@elyracode/ai 0.9.42 → 0.9.43

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.
@@ -1155,6 +1155,23 @@ export const MODELS = {
1155
1155
  contextWindow: 1000000,
1156
1156
  maxTokens: 128000,
1157
1157
  },
1158
+ "global.moonshotai.kimi-k3": {
1159
+ id: "global.moonshotai.kimi-k3",
1160
+ name: "Kimi K3 (Global)",
1161
+ api: "bedrock-converse-stream",
1162
+ provider: "amazon-bedrock",
1163
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1164
+ reasoning: true,
1165
+ input: ["text", "image"],
1166
+ cost: {
1167
+ input: 3,
1168
+ output: 15,
1169
+ cacheRead: 0.3,
1170
+ cacheWrite: 3.75,
1171
+ },
1172
+ contextWindow: 1048576,
1173
+ maxTokens: 128000,
1174
+ },
1158
1175
  "global.openai.gpt-5.6-luna": {
1159
1176
  id: "global.openai.gpt-5.6-luna",
1160
1177
  name: "GPT-5.6 Luna (Global)",
@@ -1223,6 +1240,40 @@ export const MODELS = {
1223
1240
  contextWindow: 1050000,
1224
1241
  maxTokens: 128000,
1225
1242
  },
1243
+ "global.openai.gpt-6-luna": {
1244
+ id: "global.openai.gpt-6-luna",
1245
+ name: "GPT-6 Luna (Global)",
1246
+ api: "bedrock-converse-stream",
1247
+ provider: "amazon-bedrock",
1248
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1249
+ reasoning: true,
1250
+ input: ["text", "image"],
1251
+ cost: {
1252
+ input: 0.1,
1253
+ output: 0.5,
1254
+ cacheRead: 0.01,
1255
+ cacheWrite: 0.125,
1256
+ },
1257
+ contextWindow: 1050000,
1258
+ maxTokens: 128000,
1259
+ },
1260
+ "global.openai.gpt-6-sol": {
1261
+ id: "global.openai.gpt-6-sol",
1262
+ name: "GPT-6 Sol (Global)",
1263
+ api: "bedrock-converse-stream",
1264
+ provider: "amazon-bedrock",
1265
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1266
+ reasoning: true,
1267
+ input: ["text", "image"],
1268
+ cost: {
1269
+ input: 2,
1270
+ output: 10,
1271
+ cacheRead: 0.2,
1272
+ cacheWrite: 2.5,
1273
+ },
1274
+ contextWindow: 1050000,
1275
+ maxTokens: 128000,
1276
+ },
1226
1277
  "global.xai.grok-4.6": {
1227
1278
  id: "global.xai.grok-4.6",
1228
1279
  name: "Grok 4.6 (Global)",
@@ -1604,7 +1655,7 @@ export const MODELS = {
1604
1655
  cacheRead: 0,
1605
1656
  cacheWrite: 0,
1606
1657
  },
1607
- contextWindow: 204800,
1658
+ contextWindow: 196608,
1608
1659
  maxTokens: 131072,
1609
1660
  },
1610
1661
  "minimax.minimax-m2.5": {
@@ -1638,7 +1689,7 @@ export const MODELS = {
1638
1689
  cacheRead: 0,
1639
1690
  cacheWrite: 0,
1640
1691
  },
1641
- contextWindow: 256000,
1692
+ contextWindow: 262144,
1642
1693
  maxTokens: 8192,
1643
1694
  },
1644
1695
  "mistral.magistral-small-2509": {
@@ -1723,7 +1774,7 @@ export const MODELS = {
1723
1774
  cacheRead: 0,
1724
1775
  cacheWrite: 0,
1725
1776
  },
1726
- contextWindow: 256000,
1777
+ contextWindow: 262144,
1727
1778
  maxTokens: 8192,
1728
1779
  },
1729
1780
  "mistral.pixtral-large-2502-v1:0": {
@@ -1791,7 +1842,7 @@ export const MODELS = {
1791
1842
  cacheRead: 0,
1792
1843
  cacheWrite: 0,
1793
1844
  },
1794
- contextWindow: 262143,
1845
+ contextWindow: 262144,
1795
1846
  maxTokens: 16000,
1796
1847
  },
1797
1848
  "moonshotai.kimi-k2.5": {
@@ -1808,7 +1859,7 @@ export const MODELS = {
1808
1859
  cacheRead: 0,
1809
1860
  cacheWrite: 0,
1810
1861
  },
1811
- contextWindow: 262143,
1862
+ contextWindow: 262144,
1812
1863
  maxTokens: 16384,
1813
1864
  },
1814
1865
  "nvidia.nemotron-nano-12b-v2": {
@@ -1825,7 +1876,7 @@ export const MODELS = {
1825
1876
  cacheRead: 0,
1826
1877
  cacheWrite: 0,
1827
1878
  },
1828
- contextWindow: 128000,
1879
+ contextWindow: 131072,
1829
1880
  maxTokens: 8192,
1830
1881
  },
1831
1882
  "nvidia.nemotron-nano-3-30b": {
@@ -1894,7 +1945,7 @@ export const MODELS = {
1894
1945
  cacheRead: 0.275,
1895
1946
  cacheWrite: 0,
1896
1947
  },
1897
- contextWindow: 272000,
1948
+ contextWindow: 1000000,
1898
1949
  maxTokens: 128000,
1899
1950
  },
1900
1951
  "openai.gpt-5.5": {
@@ -1912,7 +1963,7 @@ export const MODELS = {
1912
1963
  cacheRead: 0.55,
1913
1964
  cacheWrite: 0,
1914
1965
  },
1915
- contextWindow: 272000,
1966
+ contextWindow: 1000000,
1916
1967
  maxTokens: 128000,
1917
1968
  },
1918
1969
  "openai.gpt-5.6-luna": {
@@ -1983,6 +2034,40 @@ export const MODELS = {
1983
2034
  contextWindow: 1050000,
1984
2035
  maxTokens: 128000,
1985
2036
  },
2037
+ "openai.gpt-6-luna": {
2038
+ id: "openai.gpt-6-luna",
2039
+ name: "GPT-6 Luna",
2040
+ api: "bedrock-converse-stream",
2041
+ provider: "amazon-bedrock",
2042
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2043
+ reasoning: true,
2044
+ input: ["text", "image"],
2045
+ cost: {
2046
+ input: 0.11,
2047
+ output: 0.55,
2048
+ cacheRead: 0.011,
2049
+ cacheWrite: 0.1375,
2050
+ },
2051
+ contextWindow: 1050000,
2052
+ maxTokens: 128000,
2053
+ },
2054
+ "openai.gpt-6-sol": {
2055
+ id: "openai.gpt-6-sol",
2056
+ name: "GPT-6 Sol",
2057
+ api: "bedrock-converse-stream",
2058
+ provider: "amazon-bedrock",
2059
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2060
+ reasoning: true,
2061
+ input: ["text", "image"],
2062
+ cost: {
2063
+ input: 2.2,
2064
+ output: 11,
2065
+ cacheRead: 0.22,
2066
+ cacheWrite: 2.75,
2067
+ },
2068
+ contextWindow: 1050000,
2069
+ maxTokens: 128000,
2070
+ },
1986
2071
  "openai.gpt-oss-120b": {
1987
2072
  id: "openai.gpt-oss-120b",
1988
2073
  name: "gpt-oss-120b",
@@ -1997,8 +2082,8 @@ export const MODELS = {
1997
2082
  cacheRead: 0,
1998
2083
  cacheWrite: 0,
1999
2084
  },
2000
- contextWindow: 128000,
2001
- maxTokens: 16384,
2085
+ contextWindow: 131072,
2086
+ maxTokens: 131072,
2002
2087
  },
2003
2088
  "openai.gpt-oss-120b-1:0": {
2004
2089
  id: "openai.gpt-oss-120b-1:0",
@@ -2014,8 +2099,8 @@ export const MODELS = {
2014
2099
  cacheRead: 0,
2015
2100
  cacheWrite: 0,
2016
2101
  },
2017
- contextWindow: 128000,
2018
- maxTokens: 16384,
2102
+ contextWindow: 131072,
2103
+ maxTokens: 128000,
2019
2104
  },
2020
2105
  "openai.gpt-oss-20b": {
2021
2106
  id: "openai.gpt-oss-20b",
@@ -2031,8 +2116,8 @@ export const MODELS = {
2031
2116
  cacheRead: 0,
2032
2117
  cacheWrite: 0,
2033
2118
  },
2034
- contextWindow: 128000,
2035
- maxTokens: 16384,
2119
+ contextWindow: 131072,
2120
+ maxTokens: 131072,
2036
2121
  },
2037
2122
  "openai.gpt-oss-20b-1:0": {
2038
2123
  id: "openai.gpt-oss-20b-1:0",
@@ -2048,8 +2133,8 @@ export const MODELS = {
2048
2133
  cacheRead: 0,
2049
2134
  cacheWrite: 0,
2050
2135
  },
2051
- contextWindow: 128000,
2052
- maxTokens: 16384,
2136
+ contextWindow: 131072,
2137
+ maxTokens: 128000,
2053
2138
  },
2054
2139
  "openai.gpt-oss-safeguard-120b": {
2055
2140
  id: "openai.gpt-oss-safeguard-120b",
@@ -2682,6 +2767,23 @@ export const MODELS = {
2682
2767
  contextWindow: 128000,
2683
2768
  maxTokens: 8192,
2684
2769
  },
2770
+ "us.moonshotai.kimi-k3": {
2771
+ id: "us.moonshotai.kimi-k3",
2772
+ name: "Kimi K3 (US)",
2773
+ api: "bedrock-converse-stream",
2774
+ provider: "amazon-bedrock",
2775
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2776
+ reasoning: true,
2777
+ input: ["text", "image"],
2778
+ cost: {
2779
+ input: 3.3,
2780
+ output: 16.5,
2781
+ cacheRead: 0.33,
2782
+ cacheWrite: 4.125,
2783
+ },
2784
+ contextWindow: 1048576,
2785
+ maxTokens: 128000,
2786
+ },
2685
2787
  "us.openai.gpt-5.6-luna": {
2686
2788
  id: "us.openai.gpt-5.6-luna",
2687
2789
  name: "GPT-5.6 Luna (US)",
@@ -2750,6 +2852,40 @@ export const MODELS = {
2750
2852
  contextWindow: 1050000,
2751
2853
  maxTokens: 128000,
2752
2854
  },
2855
+ "us.openai.gpt-6-luna": {
2856
+ id: "us.openai.gpt-6-luna",
2857
+ name: "GPT-6 Luna (US)",
2858
+ api: "bedrock-converse-stream",
2859
+ provider: "amazon-bedrock",
2860
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2861
+ reasoning: true,
2862
+ input: ["text", "image"],
2863
+ cost: {
2864
+ input: 0.11,
2865
+ output: 0.55,
2866
+ cacheRead: 0.011,
2867
+ cacheWrite: 0.1375,
2868
+ },
2869
+ contextWindow: 1050000,
2870
+ maxTokens: 128000,
2871
+ },
2872
+ "us.openai.gpt-6-sol": {
2873
+ id: "us.openai.gpt-6-sol",
2874
+ name: "GPT-6 Sol (US)",
2875
+ api: "bedrock-converse-stream",
2876
+ provider: "amazon-bedrock",
2877
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2878
+ reasoning: true,
2879
+ input: ["text", "image"],
2880
+ cost: {
2881
+ input: 2.2,
2882
+ output: 11,
2883
+ cacheRead: 0.22,
2884
+ cacheWrite: 2.75,
2885
+ },
2886
+ contextWindow: 1050000,
2887
+ maxTokens: 128000,
2888
+ },
2753
2889
  "us.writer.palmyra-x4-v1:0": {
2754
2890
  id: "us.writer.palmyra-x4-v1:0",
2755
2891
  name: "Palmyra X4 (US)",
@@ -2883,7 +3019,7 @@ export const MODELS = {
2883
3019
  cacheRead: 0,
2884
3020
  cacheWrite: 0,
2885
3021
  },
2886
- contextWindow: 204800,
3022
+ contextWindow: 202752,
2887
3023
  maxTokens: 131072,
2888
3024
  },
2889
3025
  "zai.glm-4.7-flash": {
@@ -2900,7 +3036,7 @@ export const MODELS = {
2900
3036
  cacheRead: 0,
2901
3037
  cacheWrite: 0,
2902
3038
  },
2903
- contextWindow: 200000,
3039
+ contextWindow: 202752,
2904
3040
  maxTokens: 131072,
2905
3041
  },
2906
3042
  "zai.glm-5": {
@@ -3750,6 +3886,40 @@ export const MODELS = {
3750
3886
  contextWindow: 1050000,
3751
3887
  maxTokens: 128000,
3752
3888
  },
3889
+ "gpt-6-luna": {
3890
+ id: "gpt-6-luna",
3891
+ name: "GPT-6 Luna",
3892
+ api: "azure-openai-responses",
3893
+ provider: "azure-openai-responses",
3894
+ baseUrl: "",
3895
+ reasoning: true,
3896
+ input: ["text", "image"],
3897
+ cost: {
3898
+ input: 0.1,
3899
+ output: 0.5,
3900
+ cacheRead: 0.01,
3901
+ cacheWrite: 0.125,
3902
+ },
3903
+ contextWindow: 1050000,
3904
+ maxTokens: 128000,
3905
+ },
3906
+ "gpt-6-sol": {
3907
+ id: "gpt-6-sol",
3908
+ name: "GPT-6 Sol",
3909
+ api: "azure-openai-responses",
3910
+ provider: "azure-openai-responses",
3911
+ baseUrl: "",
3912
+ reasoning: true,
3913
+ input: ["text", "image"],
3914
+ cost: {
3915
+ input: 2,
3916
+ output: 10,
3917
+ cacheRead: 0.2,
3918
+ cacheWrite: 2.5,
3919
+ },
3920
+ contextWindow: 1050000,
3921
+ maxTokens: 128000,
3922
+ },
3753
3923
  "gpt-realtime-2.1": {
3754
3924
  id: "gpt-realtime-2.1",
3755
3925
  name: "GPT-Realtime-2.1",
@@ -4048,6 +4218,23 @@ export const MODELS = {
4048
4218
  contextWindow: 1000000,
4049
4219
  maxTokens: 128000,
4050
4220
  },
4221
+ "claude-opus-5.5": {
4222
+ id: "claude-opus-5.5",
4223
+ name: "Claude Opus 5.5",
4224
+ api: "anthropic-messages",
4225
+ provider: "cloudflare-ai-gateway",
4226
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4227
+ reasoning: true,
4228
+ input: ["text", "image"],
4229
+ cost: {
4230
+ input: 4,
4231
+ output: 20,
4232
+ cacheRead: 0.2,
4233
+ cacheWrite: 5,
4234
+ },
4235
+ contextWindow: 1000000,
4236
+ maxTokens: 128000,
4237
+ },
4051
4238
  "claude-sonnet-4.5": {
4052
4239
  id: "claude-sonnet-4.5",
4053
4240
  name: "Claude Sonnet 4.5 (latest)",
@@ -4435,6 +4622,40 @@ export const MODELS = {
4435
4622
  contextWindow: 1050000,
4436
4623
  maxTokens: 128000,
4437
4624
  },
4625
+ "gpt-6-luna": {
4626
+ id: "gpt-6-luna",
4627
+ name: "GPT-6 Luna",
4628
+ api: "openai-responses",
4629
+ provider: "cloudflare-ai-gateway",
4630
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4631
+ reasoning: true,
4632
+ input: ["text", "image"],
4633
+ cost: {
4634
+ input: 0.1,
4635
+ output: 0.5,
4636
+ cacheRead: 0.01,
4637
+ cacheWrite: 0.125,
4638
+ },
4639
+ contextWindow: 1050000,
4640
+ maxTokens: 128000,
4641
+ },
4642
+ "gpt-6-sol": {
4643
+ id: "gpt-6-sol",
4644
+ name: "GPT-6 Sol",
4645
+ api: "openai-responses",
4646
+ provider: "cloudflare-ai-gateway",
4647
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4648
+ reasoning: true,
4649
+ input: ["text", "image"],
4650
+ cost: {
4651
+ input: 2,
4652
+ output: 10,
4653
+ cacheRead: 0.2,
4654
+ cacheWrite: 2.5,
4655
+ },
4656
+ contextWindow: 1050000,
4657
+ maxTokens: 128000,
4658
+ },
4438
4659
  "o3": {
4439
4660
  id: "o3",
4440
4661
  name: "o3",
@@ -4941,6 +5162,23 @@ export const MODELS = {
4941
5162
  contextWindow: 1000000,
4942
5163
  maxTokens: 384000,
4943
5164
  },
5165
+ "accounts/fireworks/models/ember-1": {
5166
+ id: "accounts/fireworks/models/ember-1",
5167
+ name: "Ember-1",
5168
+ api: "anthropic-messages",
5169
+ provider: "fireworks",
5170
+ baseUrl: "https://api.fireworks.ai/inference",
5171
+ reasoning: true,
5172
+ input: ["text", "image"],
5173
+ cost: {
5174
+ input: 3,
5175
+ output: 15,
5176
+ cacheRead: 0.3,
5177
+ cacheWrite: 0,
5178
+ },
5179
+ contextWindow: 1048576,
5180
+ maxTokens: 131072,
5181
+ },
4944
5182
  "accounts/fireworks/models/glm-5p2": {
4945
5183
  id: "accounts/fireworks/models/glm-5p2",
4946
5184
  name: "GLM 5.2",
@@ -5535,6 +5773,25 @@ export const MODELS = {
5535
5773
  contextWindow: 1000000,
5536
5774
  maxTokens: 64000,
5537
5775
  },
5776
+ "claude-opus-5.5": {
5777
+ id: "claude-opus-5.5",
5778
+ name: "Claude Opus 5.5",
5779
+ api: "openai-completions",
5780
+ provider: "github-copilot",
5781
+ baseUrl: "https://api.individual.githubcopilot.com",
5782
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
5783
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5784
+ reasoning: true,
5785
+ input: ["text", "image"],
5786
+ cost: {
5787
+ input: 4,
5788
+ output: 20,
5789
+ cacheRead: 0.2,
5790
+ cacheWrite: 5,
5791
+ },
5792
+ contextWindow: 1000000,
5793
+ maxTokens: 128000,
5794
+ },
5538
5795
  "claude-sonnet-4.6": {
5539
5796
  id: "claude-sonnet-4.6",
5540
5797
  name: "Claude Sonnet 4.6",
@@ -5838,6 +6095,44 @@ export const MODELS = {
5838
6095
  contextWindow: 1050000,
5839
6096
  maxTokens: 128000,
5840
6097
  },
6098
+ "gpt-6-luna": {
6099
+ id: "gpt-6-luna",
6100
+ name: "GPT-6 Luna",
6101
+ api: "openai-completions",
6102
+ provider: "github-copilot",
6103
+ baseUrl: "https://api.individual.githubcopilot.com",
6104
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
6105
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6106
+ reasoning: true,
6107
+ input: ["text", "image"],
6108
+ cost: {
6109
+ input: 0.1,
6110
+ output: 0.5,
6111
+ cacheRead: 0.01,
6112
+ cacheWrite: 0.125,
6113
+ },
6114
+ contextWindow: 1050000,
6115
+ maxTokens: 128000,
6116
+ },
6117
+ "gpt-6-sol": {
6118
+ id: "gpt-6-sol",
6119
+ name: "GPT-6 Sol",
6120
+ api: "openai-completions",
6121
+ provider: "github-copilot",
6122
+ baseUrl: "https://api.individual.githubcopilot.com",
6123
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
6124
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6125
+ reasoning: true,
6126
+ input: ["text", "image"],
6127
+ cost: {
6128
+ input: 2,
6129
+ output: 10,
6130
+ cacheRead: 0.2,
6131
+ cacheWrite: 2.5,
6132
+ },
6133
+ contextWindow: 1050000,
6134
+ maxTokens: 128000,
6135
+ },
5841
6136
  "grok-4.5": {
5842
6137
  id: "grok-4.5",
5843
6138
  name: "Grok 4.5",
@@ -6021,8 +6316,8 @@ export const MODELS = {
6021
6316
  cacheRead: 0,
6022
6317
  cacheWrite: 0,
6023
6318
  },
6024
- contextWindow: 131072,
6025
- maxTokens: 65536,
6319
+ contextWindow: 128000,
6320
+ maxTokens: 64000,
6026
6321
  },
6027
6322
  "gemini-2.5-flash": {
6028
6323
  id: "gemini-2.5-flash",
@@ -6127,7 +6422,7 @@ export const MODELS = {
6127
6422
  cacheWrite: 0,
6128
6423
  },
6129
6424
  contextWindow: 65536,
6130
- maxTokens: 65536,
6425
+ maxTokens: 4096,
6131
6426
  },
6132
6427
  "gemini-3.1-flash-lite-preview": {
6133
6428
  id: "gemini-3.1-flash-lite-preview",
@@ -8185,7 +8480,7 @@ export const MODELS = {
8185
8480
  cacheRead: 0.06,
8186
8481
  cacheWrite: 0,
8187
8482
  },
8188
- contextWindow: 1048576,
8483
+ contextWindow: 1000000,
8189
8484
  maxTokens: 512000,
8190
8485
  },
8191
8486
  },
@@ -8238,7 +8533,7 @@ export const MODELS = {
8238
8533
  cacheRead: 0.06,
8239
8534
  cacheWrite: 0,
8240
8535
  },
8241
- contextWindow: 1048576,
8536
+ contextWindow: 1000000,
8242
8537
  maxTokens: 512000,
8243
8538
  },
8244
8539
  },
@@ -8876,7 +9171,7 @@ export const MODELS = {
8876
9171
  cacheWrite: 0,
8877
9172
  },
8878
9173
  contextWindow: 1048576,
8879
- maxTokens: 131072,
9174
+ maxTokens: 1048576,
8880
9175
  },
8881
9176
  },
8882
9177
  "moonshotai-cn": {
@@ -8950,7 +9245,7 @@ export const MODELS = {
8950
9245
  cacheWrite: 0,
8951
9246
  },
8952
9247
  contextWindow: 1048576,
8953
- maxTokens: 131072,
9248
+ maxTokens: 1048576,
8954
9249
  },
8955
9250
  },
8956
9251
  "openai": {
@@ -9505,6 +9800,40 @@ export const MODELS = {
9505
9800
  contextWindow: 1050000,
9506
9801
  maxTokens: 128000,
9507
9802
  },
9803
+ "gpt-6-luna": {
9804
+ id: "gpt-6-luna",
9805
+ name: "GPT-6 Luna",
9806
+ api: "openai-responses",
9807
+ provider: "openai",
9808
+ baseUrl: "https://api.openai.com/v1",
9809
+ reasoning: true,
9810
+ input: ["text", "image"],
9811
+ cost: {
9812
+ input: 0.1,
9813
+ output: 0.5,
9814
+ cacheRead: 0.01,
9815
+ cacheWrite: 0.125,
9816
+ },
9817
+ contextWindow: 1050000,
9818
+ maxTokens: 128000,
9819
+ },
9820
+ "gpt-6-sol": {
9821
+ id: "gpt-6-sol",
9822
+ name: "GPT-6 Sol",
9823
+ api: "openai-responses",
9824
+ provider: "openai",
9825
+ baseUrl: "https://api.openai.com/v1",
9826
+ reasoning: true,
9827
+ input: ["text", "image"],
9828
+ cost: {
9829
+ input: 2,
9830
+ output: 10,
9831
+ cacheRead: 0.2,
9832
+ cacheWrite: 2.5,
9833
+ },
9834
+ contextWindow: 1050000,
9835
+ maxTokens: 128000,
9836
+ },
9508
9837
  "gpt-realtime-2.1": {
9509
9838
  id: "gpt-realtime-2.1",
9510
9839
  name: "GPT-Realtime-2.1",
@@ -9964,6 +10293,23 @@ export const MODELS = {
9964
10293
  contextWindow: 1000000,
9965
10294
  maxTokens: 128000,
9966
10295
  },
10296
+ "claude-opus-5-5": {
10297
+ id: "claude-opus-5-5",
10298
+ name: "Claude Opus 5.5",
10299
+ api: "anthropic-messages",
10300
+ provider: "opencode",
10301
+ baseUrl: "https://opencode.ai/zen",
10302
+ reasoning: true,
10303
+ input: ["text", "image"],
10304
+ cost: {
10305
+ input: 4,
10306
+ output: 20,
10307
+ cacheRead: 0.2,
10308
+ cacheWrite: 5,
10309
+ },
10310
+ contextWindow: 1000000,
10311
+ maxTokens: 128000,
10312
+ },
9967
10313
  "claude-sonnet-4": {
9968
10314
  id: "claude-sonnet-4",
9969
10315
  name: "Claude Sonnet 4",
@@ -10678,6 +11024,40 @@ export const MODELS = {
10678
11024
  contextWindow: 1050000,
10679
11025
  maxTokens: 128000,
10680
11026
  },
11027
+ "gpt-6-luna": {
11028
+ id: "gpt-6-luna",
11029
+ name: "GPT-6 Luna",
11030
+ api: "openai-responses",
11031
+ provider: "opencode",
11032
+ baseUrl: "https://opencode.ai/zen/v1",
11033
+ reasoning: true,
11034
+ input: ["text", "image"],
11035
+ cost: {
11036
+ input: 0.1,
11037
+ output: 0.5,
11038
+ cacheRead: 0.01,
11039
+ cacheWrite: 0.125,
11040
+ },
11041
+ contextWindow: 1050000,
11042
+ maxTokens: 128000,
11043
+ },
11044
+ "gpt-6-sol": {
11045
+ id: "gpt-6-sol",
11046
+ name: "GPT-6 Sol",
11047
+ api: "openai-responses",
11048
+ provider: "opencode",
11049
+ baseUrl: "https://opencode.ai/zen/v1",
11050
+ reasoning: true,
11051
+ input: ["text", "image"],
11052
+ cost: {
11053
+ input: 2,
11054
+ output: 10,
11055
+ cacheRead: 0.2,
11056
+ cacheWrite: 2.5,
11057
+ },
11058
+ contextWindow: 1050000,
11059
+ maxTokens: 128000,
11060
+ },
10681
11061
  "grok-4.5": {
10682
11062
  id: "grok-4.5",
10683
11063
  name: "Grok 4.5",
@@ -10712,6 +11092,23 @@ export const MODELS = {
10712
11092
  contextWindow: 500000,
10713
11093
  maxTokens: 500000,
10714
11094
  },
11095
+ "grok-4.7": {
11096
+ id: "grok-4.7",
11097
+ name: "Grok 4.7 (30% Off)",
11098
+ api: "openai-responses",
11099
+ provider: "opencode",
11100
+ baseUrl: "https://opencode.ai/zen/v1",
11101
+ reasoning: true,
11102
+ input: ["text", "image"],
11103
+ cost: {
11104
+ input: 1.4,
11105
+ output: 4.2,
11106
+ cacheRead: 0.35,
11107
+ cacheWrite: 0,
11108
+ },
11109
+ contextWindow: 500000,
11110
+ maxTokens: 500000,
11111
+ },
10715
11112
  "grok-build-0.1": {
10716
11113
  id: "grok-build-0.1",
10717
11114
  name: "Grok Build 0.1",
@@ -11035,6 +11432,23 @@ export const MODELS = {
11035
11432
  contextWindow: 1000000,
11036
11433
  maxTokens: 131072,
11037
11434
  },
11435
+ "space-bunny-free": {
11436
+ id: "space-bunny-free",
11437
+ name: "Space Bunny Free",
11438
+ api: "openai-completions",
11439
+ provider: "opencode",
11440
+ baseUrl: "https://opencode.ai/zen/v1",
11441
+ reasoning: true,
11442
+ input: ["text", "image"],
11443
+ cost: {
11444
+ input: 0,
11445
+ output: 0,
11446
+ cacheRead: 0,
11447
+ cacheWrite: 0,
11448
+ },
11449
+ contextWindow: 1048576,
11450
+ maxTokens: 524288,
11451
+ },
11038
11452
  },
11039
11453
  "opencode-go": {
11040
11454
  "deepseek-v4-flash": {
@@ -11199,6 +11613,23 @@ export const MODELS = {
11199
11613
  contextWindow: 1050000,
11200
11614
  maxTokens: 128000,
11201
11615
  },
11616
+ "gpt-6-luna": {
11617
+ id: "gpt-6-luna",
11618
+ name: "GPT-6 Luna",
11619
+ api: "openai-responses",
11620
+ provider: "opencode-go",
11621
+ baseUrl: "https://opencode.ai/zen/go/v1",
11622
+ reasoning: true,
11623
+ input: ["text", "image"],
11624
+ cost: {
11625
+ input: 0.1,
11626
+ output: 0.5,
11627
+ cacheRead: 0.01,
11628
+ cacheWrite: 0.125,
11629
+ },
11630
+ contextWindow: 1050000,
11631
+ maxTokens: 128000,
11632
+ },
11202
11633
  "grok-4.6": {
11203
11634
  id: "grok-4.6",
11204
11635
  name: "Grok 4.6",
@@ -11557,6 +11988,23 @@ export const MODELS = {
11557
11988
  contextWindow: 1000000,
11558
11989
  maxTokens: 131072,
11559
11990
  },
11991
+ "space-bunny-free": {
11992
+ id: "space-bunny-free",
11993
+ name: "Space Bunny Free",
11994
+ api: "openai-completions",
11995
+ provider: "opencode-go",
11996
+ baseUrl: "https://opencode.ai/zen/go/v1",
11997
+ reasoning: true,
11998
+ input: ["text", "image"],
11999
+ cost: {
12000
+ input: 0,
12001
+ output: 0,
12002
+ cacheRead: 0,
12003
+ cacheWrite: 0,
12004
+ },
12005
+ contextWindow: 1048576,
12006
+ maxTokens: 524288,
12007
+ },
11560
12008
  },
11561
12009
  "openrouter": {
11562
12010
  "aion-labs/aion-2.0": {
@@ -11573,7 +12021,7 @@ export const MODELS = {
11573
12021
  cacheRead: 0.19999999999999998,
11574
12022
  cacheWrite: 0,
11575
12023
  },
11576
- contextWindow: 1048576,
12024
+ contextWindow: 131072,
11577
12025
  maxTokens: 32768,
11578
12026
  },
11579
12027
  "aion-labs/aion-3.0": {
@@ -11590,7 +12038,7 @@ export const MODELS = {
11590
12038
  cacheRead: 0.75,
11591
12039
  cacheWrite: 0,
11592
12040
  },
11593
- contextWindow: 1048576,
12041
+ contextWindow: 131072,
11594
12042
  maxTokens: 32768,
11595
12043
  },
11596
12044
  "aion-labs/aion-3.0-mini": {
@@ -11607,7 +12055,41 @@ export const MODELS = {
11607
12055
  cacheRead: 0.18,
11608
12056
  cacheWrite: 0,
11609
12057
  },
11610
- contextWindow: 1048576,
12058
+ contextWindow: 131072,
12059
+ maxTokens: 32768,
12060
+ },
12061
+ "aion-labs/aion-3.5": {
12062
+ id: "aion-labs/aion-3.5",
12063
+ name: "AionLabs: Aion 3.5",
12064
+ api: "openai-completions",
12065
+ provider: "openrouter",
12066
+ baseUrl: "https://openrouter.ai/api/v1",
12067
+ reasoning: true,
12068
+ input: ["text"],
12069
+ cost: {
12070
+ input: 3,
12071
+ output: 6,
12072
+ cacheRead: 0.75,
12073
+ cacheWrite: 0,
12074
+ },
12075
+ contextWindow: 262144,
12076
+ maxTokens: 32768,
12077
+ },
12078
+ "aion-labs/aion-3.5-mini": {
12079
+ id: "aion-labs/aion-3.5-mini",
12080
+ name: "AionLabs: Aion 3.5 Mini",
12081
+ api: "openai-completions",
12082
+ provider: "openrouter",
12083
+ baseUrl: "https://openrouter.ai/api/v1",
12084
+ reasoning: true,
12085
+ input: ["text"],
12086
+ cost: {
12087
+ input: 0.7,
12088
+ output: 1.4,
12089
+ cacheRead: 0.18,
12090
+ cacheWrite: 0,
12091
+ },
12092
+ contextWindow: 262144,
11611
12093
  maxTokens: 32768,
11612
12094
  },
11613
12095
  "amazon/nova-2-lite-v1": {
@@ -12317,6 +12799,23 @@ export const MODELS = {
12317
12799
  contextWindow: 262144,
12318
12800
  maxTokens: 131072,
12319
12801
  },
12802
+ "cohere/command-a-plus": {
12803
+ id: "cohere/command-a-plus",
12804
+ name: "Cohere: Command A+",
12805
+ api: "openai-completions",
12806
+ provider: "openrouter",
12807
+ baseUrl: "https://openrouter.ai/api/v1",
12808
+ reasoning: true,
12809
+ input: ["text", "image"],
12810
+ cost: {
12811
+ input: 0.3,
12812
+ output: 1.5,
12813
+ cacheRead: 0.15,
12814
+ cacheWrite: 0,
12815
+ },
12816
+ contextWindow: 192000,
12817
+ maxTokens: 64000,
12818
+ },
12320
12819
  "cohere/command-r-08-2024": {
12321
12820
  id: "cohere/command-r-08-2024",
12322
12821
  name: "Cohere: Command R (08-2024)",
@@ -12515,9 +13014,9 @@ export const MODELS = {
12515
13014
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12516
13015
  input: ["text"],
12517
13016
  cost: {
12518
- input: 0.049,
12519
- output: 0.098,
12520
- cacheRead: 0.0098,
13017
+ input: 0.088606,
13018
+ output: 0.177212,
13019
+ cacheRead: 0.017721200000000003,
12521
13020
  cacheWrite: 0,
12522
13021
  },
12523
13022
  contextWindow: 1048576,
@@ -12534,8 +13033,8 @@ export const MODELS = {
12534
13033
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12535
13034
  input: ["text"],
12536
13035
  cost: {
12537
- input: 0.04,
12538
- output: 0.64,
13036
+ input: 0.03,
13037
+ output: 0.32,
12539
13038
  cacheRead: 0.016,
12540
13039
  cacheWrite: 0,
12541
13040
  },
@@ -12572,9 +13071,9 @@ export const MODELS = {
12572
13071
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12573
13072
  input: ["text"],
12574
13073
  cost: {
12575
- input: 0.90741,
12576
- output: 1.81482,
12577
- cacheRead: 0.07561749999999999,
13074
+ input: 0.9396,
13075
+ output: 1.8792,
13076
+ cacheRead: 0.07830000000000001,
12578
13077
  cacheWrite: 0,
12579
13078
  },
12580
13079
  contextWindow: 1048576,
@@ -12591,9 +13090,9 @@ export const MODELS = {
12591
13090
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12592
13091
  input: ["text"],
12593
13092
  cost: {
12594
- input: 0.66,
12595
- output: 1.9800000000000002,
12596
- cacheRead: 0.022,
13093
+ input: 0.46199999999999997,
13094
+ output: 1.386,
13095
+ cacheRead: 0.015399999999999999,
12597
13096
  cacheWrite: 0,
12598
13097
  },
12599
13098
  contextWindow: 1048576,
@@ -12610,13 +13109,13 @@ export const MODELS = {
12610
13109
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12611
13110
  input: ["text", "image"],
12612
13111
  cost: {
12613
- input: 0.15,
12614
- output: 0.6,
12615
- cacheRead: 0.003,
13112
+ input: 0.14,
13113
+ output: 0.42,
13114
+ cacheRead: 0.004200000000000001,
12616
13115
  cacheWrite: 0,
12617
13116
  },
12618
13117
  contextWindow: 1048576,
12619
- maxTokens: 384000,
13118
+ maxTokens: 131072,
12620
13119
  },
12621
13120
  "deepseek/deepseek-v4.1-flash:batch": {
12622
13121
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -12654,6 +13153,23 @@ export const MODELS = {
12654
13153
  contextWindow: 512000,
12655
13154
  maxTokens: 460800,
12656
13155
  },
13156
+ "fireworks/ember-1": {
13157
+ id: "fireworks/ember-1",
13158
+ name: "Fireworks: Ember-1",
13159
+ api: "openai-completions",
13160
+ provider: "openrouter",
13161
+ baseUrl: "https://openrouter.ai/api/v1",
13162
+ reasoning: true,
13163
+ input: ["text", "image"],
13164
+ cost: {
13165
+ input: 3,
13166
+ output: 15,
13167
+ cacheRead: 0.3,
13168
+ cacheWrite: 0,
13169
+ },
13170
+ contextWindow: 1048576,
13171
+ maxTokens: 943718,
13172
+ },
12657
13173
  "google/gemini-2.5-flash": {
12658
13174
  id: "google/gemini-2.5-flash",
12659
13175
  name: "Google: Gemini 2.5 Flash",
@@ -13331,23 +13847,6 @@ export const MODELS = {
13331
13847
  cacheRead: 0.012,
13332
13848
  cacheWrite: 0,
13333
13849
  },
13334
- contextWindow: 131072,
13335
- maxTokens: 32768,
13336
- },
13337
- "inclusionai/ling-3.0-flash-vl:free": {
13338
- id: "inclusionai/ling-3.0-flash-vl:free",
13339
- name: "inclusionAI: Ling 3.0 Flash VL (free)",
13340
- api: "openai-completions",
13341
- provider: "openrouter",
13342
- baseUrl: "https://openrouter.ai/api/v1",
13343
- reasoning: true,
13344
- input: ["text", "image"],
13345
- cost: {
13346
- input: 0,
13347
- output: 0,
13348
- cacheRead: 0,
13349
- cacheWrite: 0,
13350
- },
13351
13850
  contextWindow: 262144,
13352
13851
  maxTokens: 32768,
13353
13852
  },
@@ -13615,13 +14114,13 @@ export const MODELS = {
13615
14114
  reasoning: true,
13616
14115
  input: ["text"],
13617
14116
  cost: {
13618
- input: 0.255,
13619
- output: 1.02,
14117
+ input: 0.3,
14118
+ output: 1.2,
13620
14119
  cacheRead: 0,
13621
14120
  cacheWrite: 0,
13622
14121
  },
13623
14122
  contextWindow: 204800,
13624
- maxTokens: 131072,
14123
+ maxTokens: 176947,
13625
14124
  },
13626
14125
  "minimax/minimax-m2.1": {
13627
14126
  id: "minimax/minimax-m2.1",
@@ -13725,23 +14224,6 @@ export const MODELS = {
13725
14224
  contextWindow: 256000,
13726
14225
  maxTokens: 204800,
13727
14226
  },
13728
- "mistralai/devstral-2512": {
13729
- id: "mistralai/devstral-2512",
13730
- name: "Mistral: Devstral 2 2512",
13731
- api: "openai-completions",
13732
- provider: "openrouter",
13733
- baseUrl: "https://openrouter.ai/api/v1",
13734
- reasoning: false,
13735
- input: ["text"],
13736
- cost: {
13737
- input: 0.39999999999999997,
13738
- output: 2,
13739
- cacheRead: 0.04,
13740
- cacheWrite: 0,
13741
- },
13742
- contextWindow: 262144,
13743
- maxTokens: 209715,
13744
- },
13745
14227
  "mistralai/ministral-14b-2512": {
13746
14228
  id: "mistralai/ministral-14b-2512",
13747
14229
  name: "Mistral: Ministral 3 14B 2512",
@@ -14176,7 +14658,7 @@ export const MODELS = {
14176
14658
  reasoning: true,
14177
14659
  input: ["text", "image"],
14178
14660
  cost: {
14179
- input: 0.7062,
14661
+ input: 0.6562,
14180
14662
  output: 3.3000000000000003,
14181
14663
  cacheRead: 0.18,
14182
14664
  cacheWrite: 0,
@@ -14235,23 +14717,6 @@ export const MODELS = {
14235
14717
  contextWindow: 262144,
14236
14718
  maxTokens: 235929,
14237
14719
  },
14238
- "nex-agi/nex-n2.5-pro": {
14239
- id: "nex-agi/nex-n2.5-pro",
14240
- name: "Nex AGI: Nex-N2.5-Pro",
14241
- api: "openai-completions",
14242
- provider: "openrouter",
14243
- baseUrl: "https://openrouter.ai/api/v1",
14244
- reasoning: true,
14245
- input: ["text", "image"],
14246
- cost: {
14247
- input: 0.075,
14248
- output: 0.25,
14249
- cacheRead: 0.015,
14250
- cacheWrite: 0,
14251
- },
14252
- contextWindow: 262144,
14253
- maxTokens: 235929,
14254
- },
14255
14720
  "nex-agi/nex-n2.5-pro:free": {
14256
14721
  id: "nex-agi/nex-n2.5-pro:free",
14257
14722
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -14380,13 +14845,13 @@ export const MODELS = {
14380
14845
  reasoning: true,
14381
14846
  input: ["text"],
14382
14847
  cost: {
14383
- input: 0.07,
14848
+ input: 0.08,
14384
14849
  output: 0.19999999999999998,
14385
14850
  cacheRead: 0.04,
14386
14851
  cacheWrite: 0,
14387
14852
  },
14388
14853
  contextWindow: 262144,
14389
- maxTokens: 235929,
14854
+ maxTokens: 131072,
14390
14855
  },
14391
14856
  "nvidia/nemotron-3.5-lightning:free": {
14392
14857
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15512,6 +15977,74 @@ export const MODELS = {
15512
15977
  contextWindow: 1050000,
15513
15978
  maxTokens: 128000,
15514
15979
  },
15980
+ "openai/gpt-6-luna": {
15981
+ id: "openai/gpt-6-luna",
15982
+ name: "OpenAI: GPT-6 Luna",
15983
+ api: "openai-completions",
15984
+ provider: "openrouter",
15985
+ baseUrl: "https://openrouter.ai/api/v1",
15986
+ reasoning: true,
15987
+ input: ["text", "image"],
15988
+ cost: {
15989
+ input: 0.09999999999999999,
15990
+ output: 0.5,
15991
+ cacheRead: 0.01,
15992
+ cacheWrite: 0.125,
15993
+ },
15994
+ contextWindow: 1050000,
15995
+ maxTokens: 128000,
15996
+ },
15997
+ "openai/gpt-6-luna-pro": {
15998
+ id: "openai/gpt-6-luna-pro",
15999
+ name: "OpenAI: GPT-6 Luna Pro",
16000
+ api: "openai-completions",
16001
+ provider: "openrouter",
16002
+ baseUrl: "https://openrouter.ai/api/v1",
16003
+ reasoning: true,
16004
+ input: ["text", "image"],
16005
+ cost: {
16006
+ input: 0.09999999999999999,
16007
+ output: 0.5,
16008
+ cacheRead: 0.01,
16009
+ cacheWrite: 0.125,
16010
+ },
16011
+ contextWindow: 1050000,
16012
+ maxTokens: 128000,
16013
+ },
16014
+ "openai/gpt-6-luna-pro:batch": {
16015
+ id: "openai/gpt-6-luna-pro:batch",
16016
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
16017
+ api: "openai-completions",
16018
+ provider: "openrouter",
16019
+ baseUrl: "https://openrouter.ai/api/v1",
16020
+ reasoning: true,
16021
+ input: ["text", "image"],
16022
+ cost: {
16023
+ input: 0.049999999999999996,
16024
+ output: 0.25,
16025
+ cacheRead: 0.005,
16026
+ cacheWrite: 0.0625,
16027
+ },
16028
+ contextWindow: 1050000,
16029
+ maxTokens: 128000,
16030
+ },
16031
+ "openai/gpt-6-luna:batch": {
16032
+ id: "openai/gpt-6-luna:batch",
16033
+ name: "OpenAI: GPT-6 Luna (batch)",
16034
+ api: "openai-completions",
16035
+ provider: "openrouter",
16036
+ baseUrl: "https://openrouter.ai/api/v1",
16037
+ reasoning: true,
16038
+ input: ["text", "image"],
16039
+ cost: {
16040
+ input: 0.049999999999999996,
16041
+ output: 0.25,
16042
+ cacheRead: 0.005,
16043
+ cacheWrite: 0.0625,
16044
+ },
16045
+ contextWindow: 1050000,
16046
+ maxTokens: 128000,
16047
+ },
15515
16048
  "openai/gpt-6-sol": {
15516
16049
  id: "openai/gpt-6-sol",
15517
16050
  name: "OpenAI: GPT-6 Sol",
@@ -15529,19 +16062,36 @@ export const MODELS = {
15529
16062
  contextWindow: 1050000,
15530
16063
  maxTokens: 128000,
15531
16064
  },
15532
- "openai/gpt-6-sol-pro": {
15533
- id: "openai/gpt-6-sol-pro",
15534
- name: "OpenAI: GPT-6 Sol Pro",
16065
+ "openai/gpt-6-sol-pro": {
16066
+ id: "openai/gpt-6-sol-pro",
16067
+ name: "OpenAI: GPT-6 Sol Pro",
16068
+ api: "openai-completions",
16069
+ provider: "openrouter",
16070
+ baseUrl: "https://openrouter.ai/api/v1",
16071
+ reasoning: true,
16072
+ input: ["text", "image"],
16073
+ cost: {
16074
+ input: 2,
16075
+ output: 10,
16076
+ cacheRead: 0.19999999999999998,
16077
+ cacheWrite: 2.5,
16078
+ },
16079
+ contextWindow: 1050000,
16080
+ maxTokens: 128000,
16081
+ },
16082
+ "openai/gpt-6-sol-pro:batch": {
16083
+ id: "openai/gpt-6-sol-pro:batch",
16084
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
15535
16085
  api: "openai-completions",
15536
16086
  provider: "openrouter",
15537
16087
  baseUrl: "https://openrouter.ai/api/v1",
15538
16088
  reasoning: true,
15539
16089
  input: ["text", "image"],
15540
16090
  cost: {
15541
- input: 2,
15542
- output: 10,
15543
- cacheRead: 0.19999999999999998,
15544
- cacheWrite: 2.5,
16091
+ input: 1,
16092
+ output: 5,
16093
+ cacheRead: 0.09999999999999999,
16094
+ cacheWrite: 1.25,
15545
16095
  },
15546
16096
  contextWindow: 1050000,
15547
16097
  maxTokens: 128000,
@@ -15631,6 +16181,23 @@ export const MODELS = {
15631
16181
  contextWindow: 131072,
15632
16182
  maxTokens: 65536,
15633
16183
  },
16184
+ "openai/gpt-oss-120b:batch": {
16185
+ id: "openai/gpt-oss-120b:batch",
16186
+ name: "OpenAI: gpt-oss-120b (batch)",
16187
+ api: "openai-completions",
16188
+ provider: "openrouter",
16189
+ baseUrl: "https://openrouter.ai/api/v1",
16190
+ reasoning: true,
16191
+ input: ["text"],
16192
+ cost: {
16193
+ input: 0.0296,
16194
+ output: 0.136,
16195
+ cacheRead: 0,
16196
+ cacheWrite: 0,
16197
+ },
16198
+ contextWindow: 131072,
16199
+ maxTokens: 117964,
16200
+ },
15634
16201
  "openai/gpt-oss-20b": {
15635
16202
  id: "openai/gpt-oss-20b",
15636
16203
  name: "OpenAI: gpt-oss-20b",
@@ -16150,13 +16717,13 @@ export const MODELS = {
16150
16717
  reasoning: false,
16151
16718
  input: ["text"],
16152
16719
  cost: {
16153
- input: 0.04815,
16154
- output: 0.19305,
16720
+ input: 0.09999999999999999,
16721
+ output: 0.3,
16155
16722
  cacheRead: 0,
16156
16723
  cacheWrite: 0,
16157
16724
  },
16158
16725
  contextWindow: 262144,
16159
- maxTokens: 32000,
16726
+ maxTokens: 235929,
16160
16727
  },
16161
16728
  "qwen/qwen3-30b-a3b-thinking-2507": {
16162
16729
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16337,13 +16904,13 @@ export const MODELS = {
16337
16904
  reasoning: false,
16338
16905
  input: ["text"],
16339
16906
  cost: {
16340
- input: 0.09,
16907
+ input: 0.09999999999999999,
16341
16908
  output: 1.1,
16342
- cacheRead: 0,
16909
+ cacheRead: 0.07,
16343
16910
  cacheWrite: 0,
16344
16911
  },
16345
16912
  contextWindow: 262144,
16346
- maxTokens: 16384,
16913
+ maxTokens: 235929,
16347
16914
  },
16348
16915
  "qwen/qwen3-next-80b-a3b-thinking": {
16349
16916
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -16838,6 +17405,40 @@ export const MODELS = {
16838
17405
  contextWindow: 1000000,
16839
17406
  maxTokens: 131072,
16840
17407
  },
17408
+ "qwen/qwen3.8-max-prime": {
17409
+ id: "qwen/qwen3.8-max-prime",
17410
+ name: "Qwen: Qwen3.8 Max Prime",
17411
+ api: "openai-completions",
17412
+ provider: "openrouter",
17413
+ baseUrl: "https://openrouter.ai/api/v1",
17414
+ reasoning: true,
17415
+ input: ["text", "image"],
17416
+ cost: {
17417
+ input: 4,
17418
+ output: 12,
17419
+ cacheRead: 0.5,
17420
+ cacheWrite: 0,
17421
+ },
17422
+ contextWindow: 1000000,
17423
+ maxTokens: 131072,
17424
+ },
17425
+ "qwen/qwen3.8-omni-flash": {
17426
+ id: "qwen/qwen3.8-omni-flash",
17427
+ name: "Qwen: Qwen3.8 Omni Flash",
17428
+ api: "openai-completions",
17429
+ provider: "openrouter",
17430
+ baseUrl: "https://openrouter.ai/api/v1",
17431
+ reasoning: true,
17432
+ input: ["text", "image"],
17433
+ cost: {
17434
+ input: 0.15,
17435
+ output: 0.47,
17436
+ cacheRead: 0.016,
17437
+ cacheWrite: 0,
17438
+ },
17439
+ contextWindow: 1000000,
17440
+ maxTokens: 131072,
17441
+ },
16841
17442
  "rekaai/reka-edge": {
16842
17443
  id: "rekaai/reka-edge",
16843
17444
  name: "Reka Edge",
@@ -16957,6 +17558,23 @@ export const MODELS = {
16957
17558
  contextWindow: 131072,
16958
17559
  maxTokens: 16384,
16959
17560
  },
17561
+ "stealth/space-bunny-alpha": {
17562
+ id: "stealth/space-bunny-alpha",
17563
+ name: "Space Bunny Alpha",
17564
+ api: "openai-completions",
17565
+ provider: "openrouter",
17566
+ baseUrl: "https://openrouter.ai/api/v1",
17567
+ reasoning: true,
17568
+ input: ["text", "image"],
17569
+ cost: {
17570
+ input: 0,
17571
+ output: 0,
17572
+ cacheRead: 0,
17573
+ cacheWrite: 0,
17574
+ },
17575
+ contextWindow: 1000000,
17576
+ maxTokens: 524288,
17577
+ },
16960
17578
  "stepfun/step-3.5-flash": {
16961
17579
  id: "stepfun/step-3.5-flash",
16962
17580
  name: "StepFun: Step 3.5 Flash",
@@ -17000,9 +17618,9 @@ export const MODELS = {
17000
17618
  reasoning: true,
17001
17619
  input: ["text"],
17002
17620
  cost: {
17003
- input: 0.0825,
17004
- output: 0.33,
17005
- cacheRead: 0.020625,
17621
+ input: 0.13199999999999998,
17622
+ output: 0.5279999999999999,
17623
+ cacheRead: 0.032999999999999995,
17006
17624
  cacheWrite: 0,
17007
17625
  },
17008
17626
  contextWindow: 262144,
@@ -17110,6 +17728,23 @@ export const MODELS = {
17110
17728
  contextWindow: 262144,
17111
17729
  maxTokens: 131072,
17112
17730
  },
17731
+ "upstage/solar-mini4": {
17732
+ id: "upstage/solar-mini4",
17733
+ name: "Upstage: Solar Mini 4",
17734
+ api: "openai-completions",
17735
+ provider: "openrouter",
17736
+ baseUrl: "https://openrouter.ai/api/v1",
17737
+ reasoning: true,
17738
+ input: ["text"],
17739
+ cost: {
17740
+ input: 0.049999999999999996,
17741
+ output: 0.19999999999999998,
17742
+ cacheRead: 0.005,
17743
+ cacheWrite: 0,
17744
+ },
17745
+ contextWindow: 524288,
17746
+ maxTokens: 131072,
17747
+ },
17113
17748
  "upstage/solar-pro-3": {
17114
17749
  id: "upstage/solar-pro-3",
17115
17750
  name: "Upstage: Solar Pro 3",
@@ -17544,9 +18179,9 @@ export const MODELS = {
17544
18179
  reasoning: true,
17545
18180
  input: ["text"],
17546
18181
  cost: {
17547
- input: 0.6537999999999999,
17548
- output: 2.0547999999999997,
17549
- cacheRead: 0.12142000000000001,
18182
+ input: 0.84,
18183
+ output: 2.64,
18184
+ cacheRead: 0.156,
17550
18185
  cacheWrite: 0,
17551
18186
  },
17552
18187
  contextWindow: 1310720,
@@ -17597,12 +18232,29 @@ export const MODELS = {
17597
18232
  cost: {
17598
18233
  input: 0.37,
17599
18234
  output: 1.25,
17600
- cacheRead: 0.075,
18235
+ cacheRead: 0.09,
17601
18236
  cacheWrite: 0,
17602
18237
  },
17603
18238
  contextWindow: 1048576,
17604
18239
  maxTokens: 131072,
17605
18240
  },
18241
+ "z-ai/glm-5.3-prime": {
18242
+ id: "z-ai/glm-5.3-prime",
18243
+ name: "Z.ai: GLM 5.3 Prime",
18244
+ api: "openai-completions",
18245
+ provider: "openrouter",
18246
+ baseUrl: "https://openrouter.ai/api/v1",
18247
+ reasoning: true,
18248
+ input: ["text"],
18249
+ cost: {
18250
+ input: 2.8,
18251
+ output: 8.8,
18252
+ cacheRead: 0.56,
18253
+ cacheWrite: 0,
18254
+ },
18255
+ contextWindow: 1000000,
18256
+ maxTokens: 131072,
18257
+ },
17606
18258
  "z-ai/glm-5.3:batch": {
17607
18259
  id: "z-ai/glm-5.3:batch",
17608
18260
  name: "Z.ai: GLM 5.3 (batch)",
@@ -17612,9 +18264,9 @@ export const MODELS = {
17612
18264
  reasoning: true,
17613
18265
  input: ["text"],
17614
18266
  cost: {
17615
- input: 0.72,
17616
- output: 2.4,
17617
- cacheRead: 0.12,
18267
+ input: 0.44999999999999996,
18268
+ output: 2,
18269
+ cacheRead: 0.09999999999999999,
17618
18270
  cacheWrite: 0,
17619
18271
  },
17620
18272
  contextWindow: 1048576,
@@ -17715,9 +18367,9 @@ export const MODELS = {
17715
18367
  reasoning: true,
17716
18368
  input: ["text", "image"],
17717
18369
  cost: {
17718
- input: 0.12,
17719
- output: 0.48,
17720
- cacheRead: 0.0036,
18370
+ input: 0.04,
18371
+ output: 1,
18372
+ cacheRead: 0.01,
17721
18373
  cacheWrite: 0,
17722
18374
  },
17723
18375
  contextWindow: 1048576,
@@ -17732,13 +18384,13 @@ export const MODELS = {
17732
18384
  reasoning: true,
17733
18385
  input: ["text"],
17734
18386
  cost: {
17735
- input: 0.54648,
17736
- output: 1.63944,
17737
- cacheRead: 0.017388,
18387
+ input: 0.39,
18388
+ output: 2.9000000000000004,
18389
+ cacheRead: 0.25,
17738
18390
  cacheWrite: 0,
17739
18391
  },
17740
18392
  contextWindow: 1048576,
17741
- maxTokens: 393216,
18393
+ maxTokens: 943718,
17742
18394
  },
17743
18395
  "~deepseek/deepseek-v4-flash-latest": {
17744
18396
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -17752,8 +18404,8 @@ export const MODELS = {
17752
18404
  input: ["text"],
17753
18405
  cost: {
17754
18406
  input: 0.03,
17755
- output: 1,
17756
- cacheRead: 0.008,
18407
+ output: 0.32,
18408
+ cacheRead: 0.016,
17757
18409
  cacheWrite: 0,
17758
18410
  },
17759
18411
  contextWindow: 1310720,
@@ -17802,9 +18454,9 @@ export const MODELS = {
17802
18454
  reasoning: true,
17803
18455
  input: ["text", "image"],
17804
18456
  cost: {
17805
- input: 1.5,
17806
- output: 7.5,
17807
- cacheRead: 0.15,
18457
+ input: 1.4,
18458
+ output: 10.75,
18459
+ cacheRead: 0.3,
17808
18460
  cacheWrite: 0,
17809
18461
  },
17810
18462
  contextWindow: 1048576,
@@ -17836,10 +18488,10 @@ export const MODELS = {
17836
18488
  reasoning: true,
17837
18489
  input: ["text", "image"],
17838
18490
  cost: {
17839
- input: 0.19999999999999998,
17840
- output: 1.2,
17841
- cacheRead: 0.02,
17842
- cacheWrite: 0.25,
18491
+ input: 0.09999999999999999,
18492
+ output: 0.5,
18493
+ cacheRead: 0.01,
18494
+ cacheWrite: 0.125,
17843
18495
  },
17844
18496
  contextWindow: 1050000,
17845
18497
  maxTokens: 128000,
@@ -17921,13 +18573,13 @@ export const MODELS = {
17921
18573
  reasoning: true,
17922
18574
  input: ["text", "image"],
17923
18575
  cost: {
17924
- input: 0.075,
17925
- output: 0.25,
17926
- cacheRead: 0.015,
18576
+ input: 0.045,
18577
+ output: 0.14,
18578
+ cacheRead: 0.01,
17927
18579
  cacheWrite: 0,
17928
18580
  },
17929
18581
  contextWindow: 1310720,
17930
- maxTokens: 943718,
18582
+ maxTokens: 128000,
17931
18583
  },
17932
18584
  "~z-ai/glm-latest": {
17933
18585
  id: "~z-ai/glm-latest",
@@ -17938,9 +18590,9 @@ export const MODELS = {
17938
18590
  reasoning: true,
17939
18591
  input: ["text"],
17940
18592
  cost: {
17941
- input: 0.6537999999999999,
17942
- output: 2.0547999999999997,
17943
- cacheRead: 0.12142000000000001,
18593
+ input: 0.5625,
18594
+ output: 2.5,
18595
+ cacheRead: 0.125,
17944
18596
  cacheWrite: 0,
17945
18597
  },
17946
18598
  contextWindow: 1310720,
@@ -17964,7 +18616,7 @@ export const MODELS = {
17964
18616
  cacheRead: 0.06,
17965
18617
  cacheWrite: 0,
17966
18618
  },
17967
- contextWindow: 202752,
18619
+ contextWindow: 196608,
17968
18620
  maxTokens: 131072,
17969
18621
  },
17970
18622
  "MiniMaxAI/MiniMax-M3": {
@@ -18076,7 +18728,7 @@ export const MODELS = {
18076
18728
  cacheRead: 0.03,
18077
18729
  cacheWrite: 0,
18078
18730
  },
18079
- contextWindow: 1000000,
18731
+ contextWindow: 1048576,
18080
18732
  maxTokens: 384000,
18081
18733
  },
18082
18734
  "deepseek-ai/DeepSeek-V4-Pro": {
@@ -18322,7 +18974,7 @@ export const MODELS = {
18322
18974
  cacheRead: 0.26,
18323
18975
  cacheWrite: 0,
18324
18976
  },
18325
- contextWindow: 512000,
18977
+ contextWindow: 1048575,
18326
18978
  maxTokens: 164000,
18327
18979
  },
18328
18980
  "zai-org/GLM-5.3": {
@@ -18875,6 +19527,23 @@ export const MODELS = {
18875
19527
  contextWindow: 991000,
18876
19528
  maxTokens: 128000,
18877
19529
  },
19530
+ "alibaba/qwen3.8-max-prime": {
19531
+ id: "alibaba/qwen3.8-max-prime",
19532
+ name: "Qwen 3.8 Max Prime",
19533
+ api: "anthropic-messages",
19534
+ provider: "vercel-ai-gateway",
19535
+ baseUrl: "https://ai-gateway.vercel.sh",
19536
+ reasoning: true,
19537
+ input: ["text", "image"],
19538
+ cost: {
19539
+ input: 4,
19540
+ output: 12,
19541
+ cacheRead: 0.5,
19542
+ cacheWrite: 0,
19543
+ },
19544
+ contextWindow: 1000000,
19545
+ maxTokens: 131072,
19546
+ },
18878
19547
  "alibaba/qwen3.8-omni-flash": {
18879
19548
  id: "alibaba/qwen3.8-omni-flash",
18880
19549
  name: "Qwen 3.8 Omni Flash",
@@ -19045,7 +19714,7 @@ export const MODELS = {
19045
19714
  cacheWrite: 18.75,
19046
19715
  },
19047
19716
  contextWindow: 200000,
19048
- maxTokens: 8192,
19717
+ maxTokens: 32000,
19049
19718
  },
19050
19719
  "anthropic/claude-opus-4.5": {
19051
19720
  id: "anthropic/claude-opus-4.5",
@@ -19219,7 +19888,7 @@ export const MODELS = {
19219
19888
  cacheWrite: 3.75,
19220
19889
  },
19221
19890
  contextWindow: 1000000,
19222
- maxTokens: 8192,
19891
+ maxTokens: 64000,
19223
19892
  },
19224
19893
  "anthropic/claude-sonnet-4.5": {
19225
19894
  id: "anthropic/claude-sonnet-4.5",
@@ -19559,7 +20228,7 @@ export const MODELS = {
19559
20228
  cacheWrite: 0,
19560
20229
  },
19561
20230
  contextWindow: 1000000,
19562
- maxTokens: 65536,
20231
+ maxTokens: 65535,
19563
20232
  },
19564
20233
  "google/gemini-2.5-flash-lite": {
19565
20234
  id: "google/gemini-2.5-flash-lite",
@@ -19576,7 +20245,7 @@ export const MODELS = {
19576
20245
  cacheWrite: 0,
19577
20246
  },
19578
20247
  contextWindow: 1048576,
19579
- maxTokens: 65536,
20248
+ maxTokens: 65535,
19580
20249
  },
19581
20250
  "google/gemini-2.5-pro": {
19582
20251
  id: "google/gemini-2.5-pro",
@@ -19593,7 +20262,7 @@ export const MODELS = {
19593
20262
  cacheWrite: 0,
19594
20263
  },
19595
20264
  contextWindow: 1048576,
19596
- maxTokens: 65536,
20265
+ maxTokens: 65535,
19597
20266
  },
19598
20267
  "google/gemini-3-flash": {
19599
20268
  id: "google/gemini-3-flash",
@@ -19712,7 +20381,7 @@ export const MODELS = {
19712
20381
  cacheWrite: 0,
19713
20382
  },
19714
20383
  contextWindow: 1000000,
19715
- maxTokens: 65536,
20384
+ maxTokens: 65535,
19716
20385
  },
19717
20386
  "google/gemini-3.8-flash": {
19718
20387
  id: "google/gemini-3.8-flash",
@@ -19729,7 +20398,7 @@ export const MODELS = {
19729
20398
  cacheWrite: 0,
19730
20399
  },
19731
20400
  contextWindow: 1000000,
19732
- maxTokens: 65536,
20401
+ maxTokens: 65535,
19733
20402
  },
19734
20403
  "google/gemma-4-26b-a4b-it": {
19735
20404
  id: "google/gemma-4-26b-a4b-it",
@@ -19910,26 +20579,9 @@ export const MODELS = {
19910
20579
  reasoning: true,
19911
20580
  input: ["text", "image"],
19912
20581
  cost: {
19913
- input: 0,
19914
- output: 0,
19915
- cacheRead: 0,
19916
- cacheWrite: 0,
19917
- },
19918
- contextWindow: 256000,
19919
- maxTokens: 32000,
19920
- },
19921
- "inclusionai/ling-3.0-flash-vl-free": {
19922
- id: "inclusionai/ling-3.0-flash-vl-free",
19923
- name: "Ling 3.0 Flash VL (Free)",
19924
- api: "anthropic-messages",
19925
- provider: "vercel-ai-gateway",
19926
- baseUrl: "https://ai-gateway.vercel.sh",
19927
- reasoning: true,
19928
- input: ["text", "image"],
19929
- cost: {
19930
- input: 0,
19931
- output: 0,
19932
- cacheRead: 0,
20582
+ input: 0.075,
20583
+ output: 0.22,
20584
+ cacheRead: 0.015,
19933
20585
  cacheWrite: 0,
19934
20586
  },
19935
20587
  contextWindow: 256000,
@@ -21463,6 +22115,74 @@ export const MODELS = {
21463
22115
  contextWindow: 1050000,
21464
22116
  maxTokens: 128000,
21465
22117
  },
22118
+ "openai/gpt-6-luna": {
22119
+ id: "openai/gpt-6-luna",
22120
+ name: "GPT-6 Luna",
22121
+ api: "anthropic-messages",
22122
+ provider: "vercel-ai-gateway",
22123
+ baseUrl: "https://ai-gateway.vercel.sh",
22124
+ reasoning: true,
22125
+ input: ["text", "image"],
22126
+ cost: {
22127
+ input: 0.09999999999999999,
22128
+ output: 0.5,
22129
+ cacheRead: 0.01,
22130
+ cacheWrite: 0.125,
22131
+ },
22132
+ contextWindow: 1050000,
22133
+ maxTokens: 128000,
22134
+ },
22135
+ "openai/gpt-6-luna-fast": {
22136
+ id: "openai/gpt-6-luna-fast",
22137
+ name: "GPT-6 Luna (Fast)",
22138
+ api: "anthropic-messages",
22139
+ provider: "vercel-ai-gateway",
22140
+ baseUrl: "https://ai-gateway.vercel.sh",
22141
+ reasoning: true,
22142
+ input: ["text", "image"],
22143
+ cost: {
22144
+ input: 0.19999999999999998,
22145
+ output: 1,
22146
+ cacheRead: 0.02,
22147
+ cacheWrite: 0.25,
22148
+ },
22149
+ contextWindow: 1050000,
22150
+ maxTokens: 128000,
22151
+ },
22152
+ "openai/gpt-6-sol": {
22153
+ id: "openai/gpt-6-sol",
22154
+ name: "GPT-6 Sol",
22155
+ api: "anthropic-messages",
22156
+ provider: "vercel-ai-gateway",
22157
+ baseUrl: "https://ai-gateway.vercel.sh",
22158
+ reasoning: true,
22159
+ input: ["text", "image"],
22160
+ cost: {
22161
+ input: 2,
22162
+ output: 10,
22163
+ cacheRead: 0.19999999999999998,
22164
+ cacheWrite: 2.5,
22165
+ },
22166
+ contextWindow: 1050000,
22167
+ maxTokens: 128000,
22168
+ },
22169
+ "openai/gpt-6-sol-fast": {
22170
+ id: "openai/gpt-6-sol-fast",
22171
+ name: "GPT-6 Sol (Fast)",
22172
+ api: "anthropic-messages",
22173
+ provider: "vercel-ai-gateway",
22174
+ baseUrl: "https://ai-gateway.vercel.sh",
22175
+ reasoning: true,
22176
+ input: ["text", "image"],
22177
+ cost: {
22178
+ input: 4,
22179
+ output: 20,
22180
+ cacheRead: 0.39999999999999997,
22181
+ cacheWrite: 5,
22182
+ },
22183
+ contextWindow: 1050000,
22184
+ maxTokens: 128000,
22185
+ },
21466
22186
  "openai/gpt-oss-120b": {
21467
22187
  id: "openai/gpt-oss-120b",
21468
22188
  name: "GPT OSS 120B",
@@ -21474,7 +22194,7 @@ export const MODELS = {
21474
22194
  cost: {
21475
22195
  input: 0.09999999999999999,
21476
22196
  output: 0.5,
21477
- cacheRead: 0,
22197
+ cacheRead: 0.09999999999999999,
21478
22198
  cacheWrite: 0,
21479
22199
  },
21480
22200
  contextWindow: 131072,