@elyracode/ai 0.9.44 → 0.9.46

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)",
@@ -1274,6 +1310,23 @@ export const MODELS = {
1274
1310
  contextWindow: 1050000,
1275
1311
  maxTokens: 128000,
1276
1312
  },
1313
+ "global.openai.gpt-6.1-sol": {
1314
+ id: "global.openai.gpt-6.1-sol",
1315
+ name: "GPT-6.1 Sol (Global)",
1316
+ api: "bedrock-converse-stream",
1317
+ provider: "amazon-bedrock",
1318
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1319
+ reasoning: true,
1320
+ input: ["text", "image"],
1321
+ cost: {
1322
+ input: 2,
1323
+ output: 10,
1324
+ cacheRead: 0.1,
1325
+ cacheWrite: 2.5,
1326
+ },
1327
+ contextWindow: 1050000,
1328
+ maxTokens: 128000,
1329
+ },
1277
1330
  "global.xai.grok-4.6": {
1278
1331
  id: "global.xai.grok-4.6",
1279
1332
  name: "Grok 4.6 (Global)",
@@ -1291,6 +1344,23 @@ export const MODELS = {
1291
1344
  contextWindow: 500000,
1292
1345
  maxTokens: 500000,
1293
1346
  },
1347
+ "global.xai.grok-4.7": {
1348
+ id: "global.xai.grok-4.7",
1349
+ name: "Grok 4.7 (Global)",
1350
+ api: "bedrock-converse-stream",
1351
+ provider: "amazon-bedrock",
1352
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1353
+ reasoning: true,
1354
+ input: ["text", "image"],
1355
+ cost: {
1356
+ input: 2,
1357
+ output: 6,
1358
+ cacheRead: 0.5,
1359
+ cacheWrite: 0,
1360
+ },
1361
+ contextWindow: 500000,
1362
+ maxTokens: 500000,
1363
+ },
1294
1364
  "google.gemma-4-26b-a4b": {
1295
1365
  id: "google.gemma-4-26b-a4b",
1296
1366
  name: "Gemma 4 26B A4B IT",
@@ -1342,6 +1412,60 @@ export const MODELS = {
1342
1412
  contextWindow: 131072,
1343
1413
  maxTokens: 8192,
1344
1414
  },
1415
+ "in.anthropic.claude-haiku-4-5-20251001-v1:0": {
1416
+ id: "in.anthropic.claude-haiku-4-5-20251001-v1:0",
1417
+ name: "Claude Haiku 4.5 (India)",
1418
+ api: "bedrock-converse-stream",
1419
+ provider: "amazon-bedrock",
1420
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1421
+ reasoning: true,
1422
+ thinkingType: "budget",
1423
+ input: ["text", "image"],
1424
+ cost: {
1425
+ input: 1.1,
1426
+ output: 5.5,
1427
+ cacheRead: 0.11,
1428
+ cacheWrite: 1.375,
1429
+ },
1430
+ contextWindow: 200000,
1431
+ maxTokens: 64000,
1432
+ },
1433
+ "in.anthropic.claude-opus-5": {
1434
+ id: "in.anthropic.claude-opus-5",
1435
+ name: "Claude Opus 5 (India)",
1436
+ api: "bedrock-converse-stream",
1437
+ provider: "amazon-bedrock",
1438
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1439
+ reasoning: true,
1440
+ thinkingType: "adaptive",
1441
+ input: ["text", "image"],
1442
+ cost: {
1443
+ input: 5.5,
1444
+ output: 27.5,
1445
+ cacheRead: 0.55,
1446
+ cacheWrite: 6.875,
1447
+ },
1448
+ contextWindow: 1000000,
1449
+ maxTokens: 128000,
1450
+ },
1451
+ "in.anthropic.claude-sonnet-5": {
1452
+ id: "in.anthropic.claude-sonnet-5",
1453
+ name: "Claude Sonnet 5 (India)",
1454
+ api: "bedrock-converse-stream",
1455
+ provider: "amazon-bedrock",
1456
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1457
+ reasoning: true,
1458
+ thinkingType: "adaptive",
1459
+ input: ["text", "image"],
1460
+ cost: {
1461
+ input: 2.2,
1462
+ output: 11,
1463
+ cacheRead: 0.22,
1464
+ cacheWrite: 2.75,
1465
+ },
1466
+ contextWindow: 1000000,
1467
+ maxTokens: 128000,
1468
+ },
1345
1469
  "in.openai.gpt-5.6-luna": {
1346
1470
  id: "in.openai.gpt-5.6-luna",
1347
1471
  name: "GPT-5.6 Luna (India)",
@@ -2068,6 +2192,23 @@ export const MODELS = {
2068
2192
  contextWindow: 1050000,
2069
2193
  maxTokens: 128000,
2070
2194
  },
2195
+ "openai.gpt-6.1-sol": {
2196
+ id: "openai.gpt-6.1-sol",
2197
+ name: "GPT-6.1 Sol",
2198
+ api: "bedrock-converse-stream",
2199
+ provider: "amazon-bedrock",
2200
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2201
+ reasoning: true,
2202
+ input: ["text", "image"],
2203
+ cost: {
2204
+ input: 2.2,
2205
+ output: 11,
2206
+ cacheRead: 0.11,
2207
+ cacheWrite: 2.75,
2208
+ },
2209
+ contextWindow: 1050000,
2210
+ maxTokens: 128000,
2211
+ },
2071
2212
  "openai.gpt-oss-120b": {
2072
2213
  id: "openai.gpt-oss-120b",
2073
2214
  name: "gpt-oss-120b",
@@ -2886,6 +3027,23 @@ export const MODELS = {
2886
3027
  contextWindow: 1050000,
2887
3028
  maxTokens: 128000,
2888
3029
  },
3030
+ "us.openai.gpt-6.1-sol": {
3031
+ id: "us.openai.gpt-6.1-sol",
3032
+ name: "GPT-6.1 Sol (US)",
3033
+ api: "bedrock-converse-stream",
3034
+ provider: "amazon-bedrock",
3035
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3036
+ reasoning: true,
3037
+ input: ["text", "image"],
3038
+ cost: {
3039
+ input: 2.2,
3040
+ output: 11,
3041
+ cacheRead: 0.11,
3042
+ cacheWrite: 2.75,
3043
+ },
3044
+ contextWindow: 1050000,
3045
+ maxTokens: 128000,
3046
+ },
2889
3047
  "us.writer.palmyra-x4-v1:0": {
2890
3048
  id: "us.writer.palmyra-x4-v1:0",
2891
3049
  name: "Palmyra X4 (US)",
@@ -2937,6 +3095,23 @@ export const MODELS = {
2937
3095
  contextWindow: 500000,
2938
3096
  maxTokens: 500000,
2939
3097
  },
3098
+ "us.xai.grok-4.7": {
3099
+ id: "us.xai.grok-4.7",
3100
+ name: "Grok 4.7 (US)",
3101
+ api: "bedrock-converse-stream",
3102
+ provider: "amazon-bedrock",
3103
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3104
+ reasoning: true,
3105
+ input: ["text", "image"],
3106
+ cost: {
3107
+ input: 2.2,
3108
+ output: 6.6,
3109
+ cacheRead: 0.55,
3110
+ cacheWrite: 0,
3111
+ },
3112
+ contextWindow: 500000,
3113
+ maxTokens: 500000,
3114
+ },
2940
3115
  "writer.palmyra-x4-v1:0": {
2941
3116
  id: "writer.palmyra-x4-v1:0",
2942
3117
  name: "Palmyra X4",
@@ -3938,6 +4113,23 @@ export const MODELS = {
3938
4113
  contextWindow: 1050000,
3939
4114
  maxTokens: 128000,
3940
4115
  },
4116
+ "gpt-6.1-sol": {
4117
+ id: "gpt-6.1-sol",
4118
+ name: "GPT-6.1 Sol",
4119
+ api: "azure-openai-responses",
4120
+ provider: "azure-openai-responses",
4121
+ baseUrl: "",
4122
+ reasoning: true,
4123
+ input: ["text", "image"],
4124
+ cost: {
4125
+ input: 2,
4126
+ output: 10,
4127
+ cacheRead: 0.1,
4128
+ cacheWrite: 2.5,
4129
+ },
4130
+ contextWindow: 1050000,
4131
+ maxTokens: 128000,
4132
+ },
3941
4133
  "gpt-daybreak-blue-latest": {
3942
4134
  id: "gpt-daybreak-blue-latest",
3943
4135
  name: "Daybreak Blue",
@@ -4121,7 +4313,7 @@ export const MODELS = {
4121
4313
  cost: {
4122
4314
  input: 0.99,
4123
4315
  output: 1.49,
4124
- cacheRead: 0,
4316
+ cacheRead: 0.99,
4125
4317
  cacheWrite: 0,
4126
4318
  },
4127
4319
  contextWindow: 131072,
@@ -4301,7 +4493,7 @@ export const MODELS = {
4301
4493
  cacheRead: 0.3,
4302
4494
  cacheWrite: 3.75,
4303
4495
  },
4304
- contextWindow: 1000000,
4496
+ contextWindow: 200000,
4305
4497
  maxTokens: 64000,
4306
4498
  },
4307
4499
  "claude-sonnet-4.6": {
@@ -4777,7 +4969,7 @@ export const MODELS = {
4777
4969
  cacheRead: 0.014,
4778
4970
  cacheWrite: 0,
4779
4971
  },
4780
- contextWindow: 1310720,
4972
+ contextWindow: 1048576,
4781
4973
  maxTokens: 1048576,
4782
4974
  },
4783
4975
  "@cf/deepseek-ai/deepseek-v4-pro-0813": {
@@ -4811,7 +5003,7 @@ export const MODELS = {
4811
5003
  cost: {
4812
5004
  input: 0.1,
4813
5005
  output: 0.3,
4814
- cacheRead: 0,
5006
+ cacheRead: 0.05,
4815
5007
  cacheWrite: 0,
4816
5008
  },
4817
5009
  contextWindow: 256000,
@@ -5066,7 +5258,7 @@ export const MODELS = {
5066
5258
  cacheRead: 0.26,
5067
5259
  cacheWrite: 0,
5068
5260
  },
5069
- contextWindow: 1310720,
5261
+ contextWindow: 1048576,
5070
5262
  maxTokens: 1048576,
5071
5263
  },
5072
5264
  "@cf/zai-org/glm-5.3-flash": {
@@ -5084,7 +5276,7 @@ export const MODELS = {
5084
5276
  cacheRead: 0.03,
5085
5277
  cacheWrite: 0,
5086
5278
  },
5087
- contextWindow: 1310720,
5279
+ contextWindow: 1048576,
5088
5280
  maxTokens: 1048576,
5089
5281
  },
5090
5282
  },
@@ -5138,9 +5330,9 @@ export const MODELS = {
5138
5330
  reasoning: true,
5139
5331
  input: ["text", "image"],
5140
5332
  cost: {
5141
- input: 0.22,
5142
- output: 0.66,
5143
- cacheRead: 0.007,
5333
+ input: 0.3,
5334
+ output: 1.2,
5335
+ cacheRead: 0.006,
5144
5336
  cacheWrite: 0,
5145
5337
  },
5146
5338
  contextWindow: 1000000,
@@ -5342,9 +5534,9 @@ export const MODELS = {
5342
5534
  reasoning: true,
5343
5535
  input: ["text", "image"],
5344
5536
  cost: {
5345
- input: 0.22,
5346
- output: 0.66,
5347
- cacheRead: 0.007,
5537
+ input: 0.3,
5538
+ output: 1.2,
5539
+ cacheRead: 0.006,
5348
5540
  cacheWrite: 0,
5349
5541
  },
5350
5542
  contextWindow: 1000000,
@@ -5677,6 +5869,25 @@ export const MODELS = {
5677
5869
  contextWindow: 1000000,
5678
5870
  maxTokens: 128000,
5679
5871
  },
5872
+ "claude-sonnet-5.5": {
5873
+ id: "claude-sonnet-5.5",
5874
+ name: "Claude Sonnet 5.5",
5875
+ api: "openai-completions",
5876
+ provider: "github-copilot",
5877
+ baseUrl: "https://api.individual.githubcopilot.com",
5878
+ 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" },
5879
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5880
+ reasoning: true,
5881
+ input: ["text", "image"],
5882
+ cost: {
5883
+ input: 2,
5884
+ output: 10,
5885
+ cacheRead: 0.2,
5886
+ cacheWrite: 2.5,
5887
+ },
5888
+ contextWindow: 1000000,
5889
+ maxTokens: 128000,
5890
+ },
5680
5891
  "gemini-3.5-flash": {
5681
5892
  id: "gemini-3.5-flash",
5682
5893
  name: "Gemini 3.5 Flash",
@@ -5981,6 +6192,25 @@ export const MODELS = {
5981
6192
  contextWindow: 1050000,
5982
6193
  maxTokens: 128000,
5983
6194
  },
6195
+ "gpt-6.1-sol": {
6196
+ id: "gpt-6.1-sol",
6197
+ name: "GPT-6.1 Sol",
6198
+ api: "openai-completions",
6199
+ provider: "github-copilot",
6200
+ baseUrl: "https://api.individual.githubcopilot.com",
6201
+ 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" },
6202
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6203
+ reasoning: true,
6204
+ input: ["text", "image"],
6205
+ cost: {
6206
+ input: 2,
6207
+ output: 10,
6208
+ cacheRead: 0.1,
6209
+ cacheWrite: 2.5,
6210
+ },
6211
+ contextWindow: 1050000,
6212
+ maxTokens: 128000,
6213
+ },
5984
6214
  "grok-4.5": {
5985
6215
  id: "grok-4.5",
5986
6216
  name: "Grok 4.5",
@@ -8397,7 +8627,7 @@ export const MODELS = {
8397
8627
  cost: {
8398
8628
  input: 0.3,
8399
8629
  output: 0.9,
8400
- cacheRead: 0,
8630
+ cacheRead: 0.03,
8401
8631
  cacheWrite: 0,
8402
8632
  },
8403
8633
  contextWindow: 256000,
@@ -8539,23 +8769,6 @@ export const MODELS = {
8539
8769
  contextWindow: 128000,
8540
8770
  maxTokens: 16384,
8541
8771
  },
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
8772
  "ministral-3b-latest": {
8560
8773
  id: "ministral-3b-latest",
8561
8774
  name: "Ministral 3B (latest)",
@@ -8618,7 +8831,7 @@ export const MODELS = {
8618
8831
  cost: {
8619
8832
  input: 0.5,
8620
8833
  output: 1.5,
8621
- cacheRead: 0,
8834
+ cacheRead: 0.05,
8622
8835
  cacheWrite: 0,
8623
8836
  },
8624
8837
  contextWindow: 262144,
@@ -8635,7 +8848,7 @@ export const MODELS = {
8635
8848
  cost: {
8636
8849
  input: 0.5,
8637
8850
  output: 1.5,
8638
- cacheRead: 0,
8851
+ cacheRead: 0.05,
8639
8852
  cacheWrite: 0,
8640
8853
  },
8641
8854
  contextWindow: 262144,
@@ -8686,7 +8899,7 @@ export const MODELS = {
8686
8899
  cost: {
8687
8900
  input: 1.5,
8688
8901
  output: 7.5,
8689
- cacheRead: 0,
8902
+ cacheRead: 0.15,
8690
8903
  cacheWrite: 0,
8691
8904
  },
8692
8905
  contextWindow: 262144,
@@ -8720,7 +8933,7 @@ export const MODELS = {
8720
8933
  cost: {
8721
8934
  input: 1.5,
8722
8935
  output: 7.5,
8723
- cacheRead: 0,
8936
+ cacheRead: 0.15,
8724
8937
  cacheWrite: 0,
8725
8938
  },
8726
8939
  contextWindow: 262144,
@@ -8771,7 +8984,7 @@ export const MODELS = {
8771
8984
  cost: {
8772
8985
  input: 0.15,
8773
8986
  output: 0.6,
8774
- cacheRead: 0,
8987
+ cacheRead: 0.015,
8775
8988
  cacheWrite: 0,
8776
8989
  },
8777
8990
  contextWindow: 256000,
@@ -8788,7 +9001,7 @@ export const MODELS = {
8788
9001
  cost: {
8789
9002
  input: 0.15,
8790
9003
  output: 0.6,
8791
- cacheRead: 0,
9004
+ cacheRead: 0.015,
8792
9005
  cacheWrite: 0,
8793
9006
  },
8794
9007
  contextWindow: 256000,
@@ -9682,24 +9895,41 @@ export const MODELS = {
9682
9895
  contextWindow: 1050000,
9683
9896
  maxTokens: 128000,
9684
9897
  },
9685
- "gpt-daybreak-blue-latest": {
9686
- id: "gpt-daybreak-blue-latest",
9687
- name: "Daybreak Blue",
9898
+ "gpt-6.1-sol": {
9899
+ id: "gpt-6.1-sol",
9900
+ name: "GPT-6.1 Sol",
9688
9901
  api: "openai-responses",
9689
9902
  provider: "openai",
9690
9903
  baseUrl: "https://api.openai.com/v1",
9691
9904
  reasoning: true,
9692
9905
  input: ["text", "image"],
9693
9906
  cost: {
9694
- input: 4,
9695
- output: 20,
9696
- cacheRead: 0.4,
9697
- cacheWrite: 5,
9907
+ input: 2,
9908
+ output: 10,
9909
+ cacheRead: 0.1,
9910
+ cacheWrite: 2.5,
9698
9911
  },
9699
9912
  contextWindow: 1050000,
9700
9913
  maxTokens: 128000,
9701
9914
  },
9702
- "gpt-daybreak-red-latest": {
9915
+ "gpt-daybreak-blue-latest": {
9916
+ id: "gpt-daybreak-blue-latest",
9917
+ name: "Daybreak Blue",
9918
+ api: "openai-responses",
9919
+ provider: "openai",
9920
+ baseUrl: "https://api.openai.com/v1",
9921
+ reasoning: true,
9922
+ input: ["text", "image"],
9923
+ cost: {
9924
+ input: 4,
9925
+ output: 20,
9926
+ cacheRead: 0.4,
9927
+ cacheWrite: 5,
9928
+ },
9929
+ contextWindow: 1050000,
9930
+ maxTokens: 128000,
9931
+ },
9932
+ "gpt-daybreak-red-latest": {
9703
9933
  id: "gpt-daybreak-red-latest",
9704
9934
  name: "Daybreak Red",
9705
9935
  api: "openai-responses",
@@ -10260,6 +10490,23 @@ export const MODELS = {
10260
10490
  contextWindow: 1000000,
10261
10491
  maxTokens: 128000,
10262
10492
  },
10493
+ "claude-sonnet-5-5": {
10494
+ id: "claude-sonnet-5-5",
10495
+ name: "Claude Sonnet 5.5",
10496
+ api: "anthropic-messages",
10497
+ provider: "opencode",
10498
+ baseUrl: "https://opencode.ai/zen",
10499
+ reasoning: true,
10500
+ input: ["text", "image"],
10501
+ cost: {
10502
+ input: 2,
10503
+ output: 10,
10504
+ cacheRead: 0.2,
10505
+ cacheWrite: 2.5,
10506
+ },
10507
+ contextWindow: 1000000,
10508
+ maxTokens: 128000,
10509
+ },
10263
10510
  "deepseek-v4-flash": {
10264
10511
  id: "deepseek-v4-flash",
10265
10512
  name: "DeepSeek V4 Flash",
@@ -10336,6 +10583,23 @@ export const MODELS = {
10336
10583
  contextWindow: 1000000,
10337
10584
  maxTokens: 384000,
10338
10585
  },
10586
+ "fledge-alpha-free": {
10587
+ id: "fledge-alpha-free",
10588
+ name: "Fledge Alpha Free",
10589
+ api: "openai-completions",
10590
+ provider: "opencode",
10591
+ baseUrl: "https://opencode.ai/zen/v1",
10592
+ reasoning: true,
10593
+ input: ["text", "image"],
10594
+ cost: {
10595
+ input: 0,
10596
+ output: 0,
10597
+ cacheRead: 0,
10598
+ cacheWrite: 0,
10599
+ },
10600
+ contextWindow: 1048576,
10601
+ maxTokens: 131072,
10602
+ },
10339
10603
  "gemini-3-flash": {
10340
10604
  id: "gemini-3-flash",
10341
10605
  name: "Gemini 3 Flash",
@@ -10940,6 +11204,23 @@ export const MODELS = {
10940
11204
  contextWindow: 1050000,
10941
11205
  maxTokens: 128000,
10942
11206
  },
11207
+ "gpt-6.1-sol": {
11208
+ id: "gpt-6.1-sol",
11209
+ name: "GPT-6.1 Sol",
11210
+ api: "openai-responses",
11211
+ provider: "opencode",
11212
+ baseUrl: "https://opencode.ai/zen/v1",
11213
+ reasoning: true,
11214
+ input: ["text", "image"],
11215
+ cost: {
11216
+ input: 2,
11217
+ output: 10,
11218
+ cacheRead: 0.1,
11219
+ cacheWrite: 2.5,
11220
+ },
11221
+ contextWindow: 1050000,
11222
+ maxTokens: 128000,
11223
+ },
10943
11224
  "grok-4.5": {
10944
11225
  id: "grok-4.5",
10945
11226
  name: "Grok 4.5",
@@ -11093,6 +11374,23 @@ export const MODELS = {
11093
11374
  contextWindow: 262144,
11094
11375
  maxTokens: 32768,
11095
11376
  },
11377
+ "ling-3.1-flash-free": {
11378
+ id: "ling-3.1-flash-free",
11379
+ name: "Ling 3.1 Flash Free",
11380
+ api: "openai-completions",
11381
+ provider: "opencode",
11382
+ baseUrl: "https://opencode.ai/zen/v1",
11383
+ reasoning: true,
11384
+ input: ["text"],
11385
+ cost: {
11386
+ input: 0,
11387
+ output: 0,
11388
+ cacheRead: 0,
11389
+ cacheWrite: 0,
11390
+ },
11391
+ contextWindow: 262144,
11392
+ maxTokens: 32768,
11393
+ },
11096
11394
  "longcat-2.5-preview-free": {
11097
11395
  id: "longcat-2.5-preview-free",
11098
11396
  name: "LongCat 2.5 Preview Free",
@@ -12493,6 +12791,23 @@ export const MODELS = {
12493
12791
  contextWindow: 1000000,
12494
12792
  maxTokens: 128000,
12495
12793
  },
12794
+ "anthropic/claude-sonnet-5.5:batch": {
12795
+ id: "anthropic/claude-sonnet-5.5:batch",
12796
+ name: "Anthropic: Claude Sonnet 5.5 (batch)",
12797
+ api: "openai-completions",
12798
+ provider: "openrouter",
12799
+ baseUrl: "https://openrouter.ai/api/v1",
12800
+ reasoning: true,
12801
+ input: ["text", "image"],
12802
+ cost: {
12803
+ input: 1,
12804
+ output: 5,
12805
+ cacheRead: 0.09999999999999999,
12806
+ cacheWrite: 1.25,
12807
+ },
12808
+ contextWindow: 1000000,
12809
+ maxTokens: 128000,
12810
+ },
12496
12811
  "anthropic/claude-sonnet-5:batch": {
12497
12812
  id: "anthropic/claude-sonnet-5:batch",
12498
12813
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -12510,6 +12825,23 @@ export const MODELS = {
12510
12825
  contextWindow: 1000000,
12511
12826
  maxTokens: 128000,
12512
12827
  },
12828
+ "apodex/apodex-1.1-mini:free": {
12829
+ id: "apodex/apodex-1.1-mini:free",
12830
+ name: "Apodex: Apodex 1.1 Mini (free)",
12831
+ api: "openai-completions",
12832
+ provider: "openrouter",
12833
+ baseUrl: "https://openrouter.ai/api/v1",
12834
+ reasoning: true,
12835
+ input: ["text"],
12836
+ cost: {
12837
+ input: 0,
12838
+ output: 0,
12839
+ cacheRead: 0,
12840
+ cacheWrite: 0,
12841
+ },
12842
+ contextWindow: 262144,
12843
+ maxTokens: 235929,
12844
+ },
12513
12845
  "arcee-ai/trinity-large-thinking": {
12514
12846
  id: "arcee-ai/trinity-large-thinking",
12515
12847
  name: "Arcee AI: Trinity Large Thinking",
@@ -12746,7 +13078,7 @@ export const MODELS = {
12746
13078
  cacheWrite: 0,
12747
13079
  },
12748
13080
  contextWindow: 163840,
12749
- maxTokens: 147456,
13081
+ maxTokens: 115200,
12750
13082
  },
12751
13083
  "deepseek/deepseek-chat-v3.1": {
12752
13084
  id: "deepseek/deepseek-chat-v3.1",
@@ -12842,9 +13174,9 @@ export const MODELS = {
12842
13174
  reasoning: true,
12843
13175
  input: ["text"],
12844
13176
  cost: {
12845
- input: 0.13440000000000002,
12846
- output: 0.2016,
12847
- cacheRead: 0.06720000000000001,
13177
+ input: 0.27,
13178
+ output: 0.41,
13179
+ cacheRead: 0,
12848
13180
  cacheWrite: 0,
12849
13181
  },
12850
13182
  contextWindow: 163840,
@@ -12861,13 +13193,13 @@ export const MODELS = {
12861
13193
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12862
13194
  input: ["text"],
12863
13195
  cost: {
12864
- input: 0.06538,
12865
- output: 0.13076,
12866
- cacheRead: 0.013076,
13196
+ input: 0.028,
13197
+ output: 0.056,
13198
+ cacheRead: 0.0056,
12867
13199
  cacheWrite: 0,
12868
13200
  },
12869
13201
  contextWindow: 1048576,
12870
- maxTokens: 131072,
13202
+ maxTokens: 384000,
12871
13203
  },
12872
13204
  "deepseek/deepseek-v4-flash-0731": {
12873
13205
  id: "deepseek/deepseek-v4-flash-0731",
@@ -12880,12 +13212,12 @@ export const MODELS = {
12880
13212
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12881
13213
  input: ["text"],
12882
13214
  cost: {
12883
- input: 0.020999999999999998,
12884
- output: 0.32,
12885
- cacheRead: 0.016,
13215
+ input: 0.0188,
13216
+ output: 1.28,
13217
+ cacheRead: 0.0188,
12886
13218
  cacheWrite: 0,
12887
13219
  },
12888
- contextWindow: 1310720,
13220
+ contextWindow: 1048576,
12889
13221
  maxTokens: 943718,
12890
13222
  },
12891
13223
  "deepseek/deepseek-v4-flash-vision-exp": {
@@ -12899,13 +13231,13 @@ export const MODELS = {
12899
13231
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12900
13232
  input: ["text", "image"],
12901
13233
  cost: {
12902
- input: 0.44,
12903
- output: 1.32,
12904
- cacheRead: 0.014,
13234
+ input: 0.21559999999999999,
13235
+ output: 0.6468,
13236
+ cacheRead: 0.00686,
12905
13237
  cacheWrite: 0,
12906
13238
  },
12907
13239
  contextWindow: 1048576,
12908
- maxTokens: 943717,
13240
+ maxTokens: 262144,
12909
13241
  },
12910
13242
  "deepseek/deepseek-v4-pro": {
12911
13243
  id: "deepseek/deepseek-v4-pro",
@@ -12918,9 +13250,9 @@ export const MODELS = {
12918
13250
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12919
13251
  input: ["text"],
12920
13252
  cost: {
12921
- input: 0.7829999999999999,
12922
- output: 1.5659999999999998,
12923
- cacheRead: 0.06525,
13253
+ input: 0.20879999999999999,
13254
+ output: 0.41759999999999997,
13255
+ cacheRead: 0.0174,
12924
13256
  cacheWrite: 0,
12925
13257
  },
12926
13258
  contextWindow: 1048576,
@@ -12937,13 +13269,13 @@ export const MODELS = {
12937
13269
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12938
13270
  input: ["text"],
12939
13271
  cost: {
12940
- input: 0.3995,
12941
- output: 4.199999999999999,
12942
- cacheRead: 0.399,
13272
+ input: 0.66,
13273
+ output: 1.9800000000000002,
13274
+ cacheRead: 0.022,
12943
13275
  cacheWrite: 0,
12944
13276
  },
12945
13277
  contextWindow: 1048576,
12946
- maxTokens: 943718,
13278
+ maxTokens: 393216,
12947
13279
  },
12948
13280
  "deepseek/deepseek-v4.1-flash": {
12949
13281
  id: "deepseek/deepseek-v4.1-flash",
@@ -13502,9 +13834,9 @@ export const MODELS = {
13502
13834
  reasoning: true,
13503
13835
  input: ["text", "image"],
13504
13836
  cost: {
13505
- input: 0.09,
13506
- output: 0.3,
13507
- cacheRead: 0.049999999999999996,
13837
+ input: 0.0675,
13838
+ output: 0.22499999999999998,
13839
+ cacheRead: 0.0375,
13508
13840
  cacheWrite: 0,
13509
13841
  },
13510
13842
  contextWindow: 262144,
@@ -13638,13 +13970,13 @@ export const MODELS = {
13638
13970
  reasoning: true,
13639
13971
  input: ["text"],
13640
13972
  cost: {
13641
- input: 0.06,
13642
- output: 0.18,
13643
- cacheRead: 0.012,
13973
+ input: 0.041999999999999996,
13974
+ output: 0.12319999999999999,
13975
+ cacheRead: 0.008400000000000001,
13644
13976
  cacheWrite: 0,
13645
13977
  },
13646
13978
  contextWindow: 262144,
13647
- maxTokens: 235929,
13979
+ maxTokens: 32768,
13648
13980
  },
13649
13981
  "inclusionai/ling-3.0-flash-sante:free": {
13650
13982
  id: "inclusionai/ling-3.0-flash-sante:free",
@@ -13680,6 +14012,23 @@ export const MODELS = {
13680
14012
  contextWindow: 262144,
13681
14013
  maxTokens: 32768,
13682
14014
  },
14015
+ "inclusionai/ling-3.1-flash": {
14016
+ id: "inclusionai/ling-3.1-flash",
14017
+ name: "inclusionAI: Ling 3.1 Flash",
14018
+ api: "openai-completions",
14019
+ provider: "openrouter",
14020
+ baseUrl: "https://openrouter.ai/api/v1",
14021
+ reasoning: true,
14022
+ input: ["text"],
14023
+ cost: {
14024
+ input: 0,
14025
+ output: 0,
14026
+ cacheRead: 0,
14027
+ cacheWrite: 0,
14028
+ },
14029
+ contextWindow: 262144,
14030
+ maxTokens: 32768,
14031
+ },
13683
14032
  "kwaipilot/kat-coder-pro-v2.5": {
13684
14033
  id: "kwaipilot/kat-coder-pro-v2.5",
13685
14034
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -13825,13 +14174,13 @@ export const MODELS = {
13825
14174
  reasoning: true,
13826
14175
  input: ["text", "image"],
13827
14176
  cost: {
13828
- input: 0.3,
13829
- output: 1.2,
14177
+ input: 0.35,
14178
+ output: 1.5,
13830
14179
  cacheRead: 0.04,
13831
14180
  cacheWrite: 0,
13832
14181
  },
13833
14182
  contextWindow: 131072,
13834
- maxTokens: 16384,
14183
+ maxTokens: 117964,
13835
14184
  },
13836
14185
  "meta/muse-spark-1.1": {
13837
14186
  id: "meta/muse-spark-1.1",
@@ -13927,7 +14276,7 @@ export const MODELS = {
13927
14276
  reasoning: true,
13928
14277
  input: ["text"],
13929
14278
  cost: {
13930
- input: 0.39999999999999997,
14279
+ input: 0.55,
13931
14280
  output: 2.2,
13932
14281
  cacheRead: 0,
13933
14282
  cacheWrite: 0,
@@ -13995,13 +14344,13 @@ export const MODELS = {
13995
14344
  reasoning: true,
13996
14345
  input: ["text"],
13997
14346
  cost: {
13998
- input: 0.3,
13999
- output: 1.2,
14000
- cacheRead: 0.06,
14347
+ input: 0.21,
14348
+ output: 0.84,
14349
+ cacheRead: 0.041999999999999996,
14001
14350
  cacheWrite: 0,
14002
14351
  },
14003
14352
  contextWindow: 204800,
14004
- maxTokens: 131072,
14353
+ maxTokens: 176947,
14005
14354
  },
14006
14355
  "minimax/minimax-m3": {
14007
14356
  id: "minimax/minimax-m3",
@@ -14473,11 +14822,11 @@ export const MODELS = {
14473
14822
  cost: {
14474
14823
  input: 0.6,
14475
14824
  output: 2.5,
14476
- cacheRead: 0.15,
14825
+ cacheRead: 0,
14477
14826
  cacheWrite: 0,
14478
14827
  },
14479
14828
  contextWindow: 262144,
14480
- maxTokens: 98304,
14829
+ maxTokens: 235929,
14481
14830
  },
14482
14831
  "moonshotai/kimi-k2.5": {
14483
14832
  id: "moonshotai/kimi-k2.5",
@@ -14505,9 +14854,9 @@ export const MODELS = {
14505
14854
  reasoning: true,
14506
14855
  input: ["text", "image"],
14507
14856
  cost: {
14508
- input: 0.65,
14509
- output: 3.41,
14510
- cacheRead: 0.15,
14857
+ input: 0.95,
14858
+ output: 4,
14859
+ cacheRead: 0.16,
14511
14860
  cacheWrite: 0,
14512
14861
  },
14513
14862
  contextWindow: 262144,
@@ -14522,8 +14871,8 @@ export const MODELS = {
14522
14871
  reasoning: true,
14523
14872
  input: ["text", "image"],
14524
14873
  cost: {
14525
- input: 0.6562,
14526
- output: 3.3000000000000003,
14874
+ input: 0.6712,
14875
+ output: 3.35,
14527
14876
  cacheRead: 0.18,
14528
14877
  cacheWrite: 0,
14529
14878
  },
@@ -14539,9 +14888,9 @@ export const MODELS = {
14539
14888
  reasoning: true,
14540
14889
  input: ["text", "image"],
14541
14890
  cost: {
14542
- input: 3,
14543
- output: 15,
14544
- cacheRead: 0.3,
14891
+ input: 2.7,
14892
+ output: 13.5,
14893
+ cacheRead: 0.27,
14545
14894
  cacheWrite: 0,
14546
14895
  },
14547
14896
  contextWindow: 1048576,
@@ -14658,13 +15007,13 @@ export const MODELS = {
14658
15007
  reasoning: true,
14659
15008
  input: ["text"],
14660
15009
  cost: {
14661
- input: 0.6,
14662
- output: 2.4,
14663
- cacheRead: 0.12,
15010
+ input: 0.5,
15011
+ output: 2.2,
15012
+ cacheRead: 0.09999999999999999,
14664
15013
  cacheWrite: 0,
14665
15014
  },
14666
15015
  contextWindow: 262144,
14667
- maxTokens: 182520,
15016
+ maxTokens: 16384,
14668
15017
  },
14669
15018
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
14670
15019
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14692,13 +15041,13 @@ export const MODELS = {
14692
15041
  reasoning: true,
14693
15042
  input: ["text"],
14694
15043
  cost: {
14695
- input: 0.08,
14696
- output: 0.19999999999999998,
14697
- cacheRead: 0.04,
15044
+ input: 0.0595,
15045
+ output: 0.16999999999999998,
15046
+ cacheRead: 0.02975,
14698
15047
  cacheWrite: 0,
14699
15048
  },
14700
- contextWindow: 1000000,
14701
- maxTokens: 32768,
15049
+ contextWindow: 262144,
15050
+ maxTokens: 131072,
14702
15051
  },
14703
15052
  "nvidia/nemotron-3.5-lightning:free": {
14704
15053
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15960,6 +16309,40 @@ export const MODELS = {
15960
16309
  contextWindow: 1050000,
15961
16310
  maxTokens: 128000,
15962
16311
  },
16312
+ "openai/gpt-6.1-sol": {
16313
+ id: "openai/gpt-6.1-sol",
16314
+ name: "OpenAI: GPT-6.1 Sol",
16315
+ api: "openai-completions",
16316
+ provider: "openrouter",
16317
+ baseUrl: "https://openrouter.ai/api/v1",
16318
+ reasoning: true,
16319
+ input: ["text", "image"],
16320
+ cost: {
16321
+ input: 2,
16322
+ output: 10,
16323
+ cacheRead: 0.09999999999999999,
16324
+ cacheWrite: 2.5,
16325
+ },
16326
+ contextWindow: 1050000,
16327
+ maxTokens: 128000,
16328
+ },
16329
+ "openai/gpt-6.1-sol-pro": {
16330
+ id: "openai/gpt-6.1-sol-pro",
16331
+ name: "OpenAI: GPT-6.1 Sol Pro",
16332
+ api: "openai-completions",
16333
+ provider: "openrouter",
16334
+ baseUrl: "https://openrouter.ai/api/v1",
16335
+ reasoning: true,
16336
+ input: ["text", "image"],
16337
+ cost: {
16338
+ input: 2,
16339
+ output: 10,
16340
+ cacheRead: 0.09999999999999999,
16341
+ cacheWrite: 2.5,
16342
+ },
16343
+ contextWindow: 1050000,
16344
+ maxTokens: 128000,
16345
+ },
15963
16346
  "openai/gpt-audio": {
15964
16347
  id: "openai/gpt-audio",
15965
16348
  name: "OpenAI: GPT Audio",
@@ -16020,13 +16403,13 @@ export const MODELS = {
16020
16403
  reasoning: true,
16021
16404
  input: ["text"],
16022
16405
  cost: {
16023
- input: 0.15,
16024
- output: 0.6,
16025
- cacheRead: 0.075,
16406
+ input: 0.037,
16407
+ output: 0.16999999999999998,
16408
+ cacheRead: 0,
16026
16409
  cacheWrite: 0,
16027
16410
  },
16028
16411
  contextWindow: 131072,
16029
- maxTokens: 65536,
16412
+ maxTokens: 117964,
16030
16413
  },
16031
16414
  "openai/gpt-oss-120b:batch": {
16032
16415
  id: "openai/gpt-oss-120b:batch",
@@ -16056,7 +16439,7 @@ export const MODELS = {
16056
16439
  cost: {
16057
16440
  input: 0.018,
16058
16441
  output: 0.09,
16059
- cacheRead: 0,
16442
+ cacheRead: 0.009,
16060
16443
  cacheWrite: 0,
16061
16444
  },
16062
16445
  contextWindow: 131072,
@@ -16413,7 +16796,7 @@ export const MODELS = {
16413
16796
  cost: {
16414
16797
  input: 0.075,
16415
16798
  output: 0.5,
16416
- cacheRead: 0,
16799
+ cacheRead: 0.0375,
16417
16800
  cacheWrite: 0,
16418
16801
  },
16419
16802
  contextWindow: 262144,
@@ -16581,13 +16964,13 @@ export const MODELS = {
16581
16964
  reasoning: false,
16582
16965
  input: ["text"],
16583
16966
  cost: {
16584
- input: 0.09999999999999999,
16585
- output: 0.3,
16967
+ input: 0.04815,
16968
+ output: 0.19305,
16586
16969
  cacheRead: 0,
16587
16970
  cacheWrite: 0,
16588
16971
  },
16589
16972
  contextWindow: 262144,
16590
- maxTokens: 235929,
16973
+ maxTokens: 32000,
16591
16974
  },
16592
16975
  "qwen/qwen3-30b-a3b-thinking-2507": {
16593
16976
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16791,7 +17174,7 @@ export const MODELS = {
16791
17174
  cacheWrite: 0,
16792
17175
  },
16793
17176
  contextWindow: 262144,
16794
- maxTokens: 235929,
17177
+ maxTokens: 32768,
16795
17178
  },
16796
17179
  "qwen/qwen3-vl-235b-a22b-instruct": {
16797
17180
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -16927,7 +17310,7 @@ export const MODELS = {
16927
17310
  cacheWrite: 0,
16928
17311
  },
16929
17312
  contextWindow: 262144,
16930
- maxTokens: 235929,
17313
+ maxTokens: 65536,
16931
17314
  },
16932
17315
  "qwen/qwen3.5-27b": {
16933
17316
  id: "qwen/qwen3.5-27b",
@@ -16955,13 +17338,13 @@ export const MODELS = {
16955
17338
  reasoning: true,
16956
17339
  input: ["text", "image"],
16957
17340
  cost: {
16958
- input: 0.1625,
16959
- output: 1.3,
16960
- cacheRead: 0,
17341
+ input: 0.15,
17342
+ output: 1,
17343
+ cacheRead: 0.049999999999999996,
16961
17344
  cacheWrite: 0,
16962
17345
  },
16963
17346
  contextWindow: 262144,
16964
- maxTokens: 65536,
17347
+ maxTokens: 235929,
16965
17348
  },
16966
17349
  "qwen/qwen3.5-397b-a17b": {
16967
17350
  id: "qwen/qwen3.5-397b-a17b",
@@ -17482,9 +17865,9 @@ export const MODELS = {
17482
17865
  reasoning: true,
17483
17866
  input: ["text"],
17484
17867
  cost: {
17485
- input: 0.0825,
17486
- output: 0.33,
17487
- cacheRead: 0.020625,
17868
+ input: 0.13199999999999998,
17869
+ output: 0.5279999999999999,
17870
+ cacheRead: 0.032999999999999995,
17488
17871
  cacheWrite: 0,
17489
17872
  },
17490
17873
  contextWindow: 262144,
@@ -17516,13 +17899,13 @@ export const MODELS = {
17516
17899
  reasoning: true,
17517
17900
  input: ["text", "image"],
17518
17901
  cost: {
17519
- input: 1,
17902
+ input: 0.95,
17520
17903
  output: 4.05,
17521
- cacheRead: 0.16999999999999998,
17904
+ cacheRead: 0.16,
17522
17905
  cacheWrite: 0,
17523
17906
  },
17524
17907
  contextWindow: 524288,
17525
- maxTokens: 471859,
17908
+ maxTokens: 262144,
17526
17909
  },
17527
17910
  "thinkingmachines/inkling-small": {
17528
17911
  id: "thinkingmachines/inkling-small",
@@ -17575,8 +17958,25 @@ export const MODELS = {
17575
17958
  contextWindow: 1048576,
17576
17959
  maxTokens: 262144,
17577
17960
  },
17578
- "unbiased/pareto": {
17579
- id: "unbiased/pareto",
17961
+ "typesafe/jev-router": {
17962
+ id: "typesafe/jev-router",
17963
+ name: "TypeSafe: Jev Router",
17964
+ api: "openai-completions",
17965
+ provider: "openrouter",
17966
+ baseUrl: "https://openrouter.ai/api/v1",
17967
+ reasoning: true,
17968
+ input: ["text", "image"],
17969
+ cost: {
17970
+ input: -1000000,
17971
+ output: -1000000,
17972
+ cacheRead: 0,
17973
+ cacheWrite: 0,
17974
+ },
17975
+ contextWindow: 1000000,
17976
+ maxTokens: 4096,
17977
+ },
17978
+ "unbiased/pareto": {
17979
+ id: "unbiased/pareto",
17580
17980
  name: "Pareto",
17581
17981
  api: "openai-completions",
17582
17982
  provider: "openrouter",
@@ -17592,6 +17992,23 @@ export const MODELS = {
17592
17992
  contextWindow: 262144,
17593
17993
  maxTokens: 131072,
17594
17994
  },
17995
+ "unbiased/pareto-26.10-preview": {
17996
+ id: "unbiased/pareto-26.10-preview",
17997
+ name: "Pareto 26.10 Preview",
17998
+ api: "openai-completions",
17999
+ provider: "openrouter",
18000
+ baseUrl: "https://openrouter.ai/api/v1",
18001
+ reasoning: false,
18002
+ input: ["text", "image"],
18003
+ cost: {
18004
+ input: 0.7999999999999999,
18005
+ output: 3.1999999999999997,
18006
+ cacheRead: 0.03,
18007
+ cacheWrite: 0,
18008
+ },
18009
+ contextWindow: 1048576,
18010
+ maxTokens: 131072,
18011
+ },
17595
18012
  "upstage/solar-mini4": {
17596
18013
  id: "upstage/solar-mini4",
17597
18014
  name: "Upstage: Solar Mini 4",
@@ -17737,9 +18154,9 @@ export const MODELS = {
17737
18154
  reasoning: true,
17738
18155
  input: ["text", "image"],
17739
18156
  cost: {
17740
- input: 1.5999999999999999,
17741
- output: 4.8,
17742
- cacheRead: 0.39999999999999997,
18157
+ input: 2,
18158
+ output: 6,
18159
+ cacheRead: 0.5,
17743
18160
  cacheWrite: 0,
17744
18161
  },
17745
18162
  contextWindow: 500000,
@@ -17810,7 +18227,7 @@ export const MODELS = {
17810
18227
  cacheRead: 0.0028,
17811
18228
  cacheWrite: 0,
17812
18229
  },
17813
- contextWindow: 1048576,
18230
+ contextWindow: 1050000,
17814
18231
  maxTokens: 131072,
17815
18232
  },
17816
18233
  "xiaomi/mimo-v2.6-pro": {
@@ -17926,7 +18343,7 @@ export const MODELS = {
17926
18343
  cost: {
17927
18344
  input: 0.3,
17928
18345
  output: 0.8999999999999999,
17929
- cacheRead: 0.055,
18346
+ cacheRead: 0.049999999999999996,
17930
18347
  cacheWrite: 0,
17931
18348
  },
17932
18349
  contextWindow: 131072,
@@ -18009,9 +18426,9 @@ export const MODELS = {
18009
18426
  reasoning: true,
18010
18427
  input: ["text"],
18011
18428
  cost: {
18012
- input: 0.9646,
18013
- output: 3.0316,
18014
- cacheRead: 0.17914,
18429
+ input: 1.4,
18430
+ output: 4.4,
18431
+ cacheRead: 0.26,
18015
18432
  cacheWrite: 0,
18016
18433
  },
18017
18434
  contextWindow: 204800,
@@ -18026,13 +18443,13 @@ export const MODELS = {
18026
18443
  reasoning: true,
18027
18444
  input: ["text"],
18028
18445
  cost: {
18029
- input: 0.6496,
18030
- output: 2.0416,
18031
- cacheRead: 0.12064,
18446
+ input: 0.41,
18447
+ output: 3.9899999999999998,
18448
+ cacheRead: 0.26,
18032
18449
  cacheWrite: 0,
18033
18450
  },
18034
18451
  contextWindow: 1048576,
18035
- maxTokens: 131072,
18452
+ maxTokens: 943718,
18036
18453
  },
18037
18454
  "z-ai/glm-5.3": {
18038
18455
  id: "z-ai/glm-5.3",
@@ -18043,13 +18460,13 @@ export const MODELS = {
18043
18460
  reasoning: true,
18044
18461
  input: ["text"],
18045
18462
  cost: {
18046
- input: 0.1785,
18047
- output: 2.8049999999999997,
18048
- cacheRead: 0.146625,
18463
+ input: 1.4,
18464
+ output: 4.4,
18465
+ cacheRead: 0.14,
18049
18466
  cacheWrite: 0,
18050
18467
  },
18051
- contextWindow: 1310720,
18052
- maxTokens: 943718,
18468
+ contextWindow: 1048576,
18469
+ maxTokens: 131072,
18053
18470
  },
18054
18471
  "z-ai/glm-5.3-flash": {
18055
18472
  id: "z-ai/glm-5.3-flash",
@@ -18065,7 +18482,7 @@ export const MODELS = {
18065
18482
  cacheRead: 0.03,
18066
18483
  cacheWrite: 0,
18067
18484
  },
18068
- contextWindow: 1310720,
18485
+ contextWindow: 1048576,
18069
18486
  maxTokens: 943717,
18070
18487
  },
18071
18488
  "z-ai/glm-5.3-flash:batch": {
@@ -18231,7 +18648,7 @@ export const MODELS = {
18231
18648
  reasoning: true,
18232
18649
  input: ["text", "image"],
18233
18650
  cost: {
18234
- input: 0.03,
18651
+ input: 0.02,
18235
18652
  output: 0.6,
18236
18653
  cacheRead: 0.01,
18237
18654
  cacheWrite: 0,
@@ -18248,9 +18665,9 @@ export const MODELS = {
18248
18665
  reasoning: true,
18249
18666
  input: ["text"],
18250
18667
  cost: {
18251
- input: 0.22592,
18252
- output: 1.9584000000000001,
18253
- cacheRead: 0.08832,
18668
+ input: 0.12,
18669
+ output: 4.199999999999999,
18670
+ cacheRead: 0.09999999999999999,
18254
18671
  cacheWrite: 0,
18255
18672
  },
18256
18673
  contextWindow: 1048576,
@@ -18267,12 +18684,12 @@ export const MODELS = {
18267
18684
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18268
18685
  input: ["text"],
18269
18686
  cost: {
18270
- input: 0.020999999999999998,
18271
- output: 0.32,
18272
- cacheRead: 0.016,
18687
+ input: 0.0188,
18688
+ output: 1.28,
18689
+ cacheRead: 0.0188,
18273
18690
  cacheWrite: 0,
18274
18691
  },
18275
- contextWindow: 1310720,
18692
+ contextWindow: 1048576,
18276
18693
  maxTokens: 943718,
18277
18694
  },
18278
18695
  "~google/gemini-flash-latest": {
@@ -18318,9 +18735,9 @@ export const MODELS = {
18318
18735
  reasoning: true,
18319
18736
  input: ["text", "image"],
18320
18737
  cost: {
18321
- input: 0.875,
18322
- output: 11.2,
18323
- cacheRead: 0.29,
18738
+ input: 0.9895,
18739
+ output: 13,
18740
+ cacheRead: 0.44999999999999996,
18324
18741
  cacheWrite: 0,
18325
18742
  },
18326
18743
  contextWindow: 1048576,
@@ -18388,7 +18805,7 @@ export const MODELS = {
18388
18805
  cost: {
18389
18806
  input: 2,
18390
18807
  output: 10,
18391
- cacheRead: 0.19999999999999998,
18808
+ cacheRead: 0.09999999999999999,
18392
18809
  cacheWrite: 2.5,
18393
18810
  },
18394
18811
  contextWindow: 1050000,
@@ -18420,9 +18837,9 @@ export const MODELS = {
18420
18837
  reasoning: true,
18421
18838
  input: ["text", "image"],
18422
18839
  cost: {
18423
- input: 1.5999999999999999,
18424
- output: 4.8,
18425
- cacheRead: 0.39999999999999997,
18840
+ input: 2,
18841
+ output: 6,
18842
+ cacheRead: 0.5,
18426
18843
  cacheWrite: 0,
18427
18844
  },
18428
18845
  contextWindow: 500000,
@@ -18437,13 +18854,13 @@ export const MODELS = {
18437
18854
  reasoning: true,
18438
18855
  input: ["text", "image"],
18439
18856
  cost: {
18440
- input: 0.045,
18441
- output: 0.14,
18442
- cacheRead: 0.01,
18857
+ input: 0.035,
18858
+ output: 0.5,
18859
+ cacheRead: 0.035,
18443
18860
  cacheWrite: 0,
18444
18861
  },
18445
- contextWindow: 1310720,
18446
- maxTokens: 128000,
18862
+ contextWindow: 1048576,
18863
+ maxTokens: 131072,
18447
18864
  },
18448
18865
  "~z-ai/glm-latest": {
18449
18866
  id: "~z-ai/glm-latest",
@@ -18454,13 +18871,13 @@ export const MODELS = {
18454
18871
  reasoning: true,
18455
18872
  input: ["text"],
18456
18873
  cost: {
18457
- input: 0.1785,
18458
- output: 2.8049999999999997,
18459
- cacheRead: 0.146625,
18874
+ input: 0.12,
18875
+ output: 4,
18876
+ cacheRead: 0.08,
18460
18877
  cacheWrite: 0,
18461
18878
  },
18462
- contextWindow: 1310720,
18463
- maxTokens: 943718,
18879
+ contextWindow: 1048576,
18880
+ maxTokens: 131072,
18464
18881
  },
18465
18882
  },
18466
18883
  "together": {
@@ -18595,34 +19012,15 @@ export const MODELS = {
18595
19012
  contextWindow: 1048576,
18596
19013
  maxTokens: 384000,
18597
19014
  },
18598
- "deepseek-ai/DeepSeek-V4-Pro": {
18599
- id: "deepseek-ai/DeepSeek-V4-Pro",
18600
- name: "DeepSeek V4 Pro",
18601
- api: "openai-completions",
18602
- provider: "together",
18603
- baseUrl: "https://api.together.ai/v1",
18604
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18605
- reasoning: true,
18606
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
18607
- input: ["text"],
18608
- cost: {
18609
- input: 1.74,
18610
- output: 3.48,
18611
- cacheRead: 0.2,
18612
- cacheWrite: 0,
18613
- },
18614
- contextWindow: 512000,
18615
- maxTokens: 384000,
18616
- },
18617
19015
  "deepseek-ai/DeepSeek-V4-Pro-0813": {
18618
19016
  id: "deepseek-ai/DeepSeek-V4-Pro-0813",
18619
19017
  name: "DeepSeek V4 Pro 0813",
18620
19018
  api: "openai-completions",
18621
19019
  provider: "together",
18622
19020
  baseUrl: "https://api.together.ai/v1",
18623
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19021
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18624
19022
  reasoning: true,
18625
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19023
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
18626
19024
  input: ["text"],
18627
19025
  cost: {
18628
19026
  input: 1.32,
@@ -18652,25 +19050,6 @@ export const MODELS = {
18652
19050
  contextWindow: 1048576,
18653
19051
  maxTokens: 384000,
18654
19052
  },
18655
- "google/gemma-4-31B-it": {
18656
- id: "google/gemma-4-31B-it",
18657
- name: "Gemma 4 31B Instruct",
18658
- api: "openai-completions",
18659
- provider: "together",
18660
- baseUrl: "https://api.together.ai/v1",
18661
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18662
- reasoning: true,
18663
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18664
- input: ["text", "image"],
18665
- cost: {
18666
- input: 0.39,
18667
- output: 0.97,
18668
- cacheRead: 0,
18669
- cacheWrite: 0,
18670
- },
18671
- contextWindow: 262144,
18672
- maxTokens: 131072,
18673
- },
18674
19053
  "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
18675
19054
  id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
18676
19055
  name: "Llama 3.3 70B",
@@ -18689,44 +19068,6 @@ export const MODELS = {
18689
19068
  contextWindow: 131072,
18690
19069
  maxTokens: 131072,
18691
19070
  },
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
19071
  "moonshotai/Kimi-K3": {
18731
19072
  id: "moonshotai/Kimi-K3",
18732
19073
  name: "Kimi K3",
@@ -18784,25 +19125,6 @@ export const MODELS = {
18784
19125
  contextWindow: 131072,
18785
19126
  maxTokens: 131072,
18786
19127
  },
18787
- "openai/gpt-oss-20b": {
18788
- id: "openai/gpt-oss-20b",
18789
- name: "GPT OSS 20B",
18790
- api: "openai-completions",
18791
- provider: "together",
18792
- baseUrl: "https://api.together.ai/v1",
18793
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
18794
- reasoning: true,
18795
- thinkingLevelMap: { "off": null, "minimal": null },
18796
- input: ["text"],
18797
- cost: {
18798
- input: 0.05,
18799
- output: 0.2,
18800
- cacheRead: 0,
18801
- cacheWrite: 0,
18802
- },
18803
- contextWindow: 131072,
18804
- maxTokens: 131072,
18805
- },
18806
19128
  "thinkingmachines/Inkling": {
18807
19129
  id: "thinkingmachines/Inkling",
18808
19130
  name: "Inkling",
@@ -20094,6 +20416,23 @@ export const MODELS = {
20094
20416
  contextWindow: 1048576,
20095
20417
  maxTokens: 32768,
20096
20418
  },
20419
+ "deepseek/deepseek-v4.1-flash-fast": {
20420
+ id: "deepseek/deepseek-v4.1-flash-fast",
20421
+ name: "DeepSeek V4.1 Flash Fast",
20422
+ api: "anthropic-messages",
20423
+ provider: "vercel-ai-gateway",
20424
+ baseUrl: "https://ai-gateway.vercel.sh",
20425
+ reasoning: true,
20426
+ input: ["text", "image"],
20427
+ cost: {
20428
+ input: 0.3,
20429
+ output: 1.2,
20430
+ cacheRead: 0.006,
20431
+ cacheWrite: 0,
20432
+ },
20433
+ contextWindow: 1048576,
20434
+ maxTokens: 1000000,
20435
+ },
20097
20436
  "fireworks/ember-1": {
20098
20437
  id: "fireworks/ember-1",
20099
20438
  name: "Ember-1",
@@ -20409,9 +20748,9 @@ export const MODELS = {
20409
20748
  reasoning: true,
20410
20749
  input: ["text"],
20411
20750
  cost: {
20412
- input: 0.06,
20413
- output: 0.18,
20414
- cacheRead: 0.012,
20751
+ input: 0.075,
20752
+ output: 0.22,
20753
+ cacheRead: 0.015,
20415
20754
  cacheWrite: 0,
20416
20755
  },
20417
20756
  contextWindow: 256000,
@@ -20468,6 +20807,40 @@ export const MODELS = {
20468
20807
  contextWindow: 256000,
20469
20808
  maxTokens: 32000,
20470
20809
  },
20810
+ "inclusionai/ling-3.1-flash": {
20811
+ id: "inclusionai/ling-3.1-flash",
20812
+ name: "Ling 3.1 Flash",
20813
+ api: "anthropic-messages",
20814
+ provider: "vercel-ai-gateway",
20815
+ baseUrl: "https://ai-gateway.vercel.sh",
20816
+ reasoning: true,
20817
+ input: ["text"],
20818
+ cost: {
20819
+ input: 0,
20820
+ output: 0,
20821
+ cacheRead: 0,
20822
+ cacheWrite: 0,
20823
+ },
20824
+ contextWindow: 262144,
20825
+ maxTokens: 32768,
20826
+ },
20827
+ "inclusionai/ling-3.1-flash-free": {
20828
+ id: "inclusionai/ling-3.1-flash-free",
20829
+ name: "Ling 3.1 Flash (Free)",
20830
+ api: "anthropic-messages",
20831
+ provider: "vercel-ai-gateway",
20832
+ baseUrl: "https://ai-gateway.vercel.sh",
20833
+ reasoning: true,
20834
+ input: ["text"],
20835
+ cost: {
20836
+ input: 0,
20837
+ output: 0,
20838
+ cacheRead: 0,
20839
+ cacheWrite: 0,
20840
+ },
20841
+ contextWindow: 262144,
20842
+ maxTokens: 32768,
20843
+ },
20471
20844
  "interfaze/interfaze-beta": {
20472
20845
  id: "interfaze/interfaze-beta",
20473
20846
  name: "Interfaze Beta",
@@ -22081,6 +22454,40 @@ export const MODELS = {
22081
22454
  contextWindow: 1050000,
22082
22455
  maxTokens: 128000,
22083
22456
  },
22457
+ "openai/gpt-6.1-sol": {
22458
+ id: "openai/gpt-6.1-sol",
22459
+ name: "GPT-6.1 Sol",
22460
+ api: "anthropic-messages",
22461
+ provider: "vercel-ai-gateway",
22462
+ baseUrl: "https://ai-gateway.vercel.sh",
22463
+ reasoning: true,
22464
+ input: ["text", "image"],
22465
+ cost: {
22466
+ input: 2,
22467
+ output: 10,
22468
+ cacheRead: 0.09999999999999999,
22469
+ cacheWrite: 2.5,
22470
+ },
22471
+ contextWindow: 1050000,
22472
+ maxTokens: 128000,
22473
+ },
22474
+ "openai/gpt-6.1-sol-fast": {
22475
+ id: "openai/gpt-6.1-sol-fast",
22476
+ name: "GPT-6.1 Sol (Fast)",
22477
+ api: "anthropic-messages",
22478
+ provider: "vercel-ai-gateway",
22479
+ baseUrl: "https://ai-gateway.vercel.sh",
22480
+ reasoning: true,
22481
+ input: ["text", "image"],
22482
+ cost: {
22483
+ input: 4,
22484
+ output: 20,
22485
+ cacheRead: 0.19999999999999998,
22486
+ cacheWrite: 5,
22487
+ },
22488
+ contextWindow: 1050000,
22489
+ maxTokens: 128000,
22490
+ },
22084
22491
  "openai/gpt-oss-120b": {
22085
22492
  id: "openai/gpt-oss-120b",
22086
22493
  name: "GPT OSS 120B",
@@ -22770,9 +23177,9 @@ export const MODELS = {
22770
23177
  reasoning: true,
22771
23178
  input: ["text", "image"],
22772
23179
  cost: {
22773
- input: 0.14,
22774
- output: 0.28,
22775
- cacheRead: 0.0028,
23180
+ input: 0.04,
23181
+ output: 1.28,
23182
+ cacheRead: 0.04,
22776
23183
  cacheWrite: 0,
22777
23184
  },
22778
23185
  contextWindow: 1048576,