@elyracode/ai 0.9.34 → 0.9.35

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.
@@ -4035,9 +4035,26 @@ export const MODELS = {
4035
4035
  reasoning: true,
4036
4036
  input: ["text"],
4037
4037
  cost: {
4038
- input: 0.14,
4039
- output: 0.28,
4040
- cacheRead: 0.028,
4038
+ input: 0.22,
4039
+ output: 0.66,
4040
+ cacheRead: 0.007,
4041
+ cacheWrite: 0,
4042
+ },
4043
+ contextWindow: 1000000,
4044
+ maxTokens: 384000,
4045
+ },
4046
+ "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4047
+ id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4048
+ name: "DeepSeek V4 Flash Vision Exp",
4049
+ api: "anthropic-messages",
4050
+ provider: "fireworks",
4051
+ baseUrl: "https://api.fireworks.ai/inference",
4052
+ reasoning: true,
4053
+ input: ["text", "image"],
4054
+ cost: {
4055
+ input: 0.22,
4056
+ output: 0.66,
4057
+ cacheRead: 0.007,
4041
4058
  cacheWrite: 0,
4042
4059
  },
4043
4060
  contextWindow: 1000000,
@@ -4105,7 +4122,7 @@ export const MODELS = {
4105
4122
  cost: {
4106
4123
  input: 0.15,
4107
4124
  output: 0.5,
4108
- cacheRead: 0.029,
4125
+ cacheRead: 0.03,
4109
4126
  cacheWrite: 0,
4110
4127
  },
4111
4128
  contextWindow: 1000000,
@@ -5262,6 +5279,24 @@ export const MODELS = {
5262
5279
  contextWindow: 1048576,
5263
5280
  maxTokens: 65536,
5264
5281
  },
5282
+ "gemini-3.8-flash": {
5283
+ id: "gemini-3.8-flash",
5284
+ name: "Gemini 3.8 Flash",
5285
+ api: "google-generative-ai",
5286
+ provider: "google",
5287
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5288
+ reasoning: true,
5289
+ thinkingLevelMap: { "off": null },
5290
+ input: ["text", "image"],
5291
+ cost: {
5292
+ input: 0.75,
5293
+ output: 3.75,
5294
+ cacheRead: 0.075,
5295
+ cacheWrite: 0,
5296
+ },
5297
+ contextWindow: 1048576,
5298
+ maxTokens: 65536,
5299
+ },
5265
5300
  "gemini-flash-latest": {
5266
5301
  id: "gemini-flash-latest",
5267
5302
  name: "Gemini Flash Latest",
@@ -6348,6 +6383,24 @@ export const MODELS = {
6348
6383
  contextWindow: 1048576,
6349
6384
  maxTokens: 384000,
6350
6385
  },
6386
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
6387
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
6388
+ name: "DeepSeek V4 Flash Vision Exp",
6389
+ api: "openai-completions",
6390
+ provider: "huggingface",
6391
+ baseUrl: "https://router.huggingface.co/v1",
6392
+ compat: { "supportsDeveloperRole": false },
6393
+ reasoning: true,
6394
+ input: ["text", "image"],
6395
+ cost: {
6396
+ input: 0.44,
6397
+ output: 1.32,
6398
+ cacheRead: 0,
6399
+ cacheWrite: 0,
6400
+ },
6401
+ contextWindow: 1048576,
6402
+ maxTokens: 384000,
6403
+ },
6351
6404
  "deepseek-ai/DeepSeek-V4-Pro": {
6352
6405
  id: "deepseek-ai/DeepSeek-V4-Pro",
6353
6406
  name: "DeepSeek V4 Pro",
@@ -6670,7 +6723,7 @@ export const MODELS = {
6670
6723
  cacheWrite: 0,
6671
6724
  },
6672
6725
  contextWindow: 262144,
6673
- maxTokens: 64000,
6726
+ maxTokens: 128000,
6674
6727
  },
6675
6728
  "thinkingmachines/Inkling": {
6676
6729
  id: "thinkingmachines/Inkling",
@@ -9223,6 +9276,24 @@ export const MODELS = {
9223
9276
  contextWindow: 1048576,
9224
9277
  maxTokens: 65536,
9225
9278
  },
9279
+ "gemini-3.8-flash": {
9280
+ id: "gemini-3.8-flash",
9281
+ name: "Gemini 3.8 Flash",
9282
+ api: "google-generative-ai",
9283
+ provider: "opencode",
9284
+ baseUrl: "https://opencode.ai/zen/v1",
9285
+ reasoning: true,
9286
+ thinkingLevelMap: { "off": null },
9287
+ input: ["text", "image"],
9288
+ cost: {
9289
+ input: 1.5,
9290
+ output: 7.5,
9291
+ cacheRead: 0.15,
9292
+ cacheWrite: 0,
9293
+ },
9294
+ contextWindow: 1048576,
9295
+ maxTokens: 65536,
9296
+ },
9226
9297
  "glm-5": {
9227
9298
  id: "glm-5",
9228
9299
  name: "GLM-5",
@@ -9854,6 +9925,23 @@ export const MODELS = {
9854
9925
  contextWindow: 1048576,
9855
9926
  maxTokens: 131072,
9856
9927
  },
9928
+ "muse-spark-1.3-contributor-free": {
9929
+ id: "muse-spark-1.3-contributor-free",
9930
+ name: "Muse Spark 1.3 Free",
9931
+ api: "openai-responses",
9932
+ provider: "opencode",
9933
+ baseUrl: "https://opencode.ai/zen/v1",
9934
+ reasoning: true,
9935
+ input: ["text", "image"],
9936
+ cost: {
9937
+ input: 0,
9938
+ output: 0,
9939
+ cacheRead: 0,
9940
+ cacheWrite: 0,
9941
+ },
9942
+ contextWindow: 1048576,
9943
+ maxTokens: 131072,
9944
+ },
9857
9945
  "nemotron-3-ultra-free": {
9858
9946
  id: "nemotron-3-ultra-free",
9859
9947
  name: "Nemotron 3 Ultra Free",
@@ -10099,7 +10187,7 @@ export const MODELS = {
10099
10187
  cacheWrite: 0,
10100
10188
  },
10101
10189
  contextWindow: 256000,
10102
- maxTokens: 64000,
10190
+ maxTokens: 128000,
10103
10191
  },
10104
10192
  "hy4-preview": {
10105
10193
  id: "hy4-preview",
@@ -10271,6 +10359,23 @@ export const MODELS = {
10271
10359
  contextWindow: 1048576,
10272
10360
  maxTokens: 131072,
10273
10361
  },
10362
+ "muse-spark-1.3-contributor": {
10363
+ id: "muse-spark-1.3-contributor",
10364
+ name: "Muse Spark 1.3 Contributor",
10365
+ api: "openai-responses",
10366
+ provider: "opencode-go",
10367
+ baseUrl: "https://opencode.ai/zen/go/v1",
10368
+ reasoning: true,
10369
+ input: ["text", "image"],
10370
+ cost: {
10371
+ input: 0.1,
10372
+ output: 0.2,
10373
+ cacheRead: 0.002,
10374
+ cacheWrite: 0,
10375
+ },
10376
+ contextWindow: 1048576,
10377
+ maxTokens: 131072,
10378
+ },
10274
10379
  "qwen3.6-plus": {
10275
10380
  id: "qwen3.6-plus",
10276
10381
  name: "Qwen3.6 Plus",
@@ -10548,6 +10653,24 @@ export const MODELS = {
10548
10653
  contextWindow: 1000000,
10549
10654
  maxTokens: 128000,
10550
10655
  },
10656
+ "anthropic/claude-fable-5.1:batch": {
10657
+ id: "anthropic/claude-fable-5.1:batch",
10658
+ name: "Anthropic: Claude Fable 5.1 (batch)",
10659
+ api: "openai-completions",
10660
+ provider: "openrouter",
10661
+ baseUrl: "https://openrouter.ai/api/v1",
10662
+ reasoning: true,
10663
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10664
+ input: ["text", "image"],
10665
+ cost: {
10666
+ input: 5,
10667
+ output: 25,
10668
+ cacheRead: 0.125,
10669
+ cacheWrite: 6.25,
10670
+ },
10671
+ contextWindow: 1000000,
10672
+ maxTokens: 128000,
10673
+ },
10551
10674
  "anthropic/claude-fable-5:batch": {
10552
10675
  id: "anthropic/claude-fable-5:batch",
10553
10676
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -11142,13 +11265,13 @@ export const MODELS = {
11142
11265
  reasoning: false,
11143
11266
  input: ["text"],
11144
11267
  cost: {
11145
- input: 0.2574,
11146
- output: 1.0287,
11268
+ input: 0.32,
11269
+ output: 0.8899999999999999,
11147
11270
  cacheRead: 0,
11148
11271
  cacheWrite: 0,
11149
11272
  },
11150
11273
  contextWindow: 163840,
11151
- maxTokens: 16000,
11274
+ maxTokens: 16384,
11152
11275
  },
11153
11276
  "deepseek/deepseek-chat-v3-0324": {
11154
11277
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11280,9 +11403,9 @@ export const MODELS = {
11280
11403
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11281
11404
  input: ["text"],
11282
11405
  cost: {
11283
- input: 0.07322000000000001,
11284
- output: 0.14644000000000001,
11285
- cacheRead: 0.014644,
11406
+ input: 0.07784,
11407
+ output: 0.15568,
11408
+ cacheRead: 0.015568,
11286
11409
  cacheWrite: 0,
11287
11410
  },
11288
11411
  contextWindow: 1048576,
@@ -11356,13 +11479,13 @@ export const MODELS = {
11356
11479
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11357
11480
  input: ["text"],
11358
11481
  cost: {
11359
- input: 1.5999999999999999,
11360
- output: 3.1999999999999997,
11361
- cacheRead: 0.135,
11482
+ input: 1.030776,
11483
+ output: 2.061552,
11484
+ cacheRead: 0.085898,
11362
11485
  cacheWrite: 0,
11363
11486
  },
11364
11487
  contextWindow: 1048576,
11365
- maxTokens: 393216,
11488
+ maxTokens: 384000,
11366
11489
  },
11367
11490
  "deepseek/deepseek-v4-pro-0813": {
11368
11491
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11836,10 +11959,44 @@ export const MODELS = {
11836
11959
  reasoning: true,
11837
11960
  input: ["text", "image"],
11838
11961
  cost: {
11839
- input: 0.1875,
11840
- output: 0.9375,
11841
- cacheRead: 0.01875,
11842
- cacheWrite: 0.0208333333333333,
11962
+ input: 0.375,
11963
+ output: 1.875,
11964
+ cacheRead: 0.0375,
11965
+ cacheWrite: 0.0416666666666667,
11966
+ },
11967
+ contextWindow: 1048576,
11968
+ maxTokens: 65536,
11969
+ },
11970
+ "google/gemini-3.8-flash": {
11971
+ id: "google/gemini-3.8-flash",
11972
+ name: "Google: Gemini 3.8 Flash",
11973
+ api: "openai-completions",
11974
+ provider: "openrouter",
11975
+ baseUrl: "https://openrouter.ai/api/v1",
11976
+ reasoning: true,
11977
+ input: ["text", "image"],
11978
+ cost: {
11979
+ input: 0.75,
11980
+ output: 3.75,
11981
+ cacheRead: 0.075,
11982
+ cacheWrite: 0.0416666666666667,
11983
+ },
11984
+ contextWindow: 1048576,
11985
+ maxTokens: 65536,
11986
+ },
11987
+ "google/gemini-3.8-flash:batch": {
11988
+ id: "google/gemini-3.8-flash:batch",
11989
+ name: "Google: Gemini 3.8 Flash (batch)",
11990
+ api: "openai-completions",
11991
+ provider: "openrouter",
11992
+ baseUrl: "https://openrouter.ai/api/v1",
11993
+ reasoning: true,
11994
+ input: ["text", "image"],
11995
+ cost: {
11996
+ input: 0.375,
11997
+ output: 1.875,
11998
+ cacheRead: 0.0375,
11999
+ cacheWrite: 0.0416666666666667,
11843
12000
  },
11844
12001
  contextWindow: 1048576,
11845
12002
  maxTokens: 65536,
@@ -12048,6 +12205,23 @@ export const MODELS = {
12048
12205
  contextWindow: 262144,
12049
12206
  maxTokens: 32768,
12050
12207
  },
12208
+ "inclusionai/ling-3.0-flash-fin": {
12209
+ id: "inclusionai/ling-3.0-flash-fin",
12210
+ name: "Ling 3.0 Flash Fin",
12211
+ api: "openai-completions",
12212
+ provider: "openrouter",
12213
+ baseUrl: "https://openrouter.ai/api/v1",
12214
+ reasoning: true,
12215
+ input: ["text"],
12216
+ cost: {
12217
+ input: 0.06,
12218
+ output: 0.18,
12219
+ cacheRead: 0.012,
12220
+ cacheWrite: 0,
12221
+ },
12222
+ contextWindow: 262144,
12223
+ maxTokens: 235929,
12224
+ },
12051
12225
  "inclusionai/ling-3.0-flash-fin:free": {
12052
12226
  id: "inclusionai/ling-3.0-flash-fin:free",
12053
12227
  name: "Ling 3.0 Flash Fin (free)",
@@ -12176,13 +12350,13 @@ export const MODELS = {
12176
12350
  reasoning: false,
12177
12351
  input: ["text"],
12178
12352
  cost: {
12179
- input: 0.71,
12180
- output: 0.71,
12181
- cacheRead: 0.71,
12353
+ input: 0.09999999999999999,
12354
+ output: 0.32,
12355
+ cacheRead: 0,
12182
12356
  cacheWrite: 0,
12183
12357
  },
12184
12358
  contextWindow: 131072,
12185
- maxTokens: 115200,
12359
+ maxTokens: 16384,
12186
12360
  },
12187
12361
  "meta-llama/llama-4-maverick": {
12188
12362
  id: "meta-llama/llama-4-maverick",
@@ -12228,12 +12402,12 @@ export const MODELS = {
12228
12402
  input: ["text", "image"],
12229
12403
  cost: {
12230
12404
  input: 0.3,
12231
- output: 1.2,
12405
+ output: 1.1,
12232
12406
  cacheRead: 0.04,
12233
12407
  cacheWrite: 0,
12234
12408
  },
12235
12409
  contextWindow: 131072,
12236
- maxTokens: 16384,
12410
+ maxTokens: 117964,
12237
12411
  },
12238
12412
  "meta/muse-glimmer-30b:batch": {
12239
12413
  id: "meta/muse-glimmer-30b:batch",
@@ -12303,6 +12477,40 @@ export const MODELS = {
12303
12477
  contextWindow: 1048576,
12304
12478
  maxTokens: 943718,
12305
12479
  },
12480
+ "meta/muse-spark-1.3": {
12481
+ id: "meta/muse-spark-1.3",
12482
+ name: "Meta: Muse Spark 1.3",
12483
+ api: "openai-completions",
12484
+ provider: "openrouter",
12485
+ baseUrl: "https://openrouter.ai/api/v1",
12486
+ reasoning: true,
12487
+ input: ["text", "image"],
12488
+ cost: {
12489
+ input: 1.25,
12490
+ output: 4.25,
12491
+ cacheRead: 0.15,
12492
+ cacheWrite: 0,
12493
+ },
12494
+ contextWindow: 1048576,
12495
+ maxTokens: 943718,
12496
+ },
12497
+ "meta/muse-spark-1.3-contributor": {
12498
+ id: "meta/muse-spark-1.3-contributor",
12499
+ name: "Meta: Muse Spark 1.3 Contributor",
12500
+ api: "openai-completions",
12501
+ provider: "openrouter",
12502
+ baseUrl: "https://openrouter.ai/api/v1",
12503
+ reasoning: true,
12504
+ input: ["text", "image"],
12505
+ cost: {
12506
+ input: 0.09999999999999999,
12507
+ output: 0.19999999999999998,
12508
+ cacheRead: 0.002,
12509
+ cacheWrite: 0,
12510
+ },
12511
+ contextWindow: 1048576,
12512
+ maxTokens: 943718,
12513
+ },
12306
12514
  "minimax/minimax-m1": {
12307
12515
  id: "minimax/minimax-m1",
12308
12516
  name: "MiniMax: MiniMax M1",
@@ -12943,11 +13151,11 @@ export const MODELS = {
12943
13151
  cost: {
12944
13152
  input: 0.049999999999999996,
12945
13153
  output: 0.19999999999999998,
12946
- cacheRead: 0.024999999999999998,
13154
+ cacheRead: 0.03,
12947
13155
  cacheWrite: 0,
12948
13156
  },
12949
13157
  contextWindow: 262144,
12950
- maxTokens: 228000,
13158
+ maxTokens: 235929,
12951
13159
  },
12952
13160
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12953
13161
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -13008,31 +13216,14 @@ export const MODELS = {
13008
13216
  baseUrl: "https://openrouter.ai/api/v1",
13009
13217
  reasoning: true,
13010
13218
  input: ["text"],
13011
- cost: {
13012
- input: 0.5,
13013
- output: 2.2,
13014
- cacheRead: 0.09999999999999999,
13015
- cacheWrite: 0,
13016
- },
13017
- contextWindow: 262144,
13018
- maxTokens: 16384,
13019
- },
13020
- "nvidia/nemotron-3-ultra-550b-a55b:batch": {
13021
- id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
13022
- name: "NVIDIA: Nemotron 3 Ultra (batch)",
13023
- api: "openai-completions",
13024
- provider: "openrouter",
13025
- baseUrl: "https://openrouter.ai/api/v1",
13026
- reasoning: true,
13027
- input: ["text"],
13028
13219
  cost: {
13029
13220
  input: 0.6,
13030
- output: 3.5999999999999996,
13031
- cacheRead: 0.19999999999999998,
13221
+ output: 2.4,
13222
+ cacheRead: 0.12,
13032
13223
  cacheWrite: 0,
13033
13224
  },
13034
- contextWindow: 512288,
13035
- maxTokens: 461059,
13225
+ contextWindow: 262144,
13226
+ maxTokens: 182520,
13036
13227
  },
13037
13228
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13038
13229
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -15085,13 +15276,13 @@ export const MODELS = {
15085
15276
  reasoning: true,
15086
15277
  input: ["text", "image"],
15087
15278
  cost: {
15088
- input: 0.39,
15089
- output: 2.34,
15090
- cacheRead: 0,
15279
+ input: 0.55,
15280
+ output: 3.5,
15281
+ cacheRead: 0.22499999999999998,
15091
15282
  cacheWrite: 0,
15092
15283
  },
15093
15284
  contextWindow: 262144,
15094
- maxTokens: 65536,
15285
+ maxTokens: 235929,
15095
15286
  },
15096
15287
  "qwen/qwen3.5-9b": {
15097
15288
  id: "qwen/qwen3.5-9b",
@@ -15340,9 +15531,9 @@ export const MODELS = {
15340
15531
  reasoning: true,
15341
15532
  input: ["text"],
15342
15533
  cost: {
15343
- input: 2.5,
15344
- output: 6.25,
15345
- cacheRead: 0.5,
15534
+ input: 2,
15535
+ output: 6,
15536
+ cacheRead: 0.25,
15346
15537
  cacheWrite: 0,
15347
15538
  },
15348
15539
  contextWindow: 1010000,
@@ -15357,10 +15548,10 @@ export const MODELS = {
15357
15548
  reasoning: true,
15358
15549
  input: ["text", "image"],
15359
15550
  cost: {
15360
- input: 0.425,
15361
- output: 2.5500000000000003,
15551
+ input: 0.42,
15552
+ output: 3,
15362
15553
  cacheRead: 0.08499999999999999,
15363
- cacheWrite: 0.53125,
15554
+ cacheWrite: 0,
15364
15555
  },
15365
15556
  contextWindow: 1000000,
15366
15557
  maxTokens: 131072,
@@ -15884,13 +16075,13 @@ export const MODELS = {
15884
16075
  reasoning: true,
15885
16076
  input: ["text"],
15886
16077
  cost: {
15887
- input: 0.43,
15888
- output: 1.75,
15889
- cacheRead: 0.08,
16078
+ input: 0.55,
16079
+ output: 2.2,
16080
+ cacheRead: 0.11,
15890
16081
  cacheWrite: 0,
15891
16082
  },
15892
16083
  contextWindow: 204800,
15893
- maxTokens: 16384,
16084
+ maxTokens: 131072,
15894
16085
  },
15895
16086
  "z-ai/glm-4.6v": {
15896
16087
  id: "z-ai/glm-4.6v",
@@ -16003,13 +16194,13 @@ export const MODELS = {
16003
16194
  reasoning: true,
16004
16195
  input: ["text"],
16005
16196
  cost: {
16006
- input: 1.19,
16007
- output: 3.74,
16008
- cacheRead: 0.221,
16197
+ input: 0.966,
16198
+ output: 3.036,
16199
+ cacheRead: 0.1932,
16009
16200
  cacheWrite: 0,
16010
16201
  },
16011
16202
  contextWindow: 1048576,
16012
- maxTokens: 262144,
16203
+ maxTokens: 131072,
16013
16204
  },
16014
16205
  "z-ai/glm-5.2:free": {
16015
16206
  id: "z-ai/glm-5.2:free",
@@ -16039,11 +16230,11 @@ export const MODELS = {
16039
16230
  cost: {
16040
16231
  input: 1.4,
16041
16232
  output: 4.4,
16042
- cacheRead: 0.26,
16233
+ cacheRead: 0.14,
16043
16234
  cacheWrite: 0,
16044
16235
  },
16045
16236
  contextWindow: 1310720,
16046
- maxTokens: 131072,
16237
+ maxTokens: 262144,
16047
16238
  },
16048
16239
  "z-ai/glm-5.3-flash": {
16049
16240
  id: "z-ai/glm-5.3-flash",
@@ -16176,13 +16367,13 @@ export const MODELS = {
16176
16367
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
16177
16368
  input: ["text"],
16178
16369
  cost: {
16179
- input: 0.049980000000000004,
16180
- output: 0.09996000000000001,
16181
- cacheRead: 0.009996000000000001,
16370
+ input: 0.049999999999999996,
16371
+ output: 0.16,
16372
+ cacheRead: 0.013000000000000001,
16182
16373
  cacheWrite: 0,
16183
16374
  },
16184
16375
  contextWindow: 1310720,
16185
- maxTokens: 131072,
16376
+ maxTokens: 393216,
16186
16377
  },
16187
16378
  "~google/gemini-flash-latest": {
16188
16379
  id: "~google/gemini-flash-latest",
@@ -16227,9 +16418,9 @@ export const MODELS = {
16227
16418
  reasoning: true,
16228
16419
  input: ["text", "image"],
16229
16420
  cost: {
16230
- input: 2.5500000000000003,
16231
- output: 12.75,
16232
- cacheRead: 0.25599998999999996,
16421
+ input: 2.5,
16422
+ output: 14,
16423
+ cacheRead: 0.29,
16233
16424
  cacheWrite: 0,
16234
16425
  },
16235
16426
  contextWindow: 1048576,
@@ -16286,6 +16477,23 @@ export const MODELS = {
16286
16477
  contextWindow: 500000,
16287
16478
  maxTokens: 450000,
16288
16479
  },
16480
+ "~z-ai/glm-flash-latest": {
16481
+ id: "~z-ai/glm-flash-latest",
16482
+ name: "Z.ai: GLM Flash Latest",
16483
+ api: "openai-completions",
16484
+ provider: "openrouter",
16485
+ baseUrl: "https://openrouter.ai/api/v1",
16486
+ reasoning: true,
16487
+ input: ["text", "image"],
16488
+ cost: {
16489
+ input: 0.07125000000000001,
16490
+ output: 0.2375,
16491
+ cacheRead: 0.01425,
16492
+ cacheWrite: 0,
16493
+ },
16494
+ contextWindow: 1310720,
16495
+ maxTokens: 131072,
16496
+ },
16289
16497
  "~z-ai/glm-latest": {
16290
16498
  id: "~z-ai/glm-latest",
16291
16499
  name: "Z.ai: GLM Latest",
@@ -16295,9 +16503,9 @@ export const MODELS = {
16295
16503
  reasoning: true,
16296
16504
  input: ["text"],
16297
16505
  cost: {
16298
- input: 1.17,
16299
- output: 3.9600000000000004,
16300
- cacheRead: 0.234,
16506
+ input: 1.1480000000000001,
16507
+ output: 3.608,
16508
+ cacheRead: 0.18860000000000002,
16301
16509
  cacheWrite: 0,
16302
16510
  },
16303
16511
  contextWindow: 1310720,
@@ -17213,6 +17421,23 @@ export const MODELS = {
17213
17421
  contextWindow: 1000000,
17214
17422
  maxTokens: 128000,
17215
17423
  },
17424
+ "alibaba/qwen3.8-max-0902": {
17425
+ id: "alibaba/qwen3.8-max-0902",
17426
+ name: "Qwen3.8 Max 0902",
17427
+ api: "anthropic-messages",
17428
+ provider: "vercel-ai-gateway",
17429
+ baseUrl: "https://ai-gateway.vercel.sh",
17430
+ reasoning: true,
17431
+ input: ["text", "image"],
17432
+ cost: {
17433
+ input: 2,
17434
+ output: 6,
17435
+ cacheRead: 0.25,
17436
+ cacheWrite: 2.5,
17437
+ },
17438
+ contextWindow: 991000,
17439
+ maxTokens: 128000,
17440
+ },
17216
17441
  "amazon/nova-2-lite": {
17217
17442
  id: "amazon/nova-2-lite",
17218
17443
  name: "Nova 2 Lite",
@@ -17644,23 +17869,6 @@ export const MODELS = {
17644
17869
  contextWindow: 128000,
17645
17870
  maxTokens: 8192,
17646
17871
  },
17647
- "deepseek/deepseek-v3": {
17648
- id: "deepseek/deepseek-v3",
17649
- name: "DeepSeek V3 0324",
17650
- api: "anthropic-messages",
17651
- provider: "vercel-ai-gateway",
17652
- baseUrl: "https://ai-gateway.vercel.sh",
17653
- reasoning: false,
17654
- input: ["text"],
17655
- cost: {
17656
- input: 0.27,
17657
- output: 1.12,
17658
- cacheRead: 0.135,
17659
- cacheWrite: 0,
17660
- },
17661
- contextWindow: 163840,
17662
- maxTokens: 163840,
17663
- },
17664
17872
  "deepseek/deepseek-v3.1": {
17665
17873
  id: "deepseek/deepseek-v3.1",
17666
17874
  name: "DeepSeek V3.1",
@@ -17984,6 +18192,23 @@ export const MODELS = {
17984
18192
  contextWindow: 1000000,
17985
18193
  maxTokens: 65536,
17986
18194
  },
18195
+ "google/gemini-3.8-flash": {
18196
+ id: "google/gemini-3.8-flash",
18197
+ name: "Gemini 3.8 Flash",
18198
+ api: "anthropic-messages",
18199
+ provider: "vercel-ai-gateway",
18200
+ baseUrl: "https://ai-gateway.vercel.sh",
18201
+ reasoning: true,
18202
+ input: ["text", "image"],
18203
+ cost: {
18204
+ input: 0.75,
18205
+ output: 3.75,
18206
+ cacheRead: 0.075,
18207
+ cacheWrite: 0,
18208
+ },
18209
+ contextWindow: 1000000,
18210
+ maxTokens: 65536,
18211
+ },
17987
18212
  "google/gemma-4-26b-a4b-it": {
17988
18213
  id: "google/gemma-4-26b-a4b-it",
17989
18214
  name: "Google Gemma 4 26B A4B",
@@ -18341,6 +18566,40 @@ export const MODELS = {
18341
18566
  contextWindow: 1048576,
18342
18567
  maxTokens: 1048576,
18343
18568
  },
18569
+ "meta/muse-spark-1.3": {
18570
+ id: "meta/muse-spark-1.3",
18571
+ name: "Muse Spark 1.3",
18572
+ api: "anthropic-messages",
18573
+ provider: "vercel-ai-gateway",
18574
+ baseUrl: "https://ai-gateway.vercel.sh",
18575
+ reasoning: true,
18576
+ input: ["text", "image"],
18577
+ cost: {
18578
+ input: 1.25,
18579
+ output: 4.25,
18580
+ cacheRead: 0.15,
18581
+ cacheWrite: 0,
18582
+ },
18583
+ contextWindow: 1048576,
18584
+ maxTokens: 1048576,
18585
+ },
18586
+ "meta/muse-spark-1.3-contributor": {
18587
+ id: "meta/muse-spark-1.3-contributor",
18588
+ name: "Muse Spark 1.3 Contributor",
18589
+ api: "anthropic-messages",
18590
+ provider: "vercel-ai-gateway",
18591
+ baseUrl: "https://ai-gateway.vercel.sh",
18592
+ reasoning: true,
18593
+ input: ["text", "image"],
18594
+ cost: {
18595
+ input: 0.09999999999999999,
18596
+ output: 0.19999999999999998,
18597
+ cacheRead: 0.002,
18598
+ cacheWrite: 0,
18599
+ },
18600
+ contextWindow: 1048576,
18601
+ maxTokens: 1048576,
18602
+ },
18344
18603
  "minimax/minimax-m2": {
18345
18604
  id: "minimax/minimax-m2",
18346
18605
  name: "MiniMax M2",
@@ -20541,14 +20800,31 @@ export const MODELS = {
20541
20800
  reasoning: true,
20542
20801
  input: ["text"],
20543
20802
  cost: {
20544
- input: 1.4,
20545
- output: 4.4,
20546
- cacheRead: 0.14,
20803
+ input: 0.7,
20804
+ output: 2.2,
20805
+ cacheRead: 0.13,
20547
20806
  cacheWrite: 0,
20548
20807
  },
20549
20808
  contextWindow: 1000000,
20550
20809
  maxTokens: 1000000,
20551
20810
  },
20811
+ "zai/glm-5.3-fast": {
20812
+ id: "zai/glm-5.3-fast",
20813
+ name: "GLM 5.3 Fast",
20814
+ api: "anthropic-messages",
20815
+ provider: "vercel-ai-gateway",
20816
+ baseUrl: "https://ai-gateway.vercel.sh",
20817
+ reasoning: true,
20818
+ input: ["text"],
20819
+ cost: {
20820
+ input: 2.0999999999999996,
20821
+ output: 6.6000000000000005,
20822
+ cacheRead: 0.21,
20823
+ cacheWrite: 0,
20824
+ },
20825
+ contextWindow: 1048576,
20826
+ maxTokens: 262144,
20827
+ },
20552
20828
  "zai/glm-5.3-flash": {
20553
20829
  id: "zai/glm-5.3-flash",
20554
20830
  name: "GLM 5.3 Flash",
@@ -20566,6 +20842,23 @@ export const MODELS = {
20566
20842
  contextWindow: 1000000,
20567
20843
  maxTokens: 131000,
20568
20844
  },
20845
+ "zai/glm-5.3-promo-50": {
20846
+ id: "zai/glm-5.3-promo-50",
20847
+ name: "GLM 5.3 (50% off)",
20848
+ api: "anthropic-messages",
20849
+ provider: "vercel-ai-gateway",
20850
+ baseUrl: "https://ai-gateway.vercel.sh",
20851
+ reasoning: true,
20852
+ input: ["text"],
20853
+ cost: {
20854
+ input: 0.7,
20855
+ output: 2.2,
20856
+ cacheRead: 0.13,
20857
+ cacheWrite: 0,
20858
+ },
20859
+ contextWindow: 1048576,
20860
+ maxTokens: 1048576,
20861
+ },
20569
20862
  "zai/glm-5v-turbo": {
20570
20863
  id: "zai/glm-5v-turbo",
20571
20864
  name: "GLM 5V Turbo",