3780279 · crush · git.iko.soy

9 {

10 "id": "deepseek-v4-flash",

11 "name": "DeepSeek V4 Flash",

12− "cost_per_1m_in": 0.14,

12+ "cost_per_1m_in": 0.1416,

13− "cost_per_1m_out": 0.28,

13+ "cost_per_1m_out": 0.2832,

14− "cost_per_1m_in_cached": 0.07,

14+ "cost_per_1m_in_cached": 0.0708,

15 "cost_per_1m_out_cached": 0,

16 "context_window": 1048576,

17 "default_max_tokens": 104857,

21 {

22 "id": "deepseek-v4-pro",

23 "name": "DeepSeek V4 Pro",

24− "cost_per_1m_in": 1.7562,

24+ "cost_per_1m_in": 1.7422,

25− "cost_per_1m_out": 3.5524,

25+ "cost_per_1m_out": 3.6396,

26− "cost_per_1m_in_cached": 0.8781,

26+ "cost_per_1m_in_cached": 0.8711,

27 "cost_per_1m_out_cached": 0,

28 "context_window": 1048576,

29 "default_max_tokens": 60000,

33 {

34 "id": "gemma-4-26b-a4b-it",

35 "name": "Gemma 4 26B A4B",

36− "cost_per_1m_in": 0.102,

36+ "cost_per_1m_in": 0.12,

37− "cost_per_1m_out": 0.394,

37+ "cost_per_1m_out": 0.408,

38− "cost_per_1m_in_cached": 0.051,

38+ "cost_per_1m_in_cached": 0.06,

39 "cost_per_1m_out_cached": 0,

40 "context_window": 256000,

41 "default_max_tokens": 25600,

57 {

58 "id": "glm-5.1",

59 "name": "GLM-5.1",

60− "cost_per_1m_in": 1.31,

60+ "cost_per_1m_in": 1.33,

61− "cost_per_1m_out": 4.2,

61+ "cost_per_1m_out": 4.22,

62− "cost_per_1m_in_cached": 0.655,

62+ "cost_per_1m_in_cached": 0.665,

63 "cost_per_1m_out_cached": 0,

64 "context_window": 202750,

65 "default_max_tokens": 3276,

69 {

70 "id": "gpt-oss-120b",

71 "name": "gpt-oss-120b",

72− "cost_per_1m_in": 0.166,

72+ "cost_per_1m_in": 0.178,

73− "cost_per_1m_out": 0.632,

73+ "cost_per_1m_out": 0.68,

74− "cost_per_1m_in_cached": 0.083,

74+ "cost_per_1m_in_cached": 0.089,

75 "cost_per_1m_out_cached": 0,

76 "context_window": 131072,

77 "default_max_tokens": 13107,

87 {

88 "id": "kimi-k2.5",

89 "name": "Kimi K2.5",

90− "cost_per_1m_in": 0.552,

90+ "cost_per_1m_in": 0.556,

91− "cost_per_1m_out": 2.84,

91+ "cost_per_1m_out": 2.88,

92− "cost_per_1m_in_cached": 0.276,

92+ "cost_per_1m_in_cached": 0.278,

93 "cost_per_1m_out_cached": 0,

94 "context_window": 262144,

95 "default_max_tokens": 26214,

96 "can_reason": true,

97− "supports_attachments": true

97+ "supports_attachments": false

98 },

99 {

100 "id": "kimi-k2.6",

101 "name": "Kimi K2.6",

102− "cost_per_1m_in": 0.978,

102+ "cost_per_1m_in": 0.918,

103− "cost_per_1m_out": 4.12,

103+ "cost_per_1m_out": 4.151,

104− "cost_per_1m_in_cached": 0.489,

104+ "cost_per_1m_in_cached": 0.459,

105 "cost_per_1m_out_cached": 0,

106 "context_window": 262142,

107 "default_max_tokens": 26214,

108 "can_reason": true,

109− "supports_attachments": true

109+ "supports_attachments": false

110 },

111 {

112 "id": "llama-3.3-70b-instruct",

113 "name": "Llama 3.3 70B Instruct",

114− "cost_per_1m_in": 0.614,

114+ "cost_per_1m_in": 0.638,

115− "cost_per_1m_out": 0.864,

115+ "cost_per_1m_out": 0.768,

116− "cost_per_1m_in_cached": 0.307,

116+ "cost_per_1m_in_cached": 0.319,

117 "cost_per_1m_out_cached": 0,

118 "context_window": 128000,

119 "default_max_tokens": 12800,

130 "context_window": 430000,

131 "default_max_tokens": 43000,

132 "can_reason": true,

133− "supports_attachments": true

133+ "supports_attachments": false

134 },

135 {

136 "id": "minimax-m2.7",

154 "context_window": 128000,

155 "default_max_tokens": 12800,

156 "can_reason": false,

157− "supports_attachments": true

157+ "supports_attachments": false

158 },

159 {

160 "id": "qwen3.6-flash",

195 {

196 "id": "qwen3-coder-480b-a35b-instruct-int4-mixed-ar",

197 "name": "Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",

198− "cost_per_1m_in": 0.769,

198+ "cost_per_1m_in": 0.871,

199− "cost_per_1m_out": 2.235,

199+ "cost_per_1m_out": 2.805,

200− "cost_per_1m_in_cached": 0.3845,

200+ "cost_per_1m_in_cached": 0.4355,

201 "cost_per_1m_out_cached": 0,

202 "context_window": 106000,

203 "default_max_tokens": 10600,

207 {

208 "id": "qwen3-next-80b-a3b-instruct",

209 "name": "Qwen3 Next 80B A3B Instruct",

210− "cost_per_1m_in": 0.1175,

210+ "cost_per_1m_in": 0.128,

211− "cost_per_1m_out": 1.136,

211+ "cost_per_1m_out": 1.28,

212− "cost_per_1m_in_cached": 0.05875,

212+ "cost_per_1m_in_cached": 0.064,

213 "cost_per_1m_out_cached": 0,

214 "context_window": 262144,

215 "default_max_tokens": 26214,