrx-instruct",
|
|
12330
|
-
"slug": "databricks_dbrx-instruct"
|
|
12331
|
-
},
|
|
12332
|
-
"databricks/databricks-dbrx-instruct": {
|
|
12333
|
-
"company": "Databricks",
|
|
12334
|
-
"label": "DBRX Instruct",
|
|
12335
|
-
"description": "Databricks Instruct model.",
|
|
12336
|
-
"release_date": "2024-03-27",
|
|
12337
|
-
"open_source": false,
|
|
12338
|
-
"properties": {
|
|
12339
|
-
"context_window": 32768,
|
|
12340
|
-
"max_tokens": 4096,
|
|
12341
|
-
"training_cutoff": "2023-12",
|
|
12342
|
-
"reasoning_model": false
|
|
12343
|
-
},
|
|
12344
|
-
"supports": {
|
|
12345
|
-
"images": false,
|
|
12346
|
-
"files": false,
|
|
12347
|
-
"batch": true,
|
|
12348
|
-
"temperature": true,
|
|
12349
|
-
"tools": true
|
|
12350
|
-
},
|
|
12351
|
-
"metadata": {
|
|
12352
|
-
"deprecated": true,
|
|
12353
|
-
"available_for_everyone": false,
|
|
12354
|
-
"available_as_evaluator": false,
|
|
12355
|
-
"ignored_for_cost": false
|
|
12356
|
-
},
|
|
12357
|
-
"provider_properties": {},
|
|
12358
|
-
"costs_per_million_token": {
|
|
12359
|
-
"input": 2.25,
|
|
12360
|
-
"output": 6.75,
|
|
12361
|
-
"batch": {
|
|
12362
|
-
"input_discount": 0.5,
|
|
12363
|
-
"output_discount": 0.5
|
|
12364
|
-
}
|
|
12365
|
-
},
|
|
12366
|
-
"alternative_keys": [
|
|
12367
|
-
"databricks/dbrx-instruct"
|
|
12368
|
-
],
|
|
12369
|
-
"default_parameters": {
|
|
12370
|
-
"reasoning_effort": "high"
|
|
12371
|
-
},
|
|
12372
|
-
"provider_endpoint": "databricks-dbrx-instruct",
|
|
12373
|
-
"provider_name": "databricks",
|
|
12374
|
-
"full_key": "databricks/databricks-dbrx-instruct",
|
|
12375
|
-
"slug": "databricks_databricks-dbrx-instruct"
|
|
12376
|
-
},
|
|
12377
12504
|
"cohere/command-r-03-2024": {
|
|
12378
12505
|
"company": "Cohere",
|
|
12379
12506
|
"label": "Command R (03/2024)",
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
base-config:
|
|
2
|
-
company:
|
|
2
|
+
company: Moonshot AI
|
|
3
3
|
documentation_url: https://platform.moonshot.ai/docs
|
|
4
4
|
open_source: true
|
|
5
5
|
supports:
|
|
@@ -11,16 +11,43 @@ base-config:
|
|
|
11
11
|
available_for_everyone: true
|
|
12
12
|
ignored_for_cost: false
|
|
13
13
|
|
|
14
|
+
kimi-k2.5-models:
|
|
15
|
+
|
|
16
|
+
kimi/kimi-k2.5:
|
|
17
|
+
label: Kimi K2.5
|
|
18
|
+
release_date: 2026-01-26
|
|
19
|
+
supports:
|
|
20
|
+
images: true
|
|
21
|
+
temperature: false
|
|
22
|
+
properties:
|
|
23
|
+
reasoning_model: false
|
|
24
|
+
context_window: 262_144
|
|
25
|
+
max_tokens: 128_000
|
|
26
|
+
default_parameters:
|
|
27
|
+
temperature: 0.6
|
|
28
|
+
top_p: 0.95
|
|
29
|
+
costs_per_million_token:
|
|
30
|
+
input: 0.6
|
|
31
|
+
output: 3.0
|
|
32
|
+
cache:
|
|
33
|
+
read: 0.1
|
|
34
|
+
alternative_keys:
|
|
35
|
+
- kimi/kimi-k2.5-thinking:
|
|
36
|
+
properties:
|
|
37
|
+
reasoning_model: true
|
|
38
|
+
default_parameters:
|
|
39
|
+
temperature: 1.0
|
|
40
|
+
|
|
14
41
|
kimi-k2-models:
|
|
15
42
|
kimi/kimi-k2-thinking:
|
|
16
43
|
label: Kimi K2 Thinking
|
|
17
44
|
release_date: 2025-11-06
|
|
18
45
|
properties:
|
|
19
|
-
reasoning_model:
|
|
46
|
+
reasoning_model: false
|
|
20
47
|
context_window: 256_000
|
|
21
48
|
max_tokens: 32_000
|
|
22
49
|
default_parameters:
|
|
23
|
-
temperature:
|
|
50
|
+
temperature: 0.6
|
|
24
51
|
costs_per_million_token:
|
|
25
52
|
input: 0.6
|
|
26
53
|
output: 2.5
|
|
@@ -35,6 +35,19 @@ gpt-5-models:
|
|
|
35
35
|
training_cutoff: "2024-09"
|
|
36
36
|
reasoning_model: true
|
|
37
37
|
|
|
38
|
+
openai/gpt-5.2-codex:
|
|
39
|
+
label: GPT 5.2 Codex
|
|
40
|
+
documentation_url: https://platform.openai.com/docs/models/gpt-5.2-codex
|
|
41
|
+
description: GPT 5.2 optimized for code
|
|
42
|
+
release_date: 2025-12-11
|
|
43
|
+
properties:
|
|
44
|
+
context_window: 400_000
|
|
45
|
+
costs_per_million_token:
|
|
46
|
+
input: 1.75
|
|
47
|
+
output: 14
|
|
48
|
+
cache:
|
|
49
|
+
read: 0.175
|
|
50
|
+
|
|
38
51
|
openai/gpt-5.2-2025-12-11:
|
|
39
52
|
label: GPT 5.2
|
|
40
53
|
documentation_url: https://platform.openai.com/docs/models/gpt-5.2
|
|
@@ -70,7 +83,7 @@ gpt-5-models:
|
|
|
70
83
|
openai/gpt-5.1-codex-max:
|
|
71
84
|
label: GPT 5.1 Codex Max
|
|
72
85
|
release_date: 2025-12-04
|
|
73
|
-
description:
|
|
86
|
+
description: GPT 5.1 optimized for code
|
|
74
87
|
costs_per_million_token:
|
|
75
88
|
input: 1.25
|
|
76
89
|
output: 10.0
|
|
@@ -79,7 +92,7 @@ gpt-5-models:
|
|
|
79
92
|
openai/gpt-5.1-codex:
|
|
80
93
|
label: GPT 5.1 Codex
|
|
81
94
|
documentation_url: https://platform.openai.com/docs/models/gpt-5.1-codex
|
|
82
|
-
description:
|
|
95
|
+
description: GPT 5.1 optimized for code
|
|
83
96
|
release_date: 2025-11-13
|
|
84
97
|
costs_per_million_token:
|
|
85
98
|
input: 1.25
|
|
@@ -841,24 +854,3 @@ gpt-3.5-models:
|
|
|
841
854
|
input: 1.5
|
|
842
855
|
output: 2.0
|
|
843
856
|
documentation_url: https://platform.openai.com/docs/models/gpt-3.5-turbo-instruct
|
|
844
|
-
|
|
845
|
-
databricks-models:
|
|
846
|
-
base-config:
|
|
847
|
-
company: Databricks
|
|
848
|
-
|
|
849
|
-
databricks/databricks-dbrx-instruct:
|
|
850
|
-
label: DBRX Instruct
|
|
851
|
-
description: Databricks Instruct model.
|
|
852
|
-
release_date: 2024-03-27
|
|
853
|
-
properties:
|
|
854
|
-
context_window: 32_768
|
|
855
|
-
max_tokens: 4_096
|
|
856
|
-
training_cutoff: "2023-12"
|
|
857
|
-
metadata:
|
|
858
|
-
available_for_everyone: false
|
|
859
|
-
deprecated: true
|
|
860
|
-
costs_per_million_token:
|
|
861
|
-
input: 2.25
|
|
862
|
-
output: 6.75
|
|
863
|
-
alternative_keys:
|
|
864
|
-
- databricks/dbrx-instruct
|
|
@@ -18,6 +18,25 @@ base-config:
|
|
|
18
18
|
write_markup: 1
|
|
19
19
|
|
|
20
20
|
zai-models:
|
|
21
|
+
zai/glm-4.7-flashx:
|
|
22
|
+
label: GLM 4.7 Flash
|
|
23
|
+
description: "z.AI lightweight fast model"
|
|
24
|
+
release_date: 2026-01-19
|
|
25
|
+
properties:
|
|
26
|
+
context_window: 200_000
|
|
27
|
+
max_tokens: 128_000
|
|
28
|
+
costs_per_million_token:
|
|
29
|
+
input: 0.07
|
|
30
|
+
output: 0.4
|
|
31
|
+
cache:
|
|
32
|
+
read: 0.01
|
|
33
|
+
default_parameters:
|
|
34
|
+
# from https://huggingface.co/zai-org/GLM-4.7-Flash
|
|
35
|
+
temperature: 1
|
|
36
|
+
top_p: 0.95
|
|
37
|
+
provider_properties:
|
|
38
|
+
clear_thinking: false
|
|
39
|
+
|
|
21
40
|
zai/glm-4.7:
|
|
22
41
|
label: GLM 4.7
|
|
23
42
|
description: "Latest model from ZAI"
|
|
@@ -46,9 +65,11 @@ zai-models:
|
|
|
46
65
|
read: 0.11
|
|
47
66
|
alternative_keys:
|
|
48
67
|
- fireworks/glm-4p5:
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
68
|
+
metadata:
|
|
69
|
+
deprecated: true
|
|
70
|
+
costs_per_million_token:
|
|
71
|
+
input: 0.55
|
|
72
|
+
output: 2.19
|
|
52
73
|
|
|
53
74
|
zai/glm-4.5-air:
|
|
54
75
|
label: GLM 4.5 Air
|