@elyracode/ai 0.9.44 → 0.9.45

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.
@@ -309,6 +309,24 @@ export const MODELS = {
309
309
  contextWindow: 1000000,
310
310
  maxTokens: 128000,
311
311
  },
312
+ "anthropic.claude-sonnet-5-5": {
313
+ id: "anthropic.claude-sonnet-5-5",
314
+ name: "Claude Sonnet 5.5",
315
+ api: "bedrock-converse-stream",
316
+ provider: "amazon-bedrock",
317
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
318
+ reasoning: true,
319
+ thinkingType: "adaptive",
320
+ input: ["text", "image"],
321
+ cost: {
322
+ input: 2,
323
+ output: 10,
324
+ cacheRead: 0.2,
325
+ cacheWrite: 2.5,
326
+ },
327
+ contextWindow: 1000000,
328
+ maxTokens: 128000,
329
+ },
312
330
  "apac.amazon.nova-lite-v1:0": {
313
331
  id: "apac.amazon.nova-lite-v1:0",
314
332
  name: "Nova Lite (APAC)",
@@ -1155,6 +1173,24 @@ export const MODELS = {
1155
1173
  contextWindow: 1000000,
1156
1174
  maxTokens: 128000,
1157
1175
  },
1176
+ "global.anthropic.claude-sonnet-5-5": {
1177
+ id: "global.anthropic.claude-sonnet-5-5",
1178
+ name: "Claude Sonnet 5.5 (Global)",
1179
+ api: "bedrock-converse-stream",
1180
+ provider: "amazon-bedrock",
1181
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1182
+ reasoning: true,
1183
+ thinkingType: "adaptive",
1184
+ input: ["text", "image"],
1185
+ cost: {
1186
+ input: 2,
1187
+ output: 10,
1188
+ cacheRead: 0.2,
1189
+ cacheWrite: 2.5,
1190
+ },
1191
+ contextWindow: 1000000,
1192
+ maxTokens: 128000,
1193
+ },
1158
1194
  "global.moonshotai.kimi-k3": {
1159
1195
  id: "global.moonshotai.kimi-k3",
1160
1196
  name: "Kimi K3 (Global)",
@@ -1291,6 +1327,23 @@ export const MODELS = {
1291
1327
  contextWindow: 500000,
1292
1328
  maxTokens: 500000,
1293
1329
  },
1330
+ "global.xai.grok-4.7": {
1331
+ id: "global.xai.grok-4.7",
1332
+ name: "Grok 4.7 (Global)",
1333
+ api: "bedrock-converse-stream",
1334
+ provider: "amazon-bedrock",
1335
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1336
+ reasoning: true,
1337
+ input: ["text", "image"],
1338
+ cost: {
1339
+ input: 2,
1340
+ output: 6,
1341
+ cacheRead: 0.5,
1342
+ cacheWrite: 0,
1343
+ },
1344
+ contextWindow: 500000,
1345
+ maxTokens: 500000,
1346
+ },
1294
1347
  "google.gemma-4-26b-a4b": {
1295
1348
  id: "google.gemma-4-26b-a4b",
1296
1349
  name: "Gemma 4 26B A4B IT",
@@ -2937,6 +2990,23 @@ export const MODELS = {
2937
2990
  contextWindow: 500000,
2938
2991
  maxTokens: 500000,
2939
2992
  },
2993
+ "us.xai.grok-4.7": {
2994
+ id: "us.xai.grok-4.7",
2995
+ name: "Grok 4.7 (US)",
2996
+ api: "bedrock-converse-stream",
2997
+ provider: "amazon-bedrock",
2998
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2999
+ reasoning: true,
3000
+ input: ["text", "image"],
3001
+ cost: {
3002
+ input: 2.2,
3003
+ output: 6.6,
3004
+ cacheRead: 0.55,
3005
+ cacheWrite: 0,
3006
+ },
3007
+ contextWindow: 500000,
3008
+ maxTokens: 500000,
3009
+ },
2940
3010
  "writer.palmyra-x4-v1:0": {
2941
3011
  id: "writer.palmyra-x4-v1:0",
2942
3012
  name: "Palmyra X4",
@@ -3938,6 +4008,23 @@ export const MODELS = {
3938
4008
  contextWindow: 1050000,
3939
4009
  maxTokens: 128000,
3940
4010
  },
4011
+ "gpt-6.1-sol": {
4012
+ id: "gpt-6.1-sol",
4013
+ name: "GPT-6.1 Sol",
4014
+ api: "azure-openai-responses",
4015
+ provider: "azure-openai-responses",
4016
+ baseUrl: "",
4017
+ reasoning: true,
4018
+ input: ["text", "image"],
4019
+ cost: {
4020
+ input: 2,
4021
+ output: 10,
4022
+ cacheRead: 0.1,
4023
+ cacheWrite: 2.5,
4024
+ },
4025
+ contextWindow: 1050000,
4026
+ maxTokens: 128000,
4027
+ },
3941
4028
  "gpt-daybreak-blue-latest": {
3942
4029
  id: "gpt-daybreak-blue-latest",
3943
4030
  name: "Daybreak Blue",
@@ -4121,7 +4208,7 @@ export const MODELS = {
4121
4208
  cost: {
4122
4209
  input: 0.99,
4123
4210
  output: 1.49,
4124
- cacheRead: 0,
4211
+ cacheRead: 0.99,
4125
4212
  cacheWrite: 0,
4126
4213
  },
4127
4214
  contextWindow: 131072,
@@ -4301,7 +4388,7 @@ export const MODELS = {
4301
4388
  cacheRead: 0.3,
4302
4389
  cacheWrite: 3.75,
4303
4390
  },
4304
- contextWindow: 1000000,
4391
+ contextWindow: 200000,
4305
4392
  maxTokens: 64000,
4306
4393
  },
4307
4394
  "claude-sonnet-4.6": {
@@ -4777,7 +4864,7 @@ export const MODELS = {
4777
4864
  cacheRead: 0.014,
4778
4865
  cacheWrite: 0,
4779
4866
  },
4780
- contextWindow: 1310720,
4867
+ contextWindow: 1048576,
4781
4868
  maxTokens: 1048576,
4782
4869
  },
4783
4870
  "@cf/deepseek-ai/deepseek-v4-pro-0813": {
@@ -5066,7 +5153,7 @@ export const MODELS = {
5066
5153
  cacheRead: 0.26,
5067
5154
  cacheWrite: 0,
5068
5155
  },
5069
- contextWindow: 1310720,
5156
+ contextWindow: 1048576,
5070
5157
  maxTokens: 1048576,
5071
5158
  },
5072
5159
  "@cf/zai-org/glm-5.3-flash": {
@@ -5084,7 +5171,7 @@ export const MODELS = {
5084
5171
  cacheRead: 0.03,
5085
5172
  cacheWrite: 0,
5086
5173
  },
5087
- contextWindow: 1310720,
5174
+ contextWindow: 1048576,
5088
5175
  maxTokens: 1048576,
5089
5176
  },
5090
5177
  },
@@ -5677,6 +5764,25 @@ export const MODELS = {
5677
5764
  contextWindow: 1000000,
5678
5765
  maxTokens: 128000,
5679
5766
  },
5767
+ "claude-sonnet-5.5": {
5768
+ id: "claude-sonnet-5.5",
5769
+ name: "Claude Sonnet 5.5",
5770
+ api: "openai-completions",
5771
+ provider: "github-copilot",
5772
+ baseUrl: "https://api.individual.githubcopilot.com",
5773
+ 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" },
5774
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5775
+ reasoning: true,
5776
+ input: ["text", "image"],
5777
+ cost: {
5778
+ input: 2,
5779
+ output: 10,
5780
+ cacheRead: 0.2,
5781
+ cacheWrite: 2.5,
5782
+ },
5783
+ contextWindow: 1000000,
5784
+ maxTokens: 128000,
5785
+ },
5680
5786
  "gemini-3.5-flash": {
5681
5787
  id: "gemini-3.5-flash",
5682
5788
  name: "Gemini 3.5 Flash",
@@ -5981,6 +6087,25 @@ export const MODELS = {
5981
6087
  contextWindow: 1050000,
5982
6088
  maxTokens: 128000,
5983
6089
  },
6090
+ "gpt-6.1-sol": {
6091
+ id: "gpt-6.1-sol",
6092
+ name: "GPT-6.1 Sol",
6093
+ api: "openai-completions",
6094
+ provider: "github-copilot",
6095
+ baseUrl: "https://api.individual.githubcopilot.com",
6096
+ 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" },
6097
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6098
+ reasoning: true,
6099
+ input: ["text", "image"],
6100
+ cost: {
6101
+ input: 2,
6102
+ output: 10,
6103
+ cacheRead: 0.1,
6104
+ cacheWrite: 2.5,
6105
+ },
6106
+ contextWindow: 1050000,
6107
+ maxTokens: 128000,
6108
+ },
5984
6109
  "grok-4.5": {
5985
6110
  id: "grok-4.5",
5986
6111
  name: "Grok 4.5",
@@ -8397,7 +8522,7 @@ export const MODELS = {
8397
8522
  cost: {
8398
8523
  input: 0.3,
8399
8524
  output: 0.9,
8400
- cacheRead: 0,
8525
+ cacheRead: 0.03,
8401
8526
  cacheWrite: 0,
8402
8527
  },
8403
8528
  contextWindow: 256000,
@@ -8539,23 +8664,6 @@ export const MODELS = {
8539
8664
  contextWindow: 128000,
8540
8665
  maxTokens: 16384,
8541
8666
  },
8542
- "magistral-small": {
8543
- id: "magistral-small",
8544
- name: "Magistral Small",
8545
- api: "mistral-conversations",
8546
- provider: "mistral",
8547
- baseUrl: "https://api.mistral.ai",
8548
- reasoning: true,
8549
- input: ["text"],
8550
- cost: {
8551
- input: 0.5,
8552
- output: 1.5,
8553
- cacheRead: 0,
8554
- cacheWrite: 0,
8555
- },
8556
- contextWindow: 128000,
8557
- maxTokens: 128000,
8558
- },
8559
8667
  "ministral-3b-latest": {
8560
8668
  id: "ministral-3b-latest",
8561
8669
  name: "Ministral 3B (latest)",
@@ -8618,7 +8726,7 @@ export const MODELS = {
8618
8726
  cost: {
8619
8727
  input: 0.5,
8620
8728
  output: 1.5,
8621
- cacheRead: 0,
8729
+ cacheRead: 0.05,
8622
8730
  cacheWrite: 0,
8623
8731
  },
8624
8732
  contextWindow: 262144,
@@ -8635,7 +8743,7 @@ export const MODELS = {
8635
8743
  cost: {
8636
8744
  input: 0.5,
8637
8745
  output: 1.5,
8638
- cacheRead: 0,
8746
+ cacheRead: 0.05,
8639
8747
  cacheWrite: 0,
8640
8748
  },
8641
8749
  contextWindow: 262144,
@@ -8686,7 +8794,7 @@ export const MODELS = {
8686
8794
  cost: {
8687
8795
  input: 1.5,
8688
8796
  output: 7.5,
8689
- cacheRead: 0,
8797
+ cacheRead: 0.15,
8690
8798
  cacheWrite: 0,
8691
8799
  },
8692
8800
  contextWindow: 262144,
@@ -8720,7 +8828,7 @@ export const MODELS = {
8720
8828
  cost: {
8721
8829
  input: 1.5,
8722
8830
  output: 7.5,
8723
- cacheRead: 0,
8831
+ cacheRead: 0.15,
8724
8832
  cacheWrite: 0,
8725
8833
  },
8726
8834
  contextWindow: 262144,
@@ -8771,7 +8879,7 @@ export const MODELS = {
8771
8879
  cost: {
8772
8880
  input: 0.15,
8773
8881
  output: 0.6,
8774
- cacheRead: 0,
8882
+ cacheRead: 0.015,
8775
8883
  cacheWrite: 0,
8776
8884
  },
8777
8885
  contextWindow: 256000,
@@ -8788,7 +8896,7 @@ export const MODELS = {
8788
8896
  cost: {
8789
8897
  input: 0.15,
8790
8898
  output: 0.6,
8791
- cacheRead: 0,
8899
+ cacheRead: 0.015,
8792
8900
  cacheWrite: 0,
8793
8901
  },
8794
8902
  contextWindow: 256000,
@@ -9682,6 +9790,23 @@ export const MODELS = {
9682
9790
  contextWindow: 1050000,
9683
9791
  maxTokens: 128000,
9684
9792
  },
9793
+ "gpt-6.1-sol": {
9794
+ id: "gpt-6.1-sol",
9795
+ name: "GPT-6.1 Sol",
9796
+ api: "openai-responses",
9797
+ provider: "openai",
9798
+ baseUrl: "https://api.openai.com/v1",
9799
+ reasoning: true,
9800
+ input: ["text", "image"],
9801
+ cost: {
9802
+ input: 2,
9803
+ output: 10,
9804
+ cacheRead: 0.1,
9805
+ cacheWrite: 2.5,
9806
+ },
9807
+ contextWindow: 1050000,
9808
+ maxTokens: 128000,
9809
+ },
9685
9810
  "gpt-daybreak-blue-latest": {
9686
9811
  id: "gpt-daybreak-blue-latest",
9687
9812
  name: "Daybreak Blue",
@@ -10260,6 +10385,23 @@ export const MODELS = {
10260
10385
  contextWindow: 1000000,
10261
10386
  maxTokens: 128000,
10262
10387
  },
10388
+ "claude-sonnet-5-5": {
10389
+ id: "claude-sonnet-5-5",
10390
+ name: "Claude Sonnet 5.5",
10391
+ api: "anthropic-messages",
10392
+ provider: "opencode",
10393
+ baseUrl: "https://opencode.ai/zen",
10394
+ reasoning: true,
10395
+ input: ["text", "image"],
10396
+ cost: {
10397
+ input: 2,
10398
+ output: 10,
10399
+ cacheRead: 0.2,
10400
+ cacheWrite: 2.5,
10401
+ },
10402
+ contextWindow: 1000000,
10403
+ maxTokens: 128000,
10404
+ },
10263
10405
  "deepseek-v4-flash": {
10264
10406
  id: "deepseek-v4-flash",
10265
10407
  name: "DeepSeek V4 Flash",
@@ -10940,6 +11082,23 @@ export const MODELS = {
10940
11082
  contextWindow: 1050000,
10941
11083
  maxTokens: 128000,
10942
11084
  },
11085
+ "gpt-6.1-sol": {
11086
+ id: "gpt-6.1-sol",
11087
+ name: "GPT-6.1 Sol",
11088
+ api: "openai-responses",
11089
+ provider: "opencode",
11090
+ baseUrl: "https://opencode.ai/zen/v1",
11091
+ reasoning: true,
11092
+ input: ["text", "image"],
11093
+ cost: {
11094
+ input: 2,
11095
+ output: 10,
11096
+ cacheRead: 0.1,
11097
+ cacheWrite: 2.5,
11098
+ },
11099
+ contextWindow: 1050000,
11100
+ maxTokens: 128000,
11101
+ },
10943
11102
  "grok-4.5": {
10944
11103
  id: "grok-4.5",
10945
11104
  name: "Grok 4.5",
@@ -12493,6 +12652,23 @@ export const MODELS = {
12493
12652
  contextWindow: 1000000,
12494
12653
  maxTokens: 128000,
12495
12654
  },
12655
+ "anthropic/claude-sonnet-5.5:batch": {
12656
+ id: "anthropic/claude-sonnet-5.5:batch",
12657
+ name: "Anthropic: Claude Sonnet 5.5 (batch)",
12658
+ api: "openai-completions",
12659
+ provider: "openrouter",
12660
+ baseUrl: "https://openrouter.ai/api/v1",
12661
+ reasoning: true,
12662
+ input: ["text", "image"],
12663
+ cost: {
12664
+ input: 1,
12665
+ output: 5,
12666
+ cacheRead: 0.09999999999999999,
12667
+ cacheWrite: 1.25,
12668
+ },
12669
+ contextWindow: 1000000,
12670
+ maxTokens: 128000,
12671
+ },
12496
12672
  "anthropic/claude-sonnet-5:batch": {
12497
12673
  id: "anthropic/claude-sonnet-5:batch",
12498
12674
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -12808,13 +12984,13 @@ export const MODELS = {
12808
12984
  reasoning: true,
12809
12985
  input: ["text"],
12810
12986
  cost: {
12811
- input: 0.27,
12987
+ input: 0.3,
12812
12988
  output: 1,
12813
- cacheRead: 0,
12989
+ cacheRead: 0.135,
12814
12990
  cacheWrite: 0,
12815
12991
  },
12816
12992
  contextWindow: 163840,
12817
- maxTokens: 147456,
12993
+ maxTokens: 65536,
12818
12994
  },
12819
12995
  "deepseek/deepseek-v3.2": {
12820
12996
  id: "deepseek/deepseek-v3.2",
@@ -12842,9 +13018,9 @@ export const MODELS = {
12842
13018
  reasoning: true,
12843
13019
  input: ["text"],
12844
13020
  cost: {
12845
- input: 0.13440000000000002,
12846
- output: 0.2016,
12847
- cacheRead: 0.06720000000000001,
13021
+ input: 0.27,
13022
+ output: 0.41,
13023
+ cacheRead: 0,
12848
13024
  cacheWrite: 0,
12849
13025
  },
12850
13026
  contextWindow: 163840,
@@ -12861,9 +13037,9 @@ export const MODELS = {
12861
13037
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12862
13038
  input: ["text"],
12863
13039
  cost: {
12864
- input: 0.06538,
12865
- output: 0.13076,
12866
- cacheRead: 0.013076,
13040
+ input: 0.14,
13041
+ output: 0.28,
13042
+ cacheRead: 0.028,
12867
13043
  cacheWrite: 0,
12868
13044
  },
12869
13045
  contextWindow: 1048576,
@@ -12880,12 +13056,12 @@ export const MODELS = {
12880
13056
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12881
13057
  input: ["text"],
12882
13058
  cost: {
12883
- input: 0.020999999999999998,
12884
- output: 0.32,
12885
- cacheRead: 0.016,
13059
+ input: 0.01,
13060
+ output: 1.28,
13061
+ cacheRead: 0.01,
12886
13062
  cacheWrite: 0,
12887
13063
  },
12888
- contextWindow: 1310720,
13064
+ contextWindow: 1048576,
12889
13065
  maxTokens: 943718,
12890
13066
  },
12891
13067
  "deepseek/deepseek-v4-flash-vision-exp": {
@@ -12899,13 +13075,13 @@ export const MODELS = {
12899
13075
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12900
13076
  input: ["text", "image"],
12901
13077
  cost: {
12902
- input: 0.44,
12903
- output: 1.32,
12904
- cacheRead: 0.014,
13078
+ input: 0.21559999999999999,
13079
+ output: 0.6468,
13080
+ cacheRead: 0.00686,
12905
13081
  cacheWrite: 0,
12906
13082
  },
12907
13083
  contextWindow: 1048576,
12908
- maxTokens: 943717,
13084
+ maxTokens: 262144,
12909
13085
  },
12910
13086
  "deepseek/deepseek-v4-pro": {
12911
13087
  id: "deepseek/deepseek-v4-pro",
@@ -12918,9 +13094,9 @@ export const MODELS = {
12918
13094
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12919
13095
  input: ["text"],
12920
13096
  cost: {
12921
- input: 0.7829999999999999,
12922
- output: 1.5659999999999998,
12923
- cacheRead: 0.06525,
13097
+ input: 0.9552599999999999,
13098
+ output: 1.9105199999999998,
13099
+ cacheRead: 0.07960500000000001,
12924
13100
  cacheWrite: 0,
12925
13101
  },
12926
13102
  contextWindow: 1048576,
@@ -12937,13 +13113,13 @@ export const MODELS = {
12937
13113
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12938
13114
  input: ["text"],
12939
13115
  cost: {
12940
- input: 0.3995,
12941
- output: 4.199999999999999,
12942
- cacheRead: 0.399,
13116
+ input: 1.32,
13117
+ output: 3.9600000000000004,
13118
+ cacheRead: 0.044,
12943
13119
  cacheWrite: 0,
12944
13120
  },
12945
13121
  contextWindow: 1048576,
12946
- maxTokens: 943718,
13122
+ maxTokens: 393216,
12947
13123
  },
12948
13124
  "deepseek/deepseek-v4.1-flash": {
12949
13125
  id: "deepseek/deepseek-v4.1-flash",
@@ -12956,9 +13132,9 @@ export const MODELS = {
12956
13132
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12957
13133
  input: ["text", "image"],
12958
13134
  cost: {
12959
- input: 0.3,
12960
- output: 1.2,
12961
- cacheRead: 0.006,
13135
+ input: 0.019799999999999998,
13136
+ output: 0.396,
13137
+ cacheRead: 0.0029100000000000003,
12962
13138
  cacheWrite: 0,
12963
13139
  },
12964
13140
  contextWindow: 1048576,
@@ -13825,13 +14001,13 @@ export const MODELS = {
13825
14001
  reasoning: true,
13826
14002
  input: ["text", "image"],
13827
14003
  cost: {
13828
- input: 0.3,
13829
- output: 1.2,
14004
+ input: 0.35,
14005
+ output: 1.5,
13830
14006
  cacheRead: 0.04,
13831
14007
  cacheWrite: 0,
13832
14008
  },
13833
14009
  contextWindow: 131072,
13834
- maxTokens: 16384,
14010
+ maxTokens: 117964,
13835
14011
  },
13836
14012
  "meta/muse-spark-1.1": {
13837
14013
  id: "meta/muse-spark-1.1",
@@ -13995,13 +14171,13 @@ export const MODELS = {
13995
14171
  reasoning: true,
13996
14172
  input: ["text"],
13997
14173
  cost: {
13998
- input: 0.3,
13999
- output: 1.2,
14000
- cacheRead: 0.06,
14174
+ input: 0.21,
14175
+ output: 0.84,
14176
+ cacheRead: 0.041999999999999996,
14001
14177
  cacheWrite: 0,
14002
14178
  },
14003
14179
  contextWindow: 204800,
14004
- maxTokens: 131072,
14180
+ maxTokens: 176947,
14005
14181
  },
14006
14182
  "minimax/minimax-m3": {
14007
14183
  id: "minimax/minimax-m3",
@@ -14522,8 +14698,8 @@ export const MODELS = {
14522
14698
  reasoning: true,
14523
14699
  input: ["text", "image"],
14524
14700
  cost: {
14525
- input: 0.6562,
14526
- output: 3.3000000000000003,
14701
+ input: 0.6712,
14702
+ output: 3.35,
14527
14703
  cacheRead: 0.18,
14528
14704
  cacheWrite: 0,
14529
14705
  },
@@ -14692,12 +14868,12 @@ export const MODELS = {
14692
14868
  reasoning: true,
14693
14869
  input: ["text"],
14694
14870
  cost: {
14695
- input: 0.08,
14696
- output: 0.19999999999999998,
14697
- cacheRead: 0.04,
14871
+ input: 0.06,
14872
+ output: 0.16,
14873
+ cacheRead: 0.03,
14698
14874
  cacheWrite: 0,
14699
14875
  },
14700
- contextWindow: 1000000,
14876
+ contextWindow: 262144,
14701
14877
  maxTokens: 32768,
14702
14878
  },
14703
14879
  "nvidia/nemotron-3.5-lightning:free": {
@@ -15960,6 +16136,74 @@ export const MODELS = {
15960
16136
  contextWindow: 1050000,
15961
16137
  maxTokens: 128000,
15962
16138
  },
16139
+ "openai/gpt-6.1-sol": {
16140
+ id: "openai/gpt-6.1-sol",
16141
+ name: "OpenAI: GPT-6.1 Sol",
16142
+ api: "openai-completions",
16143
+ provider: "openrouter",
16144
+ baseUrl: "https://openrouter.ai/api/v1",
16145
+ reasoning: true,
16146
+ input: ["text", "image"],
16147
+ cost: {
16148
+ input: 2,
16149
+ output: 10,
16150
+ cacheRead: 0.09999999999999999,
16151
+ cacheWrite: 2.5,
16152
+ },
16153
+ contextWindow: 1050000,
16154
+ maxTokens: 128000,
16155
+ },
16156
+ "openai/gpt-6.1-sol-pro": {
16157
+ id: "openai/gpt-6.1-sol-pro",
16158
+ name: "OpenAI: GPT-6.1 Sol Pro",
16159
+ api: "openai-completions",
16160
+ provider: "openrouter",
16161
+ baseUrl: "https://openrouter.ai/api/v1",
16162
+ reasoning: true,
16163
+ input: ["text", "image"],
16164
+ cost: {
16165
+ input: 2,
16166
+ output: 10,
16167
+ cacheRead: 0.09999999999999999,
16168
+ cacheWrite: 2.5,
16169
+ },
16170
+ contextWindow: 1050000,
16171
+ maxTokens: 128000,
16172
+ },
16173
+ "openai/gpt-6.1-sol-pro:batch": {
16174
+ id: "openai/gpt-6.1-sol-pro:batch",
16175
+ name: "OpenAI: GPT-6.1 Sol Pro (batch)",
16176
+ api: "openai-completions",
16177
+ provider: "openrouter",
16178
+ baseUrl: "https://openrouter.ai/api/v1",
16179
+ reasoning: true,
16180
+ input: ["text", "image"],
16181
+ cost: {
16182
+ input: 1,
16183
+ output: 5,
16184
+ cacheRead: 0.049999999999999996,
16185
+ cacheWrite: 1.25,
16186
+ },
16187
+ contextWindow: 1050000,
16188
+ maxTokens: 128000,
16189
+ },
16190
+ "openai/gpt-6.1-sol:batch": {
16191
+ id: "openai/gpt-6.1-sol:batch",
16192
+ name: "OpenAI: GPT-6.1 Sol (batch)",
16193
+ api: "openai-completions",
16194
+ provider: "openrouter",
16195
+ baseUrl: "https://openrouter.ai/api/v1",
16196
+ reasoning: true,
16197
+ input: ["text", "image"],
16198
+ cost: {
16199
+ input: 1,
16200
+ output: 5,
16201
+ cacheRead: 0.049999999999999996,
16202
+ cacheWrite: 1.25,
16203
+ },
16204
+ contextWindow: 1050000,
16205
+ maxTokens: 128000,
16206
+ },
15963
16207
  "openai/gpt-audio": {
15964
16208
  id: "openai/gpt-audio",
15965
16209
  name: "OpenAI: GPT Audio",
@@ -16020,13 +16264,13 @@ export const MODELS = {
16020
16264
  reasoning: true,
16021
16265
  input: ["text"],
16022
16266
  cost: {
16023
- input: 0.15,
16024
- output: 0.6,
16025
- cacheRead: 0.075,
16267
+ input: 0.037,
16268
+ output: 0.16999999999999998,
16269
+ cacheRead: 0,
16026
16270
  cacheWrite: 0,
16027
16271
  },
16028
16272
  contextWindow: 131072,
16029
- maxTokens: 65536,
16273
+ maxTokens: 117964,
16030
16274
  },
16031
16275
  "openai/gpt-oss-120b:batch": {
16032
16276
  id: "openai/gpt-oss-120b:batch",
@@ -16056,7 +16300,7 @@ export const MODELS = {
16056
16300
  cost: {
16057
16301
  input: 0.018,
16058
16302
  output: 0.09,
16059
- cacheRead: 0,
16303
+ cacheRead: 0.009,
16060
16304
  cacheWrite: 0,
16061
16305
  },
16062
16306
  contextWindow: 131072,
@@ -16413,7 +16657,7 @@ export const MODELS = {
16413
16657
  cost: {
16414
16658
  input: 0.075,
16415
16659
  output: 0.5,
16416
- cacheRead: 0,
16660
+ cacheRead: 0.0375,
16417
16661
  cacheWrite: 0,
16418
16662
  },
16419
16663
  contextWindow: 262144,
@@ -16564,13 +16808,13 @@ export const MODELS = {
16564
16808
  reasoning: true,
16565
16809
  input: ["text"],
16566
16810
  cost: {
16567
- input: 0.12,
16568
- output: 0.5,
16811
+ input: 0.13,
16812
+ output: 0.52,
16569
16813
  cacheRead: 0,
16570
16814
  cacheWrite: 0,
16571
16815
  },
16572
16816
  contextWindow: 131072,
16573
- maxTokens: 16384,
16817
+ maxTokens: 8192,
16574
16818
  },
16575
16819
  "qwen/qwen3-30b-a3b-instruct-2507": {
16576
16820
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -16581,13 +16825,13 @@ export const MODELS = {
16581
16825
  reasoning: false,
16582
16826
  input: ["text"],
16583
16827
  cost: {
16584
- input: 0.09999999999999999,
16585
- output: 0.3,
16828
+ input: 0.04815,
16829
+ output: 0.19305,
16586
16830
  cacheRead: 0,
16587
16831
  cacheWrite: 0,
16588
16832
  },
16589
16833
  contextWindow: 262144,
16590
- maxTokens: 235929,
16834
+ maxTokens: 32000,
16591
16835
  },
16592
16836
  "qwen/qwen3-30b-a3b-thinking-2507": {
16593
16837
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16927,7 +17171,7 @@ export const MODELS = {
16927
17171
  cacheWrite: 0,
16928
17172
  },
16929
17173
  contextWindow: 262144,
16930
- maxTokens: 235929,
17174
+ maxTokens: 65536,
16931
17175
  },
16932
17176
  "qwen/qwen3.5-27b": {
16933
17177
  id: "qwen/qwen3.5-27b",
@@ -17482,9 +17726,9 @@ export const MODELS = {
17482
17726
  reasoning: true,
17483
17727
  input: ["text"],
17484
17728
  cost: {
17485
- input: 0.0825,
17486
- output: 0.33,
17487
- cacheRead: 0.020625,
17729
+ input: 0.13199999999999998,
17730
+ output: 0.5279999999999999,
17731
+ cacheRead: 0.032999999999999995,
17488
17732
  cacheWrite: 0,
17489
17733
  },
17490
17734
  contextWindow: 262144,
@@ -17737,9 +17981,9 @@ export const MODELS = {
17737
17981
  reasoning: true,
17738
17982
  input: ["text", "image"],
17739
17983
  cost: {
17740
- input: 1.5999999999999999,
17741
- output: 4.8,
17742
- cacheRead: 0.39999999999999997,
17984
+ input: 2,
17985
+ output: 6,
17986
+ cacheRead: 0.5,
17743
17987
  cacheWrite: 0,
17744
17988
  },
17745
17989
  contextWindow: 500000,
@@ -18009,9 +18253,9 @@ export const MODELS = {
18009
18253
  reasoning: true,
18010
18254
  input: ["text"],
18011
18255
  cost: {
18012
- input: 0.9646,
18013
- output: 3.0316,
18014
- cacheRead: 0.17914,
18256
+ input: 1.4,
18257
+ output: 4.4,
18258
+ cacheRead: 0.26,
18015
18259
  cacheWrite: 0,
18016
18260
  },
18017
18261
  contextWindow: 204800,
@@ -18026,13 +18270,13 @@ export const MODELS = {
18026
18270
  reasoning: true,
18027
18271
  input: ["text"],
18028
18272
  cost: {
18029
- input: 0.6496,
18030
- output: 2.0416,
18031
- cacheRead: 0.12064,
18273
+ input: 0.36,
18274
+ output: 3.9899999999999998,
18275
+ cacheRead: 0.26,
18032
18276
  cacheWrite: 0,
18033
18277
  },
18034
18278
  contextWindow: 1048576,
18035
- maxTokens: 131072,
18279
+ maxTokens: 943718,
18036
18280
  },
18037
18281
  "z-ai/glm-5.3": {
18038
18282
  id: "z-ai/glm-5.3",
@@ -18043,13 +18287,13 @@ export const MODELS = {
18043
18287
  reasoning: true,
18044
18288
  input: ["text"],
18045
18289
  cost: {
18046
- input: 0.1785,
18047
- output: 2.8049999999999997,
18048
- cacheRead: 0.146625,
18290
+ input: 1.4,
18291
+ output: 4.4,
18292
+ cacheRead: 0.26,
18049
18293
  cacheWrite: 0,
18050
18294
  },
18051
- contextWindow: 1310720,
18052
- maxTokens: 943718,
18295
+ contextWindow: 1048576,
18296
+ maxTokens: 943717,
18053
18297
  },
18054
18298
  "z-ai/glm-5.3-flash": {
18055
18299
  id: "z-ai/glm-5.3-flash",
@@ -18065,7 +18309,7 @@ export const MODELS = {
18065
18309
  cacheRead: 0.03,
18066
18310
  cacheWrite: 0,
18067
18311
  },
18068
- contextWindow: 1310720,
18312
+ contextWindow: 1048576,
18069
18313
  maxTokens: 943717,
18070
18314
  },
18071
18315
  "z-ai/glm-5.3-flash:batch": {
@@ -18231,9 +18475,9 @@ export const MODELS = {
18231
18475
  reasoning: true,
18232
18476
  input: ["text", "image"],
18233
18477
  cost: {
18234
- input: 0.03,
18235
- output: 0.6,
18236
- cacheRead: 0.01,
18478
+ input: 0.019799999999999998,
18479
+ output: 0.396,
18480
+ cacheRead: 0.0029100000000000003,
18237
18481
  cacheWrite: 0,
18238
18482
  },
18239
18483
  contextWindow: 1048576,
@@ -18248,13 +18492,13 @@ export const MODELS = {
18248
18492
  reasoning: true,
18249
18493
  input: ["text"],
18250
18494
  cost: {
18251
- input: 0.22592,
18252
- output: 1.9584000000000001,
18253
- cacheRead: 0.08832,
18495
+ input: 0.15,
18496
+ output: 3.5,
18497
+ cacheRead: 0.15,
18254
18498
  cacheWrite: 0,
18255
18499
  },
18256
18500
  contextWindow: 1048576,
18257
- maxTokens: 943718,
18501
+ maxTokens: 393216,
18258
18502
  },
18259
18503
  "~deepseek/deepseek-v4-flash-latest": {
18260
18504
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -18267,12 +18511,12 @@ export const MODELS = {
18267
18511
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18268
18512
  input: ["text"],
18269
18513
  cost: {
18270
- input: 0.020999999999999998,
18271
- output: 0.32,
18272
- cacheRead: 0.016,
18514
+ input: 0.009899999999999999,
18515
+ output: 0.13068,
18516
+ cacheRead: 0.0013859999999999999,
18273
18517
  cacheWrite: 0,
18274
18518
  },
18275
- contextWindow: 1310720,
18519
+ contextWindow: 1048576,
18276
18520
  maxTokens: 943718,
18277
18521
  },
18278
18522
  "~google/gemini-flash-latest": {
@@ -18318,9 +18562,9 @@ export const MODELS = {
18318
18562
  reasoning: true,
18319
18563
  input: ["text", "image"],
18320
18564
  cost: {
18321
- input: 0.875,
18322
- output: 11.2,
18323
- cacheRead: 0.29,
18565
+ input: 0.3654,
18566
+ output: 9.1343,
18567
+ cacheRead: 0.39999999999999997,
18324
18568
  cacheWrite: 0,
18325
18569
  },
18326
18570
  contextWindow: 1048576,
@@ -18388,7 +18632,7 @@ export const MODELS = {
18388
18632
  cost: {
18389
18633
  input: 2,
18390
18634
  output: 10,
18391
- cacheRead: 0.19999999999999998,
18635
+ cacheRead: 0.09999999999999999,
18392
18636
  cacheWrite: 2.5,
18393
18637
  },
18394
18638
  contextWindow: 1050000,
@@ -18420,9 +18664,9 @@ export const MODELS = {
18420
18664
  reasoning: true,
18421
18665
  input: ["text", "image"],
18422
18666
  cost: {
18423
- input: 1.5999999999999999,
18424
- output: 4.8,
18425
- cacheRead: 0.39999999999999997,
18667
+ input: 2,
18668
+ output: 6,
18669
+ cacheRead: 0.5,
18426
18670
  cacheWrite: 0,
18427
18671
  },
18428
18672
  contextWindow: 500000,
@@ -18437,13 +18681,13 @@ export const MODELS = {
18437
18681
  reasoning: true,
18438
18682
  input: ["text", "image"],
18439
18683
  cost: {
18440
- input: 0.045,
18441
- output: 0.14,
18684
+ input: 0.02,
18685
+ output: 0.24750000000000003,
18442
18686
  cacheRead: 0.01,
18443
18687
  cacheWrite: 0,
18444
18688
  },
18445
- contextWindow: 1310720,
18446
- maxTokens: 128000,
18689
+ contextWindow: 1048576,
18690
+ maxTokens: 943718,
18447
18691
  },
18448
18692
  "~z-ai/glm-latest": {
18449
18693
  id: "~z-ai/glm-latest",
@@ -18454,13 +18698,13 @@ export const MODELS = {
18454
18698
  reasoning: true,
18455
18699
  input: ["text"],
18456
18700
  cost: {
18457
- input: 0.1785,
18458
- output: 2.8049999999999997,
18459
- cacheRead: 0.146625,
18701
+ input: 0.13,
18702
+ output: 4,
18703
+ cacheRead: 0.13,
18460
18704
  cacheWrite: 0,
18461
18705
  },
18462
- contextWindow: 1310720,
18463
- maxTokens: 943718,
18706
+ contextWindow: 1048576,
18707
+ maxTokens: 131072,
18464
18708
  },
18465
18709
  },
18466
18710
  "together": {
@@ -18689,44 +18933,6 @@ export const MODELS = {
18689
18933
  contextWindow: 131072,
18690
18934
  maxTokens: 131072,
18691
18935
  },
18692
- "moonshotai/Kimi-K2.6": {
18693
- id: "moonshotai/Kimi-K2.6",
18694
- name: "Kimi K2.6",
18695
- api: "openai-completions",
18696
- provider: "together",
18697
- baseUrl: "https://api.together.ai/v1",
18698
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18699
- reasoning: true,
18700
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18701
- input: ["text", "image"],
18702
- cost: {
18703
- input: 1.2,
18704
- output: 4.5,
18705
- cacheRead: 0.2,
18706
- cacheWrite: 0,
18707
- },
18708
- contextWindow: 262144,
18709
- maxTokens: 131000,
18710
- },
18711
- "moonshotai/Kimi-K2.7-Code": {
18712
- id: "moonshotai/Kimi-K2.7-Code",
18713
- name: "Kimi K2.7 Code",
18714
- api: "openai-completions",
18715
- provider: "together",
18716
- baseUrl: "https://api.together.ai/v1",
18717
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18718
- reasoning: true,
18719
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18720
- input: ["text"],
18721
- cost: {
18722
- input: 0.95,
18723
- output: 4,
18724
- cacheRead: 0.19,
18725
- cacheWrite: 0,
18726
- },
18727
- contextWindow: 262144,
18728
- maxTokens: 131072,
18729
- },
18730
18936
  "moonshotai/Kimi-K3": {
18731
18937
  id: "moonshotai/Kimi-K3",
18732
18938
  name: "Kimi K3",
@@ -20409,9 +20615,9 @@ export const MODELS = {
20409
20615
  reasoning: true,
20410
20616
  input: ["text"],
20411
20617
  cost: {
20412
- input: 0.06,
20413
- output: 0.18,
20414
- cacheRead: 0.012,
20618
+ input: 0.075,
20619
+ output: 0.22,
20620
+ cacheRead: 0.015,
20415
20621
  cacheWrite: 0,
20416
20622
  },
20417
20623
  contextWindow: 256000,
@@ -20468,6 +20674,40 @@ export const MODELS = {
20468
20674
  contextWindow: 256000,
20469
20675
  maxTokens: 32000,
20470
20676
  },
20677
+ "inclusionai/ling-3.1-flash": {
20678
+ id: "inclusionai/ling-3.1-flash",
20679
+ name: "Ling 3.1 Flash",
20680
+ api: "anthropic-messages",
20681
+ provider: "vercel-ai-gateway",
20682
+ baseUrl: "https://ai-gateway.vercel.sh",
20683
+ reasoning: true,
20684
+ input: ["text"],
20685
+ cost: {
20686
+ input: 0,
20687
+ output: 0,
20688
+ cacheRead: 0,
20689
+ cacheWrite: 0,
20690
+ },
20691
+ contextWindow: 262144,
20692
+ maxTokens: 32768,
20693
+ },
20694
+ "inclusionai/ling-3.1-flash-free": {
20695
+ id: "inclusionai/ling-3.1-flash-free",
20696
+ name: "Ling 3.1 Flash (Free)",
20697
+ api: "anthropic-messages",
20698
+ provider: "vercel-ai-gateway",
20699
+ baseUrl: "https://ai-gateway.vercel.sh",
20700
+ reasoning: true,
20701
+ input: ["text"],
20702
+ cost: {
20703
+ input: 0,
20704
+ output: 0,
20705
+ cacheRead: 0,
20706
+ cacheWrite: 0,
20707
+ },
20708
+ contextWindow: 262144,
20709
+ maxTokens: 32768,
20710
+ },
20471
20711
  "interfaze/interfaze-beta": {
20472
20712
  id: "interfaze/interfaze-beta",
20473
20713
  name: "Interfaze Beta",
@@ -22081,6 +22321,40 @@ export const MODELS = {
22081
22321
  contextWindow: 1050000,
22082
22322
  maxTokens: 128000,
22083
22323
  },
22324
+ "openai/gpt-6.1-sol": {
22325
+ id: "openai/gpt-6.1-sol",
22326
+ name: "GPT-6.1 Sol",
22327
+ api: "anthropic-messages",
22328
+ provider: "vercel-ai-gateway",
22329
+ baseUrl: "https://ai-gateway.vercel.sh",
22330
+ reasoning: true,
22331
+ input: ["text", "image"],
22332
+ cost: {
22333
+ input: 2,
22334
+ output: 10,
22335
+ cacheRead: 0.09999999999999999,
22336
+ cacheWrite: 2.5,
22337
+ },
22338
+ contextWindow: 1050000,
22339
+ maxTokens: 128000,
22340
+ },
22341
+ "openai/gpt-6.1-sol-fast": {
22342
+ id: "openai/gpt-6.1-sol-fast",
22343
+ name: "GPT-6.1 Sol (Fast)",
22344
+ api: "anthropic-messages",
22345
+ provider: "vercel-ai-gateway",
22346
+ baseUrl: "https://ai-gateway.vercel.sh",
22347
+ reasoning: true,
22348
+ input: ["text", "image"],
22349
+ cost: {
22350
+ input: 4,
22351
+ output: 20,
22352
+ cacheRead: 0.19999999999999998,
22353
+ cacheWrite: 5,
22354
+ },
22355
+ contextWindow: 1050000,
22356
+ maxTokens: 128000,
22357
+ },
22084
22358
  "openai/gpt-oss-120b": {
22085
22359
  id: "openai/gpt-oss-120b",
22086
22360
  name: "GPT OSS 120B",