You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"GLM-4.5 is Zhipu's latest featured model. Its comprehensive capabilities in reasoning, coding, and agent reach the state-of-the-art (SOTA) level among open-source models, with a context length of up to 128k.",
22
23
},
23
-
"glm-4.5-air": {
24
+
"glm-4.6": {
24
25
maxTokens: 98_304,
25
-
contextWindow: 131_072,
26
+
contextWindow: 204_800,
26
27
supportsImages: false,
27
28
supportsPromptCache: true,
28
-
inputPrice: 0.2,
29
-
outputPrice: 1.1,
29
+
inputPrice: 0.6,
30
+
outputPrice: 2.2,
30
31
cacheWritesPrice: 0,
31
-
cacheReadsPrice: 0.03,
32
+
cacheReadsPrice: 0.11,
32
33
description:
33
-
"GLM-4.5-Air is the lightweight version of GLM-4.5. It balances performance and cost-effectiveness, and can flexibly switch to hybrid thinking models.",
34
+
"GLM-4.6 is Zhipu's newest model with an extended context window of up to 200k tokens, providing enhanced capabilities for processing longer documents and conversations.",
"GLM-4.5V is Zhipu's new generation of visual reasoning models based on the MOE architecture.",
45
+
description: "GLM-4.5V is Zhipu's new generation of visual reasoning models based on the MOE architecture.",
46
46
},
47
-
"glm-4.6": {
47
+
"glm-4.5-air": {
48
48
maxTokens: 98_304,
49
-
contextWindow: 204_800,
49
+
contextWindow: 131_072,
50
50
supportsImages: false,
51
51
supportsPromptCache: true,
52
-
inputPrice: 0.6,
53
-
outputPrice: 2.2,
52
+
inputPrice: 0.2,
53
+
outputPrice: 1.1,
54
54
cacheWritesPrice: 0,
55
-
cacheReadsPrice: 0.11,
55
+
cacheReadsPrice: 0.03,
56
56
description:
57
-
"GLM-4.6 is Zhipu's newest model with an extended context window of up to 200k tokens, providing enhanced capabilities for processing longer documents and conversations.",
58
-
}
57
+
"GLM-4.5-Air is the lightweight version of GLM-4.5. It balances performance and cost-effectiveness, and can flexibly switch to hybrid thinking models.",
58
+
},
59
+
"glm-4.5-x": {
60
+
maxTokens: 98_304,
61
+
contextWindow: 131_072,
62
+
supportsImages: false,
63
+
supportsPromptCache: true,
64
+
inputPrice: 2.2,
65
+
outputPrice: 8.9,
66
+
cacheWritesPrice: 0,
67
+
cacheReadsPrice: 0.45,
68
+
description: "GLM-4.5-X is the extended version with enhanced capabilities and performance for complex tasks.",
69
+
},
70
+
"glm-4.5-airx": {
71
+
maxTokens: 98_304,
72
+
contextWindow: 131_072,
73
+
supportsImages: false,
74
+
supportsPromptCache: true,
75
+
inputPrice: 1.1,
76
+
outputPrice: 4.5,
77
+
cacheWritesPrice: 0,
78
+
cacheReadsPrice: 0.22,
79
+
description: "GLM-4.5-AirX is the extended version of GLM-4.5-Air with enhanced capabilities.",
80
+
},
81
+
"glm-4-32b-0414-128k": {
82
+
maxTokens: 98_304,
83
+
contextWindow: 131_072,
84
+
supportsImages: false,
85
+
supportsPromptCache: false,
86
+
inputPrice: 0.1,
87
+
outputPrice: 0.1,
88
+
cacheWritesPrice: 0,
89
+
cacheReadsPrice: 0,
90
+
description: "GLM-4-32B is a 32 billion parameter model with 128k context length, optimized for efficiency.",
91
+
},
92
+
"glm-4.5-flash": {
93
+
maxTokens: 98_304,
94
+
contextWindow: 131_072,
95
+
supportsImages: false,
96
+
supportsPromptCache: false,
97
+
inputPrice: 0,
98
+
outputPrice: 0,
99
+
cacheWritesPrice: 0,
100
+
cacheReadsPrice: 0,
101
+
description: "Zhipu's most advanced free model to date.",
0 commit comments