@elyracode/ai 0.9.45 → 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.
@@ -1310,6 +1310,23 @@ export const MODELS = {
1310
1310
  contextWindow: 1050000,
1311
1311
  maxTokens: 128000,
1312
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
+ },
1313
1330
  "global.xai.grok-4.6": {
1314
1331
  id: "global.xai.grok-4.6",
1315
1332
  name: "Grok 4.6 (Global)",
@@ -1395,6 +1412,60 @@ export const MODELS = {
1395
1412
  contextWindow: 131072,
1396
1413
  maxTokens: 8192,
1397
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
+ },
1398
1469
  "in.openai.gpt-5.6-luna": {
1399
1470
  id: "in.openai.gpt-5.6-luna",
1400
1471
  name: "GPT-5.6 Luna (India)",
@@ -2121,6 +2192,23 @@ export const MODELS = {
2121
2192
  contextWindow: 1050000,
2122
2193
  maxTokens: 128000,
2123
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
+ },
2124
2212
  "openai.gpt-oss-120b": {
2125
2213
  id: "openai.gpt-oss-120b",
2126
2214
  name: "gpt-oss-120b",
@@ -2939,6 +3027,23 @@ export const MODELS = {
2939
3027
  contextWindow: 1050000,
2940
3028
  maxTokens: 128000,
2941
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
+ },
2942
3047
  "us.writer.palmyra-x4-v1:0": {
2943
3048
  id: "us.writer.palmyra-x4-v1:0",
2944
3049
  name: "Palmyra X4 (US)",
@@ -4898,7 +5003,7 @@ export const MODELS = {
4898
5003
  cost: {
4899
5004
  input: 0.1,
4900
5005
  output: 0.3,
4901
- cacheRead: 0,
5006
+ cacheRead: 0.05,
4902
5007
  cacheWrite: 0,
4903
5008
  },
4904
5009
  contextWindow: 256000,
@@ -5225,9 +5330,9 @@ export const MODELS = {
5225
5330
  reasoning: true,
5226
5331
  input: ["text", "image"],
5227
5332
  cost: {
5228
- input: 0.22,
5229
- output: 0.66,
5230
- cacheRead: 0.007,
5333
+ input: 0.3,
5334
+ output: 1.2,
5335
+ cacheRead: 0.006,
5231
5336
  cacheWrite: 0,
5232
5337
  },
5233
5338
  contextWindow: 1000000,
@@ -5429,9 +5534,9 @@ export const MODELS = {
5429
5534
  reasoning: true,
5430
5535
  input: ["text", "image"],
5431
5536
  cost: {
5432
- input: 0.22,
5433
- output: 0.66,
5434
- cacheRead: 0.007,
5537
+ input: 0.3,
5538
+ output: 1.2,
5539
+ cacheRead: 0.006,
5435
5540
  cacheWrite: 0,
5436
5541
  },
5437
5542
  contextWindow: 1000000,
@@ -10478,6 +10583,23 @@ export const MODELS = {
10478
10583
  contextWindow: 1000000,
10479
10584
  maxTokens: 384000,
10480
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
+ },
10481
10603
  "gemini-3-flash": {
10482
10604
  id: "gemini-3-flash",
10483
10605
  name: "Gemini 3 Flash",
@@ -11252,6 +11374,23 @@ export const MODELS = {
11252
11374
  contextWindow: 262144,
11253
11375
  maxTokens: 32768,
11254
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
+ },
11255
11394
  "longcat-2.5-preview-free": {
11256
11395
  id: "longcat-2.5-preview-free",
11257
11396
  name: "LongCat 2.5 Preview Free",
@@ -12686,6 +12825,23 @@ export const MODELS = {
12686
12825
  contextWindow: 1000000,
12687
12826
  maxTokens: 128000,
12688
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
+ },
12689
12845
  "arcee-ai/trinity-large-thinking": {
12690
12846
  id: "arcee-ai/trinity-large-thinking",
12691
12847
  name: "Arcee AI: Trinity Large Thinking",
@@ -12922,7 +13078,7 @@ export const MODELS = {
12922
13078
  cacheWrite: 0,
12923
13079
  },
12924
13080
  contextWindow: 163840,
12925
- maxTokens: 147456,
13081
+ maxTokens: 115200,
12926
13082
  },
12927
13083
  "deepseek/deepseek-chat-v3.1": {
12928
13084
  id: "deepseek/deepseek-chat-v3.1",
@@ -12984,13 +13140,13 @@ export const MODELS = {
12984
13140
  reasoning: true,
12985
13141
  input: ["text"],
12986
13142
  cost: {
12987
- input: 0.3,
13143
+ input: 0.27,
12988
13144
  output: 1,
12989
- cacheRead: 0.135,
13145
+ cacheRead: 0,
12990
13146
  cacheWrite: 0,
12991
13147
  },
12992
13148
  contextWindow: 163840,
12993
- maxTokens: 65536,
13149
+ maxTokens: 147456,
12994
13150
  },
12995
13151
  "deepseek/deepseek-v3.2": {
12996
13152
  id: "deepseek/deepseek-v3.2",
@@ -13037,13 +13193,13 @@ export const MODELS = {
13037
13193
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13038
13194
  input: ["text"],
13039
13195
  cost: {
13040
- input: 0.14,
13041
- output: 0.28,
13042
- cacheRead: 0.028,
13196
+ input: 0.028,
13197
+ output: 0.056,
13198
+ cacheRead: 0.0056,
13043
13199
  cacheWrite: 0,
13044
13200
  },
13045
13201
  contextWindow: 1048576,
13046
- maxTokens: 131072,
13202
+ maxTokens: 384000,
13047
13203
  },
13048
13204
  "deepseek/deepseek-v4-flash-0731": {
13049
13205
  id: "deepseek/deepseek-v4-flash-0731",
@@ -13056,9 +13212,9 @@ export const MODELS = {
13056
13212
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13057
13213
  input: ["text"],
13058
13214
  cost: {
13059
- input: 0.01,
13215
+ input: 0.0188,
13060
13216
  output: 1.28,
13061
- cacheRead: 0.01,
13217
+ cacheRead: 0.0188,
13062
13218
  cacheWrite: 0,
13063
13219
  },
13064
13220
  contextWindow: 1048576,
@@ -13094,9 +13250,9 @@ export const MODELS = {
13094
13250
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13095
13251
  input: ["text"],
13096
13252
  cost: {
13097
- input: 0.9552599999999999,
13098
- output: 1.9105199999999998,
13099
- cacheRead: 0.07960500000000001,
13253
+ input: 0.20879999999999999,
13254
+ output: 0.41759999999999997,
13255
+ cacheRead: 0.0174,
13100
13256
  cacheWrite: 0,
13101
13257
  },
13102
13258
  contextWindow: 1048576,
@@ -13113,9 +13269,9 @@ export const MODELS = {
13113
13269
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13114
13270
  input: ["text"],
13115
13271
  cost: {
13116
- input: 1.32,
13117
- output: 3.9600000000000004,
13118
- cacheRead: 0.044,
13272
+ input: 0.66,
13273
+ output: 1.9800000000000002,
13274
+ cacheRead: 0.022,
13119
13275
  cacheWrite: 0,
13120
13276
  },
13121
13277
  contextWindow: 1048576,
@@ -13132,9 +13288,9 @@ export const MODELS = {
13132
13288
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13133
13289
  input: ["text", "image"],
13134
13290
  cost: {
13135
- input: 0.019799999999999998,
13136
- output: 0.396,
13137
- cacheRead: 0.0029100000000000003,
13291
+ input: 0.3,
13292
+ output: 1.2,
13293
+ cacheRead: 0.006,
13138
13294
  cacheWrite: 0,
13139
13295
  },
13140
13296
  contextWindow: 1048576,
@@ -13678,9 +13834,9 @@ export const MODELS = {
13678
13834
  reasoning: true,
13679
13835
  input: ["text", "image"],
13680
13836
  cost: {
13681
- input: 0.09,
13682
- output: 0.3,
13683
- cacheRead: 0.049999999999999996,
13837
+ input: 0.0675,
13838
+ output: 0.22499999999999998,
13839
+ cacheRead: 0.0375,
13684
13840
  cacheWrite: 0,
13685
13841
  },
13686
13842
  contextWindow: 262144,
@@ -13814,13 +13970,13 @@ export const MODELS = {
13814
13970
  reasoning: true,
13815
13971
  input: ["text"],
13816
13972
  cost: {
13817
- input: 0.06,
13818
- output: 0.18,
13819
- cacheRead: 0.012,
13973
+ input: 0.041999999999999996,
13974
+ output: 0.12319999999999999,
13975
+ cacheRead: 0.008400000000000001,
13820
13976
  cacheWrite: 0,
13821
13977
  },
13822
13978
  contextWindow: 262144,
13823
- maxTokens: 235929,
13979
+ maxTokens: 32768,
13824
13980
  },
13825
13981
  "inclusionai/ling-3.0-flash-sante:free": {
13826
13982
  id: "inclusionai/ling-3.0-flash-sante:free",
@@ -13856,6 +14012,23 @@ export const MODELS = {
13856
14012
  contextWindow: 262144,
13857
14013
  maxTokens: 32768,
13858
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
+ },
13859
14032
  "kwaipilot/kat-coder-pro-v2.5": {
13860
14033
  id: "kwaipilot/kat-coder-pro-v2.5",
13861
14034
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -14103,7 +14276,7 @@ export const MODELS = {
14103
14276
  reasoning: true,
14104
14277
  input: ["text"],
14105
14278
  cost: {
14106
- input: 0.39999999999999997,
14279
+ input: 0.55,
14107
14280
  output: 2.2,
14108
14281
  cacheRead: 0,
14109
14282
  cacheWrite: 0,
@@ -14649,11 +14822,11 @@ export const MODELS = {
14649
14822
  cost: {
14650
14823
  input: 0.6,
14651
14824
  output: 2.5,
14652
- cacheRead: 0.15,
14825
+ cacheRead: 0,
14653
14826
  cacheWrite: 0,
14654
14827
  },
14655
14828
  contextWindow: 262144,
14656
- maxTokens: 98304,
14829
+ maxTokens: 235929,
14657
14830
  },
14658
14831
  "moonshotai/kimi-k2.5": {
14659
14832
  id: "moonshotai/kimi-k2.5",
@@ -14681,9 +14854,9 @@ export const MODELS = {
14681
14854
  reasoning: true,
14682
14855
  input: ["text", "image"],
14683
14856
  cost: {
14684
- input: 0.65,
14685
- output: 3.41,
14686
- cacheRead: 0.15,
14857
+ input: 0.95,
14858
+ output: 4,
14859
+ cacheRead: 0.16,
14687
14860
  cacheWrite: 0,
14688
14861
  },
14689
14862
  contextWindow: 262144,
@@ -14715,9 +14888,9 @@ export const MODELS = {
14715
14888
  reasoning: true,
14716
14889
  input: ["text", "image"],
14717
14890
  cost: {
14718
- input: 3,
14719
- output: 15,
14720
- cacheRead: 0.3,
14891
+ input: 2.7,
14892
+ output: 13.5,
14893
+ cacheRead: 0.27,
14721
14894
  cacheWrite: 0,
14722
14895
  },
14723
14896
  contextWindow: 1048576,
@@ -14834,13 +15007,13 @@ export const MODELS = {
14834
15007
  reasoning: true,
14835
15008
  input: ["text"],
14836
15009
  cost: {
14837
- input: 0.6,
14838
- output: 2.4,
14839
- cacheRead: 0.12,
15010
+ input: 0.5,
15011
+ output: 2.2,
15012
+ cacheRead: 0.09999999999999999,
14840
15013
  cacheWrite: 0,
14841
15014
  },
14842
15015
  contextWindow: 262144,
14843
- maxTokens: 182520,
15016
+ maxTokens: 16384,
14844
15017
  },
14845
15018
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
14846
15019
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14868,13 +15041,13 @@ export const MODELS = {
14868
15041
  reasoning: true,
14869
15042
  input: ["text"],
14870
15043
  cost: {
14871
- input: 0.06,
14872
- output: 0.16,
14873
- cacheRead: 0.03,
15044
+ input: 0.0595,
15045
+ output: 0.16999999999999998,
15046
+ cacheRead: 0.02975,
14874
15047
  cacheWrite: 0,
14875
15048
  },
14876
15049
  contextWindow: 262144,
14877
- maxTokens: 32768,
15050
+ maxTokens: 131072,
14878
15051
  },
14879
15052
  "nvidia/nemotron-3.5-lightning:free": {
14880
15053
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -16170,40 +16343,6 @@ export const MODELS = {
16170
16343
  contextWindow: 1050000,
16171
16344
  maxTokens: 128000,
16172
16345
  },
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
- },
16207
16346
  "openai/gpt-audio": {
16208
16347
  id: "openai/gpt-audio",
16209
16348
  name: "OpenAI: GPT Audio",
@@ -16808,13 +16947,13 @@ export const MODELS = {
16808
16947
  reasoning: true,
16809
16948
  input: ["text"],
16810
16949
  cost: {
16811
- input: 0.13,
16812
- output: 0.52,
16950
+ input: 0.12,
16951
+ output: 0.5,
16813
16952
  cacheRead: 0,
16814
16953
  cacheWrite: 0,
16815
16954
  },
16816
16955
  contextWindow: 131072,
16817
- maxTokens: 8192,
16956
+ maxTokens: 16384,
16818
16957
  },
16819
16958
  "qwen/qwen3-30b-a3b-instruct-2507": {
16820
16959
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -17035,7 +17174,7 @@ export const MODELS = {
17035
17174
  cacheWrite: 0,
17036
17175
  },
17037
17176
  contextWindow: 262144,
17038
- maxTokens: 235929,
17177
+ maxTokens: 32768,
17039
17178
  },
17040
17179
  "qwen/qwen3-vl-235b-a22b-instruct": {
17041
17180
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -17199,13 +17338,13 @@ export const MODELS = {
17199
17338
  reasoning: true,
17200
17339
  input: ["text", "image"],
17201
17340
  cost: {
17202
- input: 0.1625,
17203
- output: 1.3,
17204
- cacheRead: 0,
17341
+ input: 0.15,
17342
+ output: 1,
17343
+ cacheRead: 0.049999999999999996,
17205
17344
  cacheWrite: 0,
17206
17345
  },
17207
17346
  contextWindow: 262144,
17208
- maxTokens: 65536,
17347
+ maxTokens: 235929,
17209
17348
  },
17210
17349
  "qwen/qwen3.5-397b-a17b": {
17211
17350
  id: "qwen/qwen3.5-397b-a17b",
@@ -17760,13 +17899,13 @@ export const MODELS = {
17760
17899
  reasoning: true,
17761
17900
  input: ["text", "image"],
17762
17901
  cost: {
17763
- input: 1,
17902
+ input: 0.95,
17764
17903
  output: 4.05,
17765
- cacheRead: 0.16999999999999998,
17904
+ cacheRead: 0.16,
17766
17905
  cacheWrite: 0,
17767
17906
  },
17768
17907
  contextWindow: 524288,
17769
- maxTokens: 471859,
17908
+ maxTokens: 262144,
17770
17909
  },
17771
17910
  "thinkingmachines/inkling-small": {
17772
17911
  id: "thinkingmachines/inkling-small",
@@ -17819,6 +17958,23 @@ export const MODELS = {
17819
17958
  contextWindow: 1048576,
17820
17959
  maxTokens: 262144,
17821
17960
  },
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
+ },
17822
17978
  "unbiased/pareto": {
17823
17979
  id: "unbiased/pareto",
17824
17980
  name: "Pareto",
@@ -17836,6 +17992,23 @@ export const MODELS = {
17836
17992
  contextWindow: 262144,
17837
17993
  maxTokens: 131072,
17838
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
+ },
17839
18012
  "upstage/solar-mini4": {
17840
18013
  id: "upstage/solar-mini4",
17841
18014
  name: "Upstage: Solar Mini 4",
@@ -18054,7 +18227,7 @@ export const MODELS = {
18054
18227
  cacheRead: 0.0028,
18055
18228
  cacheWrite: 0,
18056
18229
  },
18057
- contextWindow: 1048576,
18230
+ contextWindow: 1050000,
18058
18231
  maxTokens: 131072,
18059
18232
  },
18060
18233
  "xiaomi/mimo-v2.6-pro": {
@@ -18170,7 +18343,7 @@ export const MODELS = {
18170
18343
  cost: {
18171
18344
  input: 0.3,
18172
18345
  output: 0.8999999999999999,
18173
- cacheRead: 0.055,
18346
+ cacheRead: 0.049999999999999996,
18174
18347
  cacheWrite: 0,
18175
18348
  },
18176
18349
  contextWindow: 131072,
@@ -18270,7 +18443,7 @@ export const MODELS = {
18270
18443
  reasoning: true,
18271
18444
  input: ["text"],
18272
18445
  cost: {
18273
- input: 0.36,
18446
+ input: 0.41,
18274
18447
  output: 3.9899999999999998,
18275
18448
  cacheRead: 0.26,
18276
18449
  cacheWrite: 0,
@@ -18289,11 +18462,11 @@ export const MODELS = {
18289
18462
  cost: {
18290
18463
  input: 1.4,
18291
18464
  output: 4.4,
18292
- cacheRead: 0.26,
18465
+ cacheRead: 0.14,
18293
18466
  cacheWrite: 0,
18294
18467
  },
18295
18468
  contextWindow: 1048576,
18296
- maxTokens: 943717,
18469
+ maxTokens: 131072,
18297
18470
  },
18298
18471
  "z-ai/glm-5.3-flash": {
18299
18472
  id: "z-ai/glm-5.3-flash",
@@ -18475,9 +18648,9 @@ export const MODELS = {
18475
18648
  reasoning: true,
18476
18649
  input: ["text", "image"],
18477
18650
  cost: {
18478
- input: 0.019799999999999998,
18479
- output: 0.396,
18480
- cacheRead: 0.0029100000000000003,
18651
+ input: 0.02,
18652
+ output: 0.6,
18653
+ cacheRead: 0.01,
18481
18654
  cacheWrite: 0,
18482
18655
  },
18483
18656
  contextWindow: 1048576,
@@ -18492,13 +18665,13 @@ export const MODELS = {
18492
18665
  reasoning: true,
18493
18666
  input: ["text"],
18494
18667
  cost: {
18495
- input: 0.15,
18496
- output: 3.5,
18497
- cacheRead: 0.15,
18668
+ input: 0.12,
18669
+ output: 4.199999999999999,
18670
+ cacheRead: 0.09999999999999999,
18498
18671
  cacheWrite: 0,
18499
18672
  },
18500
18673
  contextWindow: 1048576,
18501
- maxTokens: 393216,
18674
+ maxTokens: 943718,
18502
18675
  },
18503
18676
  "~deepseek/deepseek-v4-flash-latest": {
18504
18677
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -18511,9 +18684,9 @@ export const MODELS = {
18511
18684
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18512
18685
  input: ["text"],
18513
18686
  cost: {
18514
- input: 0.009899999999999999,
18515
- output: 0.13068,
18516
- cacheRead: 0.0013859999999999999,
18687
+ input: 0.0188,
18688
+ output: 1.28,
18689
+ cacheRead: 0.0188,
18517
18690
  cacheWrite: 0,
18518
18691
  },
18519
18692
  contextWindow: 1048576,
@@ -18562,9 +18735,9 @@ export const MODELS = {
18562
18735
  reasoning: true,
18563
18736
  input: ["text", "image"],
18564
18737
  cost: {
18565
- input: 0.3654,
18566
- output: 9.1343,
18567
- cacheRead: 0.39999999999999997,
18738
+ input: 0.9895,
18739
+ output: 13,
18740
+ cacheRead: 0.44999999999999996,
18568
18741
  cacheWrite: 0,
18569
18742
  },
18570
18743
  contextWindow: 1048576,
@@ -18681,13 +18854,13 @@ export const MODELS = {
18681
18854
  reasoning: true,
18682
18855
  input: ["text", "image"],
18683
18856
  cost: {
18684
- input: 0.02,
18685
- output: 0.24750000000000003,
18686
- cacheRead: 0.01,
18857
+ input: 0.035,
18858
+ output: 0.5,
18859
+ cacheRead: 0.035,
18687
18860
  cacheWrite: 0,
18688
18861
  },
18689
18862
  contextWindow: 1048576,
18690
- maxTokens: 943718,
18863
+ maxTokens: 131072,
18691
18864
  },
18692
18865
  "~z-ai/glm-latest": {
18693
18866
  id: "~z-ai/glm-latest",
@@ -18698,9 +18871,9 @@ export const MODELS = {
18698
18871
  reasoning: true,
18699
18872
  input: ["text"],
18700
18873
  cost: {
18701
- input: 0.13,
18874
+ input: 0.12,
18702
18875
  output: 4,
18703
- cacheRead: 0.13,
18876
+ cacheRead: 0.08,
18704
18877
  cacheWrite: 0,
18705
18878
  },
18706
18879
  contextWindow: 1048576,
@@ -18839,34 +19012,15 @@ export const MODELS = {
18839
19012
  contextWindow: 1048576,
18840
19013
  maxTokens: 384000,
18841
19014
  },
18842
- "deepseek-ai/DeepSeek-V4-Pro": {
18843
- id: "deepseek-ai/DeepSeek-V4-Pro",
18844
- name: "DeepSeek V4 Pro",
18845
- api: "openai-completions",
18846
- provider: "together",
18847
- baseUrl: "https://api.together.ai/v1",
18848
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18849
- reasoning: true,
18850
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
18851
- input: ["text"],
18852
- cost: {
18853
- input: 1.74,
18854
- output: 3.48,
18855
- cacheRead: 0.2,
18856
- cacheWrite: 0,
18857
- },
18858
- contextWindow: 512000,
18859
- maxTokens: 384000,
18860
- },
18861
19015
  "deepseek-ai/DeepSeek-V4-Pro-0813": {
18862
19016
  id: "deepseek-ai/DeepSeek-V4-Pro-0813",
18863
19017
  name: "DeepSeek V4 Pro 0813",
18864
19018
  api: "openai-completions",
18865
19019
  provider: "together",
18866
19020
  baseUrl: "https://api.together.ai/v1",
18867
- 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" },
18868
19022
  reasoning: true,
18869
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19023
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
18870
19024
  input: ["text"],
18871
19025
  cost: {
18872
19026
  input: 1.32,
@@ -18896,25 +19050,6 @@ export const MODELS = {
18896
19050
  contextWindow: 1048576,
18897
19051
  maxTokens: 384000,
18898
19052
  },
18899
- "google/gemma-4-31B-it": {
18900
- id: "google/gemma-4-31B-it",
18901
- name: "Gemma 4 31B Instruct",
18902
- api: "openai-completions",
18903
- provider: "together",
18904
- baseUrl: "https://api.together.ai/v1",
18905
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18906
- reasoning: true,
18907
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18908
- input: ["text", "image"],
18909
- cost: {
18910
- input: 0.39,
18911
- output: 0.97,
18912
- cacheRead: 0,
18913
- cacheWrite: 0,
18914
- },
18915
- contextWindow: 262144,
18916
- maxTokens: 131072,
18917
- },
18918
19053
  "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
18919
19054
  id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
18920
19055
  name: "Llama 3.3 70B",
@@ -18990,25 +19125,6 @@ export const MODELS = {
18990
19125
  contextWindow: 131072,
18991
19126
  maxTokens: 131072,
18992
19127
  },
18993
- "openai/gpt-oss-20b": {
18994
- id: "openai/gpt-oss-20b",
18995
- name: "GPT OSS 20B",
18996
- api: "openai-completions",
18997
- provider: "together",
18998
- baseUrl: "https://api.together.ai/v1",
18999
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
19000
- reasoning: true,
19001
- thinkingLevelMap: { "off": null, "minimal": null },
19002
- input: ["text"],
19003
- cost: {
19004
- input: 0.05,
19005
- output: 0.2,
19006
- cacheRead: 0,
19007
- cacheWrite: 0,
19008
- },
19009
- contextWindow: 131072,
19010
- maxTokens: 131072,
19011
- },
19012
19128
  "thinkingmachines/Inkling": {
19013
19129
  id: "thinkingmachines/Inkling",
19014
19130
  name: "Inkling",
@@ -20300,6 +20416,23 @@ export const MODELS = {
20300
20416
  contextWindow: 1048576,
20301
20417
  maxTokens: 32768,
20302
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
+ },
20303
20436
  "fireworks/ember-1": {
20304
20437
  id: "fireworks/ember-1",
20305
20438
  name: "Ember-1",
@@ -23044,9 +23177,9 @@ export const MODELS = {
23044
23177
  reasoning: true,
23045
23178
  input: ["text", "image"],
23046
23179
  cost: {
23047
- input: 0.14,
23048
- output: 0.28,
23049
- cacheRead: 0.0028,
23180
+ input: 0.04,
23181
+ output: 1.28,
23182
+ cacheRead: 0.04,
23050
23183
  cacheWrite: 0,
23051
23184
  },
23052
23185
  contextWindow: 1048576,