@elyracode/ai 0.9.52 → 0.9.53

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.
@@ -4570,6 +4570,23 @@ export const MODELS = {
4570
4570
  contextWindow: 200000,
4571
4571
  maxTokens: 64000,
4572
4572
  },
4573
+ "claude-haiku-5.5": {
4574
+ id: "claude-haiku-5.5",
4575
+ name: "Claude Haiku 5.5",
4576
+ api: "anthropic-messages",
4577
+ provider: "cloudflare-ai-gateway",
4578
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4579
+ reasoning: true,
4580
+ input: ["text", "image"],
4581
+ cost: {
4582
+ input: 0.1,
4583
+ output: 0.5,
4584
+ cacheRead: 0.01,
4585
+ cacheWrite: 0.125,
4586
+ },
4587
+ contextWindow: 1000000,
4588
+ maxTokens: 128000,
4589
+ },
4573
4590
  "claude-opus-4.5": {
4574
4591
  id: "claude-opus-4.5",
4575
4592
  name: "Claude Opus 4.5 (latest)",
@@ -6704,7 +6721,7 @@ export const MODELS = {
6704
6721
  provider: "google",
6705
6722
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6706
6723
  reasoning: true,
6707
- thinkingLevelMap: { "off": null },
6724
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6708
6725
  input: ["text", "image"],
6709
6726
  cost: {
6710
6727
  input: 0.5,
@@ -6722,7 +6739,7 @@ export const MODELS = {
6722
6739
  provider: "google",
6723
6740
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6724
6741
  reasoning: true,
6725
- thinkingLevelMap: { "off": null },
6742
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6726
6743
  input: ["text", "image"],
6727
6744
  cost: {
6728
6745
  input: 0.25,
@@ -6740,7 +6757,7 @@ export const MODELS = {
6740
6757
  provider: "google",
6741
6758
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6742
6759
  reasoning: true,
6743
- thinkingLevelMap: { "off": null },
6760
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
6744
6761
  input: ["text", "image"],
6745
6762
  cost: {
6746
6763
  input: 0.25,
@@ -6758,7 +6775,7 @@ export const MODELS = {
6758
6775
  provider: "google",
6759
6776
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6760
6777
  reasoning: true,
6761
- thinkingLevelMap: { "off": null },
6778
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6762
6779
  input: ["text", "image"],
6763
6780
  cost: {
6764
6781
  input: 0.25,
@@ -6776,7 +6793,7 @@ export const MODELS = {
6776
6793
  provider: "google",
6777
6794
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6778
6795
  reasoning: true,
6779
- thinkingLevelMap: { "off": null },
6796
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6780
6797
  input: ["text", "image"],
6781
6798
  cost: {
6782
6799
  input: 0.75,
@@ -6794,7 +6811,7 @@ export const MODELS = {
6794
6811
  provider: "google",
6795
6812
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6796
6813
  reasoning: true,
6797
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
6814
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6798
6815
  input: ["text", "image"],
6799
6816
  cost: {
6800
6817
  input: 2,
@@ -6812,7 +6829,7 @@ export const MODELS = {
6812
6829
  provider: "google",
6813
6830
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6814
6831
  reasoning: true,
6815
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
6832
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6816
6833
  input: ["text", "image"],
6817
6834
  cost: {
6818
6835
  input: 2,
@@ -6830,7 +6847,7 @@ export const MODELS = {
6830
6847
  provider: "google",
6831
6848
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6832
6849
  reasoning: true,
6833
- thinkingLevelMap: { "off": null },
6850
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6834
6851
  input: ["text", "image"],
6835
6852
  cost: {
6836
6853
  input: 1.5,
@@ -6848,7 +6865,7 @@ export const MODELS = {
6848
6865
  provider: "google",
6849
6866
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6850
6867
  reasoning: true,
6851
- thinkingLevelMap: { "off": null },
6868
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6852
6869
  input: ["text", "image"],
6853
6870
  cost: {
6854
6871
  input: 0.3,
@@ -6866,7 +6883,7 @@ export const MODELS = {
6866
6883
  provider: "google",
6867
6884
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6868
6885
  reasoning: true,
6869
- thinkingLevelMap: { "off": null },
6886
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6870
6887
  input: ["text", "image"],
6871
6888
  cost: {
6872
6889
  input: 0.75,
@@ -6884,7 +6901,7 @@ export const MODELS = {
6884
6901
  provider: "google",
6885
6902
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6886
6903
  reasoning: true,
6887
- thinkingLevelMap: { "off": null },
6904
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6888
6905
  input: ["text", "image"],
6889
6906
  cost: {
6890
6907
  input: 0.75,
@@ -6902,7 +6919,7 @@ export const MODELS = {
6902
6919
  provider: "google",
6903
6920
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6904
6921
  reasoning: true,
6905
- thinkingLevelMap: { "off": null },
6922
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6906
6923
  input: ["text", "image"],
6907
6924
  cost: {
6908
6925
  input: 0.75,
@@ -6913,6 +6930,24 @@ export const MODELS = {
6913
6930
  contextWindow: 1048576,
6914
6931
  maxTokens: 65536,
6915
6932
  },
6933
+ "gemini-4-argon": {
6934
+ id: "gemini-4-argon",
6935
+ name: "Gemini 4 Argon",
6936
+ api: "google-generative-ai",
6937
+ provider: "google",
6938
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6939
+ reasoning: true,
6940
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6941
+ input: ["text", "image"],
6942
+ cost: {
6943
+ input: 2,
6944
+ output: 10,
6945
+ cacheRead: 0.1,
6946
+ cacheWrite: 0,
6947
+ },
6948
+ contextWindow: 1048576,
6949
+ maxTokens: 32768,
6950
+ },
6916
6951
  "gemini-flash-latest": {
6917
6952
  id: "gemini-flash-latest",
6918
6953
  name: "Gemini Flash Latest",
@@ -6920,6 +6955,7 @@ export const MODELS = {
6920
6955
  provider: "google",
6921
6956
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6922
6957
  reasoning: true,
6958
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6923
6959
  input: ["text", "image"],
6924
6960
  cost: {
6925
6961
  input: 0.75,
@@ -6937,6 +6973,7 @@ export const MODELS = {
6937
6973
  provider: "google",
6938
6974
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
6939
6975
  reasoning: true,
6976
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
6940
6977
  input: ["text", "image"],
6941
6978
  cost: {
6942
6979
  input: 0.3,
@@ -7089,7 +7126,7 @@ export const MODELS = {
7089
7126
  },
7090
7127
  "gemini-2.5-flash-lite": {
7091
7128
  id: "gemini-2.5-flash-lite",
7092
- name: "Gemini 2.5 Flash Lite (Vertex)",
7129
+ name: "Gemini 2.5 Flash-Lite (Vertex)",
7093
7130
  api: "google-vertex",
7094
7131
  provider: "google-vertex",
7095
7132
  baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -7145,7 +7182,7 @@ export const MODELS = {
7145
7182
  provider: "google-vertex",
7146
7183
  baseUrl: "https://{location}-aiplatform.googleapis.com",
7147
7184
  reasoning: true,
7148
- thinkingLevelMap: { "off": null },
7185
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7149
7186
  input: ["text", "image"],
7150
7187
  cost: {
7151
7188
  input: 0.5,
@@ -7174,6 +7211,42 @@ export const MODELS = {
7174
7211
  contextWindow: 1000000,
7175
7212
  maxTokens: 64000,
7176
7213
  },
7214
+ "gemini-3.1-flash-lite": {
7215
+ id: "gemini-3.1-flash-lite",
7216
+ name: "Gemini 3.1 Flash Lite (Vertex)",
7217
+ api: "google-vertex",
7218
+ provider: "google-vertex",
7219
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7220
+ reasoning: true,
7221
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7222
+ input: ["text", "image"],
7223
+ cost: {
7224
+ input: 0.25,
7225
+ output: 1.5,
7226
+ cacheRead: 0.025,
7227
+ cacheWrite: 0,
7228
+ },
7229
+ contextWindow: 1048576,
7230
+ maxTokens: 65536,
7231
+ },
7232
+ "gemini-3.1-flash-lite-image": {
7233
+ id: "gemini-3.1-flash-lite-image",
7234
+ name: "Nano Banana 2 Lite (Vertex)",
7235
+ api: "google-vertex",
7236
+ provider: "google-vertex",
7237
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7238
+ reasoning: true,
7239
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
7240
+ input: ["text", "image"],
7241
+ cost: {
7242
+ input: 0.25,
7243
+ output: 30,
7244
+ cacheRead: 0.025,
7245
+ cacheWrite: 0,
7246
+ },
7247
+ contextWindow: 65536,
7248
+ maxTokens: 4096,
7249
+ },
7177
7250
  "gemini-3.1-pro-preview": {
7178
7251
  id: "gemini-3.1-pro-preview",
7179
7252
  name: "Gemini 3.1 Pro Preview (Vertex)",
@@ -7181,7 +7254,7 @@ export const MODELS = {
7181
7254
  provider: "google-vertex",
7182
7255
  baseUrl: "https://{location}-aiplatform.googleapis.com",
7183
7256
  reasoning: true,
7184
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
7257
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7185
7258
  input: ["text", "image"],
7186
7259
  cost: {
7187
7260
  input: 2,
@@ -7199,7 +7272,7 @@ export const MODELS = {
7199
7272
  provider: "google-vertex",
7200
7273
  baseUrl: "https://{location}-aiplatform.googleapis.com",
7201
7274
  reasoning: true,
7202
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
7275
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7203
7276
  input: ["text", "image"],
7204
7277
  cost: {
7205
7278
  input: 2,
@@ -7210,6 +7283,114 @@ export const MODELS = {
7210
7283
  contextWindow: 1048576,
7211
7284
  maxTokens: 65536,
7212
7285
  },
7286
+ "gemini-3.5-flash": {
7287
+ id: "gemini-3.5-flash",
7288
+ name: "Gemini 3.5 Flash (Vertex)",
7289
+ api: "google-vertex",
7290
+ provider: "google-vertex",
7291
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7292
+ reasoning: true,
7293
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7294
+ input: ["text", "image"],
7295
+ cost: {
7296
+ input: 1.5,
7297
+ output: 9,
7298
+ cacheRead: 0.15,
7299
+ cacheWrite: 0,
7300
+ },
7301
+ contextWindow: 1048576,
7302
+ maxTokens: 65536,
7303
+ },
7304
+ "gemini-3.5-flash-lite": {
7305
+ id: "gemini-3.5-flash-lite",
7306
+ name: "Gemini 3.5 Flash Lite (Vertex)",
7307
+ api: "google-vertex",
7308
+ provider: "google-vertex",
7309
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7310
+ reasoning: true,
7311
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7312
+ input: ["text", "image"],
7313
+ cost: {
7314
+ input: 0.3,
7315
+ output: 2.5,
7316
+ cacheRead: 0.03,
7317
+ cacheWrite: 0,
7318
+ },
7319
+ contextWindow: 1048576,
7320
+ maxTokens: 65536,
7321
+ },
7322
+ "gemini-3.6-flash": {
7323
+ id: "gemini-3.6-flash",
7324
+ name: "Gemini 3.6 Flash (Vertex)",
7325
+ api: "google-vertex",
7326
+ provider: "google-vertex",
7327
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7328
+ reasoning: true,
7329
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7330
+ input: ["text", "image"],
7331
+ cost: {
7332
+ input: 0.75,
7333
+ output: 3.75,
7334
+ cacheRead: 0.075,
7335
+ cacheWrite: 0,
7336
+ },
7337
+ contextWindow: 1048576,
7338
+ maxTokens: 65536,
7339
+ },
7340
+ "gemini-3.7-flash": {
7341
+ id: "gemini-3.7-flash",
7342
+ name: "Gemini 3.7 Flash (Vertex)",
7343
+ api: "google-vertex",
7344
+ provider: "google-vertex",
7345
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7346
+ reasoning: true,
7347
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7348
+ input: ["text", "image"],
7349
+ cost: {
7350
+ input: 0.75,
7351
+ output: 3.75,
7352
+ cacheRead: 0.075,
7353
+ cacheWrite: 0,
7354
+ },
7355
+ contextWindow: 1048576,
7356
+ maxTokens: 65536,
7357
+ },
7358
+ "gemini-3.8-flash": {
7359
+ id: "gemini-3.8-flash",
7360
+ name: "Gemini 3.8 Flash (Vertex)",
7361
+ api: "google-vertex",
7362
+ provider: "google-vertex",
7363
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7364
+ reasoning: true,
7365
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7366
+ input: ["text", "image"],
7367
+ cost: {
7368
+ input: 0.75,
7369
+ output: 3.75,
7370
+ cacheRead: 0.075,
7371
+ cacheWrite: 0,
7372
+ },
7373
+ contextWindow: 1048576,
7374
+ maxTokens: 65536,
7375
+ },
7376
+ "gemini-4-argon": {
7377
+ id: "gemini-4-argon",
7378
+ name: "Gemini 4 Argon (Vertex)",
7379
+ api: "google-vertex",
7380
+ provider: "google-vertex",
7381
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7382
+ reasoning: true,
7383
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7384
+ input: ["text", "image"],
7385
+ cost: {
7386
+ input: 2,
7387
+ output: 10,
7388
+ cacheRead: 0.1,
7389
+ cacheWrite: 0,
7390
+ },
7391
+ contextWindow: 1048576,
7392
+ maxTokens: 65536,
7393
+ },
7213
7394
  },
7214
7395
  "groq": {
7215
7396
  "llama-3.1-8b-instant": {
@@ -10685,6 +10866,23 @@ export const MODELS = {
10685
10866
  contextWindow: 200000,
10686
10867
  maxTokens: 32000,
10687
10868
  },
10869
+ "cat-jam-free": {
10870
+ id: "cat-jam-free",
10871
+ name: "Cat Jam Free",
10872
+ api: "openai-completions",
10873
+ provider: "opencode",
10874
+ baseUrl: "https://opencode.ai/zen/v1",
10875
+ reasoning: true,
10876
+ input: ["text"],
10877
+ cost: {
10878
+ input: 0,
10879
+ output: 0,
10880
+ cacheRead: 0,
10881
+ cacheWrite: 0,
10882
+ },
10883
+ contextWindow: 262144,
10884
+ maxTokens: 131072,
10885
+ },
10688
10886
  "claude-fable-5": {
10689
10887
  id: "claude-fable-5",
10690
10888
  name: "Claude Fable 5",
@@ -11164,6 +11362,23 @@ export const MODELS = {
11164
11362
  contextWindow: 1048576,
11165
11363
  maxTokens: 65536,
11166
11364
  },
11365
+ "gemini-4-argon": {
11366
+ id: "gemini-4-argon",
11367
+ name: "Gemini 4 Argon",
11368
+ api: "google-generative-ai",
11369
+ provider: "opencode",
11370
+ baseUrl: "https://opencode.ai/zen/v1",
11371
+ reasoning: true,
11372
+ input: ["text", "image"],
11373
+ cost: {
11374
+ input: 2,
11375
+ output: 10,
11376
+ cacheRead: 0.1,
11377
+ cacheWrite: 0,
11378
+ },
11379
+ contextWindow: 1048576,
11380
+ maxTokens: 65536,
11381
+ },
11167
11382
  "glm-5": {
11168
11383
  id: "glm-5",
11169
11384
  name: "GLM-5",
@@ -12120,6 +12335,23 @@ export const MODELS = {
12120
12335
  },
12121
12336
  },
12122
12337
  "opencode-go": {
12338
+ "cat-jam-free": {
12339
+ id: "cat-jam-free",
12340
+ name: "Cat Jam Free",
12341
+ api: "openai-completions",
12342
+ provider: "opencode-go",
12343
+ baseUrl: "https://opencode.ai/zen/go/v1",
12344
+ reasoning: true,
12345
+ input: ["text"],
12346
+ cost: {
12347
+ input: 0,
12348
+ output: 0,
12349
+ cacheRead: 0,
12350
+ cacheWrite: 0,
12351
+ },
12352
+ contextWindow: 262144,
12353
+ maxTokens: 131072,
12354
+ },
12123
12355
  "claude-haiku-5-5": {
12124
12356
  id: "claude-haiku-5-5",
12125
12357
  name: "Claude Haiku 5.5",
@@ -13365,23 +13597,6 @@ export const MODELS = {
13365
13597
  contextWindow: 1000000,
13366
13598
  maxTokens: 128000,
13367
13599
  },
13368
- "apodex/apodex-1.1-mini:free": {
13369
- id: "apodex/apodex-1.1-mini:free",
13370
- name: "Apodex: Apodex 1.1 Mini (free)",
13371
- api: "openai-completions",
13372
- provider: "openrouter",
13373
- baseUrl: "https://openrouter.ai/api/v1",
13374
- reasoning: true,
13375
- input: ["text"],
13376
- cost: {
13377
- input: 0,
13378
- output: 0,
13379
- cacheRead: 0,
13380
- cacheWrite: 0,
13381
- },
13382
- contextWindow: 262144,
13383
- maxTokens: 235929,
13384
- },
13385
13600
  "arcee-ai/trinity-large-thinking": {
13386
13601
  id: "arcee-ai/trinity-large-thinking",
13387
13602
  name: "Arcee AI: Trinity Large Thinking",
@@ -13733,13 +13948,13 @@ export const MODELS = {
13733
13948
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13734
13949
  input: ["text"],
13735
13950
  cost: {
13736
- input: 0.0137,
13737
- output: 1.28,
13738
- cacheRead: 0.0137,
13951
+ input: 0.091,
13952
+ output: 0.182,
13953
+ cacheRead: 0.0182,
13739
13954
  cacheWrite: 0,
13740
13955
  },
13741
13956
  contextWindow: 1048576,
13742
- maxTokens: 943718,
13957
+ maxTokens: 943717,
13743
13958
  },
13744
13959
  "deepseek/deepseek-v4-flash-0731": {
13745
13960
  id: "deepseek/deepseek-v4-flash-0731",
@@ -13752,9 +13967,9 @@ export const MODELS = {
13752
13967
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13753
13968
  input: ["text"],
13754
13969
  cost: {
13755
- input: 0.0076,
13756
- output: 1.28,
13757
- cacheRead: 0.0076,
13970
+ input: 0.016,
13971
+ output: 0.64,
13972
+ cacheRead: 0.016,
13758
13973
  cacheWrite: 0,
13759
13974
  },
13760
13975
  contextWindow: 1048576,
@@ -13790,9 +14005,9 @@ export const MODELS = {
13790
14005
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13791
14006
  input: ["text"],
13792
14007
  cost: {
13793
- input: 0.9483,
13794
- output: 1.8966,
13795
- cacheRead: 0.079025,
14008
+ input: 0.40716,
14009
+ output: 0.81432,
14010
+ cacheRead: 0.03393,
13796
14011
  cacheWrite: 0,
13797
14012
  },
13798
14013
  contextWindow: 1048576,
@@ -13828,9 +14043,9 @@ export const MODELS = {
13828
14043
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13829
14044
  input: ["text", "image"],
13830
14045
  cost: {
13831
- input: 0.3,
13832
- output: 1.2,
13833
- cacheRead: 0.006,
14046
+ input: 0.0441,
14047
+ output: 0.765,
14048
+ cacheRead: 0.0054,
13834
14049
  cacheWrite: 0,
13835
14050
  },
13836
14051
  contextWindow: 1048576,
@@ -14331,26 +14546,60 @@ export const MODELS = {
14331
14546
  contextWindow: 1048576,
14332
14547
  maxTokens: 65536,
14333
14548
  },
14334
- "google/gemini-nano-banana-2.1": {
14335
- id: "google/gemini-nano-banana-2.1",
14336
- name: "Google: Nano Banana 2.1",
14549
+ "google/gemini-4-argon": {
14550
+ id: "google/gemini-4-argon",
14551
+ name: "Google: Gemini 4 Argon",
14337
14552
  api: "openai-completions",
14338
14553
  provider: "openrouter",
14339
14554
  baseUrl: "https://openrouter.ai/api/v1",
14340
14555
  reasoning: true,
14341
14556
  input: ["text", "image"],
14342
14557
  cost: {
14343
- input: 1.5,
14344
- output: 7.5,
14345
- cacheRead: 0,
14346
- cacheWrite: 0,
14558
+ input: 2,
14559
+ output: 10,
14560
+ cacheRead: 0.09999999999999999,
14561
+ cacheWrite: 0.1875,
14347
14562
  },
14348
- contextWindow: 65536,
14349
- maxTokens: 58982,
14563
+ contextWindow: 1048576,
14564
+ maxTokens: 65536,
14350
14565
  },
14351
- "google/gemma-3-12b-it": {
14352
- id: "google/gemma-3-12b-it",
14353
- name: "Google: Gemma 3 12B",
14566
+ "google/gemini-4-argon:batch": {
14567
+ id: "google/gemini-4-argon:batch",
14568
+ name: "Google: Gemini 4 Argon (batch)",
14569
+ api: "openai-completions",
14570
+ provider: "openrouter",
14571
+ baseUrl: "https://openrouter.ai/api/v1",
14572
+ reasoning: true,
14573
+ input: ["text", "image"],
14574
+ cost: {
14575
+ input: 1,
14576
+ output: 5,
14577
+ cacheRead: 0.049999999999999996,
14578
+ cacheWrite: 0.1875,
14579
+ },
14580
+ contextWindow: 1048576,
14581
+ maxTokens: 943718,
14582
+ },
14583
+ "google/gemini-nano-banana-2.1": {
14584
+ id: "google/gemini-nano-banana-2.1",
14585
+ name: "Google: Nano Banana 2.1",
14586
+ api: "openai-completions",
14587
+ provider: "openrouter",
14588
+ baseUrl: "https://openrouter.ai/api/v1",
14589
+ reasoning: true,
14590
+ input: ["text", "image"],
14591
+ cost: {
14592
+ input: 1.5,
14593
+ output: 7.5,
14594
+ cacheRead: 0,
14595
+ cacheWrite: 0,
14596
+ },
14597
+ contextWindow: 65536,
14598
+ maxTokens: 58982,
14599
+ },
14600
+ "google/gemma-3-12b-it": {
14601
+ id: "google/gemma-3-12b-it",
14602
+ name: "Google: Gemma 3 12B",
14354
14603
  api: "openai-completions",
14355
14604
  provider: "openrouter",
14356
14605
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14391,9 +14640,9 @@ export const MODELS = {
14391
14640
  reasoning: true,
14392
14641
  input: ["text", "image"],
14393
14642
  cost: {
14394
- input: 0.0675,
14395
- output: 0.22499999999999998,
14396
- cacheRead: 0.0375,
14643
+ input: 0.0765,
14644
+ output: 0.255,
14645
+ cacheRead: 0.042499999999999996,
14397
14646
  cacheWrite: 0,
14398
14647
  },
14399
14648
  contextWindow: 262144,
@@ -14518,40 +14767,6 @@ export const MODELS = {
14518
14767
  contextWindow: 262144,
14519
14768
  maxTokens: 32768,
14520
14769
  },
14521
- "inclusionai/ling-3.0-flash-fin": {
14522
- id: "inclusionai/ling-3.0-flash-fin",
14523
- name: "inclusionAI: Ling 3.0 Flash Fin",
14524
- api: "openai-completions",
14525
- provider: "openrouter",
14526
- baseUrl: "https://openrouter.ai/api/v1",
14527
- reasoning: true,
14528
- input: ["text"],
14529
- cost: {
14530
- input: 0.041999999999999996,
14531
- output: 0.12319999999999999,
14532
- cacheRead: 0.008400000000000001,
14533
- cacheWrite: 0,
14534
- },
14535
- contextWindow: 262144,
14536
- maxTokens: 32768,
14537
- },
14538
- "inclusionai/ling-3.0-flash-sante": {
14539
- id: "inclusionai/ling-3.0-flash-sante",
14540
- name: "inclusionAI: Ling 3.0 Flash Sante",
14541
- api: "openai-completions",
14542
- provider: "openrouter",
14543
- baseUrl: "https://openrouter.ai/api/v1",
14544
- reasoning: true,
14545
- input: ["text"],
14546
- cost: {
14547
- input: 0.041999999999999996,
14548
- output: 0.12319999999999999,
14549
- cacheRead: 0.008400000000000001,
14550
- cacheWrite: 0,
14551
- },
14552
- contextWindow: 262144,
14553
- maxTokens: 32768,
14554
- },
14555
14770
  "inclusionai/ling-3.0-flash-vl": {
14556
14771
  id: "inclusionai/ling-3.0-flash-vl",
14557
14772
  name: "inclusionAI: Ling 3.0 Flash VL",
@@ -14561,12 +14776,12 @@ export const MODELS = {
14561
14776
  reasoning: true,
14562
14777
  input: ["text", "image"],
14563
14778
  cost: {
14564
- input: 0.020999999999999998,
14565
- output: 0.061599999999999995,
14566
- cacheRead: 0.004200000000000001,
14779
+ input: 0.06,
14780
+ output: 0.18,
14781
+ cacheRead: 0.012,
14567
14782
  cacheWrite: 0,
14568
14783
  },
14569
- contextWindow: 262144,
14784
+ contextWindow: 131072,
14570
14785
  maxTokens: 32768,
14571
14786
  },
14572
14787
  "inclusionai/ling-3.1-flash": {
@@ -14578,13 +14793,13 @@ export const MODELS = {
14578
14793
  reasoning: true,
14579
14794
  input: ["text"],
14580
14795
  cost: {
14581
- input: 0,
14582
- output: 0,
14583
- cacheRead: 0,
14796
+ input: 0.075,
14797
+ output: 0.22499999999999998,
14798
+ cacheRead: 0.015,
14584
14799
  cacheWrite: 0,
14585
14800
  },
14586
14801
  contextWindow: 262144,
14587
- maxTokens: 32768,
14802
+ maxTokens: 235929,
14588
14803
  },
14589
14804
  "liquid/lfm-2.5-2.6b:free": {
14590
14805
  id: "liquid/lfm-2.5-2.6b:free",
@@ -14603,6 +14818,23 @@ export const MODELS = {
14603
14818
  contextWindow: 65536,
14604
14819
  maxTokens: 8192,
14605
14820
  },
14821
+ "liquid/lfm-2.5-24b-a2b": {
14822
+ id: "liquid/lfm-2.5-24b-a2b",
14823
+ name: "LiquidAI: LFM2.5-24B-A2B",
14824
+ api: "openai-completions",
14825
+ provider: "openrouter",
14826
+ baseUrl: "https://openrouter.ai/api/v1",
14827
+ reasoning: true,
14828
+ input: ["text"],
14829
+ cost: {
14830
+ input: 0.049999999999999996,
14831
+ output: 0.7,
14832
+ cacheRead: 0.024999999999999998,
14833
+ cacheWrite: 0,
14834
+ },
14835
+ contextWindow: 128000,
14836
+ maxTokens: 8192,
14837
+ },
14606
14838
  "meituan/longcat-2.0": {
14607
14839
  id: "meituan/longcat-2.0",
14608
14840
  name: "Meituan: LongCat 2.0",
@@ -14663,13 +14895,13 @@ export const MODELS = {
14663
14895
  reasoning: false,
14664
14896
  input: ["text"],
14665
14897
  cost: {
14666
- input: 0.22,
14667
- output: 0.5,
14668
- cacheRead: 0.11,
14898
+ input: 0.59,
14899
+ output: 0.7899999999999999,
14900
+ cacheRead: 0.295,
14669
14901
  cacheWrite: 0,
14670
14902
  },
14671
14903
  contextWindow: 131072,
14672
- maxTokens: 16384,
14904
+ maxTokens: 32768,
14673
14905
  },
14674
14906
  "meta-llama/llama-4-maverick": {
14675
14907
  id: "meta-llama/llama-4-maverick",
@@ -14697,13 +14929,13 @@ export const MODELS = {
14697
14929
  reasoning: false,
14698
14930
  input: ["text", "image"],
14699
14931
  cost: {
14700
- input: 0.09999999999999999,
14701
- output: 0.3,
14932
+ input: 0.18,
14933
+ output: 0.59,
14702
14934
  cacheRead: 0,
14703
14935
  cacheWrite: 0,
14704
14936
  },
14705
14937
  contextWindow: 1310720,
14706
- maxTokens: 16384,
14938
+ maxTokens: 117964,
14707
14939
  },
14708
14940
  "meta/muse-glimmer-30b": {
14709
14941
  id: "meta/muse-glimmer-30b",
@@ -14807,6 +15039,23 @@ export const MODELS = {
14807
15039
  contextWindow: 1048576,
14808
15040
  maxTokens: 943718,
14809
15041
  },
15042
+ "meta/muse-wonder": {
15043
+ id: "meta/muse-wonder",
15044
+ name: "Meta: Muse Wonder",
15045
+ api: "openai-completions",
15046
+ provider: "openrouter",
15047
+ baseUrl: "https://openrouter.ai/api/v1",
15048
+ reasoning: true,
15049
+ input: ["text", "image"],
15050
+ cost: {
15051
+ input: 4,
15052
+ output: 20,
15053
+ cacheRead: 0.19999999999999998,
15054
+ cacheWrite: 0,
15055
+ },
15056
+ contextWindow: 1048576,
15057
+ maxTokens: 943718,
15058
+ },
14810
15059
  "minimax/minimax-m1": {
14811
15060
  id: "minimax/minimax-m1",
14812
15061
  name: "MiniMax: MiniMax M1",
@@ -14884,13 +15133,13 @@ export const MODELS = {
14884
15133
  reasoning: true,
14885
15134
  input: ["text"],
14886
15135
  cost: {
14887
- input: 0.21,
14888
- output: 0.84,
14889
- cacheRead: 0.041999999999999996,
15136
+ input: 0.3,
15137
+ output: 1.2,
15138
+ cacheRead: 0.06,
14890
15139
  cacheWrite: 0,
14891
15140
  },
14892
15141
  contextWindow: 204800,
14893
- maxTokens: 176947,
15142
+ maxTokens: 131072,
14894
15143
  },
14895
15144
  "minimax/minimax-m3": {
14896
15145
  id: "minimax/minimax-m3",
@@ -15411,9 +15660,9 @@ export const MODELS = {
15411
15660
  reasoning: true,
15412
15661
  input: ["text", "image"],
15413
15662
  cost: {
15414
- input: 0.46499999999999997,
15415
- output: 2.4499999999999997,
15416
- cacheRead: 0.0875,
15663
+ input: 0.65,
15664
+ output: 3.41,
15665
+ cacheRead: 0.15,
15417
15666
  cacheWrite: 0,
15418
15667
  },
15419
15668
  contextWindow: 262144,
@@ -15445,9 +15694,9 @@ export const MODELS = {
15445
15694
  reasoning: true,
15446
15695
  input: ["text", "image"],
15447
15696
  cost: {
15448
- input: 0.64,
15449
- output: 13.5,
15450
- cacheRead: 0.28,
15697
+ input: 0.73,
15698
+ output: 10,
15699
+ cacheRead: 0.55,
15451
15700
  cacheWrite: 0,
15452
15701
  },
15453
15702
  contextWindow: 1048576,
@@ -15564,13 +15813,13 @@ export const MODELS = {
15564
15813
  reasoning: true,
15565
15814
  input: ["text"],
15566
15815
  cost: {
15567
- input: 0.5,
15568
- output: 2.2,
15569
- cacheRead: 0.09999999999999999,
15816
+ input: 0.6,
15817
+ output: 2.4,
15818
+ cacheRead: 0.12,
15570
15819
  cacheWrite: 0,
15571
15820
  },
15572
15821
  contextWindow: 262144,
15573
- maxTokens: 16384,
15822
+ maxTokens: 182520,
15574
15823
  },
15575
15824
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
15576
15825
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -16994,13 +17243,13 @@ export const MODELS = {
16994
17243
  reasoning: true,
16995
17244
  input: ["text"],
16996
17245
  cost: {
16997
- input: 0.037,
16998
- output: 0.16999999999999998,
16999
- cacheRead: 0,
17246
+ input: 0.15,
17247
+ output: 0.6,
17248
+ cacheRead: 0.075,
17000
17249
  cacheWrite: 0,
17001
17250
  },
17002
17251
  contextWindow: 131072,
17003
- maxTokens: 117964,
17252
+ maxTokens: 65536,
17004
17253
  },
17005
17254
  "openai/gpt-oss-120b:batch": {
17006
17255
  id: "openai/gpt-oss-120b:batch",
@@ -17453,13 +17702,13 @@ export const MODELS = {
17453
17702
  reasoning: true,
17454
17703
  input: ["text"],
17455
17704
  cost: {
17456
- input: 0.09999999999999999,
17457
- output: 0.22,
17705
+ input: 0.12,
17706
+ output: 0.24,
17458
17707
  cacheRead: 0,
17459
17708
  cacheWrite: 0,
17460
17709
  },
17461
17710
  contextWindow: 40960,
17462
- maxTokens: 36864,
17711
+ maxTokens: 16384,
17463
17712
  },
17464
17713
  "qwen/qwen3-235b-a22b-2507": {
17465
17714
  id: "qwen/qwen3-235b-a22b-2507",
@@ -17759,13 +18008,13 @@ export const MODELS = {
17759
18008
  reasoning: true,
17760
18009
  input: ["text", "image"],
17761
18010
  cost: {
17762
- input: 0.08,
17763
- output: 0.75,
17764
- cacheRead: 0.04,
18011
+ input: 0.15,
18012
+ output: 1,
18013
+ cacheRead: 0.049999999999999996,
17765
18014
  cacheWrite: 0,
17766
18015
  },
17767
18016
  contextWindow: 262144,
17768
- maxTokens: 32768,
18017
+ maxTokens: 16384,
17769
18018
  },
17770
18019
  "qwen/qwen3.5-397b-a17b": {
17771
18020
  id: "qwen/qwen3.5-397b-a17b",
@@ -17878,13 +18127,13 @@ export const MODELS = {
17878
18127
  reasoning: true,
17879
18128
  input: ["text", "image"],
17880
18129
  cost: {
17881
- input: 0.15,
17882
- output: 1,
17883
- cacheRead: 0.049999999999999996,
18130
+ input: 0.09999999999999999,
18131
+ output: 0.95,
18132
+ cacheRead: 0.09999999999999999,
17884
18133
  cacheWrite: 0,
17885
18134
  },
17886
18135
  contextWindow: 262144,
17887
- maxTokens: 235929,
18136
+ maxTokens: 65536,
17888
18137
  },
17889
18138
  "qwen/qwen3.6-flash": {
17890
18139
  id: "qwen/qwen3.6-flash",
@@ -17997,13 +18246,13 @@ export const MODELS = {
17997
18246
  reasoning: true,
17998
18247
  input: ["text", "image"],
17999
18248
  cost: {
18000
- input: 0.425,
18001
- output: 2.5500000000000003,
18002
- cacheRead: 0.08499999999999999,
18003
- cacheWrite: 0.53125,
18249
+ input: 0.04,
18250
+ output: 2.3,
18251
+ cacheRead: 0.019799999999999998,
18252
+ cacheWrite: 0,
18004
18253
  },
18005
18254
  contextWindow: 1000000,
18006
- maxTokens: 131072,
18255
+ maxTokens: 235929,
18007
18256
  },
18008
18257
  "qwen/qwen3.8-flash": {
18009
18258
  id: "qwen/qwen3.8-flash",
@@ -18235,9 +18484,9 @@ export const MODELS = {
18235
18484
  reasoning: true,
18236
18485
  input: ["text"],
18237
18486
  cost: {
18238
- input: 0.13199999999999998,
18239
- output: 0.5279999999999999,
18240
- cacheRead: 0.032999999999999995,
18487
+ input: 0.0825,
18488
+ output: 0.33,
18489
+ cacheRead: 0.020625,
18241
18490
  cacheWrite: 0,
18242
18491
  },
18243
18492
  contextWindow: 262144,
@@ -18252,9 +18501,9 @@ export const MODELS = {
18252
18501
  reasoning: true,
18253
18502
  input: ["text"],
18254
18503
  cost: {
18255
- input: 0.834,
18256
- output: 2.501,
18257
- cacheRead: 0.041999999999999996,
18504
+ input: 0.7505999999999999,
18505
+ output: 2.2509,
18506
+ cacheRead: 0.0378,
18258
18507
  cacheWrite: 0,
18259
18508
  },
18260
18509
  contextWindow: 1048576,
@@ -18830,9 +19079,9 @@ export const MODELS = {
18830
19079
  reasoning: true,
18831
19080
  input: ["text"],
18832
19081
  cost: {
18833
- input: 0.039,
19082
+ input: 0.079,
18834
19083
  output: 4.8,
18835
- cacheRead: 0.038000000000000006,
19084
+ cacheRead: 0.059,
18836
19085
  cacheWrite: 0,
18837
19086
  },
18838
19087
  contextWindow: 1048576,
@@ -18847,13 +19096,13 @@ export const MODELS = {
18847
19096
  reasoning: true,
18848
19097
  input: ["text", "image"],
18849
19098
  cost: {
18850
- input: 0.15,
18851
- output: 0.5,
18852
- cacheRead: 0.03,
19099
+ input: 0.026099999999999998,
19100
+ output: 0.8999999999999999,
19101
+ cacheRead: 0.0108,
18853
19102
  cacheWrite: 0,
18854
19103
  },
18855
19104
  contextWindow: 1048576,
18856
- maxTokens: 943717,
19105
+ maxTokens: 943718,
18857
19106
  },
18858
19107
  "z-ai/glm-5.3-flash:batch": {
18859
19108
  id: "z-ai/glm-5.3-flash:batch",
@@ -19018,9 +19267,9 @@ export const MODELS = {
19018
19267
  reasoning: true,
19019
19268
  input: ["text", "image"],
19020
19269
  cost: {
19021
- input: 0.0007,
19022
- output: 0.6,
19023
- cacheRead: 0.005,
19270
+ input: 0.0441,
19271
+ output: 0.765,
19272
+ cacheRead: 0.0054,
19024
19273
  cacheWrite: 0,
19025
19274
  },
19026
19275
  contextWindow: 1048576,
@@ -19035,13 +19284,13 @@ export const MODELS = {
19035
19284
  reasoning: true,
19036
19285
  input: ["text"],
19037
19286
  cost: {
19038
- input: 0.3,
19039
- output: 5,
19040
- cacheRead: 0.219,
19287
+ input: 0.24947999999999998,
19288
+ output: 0.7484400000000001,
19289
+ cacheRead: 0.007937999999999999,
19041
19290
  cacheWrite: 0,
19042
19291
  },
19043
19292
  contextWindow: 1048576,
19044
- maxTokens: 943718,
19293
+ maxTokens: 393216,
19045
19294
  },
19046
19295
  "~deepseek/deepseek-v4-flash-latest": {
19047
19296
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -19054,9 +19303,9 @@ export const MODELS = {
19054
19303
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19055
19304
  input: ["text"],
19056
19305
  cost: {
19057
- input: 0.0076,
19058
- output: 1.28,
19059
- cacheRead: 0.0076,
19306
+ input: 0.0144,
19307
+ output: 0.576,
19308
+ cacheRead: 0.0108,
19060
19309
  cacheWrite: 0,
19061
19310
  },
19062
19311
  contextWindow: 1048576,
@@ -19105,8 +19354,8 @@ export const MODELS = {
19105
19354
  reasoning: true,
19106
19355
  input: ["text", "image"],
19107
19356
  cost: {
19108
- input: 0.39999999999999997,
19109
- output: 14.89,
19357
+ input: 0.72,
19358
+ output: 24,
19110
19359
  cacheRead: 0.3,
19111
19360
  cacheWrite: 0,
19112
19361
  },
@@ -19224,13 +19473,13 @@ export const MODELS = {
19224
19473
  reasoning: true,
19225
19474
  input: ["text", "image"],
19226
19475
  cost: {
19227
- input: 0.04,
19228
- output: 0.5,
19229
- cacheRead: 0.012499999999999999,
19476
+ input: 0.026099999999999998,
19477
+ output: 0.8999999999999999,
19478
+ cacheRead: 0.0108,
19230
19479
  cacheWrite: 0,
19231
19480
  },
19232
19481
  contextWindow: 1048576,
19233
- maxTokens: 131072,
19482
+ maxTokens: 943718,
19234
19483
  },
19235
19484
  "~z-ai/glm-latest": {
19236
19485
  id: "~z-ai/glm-latest",
@@ -19241,9 +19490,9 @@ export const MODELS = {
19241
19490
  reasoning: true,
19242
19491
  input: ["text"],
19243
19492
  cost: {
19244
- input: 0.039,
19493
+ input: 0.079,
19245
19494
  output: 4.8,
19246
- cacheRead: 0.038000000000000006,
19495
+ cacheRead: 0.059,
19247
19496
  cacheWrite: 0,
19248
19497
  },
19249
19498
  contextWindow: 1048576,
@@ -19633,48 +19882,14 @@ export const MODELS = {
19633
19882
  reasoning: true,
19634
19883
  input: ["text"],
19635
19884
  cost: {
19636
- input: 0.16,
19637
- output: 0.64,
19885
+ input: 0.15,
19886
+ output: 0.6,
19638
19887
  cacheRead: 0,
19639
19888
  cacheWrite: 0,
19640
19889
  },
19641
19890
  contextWindow: 128000,
19642
19891
  maxTokens: 8192,
19643
19892
  },
19644
- "alibaba/qwen-3.6-max-preview": {
19645
- id: "alibaba/qwen-3.6-max-preview",
19646
- name: "Qwen 3.6 Max Preview",
19647
- api: "anthropic-messages",
19648
- provider: "vercel-ai-gateway",
19649
- baseUrl: "https://ai-gateway.vercel.sh",
19650
- reasoning: true,
19651
- input: ["text"],
19652
- cost: {
19653
- input: 1.3,
19654
- output: 7.8,
19655
- cacheRead: 0.13,
19656
- cacheWrite: 1.625,
19657
- },
19658
- contextWindow: 240000,
19659
- maxTokens: 64000,
19660
- },
19661
- "alibaba/qwen3-235b-a22b-thinking": {
19662
- id: "alibaba/qwen3-235b-a22b-thinking",
19663
- name: "Qwen3 VL 235B A22B Thinking",
19664
- api: "anthropic-messages",
19665
- provider: "vercel-ai-gateway",
19666
- baseUrl: "https://ai-gateway.vercel.sh",
19667
- reasoning: true,
19668
- input: ["text", "image"],
19669
- cost: {
19670
- input: 0.39999999999999997,
19671
- output: 4,
19672
- cacheRead: 0,
19673
- cacheWrite: 0,
19674
- },
19675
- contextWindow: 131072,
19676
- maxTokens: 32768,
19677
- },
19678
19893
  "alibaba/qwen3-coder": {
19679
19894
  id: "alibaba/qwen3-coder",
19680
19895
  name: "Qwen3 Coder 480B A35B Instruct",
@@ -19684,13 +19899,13 @@ export const MODELS = {
19684
19899
  reasoning: false,
19685
19900
  input: ["text"],
19686
19901
  cost: {
19687
- input: 1.5,
19688
- output: 7.5,
19689
- cacheRead: 0.3,
19902
+ input: 0.22,
19903
+ output: 1.7999999999999998,
19904
+ cacheRead: 0.022,
19690
19905
  cacheWrite: 0,
19691
19906
  },
19692
19907
  contextWindow: 262144,
19693
- maxTokens: 65536,
19908
+ maxTokens: 32768,
19694
19909
  },
19695
19910
  "alibaba/qwen3-coder-30b-a3b": {
19696
19911
  id: "alibaba/qwen3-coder-30b-a3b",
@@ -19726,77 +19941,26 @@ export const MODELS = {
19726
19941
  contextWindow: 256000,
19727
19942
  maxTokens: 256000,
19728
19943
  },
19729
- "alibaba/qwen3-coder-plus": {
19730
- id: "alibaba/qwen3-coder-plus",
19731
- name: "Qwen3 Coder Plus",
19944
+ "alibaba/qwen3-max-thinking": {
19945
+ id: "alibaba/qwen3-max-thinking",
19946
+ name: "Qwen 3 Max Thinking",
19732
19947
  api: "anthropic-messages",
19733
19948
  provider: "vercel-ai-gateway",
19734
19949
  baseUrl: "https://ai-gateway.vercel.sh",
19735
- reasoning: false,
19950
+ reasoning: true,
19736
19951
  input: ["text"],
19737
19952
  cost: {
19738
- input: 1,
19739
- output: 5,
19740
- cacheRead: 0.19999999999999998,
19953
+ input: 1.2,
19954
+ output: 6,
19955
+ cacheRead: 0.24,
19741
19956
  cacheWrite: 0,
19742
19957
  },
19743
- contextWindow: 1000000,
19958
+ contextWindow: 256000,
19744
19959
  maxTokens: 65536,
19745
19960
  },
19746
- "alibaba/qwen3-max": {
19747
- id: "alibaba/qwen3-max",
19748
- name: "Qwen3 Max",
19749
- api: "anthropic-messages",
19750
- provider: "vercel-ai-gateway",
19751
- baseUrl: "https://ai-gateway.vercel.sh",
19752
- reasoning: false,
19753
- input: ["text"],
19754
- cost: {
19755
- input: 1.2,
19756
- output: 6,
19757
- cacheRead: 0.24,
19758
- cacheWrite: 0,
19759
- },
19760
- contextWindow: 262144,
19761
- maxTokens: 32768,
19762
- },
19763
- "alibaba/qwen3-max-preview": {
19764
- id: "alibaba/qwen3-max-preview",
19765
- name: "Qwen3 Max Preview",
19766
- api: "anthropic-messages",
19767
- provider: "vercel-ai-gateway",
19768
- baseUrl: "https://ai-gateway.vercel.sh",
19769
- reasoning: false,
19770
- input: ["text"],
19771
- cost: {
19772
- input: 1.2,
19773
- output: 6,
19774
- cacheRead: 0.24,
19775
- cacheWrite: 0,
19776
- },
19777
- contextWindow: 262144,
19778
- maxTokens: 32768,
19779
- },
19780
- "alibaba/qwen3-max-thinking": {
19781
- id: "alibaba/qwen3-max-thinking",
19782
- name: "Qwen 3 Max Thinking",
19783
- api: "anthropic-messages",
19784
- provider: "vercel-ai-gateway",
19785
- baseUrl: "https://ai-gateway.vercel.sh",
19786
- reasoning: true,
19787
- input: ["text"],
19788
- cost: {
19789
- input: 1.2,
19790
- output: 6,
19791
- cacheRead: 0.24,
19792
- cacheWrite: 0,
19793
- },
19794
- contextWindow: 256000,
19795
- maxTokens: 65536,
19796
- },
19797
- "alibaba/qwen3-next-80b-a3b-instruct": {
19798
- id: "alibaba/qwen3-next-80b-a3b-instruct",
19799
- name: "Qwen3 Next 80B A3B Instruct",
19961
+ "alibaba/qwen3-next-80b-a3b-instruct": {
19962
+ id: "alibaba/qwen3-next-80b-a3b-instruct",
19963
+ name: "Qwen3 Next 80B A3B Instruct",
19800
19964
  api: "anthropic-messages",
19801
19965
  provider: "vercel-ai-gateway",
19802
19966
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -19828,23 +19992,6 @@ export const MODELS = {
19828
19992
  contextWindow: 262144,
19829
19993
  maxTokens: 262144,
19830
19994
  },
19831
- "alibaba/qwen3-vl-235b-a22b-instruct": {
19832
- id: "alibaba/qwen3-vl-235b-a22b-instruct",
19833
- name: "Qwen3 VL 235B A22B Instruct",
19834
- api: "anthropic-messages",
19835
- provider: "vercel-ai-gateway",
19836
- baseUrl: "https://ai-gateway.vercel.sh",
19837
- reasoning: false,
19838
- input: ["text", "image"],
19839
- cost: {
19840
- input: 0.39999999999999997,
19841
- output: 1.5999999999999999,
19842
- cacheRead: 0,
19843
- cacheWrite: 0,
19844
- },
19845
- contextWindow: 131072,
19846
- maxTokens: 129024,
19847
- },
19848
19995
  "alibaba/qwen3-vl-instruct": {
19849
19996
  id: "alibaba/qwen3-vl-instruct",
19850
19997
  name: "Qwen3 VL 235B A22B Instruct",
@@ -19854,30 +20001,13 @@ export const MODELS = {
19854
20001
  reasoning: false,
19855
20002
  input: ["text", "image"],
19856
20003
  cost: {
19857
- input: 0.39999999999999997,
19858
- output: 1.5999999999999999,
19859
- cacheRead: 0,
19860
- cacheWrite: 0,
19861
- },
19862
- contextWindow: 131072,
19863
- maxTokens: 129024,
19864
- },
19865
- "alibaba/qwen3-vl-thinking": {
19866
- id: "alibaba/qwen3-vl-thinking",
19867
- name: "Qwen3 VL 235B A22B Thinking",
19868
- api: "anthropic-messages",
19869
- provider: "vercel-ai-gateway",
19870
- baseUrl: "https://ai-gateway.vercel.sh",
19871
- reasoning: true,
19872
- input: ["text", "image"],
19873
- cost: {
19874
- input: 0.39999999999999997,
19875
- output: 4,
19876
- cacheRead: 0,
20004
+ input: 0.19999999999999998,
20005
+ output: 0.88,
20006
+ cacheRead: 0.11,
19877
20007
  cacheWrite: 0,
19878
20008
  },
19879
- contextWindow: 131072,
19880
- maxTokens: 32768,
20009
+ contextWindow: 262144,
20010
+ maxTokens: 262144,
19881
20011
  },
19882
20012
  "alibaba/qwen3.5-flash": {
19883
20013
  id: "alibaba/qwen3.5-flash",
@@ -20185,23 +20315,6 @@ export const MODELS = {
20185
20315
  contextWindow: 300000,
20186
20316
  maxTokens: 8192,
20187
20317
  },
20188
- "anthropic/claude-3-haiku": {
20189
- id: "anthropic/claude-3-haiku",
20190
- name: "Claude 3 Haiku",
20191
- api: "anthropic-messages",
20192
- provider: "vercel-ai-gateway",
20193
- baseUrl: "https://ai-gateway.vercel.sh",
20194
- reasoning: false,
20195
- input: ["text", "image"],
20196
- cost: {
20197
- input: 0.25,
20198
- output: 1.25,
20199
- cacheRead: 0.03,
20200
- cacheWrite: 0.3,
20201
- },
20202
- contextWindow: 200000,
20203
- maxTokens: 4096,
20204
- },
20205
20318
  "anthropic/claude-fable-5": {
20206
20319
  id: "anthropic/claude-fable-5",
20207
20320
  name: "Claude Fable 5",
@@ -20220,6 +20333,24 @@ export const MODELS = {
20220
20333
  contextWindow: 1000000,
20221
20334
  maxTokens: 128000,
20222
20335
  },
20336
+ "anthropic/claude-fable-5-batch": {
20337
+ id: "anthropic/claude-fable-5-batch",
20338
+ name: "Claude Fable 5 (Batch)",
20339
+ api: "anthropic-messages",
20340
+ provider: "vercel-ai-gateway",
20341
+ baseUrl: "https://ai-gateway.vercel.sh",
20342
+ reasoning: true,
20343
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20344
+ input: ["text", "image"],
20345
+ cost: {
20346
+ input: 5,
20347
+ output: 25,
20348
+ cacheRead: 0.5,
20349
+ cacheWrite: 6.25,
20350
+ },
20351
+ contextWindow: 1000000,
20352
+ maxTokens: 128000,
20353
+ },
20223
20354
  "anthropic/claude-fable-5.1": {
20224
20355
  id: "anthropic/claude-fable-5.1",
20225
20356
  name: "Claude Fable 5.1",
@@ -20238,6 +20369,24 @@ export const MODELS = {
20238
20369
  contextWindow: 1000000,
20239
20370
  maxTokens: 128000,
20240
20371
  },
20372
+ "anthropic/claude-fable-5.1-batch": {
20373
+ id: "anthropic/claude-fable-5.1-batch",
20374
+ name: "Claude Fable 5.1 (Batch)",
20375
+ api: "anthropic-messages",
20376
+ provider: "vercel-ai-gateway",
20377
+ baseUrl: "https://ai-gateway.vercel.sh",
20378
+ reasoning: true,
20379
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20380
+ input: ["text", "image"],
20381
+ cost: {
20382
+ input: 5,
20383
+ output: 25,
20384
+ cacheRead: 0.125,
20385
+ cacheWrite: 6.25,
20386
+ },
20387
+ contextWindow: 1000000,
20388
+ maxTokens: 128000,
20389
+ },
20241
20390
  "anthropic/claude-haiku-4.5": {
20242
20391
  id: "anthropic/claude-haiku-4.5",
20243
20392
  name: "Claude Haiku 4.5",
@@ -20255,6 +20404,23 @@ export const MODELS = {
20255
20404
  contextWindow: 200000,
20256
20405
  maxTokens: 64000,
20257
20406
  },
20407
+ "anthropic/claude-haiku-4.5-batch": {
20408
+ id: "anthropic/claude-haiku-4.5-batch",
20409
+ name: "Claude Haiku 4.5 (Batch)",
20410
+ api: "anthropic-messages",
20411
+ provider: "vercel-ai-gateway",
20412
+ baseUrl: "https://ai-gateway.vercel.sh",
20413
+ reasoning: true,
20414
+ input: ["text", "image"],
20415
+ cost: {
20416
+ input: 0.5,
20417
+ output: 2.5,
20418
+ cacheRead: 0.049999999999999996,
20419
+ cacheWrite: 0.625,
20420
+ },
20421
+ contextWindow: 200000,
20422
+ maxTokens: 64000,
20423
+ },
20258
20424
  "anthropic/claude-haiku-5.5": {
20259
20425
  id: "anthropic/claude-haiku-5.5",
20260
20426
  name: "Claude Haiku 5.5",
@@ -20272,22 +20438,22 @@ export const MODELS = {
20272
20438
  contextWindow: 1000000,
20273
20439
  maxTokens: 128000,
20274
20440
  },
20275
- "anthropic/claude-opus-4": {
20276
- id: "anthropic/claude-opus-4",
20277
- name: "Claude Opus 4",
20441
+ "anthropic/claude-haiku-5.5-batch": {
20442
+ id: "anthropic/claude-haiku-5.5-batch",
20443
+ name: "Claude Haiku 5.5 (Batch)",
20278
20444
  api: "anthropic-messages",
20279
20445
  provider: "vercel-ai-gateway",
20280
20446
  baseUrl: "https://ai-gateway.vercel.sh",
20281
20447
  reasoning: true,
20282
20448
  input: ["text", "image"],
20283
20449
  cost: {
20284
- input: 15,
20285
- output: 75,
20286
- cacheRead: 1.5,
20287
- cacheWrite: 18.75,
20450
+ input: 0.049999999999999996,
20451
+ output: 0.25,
20452
+ cacheRead: 0.005,
20453
+ cacheWrite: 0.0625,
20288
20454
  },
20289
- contextWindow: 200000,
20290
- maxTokens: 32000,
20455
+ contextWindow: 1000000,
20456
+ maxTokens: 128000,
20291
20457
  },
20292
20458
  "anthropic/claude-opus-4.5": {
20293
20459
  id: "anthropic/claude-opus-4.5",
@@ -20306,6 +20472,23 @@ export const MODELS = {
20306
20472
  contextWindow: 200000,
20307
20473
  maxTokens: 64000,
20308
20474
  },
20475
+ "anthropic/claude-opus-4.5-batch": {
20476
+ id: "anthropic/claude-opus-4.5-batch",
20477
+ name: "Claude Opus 4.5 (Batch)",
20478
+ api: "anthropic-messages",
20479
+ provider: "vercel-ai-gateway",
20480
+ baseUrl: "https://ai-gateway.vercel.sh",
20481
+ reasoning: true,
20482
+ input: ["text", "image"],
20483
+ cost: {
20484
+ input: 2.5,
20485
+ output: 12.5,
20486
+ cacheRead: 0.25,
20487
+ cacheWrite: 3.125,
20488
+ },
20489
+ contextWindow: 200000,
20490
+ maxTokens: 64000,
20491
+ },
20309
20492
  "anthropic/claude-opus-4.6": {
20310
20493
  id: "anthropic/claude-opus-4.6",
20311
20494
  name: "Claude Opus 4.6",
@@ -20324,6 +20507,24 @@ export const MODELS = {
20324
20507
  contextWindow: 1000000,
20325
20508
  maxTokens: 128000,
20326
20509
  },
20510
+ "anthropic/claude-opus-4.6-batch": {
20511
+ id: "anthropic/claude-opus-4.6-batch",
20512
+ name: "Claude Opus 4.6 (Batch)",
20513
+ api: "anthropic-messages",
20514
+ provider: "vercel-ai-gateway",
20515
+ baseUrl: "https://ai-gateway.vercel.sh",
20516
+ reasoning: true,
20517
+ thinkingLevelMap: { "xhigh": "max" },
20518
+ input: ["text", "image"],
20519
+ cost: {
20520
+ input: 2.5,
20521
+ output: 12.5,
20522
+ cacheRead: 0.25,
20523
+ cacheWrite: 3.125,
20524
+ },
20525
+ contextWindow: 1000000,
20526
+ maxTokens: 128000,
20527
+ },
20327
20528
  "anthropic/claude-opus-4.7": {
20328
20529
  id: "anthropic/claude-opus-4.7",
20329
20530
  name: "Claude Opus 4.7",
@@ -20342,6 +20543,24 @@ export const MODELS = {
20342
20543
  contextWindow: 1000000,
20343
20544
  maxTokens: 128000,
20344
20545
  },
20546
+ "anthropic/claude-opus-4.7-batch": {
20547
+ id: "anthropic/claude-opus-4.7-batch",
20548
+ name: "Claude Opus 4.7 (Batch)",
20549
+ api: "anthropic-messages",
20550
+ provider: "vercel-ai-gateway",
20551
+ baseUrl: "https://ai-gateway.vercel.sh",
20552
+ reasoning: true,
20553
+ thinkingLevelMap: { "xhigh": "xhigh" },
20554
+ input: ["text", "image"],
20555
+ cost: {
20556
+ input: 2.5,
20557
+ output: 12.5,
20558
+ cacheRead: 0.25,
20559
+ cacheWrite: 3.125,
20560
+ },
20561
+ contextWindow: 1000000,
20562
+ maxTokens: 128000,
20563
+ },
20345
20564
  "anthropic/claude-opus-4.8": {
20346
20565
  id: "anthropic/claude-opus-4.8",
20347
20566
  name: "Claude Opus 4.8",
@@ -20360,6 +20579,24 @@ export const MODELS = {
20360
20579
  contextWindow: 1000000,
20361
20580
  maxTokens: 128000,
20362
20581
  },
20582
+ "anthropic/claude-opus-4.8-batch": {
20583
+ id: "anthropic/claude-opus-4.8-batch",
20584
+ name: "Claude Opus 4.8 (Batch)",
20585
+ api: "anthropic-messages",
20586
+ provider: "vercel-ai-gateway",
20587
+ baseUrl: "https://ai-gateway.vercel.sh",
20588
+ reasoning: true,
20589
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
20590
+ input: ["text", "image"],
20591
+ cost: {
20592
+ input: 2.5,
20593
+ output: 12.5,
20594
+ cacheRead: 0.25,
20595
+ cacheWrite: 3.125,
20596
+ },
20597
+ contextWindow: 1000000,
20598
+ maxTokens: 128000,
20599
+ },
20363
20600
  "anthropic/claude-opus-4.8-fast": {
20364
20601
  id: "anthropic/claude-opus-4.8-fast",
20365
20602
  name: "Claude Opus 4.8 (Fast)",
@@ -20395,6 +20632,23 @@ export const MODELS = {
20395
20632
  contextWindow: 1000000,
20396
20633
  maxTokens: 128000,
20397
20634
  },
20635
+ "anthropic/claude-opus-5-batch": {
20636
+ id: "anthropic/claude-opus-5-batch",
20637
+ name: "Claude Opus 5 (Batch)",
20638
+ api: "anthropic-messages",
20639
+ provider: "vercel-ai-gateway",
20640
+ baseUrl: "https://ai-gateway.vercel.sh",
20641
+ reasoning: true,
20642
+ input: ["text", "image"],
20643
+ cost: {
20644
+ input: 2.5,
20645
+ output: 12.5,
20646
+ cacheRead: 0.25,
20647
+ cacheWrite: 3.125,
20648
+ },
20649
+ contextWindow: 1000000,
20650
+ maxTokens: 128000,
20651
+ },
20398
20652
  "anthropic/claude-opus-5-fast": {
20399
20653
  id: "anthropic/claude-opus-5-fast",
20400
20654
  name: "Claude Opus 5 (Fast)",
@@ -20429,6 +20683,23 @@ export const MODELS = {
20429
20683
  contextWindow: 1000000,
20430
20684
  maxTokens: 128000,
20431
20685
  },
20686
+ "anthropic/claude-opus-5.5-batch": {
20687
+ id: "anthropic/claude-opus-5.5-batch",
20688
+ name: "Claude Opus 5.5 (Batch)",
20689
+ api: "anthropic-messages",
20690
+ provider: "vercel-ai-gateway",
20691
+ baseUrl: "https://ai-gateway.vercel.sh",
20692
+ reasoning: true,
20693
+ input: ["text", "image"],
20694
+ cost: {
20695
+ input: 2,
20696
+ output: 10,
20697
+ cacheRead: 0.09999999999999999,
20698
+ cacheWrite: 2.5,
20699
+ },
20700
+ contextWindow: 1000000,
20701
+ maxTokens: 128000,
20702
+ },
20432
20703
  "anthropic/claude-opus-5.5-fast": {
20433
20704
  id: "anthropic/claude-opus-5.5-fast",
20434
20705
  name: "Claude Opus 5.5 (Fast)",
@@ -20480,6 +20751,23 @@ export const MODELS = {
20480
20751
  contextWindow: 1000000,
20481
20752
  maxTokens: 64000,
20482
20753
  },
20754
+ "anthropic/claude-sonnet-4.5-batch": {
20755
+ id: "anthropic/claude-sonnet-4.5-batch",
20756
+ name: "Claude Sonnet 4.5 (Batch)",
20757
+ api: "anthropic-messages",
20758
+ provider: "vercel-ai-gateway",
20759
+ baseUrl: "https://ai-gateway.vercel.sh",
20760
+ reasoning: true,
20761
+ input: ["text", "image"],
20762
+ cost: {
20763
+ input: 1.5,
20764
+ output: 7.5,
20765
+ cacheRead: 0.15,
20766
+ cacheWrite: 1.875,
20767
+ },
20768
+ contextWindow: 1000000,
20769
+ maxTokens: 64000,
20770
+ },
20483
20771
  "anthropic/claude-sonnet-4.6": {
20484
20772
  id: "anthropic/claude-sonnet-4.6",
20485
20773
  name: "Claude Sonnet 4.6",
@@ -20497,6 +20785,23 @@ export const MODELS = {
20497
20785
  contextWindow: 1000000,
20498
20786
  maxTokens: 128000,
20499
20787
  },
20788
+ "anthropic/claude-sonnet-4.6-batch": {
20789
+ id: "anthropic/claude-sonnet-4.6-batch",
20790
+ name: "Claude Sonnet 4.6 (Batch)",
20791
+ api: "anthropic-messages",
20792
+ provider: "vercel-ai-gateway",
20793
+ baseUrl: "https://ai-gateway.vercel.sh",
20794
+ reasoning: true,
20795
+ input: ["text", "image"],
20796
+ cost: {
20797
+ input: 1.5,
20798
+ output: 7.5,
20799
+ cacheRead: 0.15,
20800
+ cacheWrite: 1.875,
20801
+ },
20802
+ contextWindow: 1000000,
20803
+ maxTokens: 128000,
20804
+ },
20500
20805
  "anthropic/claude-sonnet-5": {
20501
20806
  id: "anthropic/claude-sonnet-5",
20502
20807
  name: "Claude Sonnet 5",
@@ -20514,6 +20819,23 @@ export const MODELS = {
20514
20819
  contextWindow: 1000000,
20515
20820
  maxTokens: 128000,
20516
20821
  },
20822
+ "anthropic/claude-sonnet-5-batch": {
20823
+ id: "anthropic/claude-sonnet-5-batch",
20824
+ name: "Claude Sonnet 5 (Batch)",
20825
+ api: "anthropic-messages",
20826
+ provider: "vercel-ai-gateway",
20827
+ baseUrl: "https://ai-gateway.vercel.sh",
20828
+ reasoning: true,
20829
+ input: ["text", "image"],
20830
+ cost: {
20831
+ input: 1,
20832
+ output: 5,
20833
+ cacheRead: 0.09999999999999999,
20834
+ cacheWrite: 1.25,
20835
+ },
20836
+ contextWindow: 1000000,
20837
+ maxTokens: 128000,
20838
+ },
20517
20839
  "anthropic/claude-sonnet-5.5": {
20518
20840
  id: "anthropic/claude-sonnet-5.5",
20519
20841
  name: "Claude Sonnet 5.5",
@@ -20531,6 +20853,23 @@ export const MODELS = {
20531
20853
  contextWindow: 1000000,
20532
20854
  maxTokens: 128000,
20533
20855
  },
20856
+ "anthropic/claude-sonnet-5.5-batch": {
20857
+ id: "anthropic/claude-sonnet-5.5-batch",
20858
+ name: "Claude Sonnet 5.5 (Batch)",
20859
+ api: "anthropic-messages",
20860
+ provider: "vercel-ai-gateway",
20861
+ baseUrl: "https://ai-gateway.vercel.sh",
20862
+ reasoning: true,
20863
+ input: ["text", "image"],
20864
+ cost: {
20865
+ input: 1,
20866
+ output: 5,
20867
+ cacheRead: 0.049999999999999996,
20868
+ cacheWrite: 1.25,
20869
+ },
20870
+ contextWindow: 1000000,
20871
+ maxTokens: 128000,
20872
+ },
20534
20873
  "arcee-ai/trinity-large-thinking": {
20535
20874
  id: "arcee-ai/trinity-large-thinking",
20536
20875
  name: "Trinity Large Thinking",
@@ -20803,6 +21142,23 @@ export const MODELS = {
20803
21142
  contextWindow: 1048576,
20804
21143
  maxTokens: 32768,
20805
21144
  },
21145
+ "deepseek/deepseek-v4.1-flash-fast": {
21146
+ id: "deepseek/deepseek-v4.1-flash-fast",
21147
+ name: "DeepSeek V4.1 Flash Fast",
21148
+ api: "anthropic-messages",
21149
+ provider: "vercel-ai-gateway",
21150
+ baseUrl: "https://ai-gateway.vercel.sh",
21151
+ reasoning: true,
21152
+ input: ["text", "image"],
21153
+ cost: {
21154
+ input: 0.6,
21155
+ output: 2.4,
21156
+ cacheRead: 0.014,
21157
+ cacheWrite: 0,
21158
+ },
21159
+ contextWindow: 1048576,
21160
+ maxTokens: 32768,
21161
+ },
20806
21162
  "fireworks/ember-1": {
20807
21163
  id: "fireworks/ember-1",
20808
21164
  name: "Ember-1",
@@ -20837,6 +21193,23 @@ export const MODELS = {
20837
21193
  contextWindow: 1000000,
20838
21194
  maxTokens: 65535,
20839
21195
  },
21196
+ "google/gemini-2.5-flash-batch": {
21197
+ id: "google/gemini-2.5-flash-batch",
21198
+ name: "Gemini 2.5 Flash (Batch)",
21199
+ api: "anthropic-messages",
21200
+ provider: "vercel-ai-gateway",
21201
+ baseUrl: "https://ai-gateway.vercel.sh",
21202
+ reasoning: true,
21203
+ input: ["text", "image"],
21204
+ cost: {
21205
+ input: 0.15,
21206
+ output: 1.25,
21207
+ cacheRead: 0.03,
21208
+ cacheWrite: 0,
21209
+ },
21210
+ contextWindow: 1000000,
21211
+ maxTokens: 64000,
21212
+ },
20840
21213
  "google/gemini-2.5-flash-lite": {
20841
21214
  id: "google/gemini-2.5-flash-lite",
20842
21215
  name: "Gemini 2.5 Flash Lite",
@@ -20854,6 +21227,23 @@ export const MODELS = {
20854
21227
  contextWindow: 1048576,
20855
21228
  maxTokens: 65535,
20856
21229
  },
21230
+ "google/gemini-2.5-flash-lite-batch": {
21231
+ id: "google/gemini-2.5-flash-lite-batch",
21232
+ name: "Gemini 2.5 Flash Lite (Batch)",
21233
+ api: "anthropic-messages",
21234
+ provider: "vercel-ai-gateway",
21235
+ baseUrl: "https://ai-gateway.vercel.sh",
21236
+ reasoning: true,
21237
+ input: ["text", "image"],
21238
+ cost: {
21239
+ input: 0.049999999999999996,
21240
+ output: 0.19999999999999998,
21241
+ cacheRead: 0.01,
21242
+ cacheWrite: 0,
21243
+ },
21244
+ contextWindow: 1048576,
21245
+ maxTokens: 65535,
21246
+ },
20857
21247
  "google/gemini-2.5-pro": {
20858
21248
  id: "google/gemini-2.5-pro",
20859
21249
  name: "Gemini 2.5 Pro",
@@ -20871,6 +21261,23 @@ export const MODELS = {
20871
21261
  contextWindow: 1048576,
20872
21262
  maxTokens: 65535,
20873
21263
  },
21264
+ "google/gemini-2.5-pro-batch": {
21265
+ id: "google/gemini-2.5-pro-batch",
21266
+ name: "Gemini 2.5 Pro (Batch)",
21267
+ api: "anthropic-messages",
21268
+ provider: "vercel-ai-gateway",
21269
+ baseUrl: "https://ai-gateway.vercel.sh",
21270
+ reasoning: true,
21271
+ input: ["text", "image"],
21272
+ cost: {
21273
+ input: 0.625,
21274
+ output: 5,
21275
+ cacheRead: 0.125,
21276
+ cacheWrite: 0,
21277
+ },
21278
+ contextWindow: 1048576,
21279
+ maxTokens: 65535,
21280
+ },
20874
21281
  "google/gemini-3-flash": {
20875
21282
  id: "google/gemini-3-flash",
20876
21283
  name: "Gemini 3 Flash",
@@ -20888,6 +21295,23 @@ export const MODELS = {
20888
21295
  contextWindow: 1000000,
20889
21296
  maxTokens: 65000,
20890
21297
  },
21298
+ "google/gemini-3-flash-batch": {
21299
+ id: "google/gemini-3-flash-batch",
21300
+ name: "Gemini 3 Flash (Batch)",
21301
+ api: "anthropic-messages",
21302
+ provider: "vercel-ai-gateway",
21303
+ baseUrl: "https://ai-gateway.vercel.sh",
21304
+ reasoning: true,
21305
+ input: ["text", "image"],
21306
+ cost: {
21307
+ input: 0.25,
21308
+ output: 1.5,
21309
+ cacheRead: 0.049999999999999996,
21310
+ cacheWrite: 0,
21311
+ },
21312
+ contextWindow: 1000000,
21313
+ maxTokens: 64000,
21314
+ },
20891
21315
  "google/gemini-3.1-flash-lite": {
20892
21316
  id: "google/gemini-3.1-flash-lite",
20893
21317
  name: "Gemini 3.1 Flash Lite",
@@ -20905,6 +21329,23 @@ export const MODELS = {
20905
21329
  contextWindow: 1000000,
20906
21330
  maxTokens: 65000,
20907
21331
  },
21332
+ "google/gemini-3.1-flash-lite-batch": {
21333
+ id: "google/gemini-3.1-flash-lite-batch",
21334
+ name: "Gemini 3.1 Flash Lite (Batch)",
21335
+ api: "anthropic-messages",
21336
+ provider: "vercel-ai-gateway",
21337
+ baseUrl: "https://ai-gateway.vercel.sh",
21338
+ reasoning: true,
21339
+ input: ["text", "image"],
21340
+ cost: {
21341
+ input: 0.125,
21342
+ output: 0.75,
21343
+ cacheRead: 0.015,
21344
+ cacheWrite: 0,
21345
+ },
21346
+ contextWindow: 1000000,
21347
+ maxTokens: 65000,
21348
+ },
20908
21349
  "google/gemini-3.1-pro-preview": {
20909
21350
  id: "google/gemini-3.1-pro-preview",
20910
21351
  name: "Gemini 3.1 Pro Preview",
@@ -20922,18 +21363,52 @@ export const MODELS = {
20922
21363
  contextWindow: 1000000,
20923
21364
  maxTokens: 64000,
20924
21365
  },
20925
- "google/gemini-3.5-flash": {
20926
- id: "google/gemini-3.5-flash",
20927
- name: "Gemini 3.5 Flash",
21366
+ "google/gemini-3.1-pro-preview-batch": {
21367
+ id: "google/gemini-3.1-pro-preview-batch",
21368
+ name: "Gemini 3.1 Pro Preview (Batch)",
21369
+ api: "anthropic-messages",
21370
+ provider: "vercel-ai-gateway",
21371
+ baseUrl: "https://ai-gateway.vercel.sh",
21372
+ reasoning: true,
21373
+ input: ["text", "image"],
21374
+ cost: {
21375
+ input: 1,
21376
+ output: 6,
21377
+ cacheRead: 0.19999999999999998,
21378
+ cacheWrite: 0,
21379
+ },
21380
+ contextWindow: 1000000,
21381
+ maxTokens: 64000,
21382
+ },
21383
+ "google/gemini-3.5-flash": {
21384
+ id: "google/gemini-3.5-flash",
21385
+ name: "Gemini 3.5 Flash",
21386
+ api: "anthropic-messages",
21387
+ provider: "vercel-ai-gateway",
21388
+ baseUrl: "https://ai-gateway.vercel.sh",
21389
+ reasoning: true,
21390
+ input: ["text", "image"],
21391
+ cost: {
21392
+ input: 1.5,
21393
+ output: 9,
21394
+ cacheRead: 0.15,
21395
+ cacheWrite: 0,
21396
+ },
21397
+ contextWindow: 1000000,
21398
+ maxTokens: 64000,
21399
+ },
21400
+ "google/gemini-3.5-flash-batch": {
21401
+ id: "google/gemini-3.5-flash-batch",
21402
+ name: "Gemini 3.5 Flash (Batch)",
20928
21403
  api: "anthropic-messages",
20929
21404
  provider: "vercel-ai-gateway",
20930
21405
  baseUrl: "https://ai-gateway.vercel.sh",
20931
21406
  reasoning: true,
20932
21407
  input: ["text", "image"],
20933
21408
  cost: {
20934
- input: 1.5,
20935
- output: 9,
20936
- cacheRead: 0.15,
21409
+ input: 0.75,
21410
+ output: 4.5,
21411
+ cacheRead: 0.075,
20937
21412
  cacheWrite: 0,
20938
21413
  },
20939
21414
  contextWindow: 1000000,
@@ -20956,6 +21431,23 @@ export const MODELS = {
20956
21431
  contextWindow: 1000000,
20957
21432
  maxTokens: 65000,
20958
21433
  },
21434
+ "google/gemini-3.5-flash-lite-batch": {
21435
+ id: "google/gemini-3.5-flash-lite-batch",
21436
+ name: "Gemini 3.5 Flash Lite (Batch)",
21437
+ api: "anthropic-messages",
21438
+ provider: "vercel-ai-gateway",
21439
+ baseUrl: "https://ai-gateway.vercel.sh",
21440
+ reasoning: true,
21441
+ input: ["text", "image"],
21442
+ cost: {
21443
+ input: 0.15,
21444
+ output: 1.25,
21445
+ cacheRead: 0.015,
21446
+ cacheWrite: 0,
21447
+ },
21448
+ contextWindow: 1000000,
21449
+ maxTokens: 65000,
21450
+ },
20959
21451
  "google/gemini-3.6-flash": {
20960
21452
  id: "google/gemini-3.6-flash",
20961
21453
  name: "Gemini 3.6 Flash",
@@ -20973,6 +21465,23 @@ export const MODELS = {
20973
21465
  contextWindow: 1000000,
20974
21466
  maxTokens: 64000,
20975
21467
  },
21468
+ "google/gemini-3.6-flash-batch": {
21469
+ id: "google/gemini-3.6-flash-batch",
21470
+ name: "Gemini 3.6 Flash (Batch)",
21471
+ api: "anthropic-messages",
21472
+ provider: "vercel-ai-gateway",
21473
+ baseUrl: "https://ai-gateway.vercel.sh",
21474
+ reasoning: true,
21475
+ input: ["text", "image"],
21476
+ cost: {
21477
+ input: 0.375,
21478
+ output: 1.875,
21479
+ cacheRead: 0.0375,
21480
+ cacheWrite: 0,
21481
+ },
21482
+ contextWindow: 1000000,
21483
+ maxTokens: 64000,
21484
+ },
20976
21485
  "google/gemini-3.7-flash": {
20977
21486
  id: "google/gemini-3.7-flash",
20978
21487
  name: "Gemini 3.7 Flash",
@@ -20990,6 +21499,23 @@ export const MODELS = {
20990
21499
  contextWindow: 1000000,
20991
21500
  maxTokens: 65535,
20992
21501
  },
21502
+ "google/gemini-3.7-flash-batch": {
21503
+ id: "google/gemini-3.7-flash-batch",
21504
+ name: "Gemini 3.7 Flash (Batch)",
21505
+ api: "anthropic-messages",
21506
+ provider: "vercel-ai-gateway",
21507
+ baseUrl: "https://ai-gateway.vercel.sh",
21508
+ reasoning: true,
21509
+ input: ["text", "image"],
21510
+ cost: {
21511
+ input: 0.375,
21512
+ output: 1.875,
21513
+ cacheRead: 0.0375,
21514
+ cacheWrite: 0,
21515
+ },
21516
+ contextWindow: 1000000,
21517
+ maxTokens: 65535,
21518
+ },
20993
21519
  "google/gemini-3.8-flash": {
20994
21520
  id: "google/gemini-3.8-flash",
20995
21521
  name: "Gemini 3.8 Flash",
@@ -21007,6 +21533,23 @@ export const MODELS = {
21007
21533
  contextWindow: 1000000,
21008
21534
  maxTokens: 65535,
21009
21535
  },
21536
+ "google/gemini-4-argon": {
21537
+ id: "google/gemini-4-argon",
21538
+ name: "Gemini 4 Argon",
21539
+ api: "anthropic-messages",
21540
+ provider: "vercel-ai-gateway",
21541
+ baseUrl: "https://ai-gateway.vercel.sh",
21542
+ reasoning: true,
21543
+ input: ["text", "image"],
21544
+ cost: {
21545
+ input: 2,
21546
+ output: 10,
21547
+ cacheRead: 0.09999999999999999,
21548
+ cacheWrite: 0,
21549
+ },
21550
+ contextWindow: 1000000,
21551
+ maxTokens: 1000000,
21552
+ },
21010
21553
  "google/gemma-4-26b-a4b-it": {
21011
21554
  id: "google/gemma-4-26b-a4b-it",
21012
21555
  name: "Google Gemma 4 26B A4B",
@@ -21169,26 +21712,9 @@ export const MODELS = {
21169
21712
  reasoning: true,
21170
21713
  input: ["text"],
21171
21714
  cost: {
21172
- input: 0,
21173
- output: 0,
21174
- cacheRead: 0,
21175
- cacheWrite: 0,
21176
- },
21177
- contextWindow: 262144,
21178
- maxTokens: 32768,
21179
- },
21180
- "inclusionai/ling-3.1-flash-free": {
21181
- id: "inclusionai/ling-3.1-flash-free",
21182
- name: "Ling 3.1 Flash (Free)",
21183
- api: "anthropic-messages",
21184
- provider: "vercel-ai-gateway",
21185
- baseUrl: "https://ai-gateway.vercel.sh",
21186
- reasoning: true,
21187
- input: ["text"],
21188
- cost: {
21189
- input: 0,
21190
- output: 0,
21191
- cacheRead: 0,
21715
+ input: 0.3,
21716
+ output: 0.8999999999999999,
21717
+ cacheRead: 0.06,
21192
21718
  cacheWrite: 0,
21193
21719
  },
21194
21720
  contextWindow: 262144,
@@ -21211,6 +21737,23 @@ export const MODELS = {
21211
21737
  contextWindow: 1000000,
21212
21738
  maxTokens: 32000,
21213
21739
  },
21740
+ "liquid/lfm2.5-24b-a2b": {
21741
+ id: "liquid/lfm2.5-24b-a2b",
21742
+ name: "LFM2.5-24B-A2B",
21743
+ api: "anthropic-messages",
21744
+ provider: "vercel-ai-gateway",
21745
+ baseUrl: "https://ai-gateway.vercel.sh",
21746
+ reasoning: true,
21747
+ input: ["text"],
21748
+ cost: {
21749
+ input: 0.09999999999999999,
21750
+ output: 1,
21751
+ cacheRead: 0.049999999999999996,
21752
+ cacheWrite: 0,
21753
+ },
21754
+ contextWindow: 128000,
21755
+ maxTokens: 8200,
21756
+ },
21214
21757
  "meituan/longcat-2.5-preview": {
21215
21758
  id: "meituan/longcat-2.5-preview",
21216
21759
  name: "LongCat 2.5 Preview",
@@ -21415,6 +21958,23 @@ export const MODELS = {
21415
21958
  contextWindow: 1048576,
21416
21959
  maxTokens: 1048576,
21417
21960
  },
21961
+ "meta/muse-wonder-1.0": {
21962
+ id: "meta/muse-wonder-1.0",
21963
+ name: "Muse Wonder",
21964
+ api: "anthropic-messages",
21965
+ provider: "vercel-ai-gateway",
21966
+ baseUrl: "https://ai-gateway.vercel.sh",
21967
+ reasoning: true,
21968
+ input: ["text", "image"],
21969
+ cost: {
21970
+ input: 4,
21971
+ output: 20,
21972
+ cacheRead: 0.19999999999999998,
21973
+ cacheWrite: 0,
21974
+ },
21975
+ contextWindow: 1048576,
21976
+ maxTokens: 1048576,
21977
+ },
21418
21978
  "minimax/minimax-m2": {
21419
21979
  id: "minimax/minimax-m2",
21420
21980
  name: "MiniMax M2",
@@ -21908,6 +22468,23 @@ export const MODELS = {
21908
22468
  contextWindow: 262144,
21909
22469
  maxTokens: 131072,
21910
22470
  },
22471
+ "nvidia/nemotron-3.5-lightning-free": {
22472
+ id: "nvidia/nemotron-3.5-lightning-free",
22473
+ name: "Nemotron 3.5 Lightning Free",
22474
+ api: "anthropic-messages",
22475
+ provider: "vercel-ai-gateway",
22476
+ baseUrl: "https://ai-gateway.vercel.sh",
22477
+ reasoning: true,
22478
+ input: ["text"],
22479
+ cost: {
22480
+ input: 0,
22481
+ output: 0,
22482
+ cacheRead: 0,
22483
+ cacheWrite: 0,
22484
+ },
22485
+ contextWindow: 1000000,
22486
+ maxTokens: 65000,
22487
+ },
21911
22488
  "nvidia/nemotron-nano-12b-v2-vl": {
21912
22489
  id: "nvidia/nemotron-nano-12b-v2-vl",
21913
22490
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -21976,6 +22553,23 @@ export const MODELS = {
21976
22553
  contextWindow: 1047576,
21977
22554
  maxTokens: 32768,
21978
22555
  },
22556
+ "openai/gpt-4.1-batch": {
22557
+ id: "openai/gpt-4.1-batch",
22558
+ name: "GPT-4.1 (Batch)",
22559
+ api: "anthropic-messages",
22560
+ provider: "vercel-ai-gateway",
22561
+ baseUrl: "https://ai-gateway.vercel.sh",
22562
+ reasoning: false,
22563
+ input: ["text", "image"],
22564
+ cost: {
22565
+ input: 1,
22566
+ output: 4,
22567
+ cacheRead: 0.25,
22568
+ cacheWrite: 0,
22569
+ },
22570
+ contextWindow: 1047576,
22571
+ maxTokens: 32768,
22572
+ },
21979
22573
  "openai/gpt-4.1-fast": {
21980
22574
  id: "openai/gpt-4.1-fast",
21981
22575
  name: "GPT-4.1 (Fast)",
@@ -22010,6 +22604,23 @@ export const MODELS = {
22010
22604
  contextWindow: 1047576,
22011
22605
  maxTokens: 32768,
22012
22606
  },
22607
+ "openai/gpt-4.1-mini-batch": {
22608
+ id: "openai/gpt-4.1-mini-batch",
22609
+ name: "GPT-4.1 mini (Batch)",
22610
+ api: "anthropic-messages",
22611
+ provider: "vercel-ai-gateway",
22612
+ baseUrl: "https://ai-gateway.vercel.sh",
22613
+ reasoning: false,
22614
+ input: ["text", "image"],
22615
+ cost: {
22616
+ input: 0.19999999999999998,
22617
+ output: 0.7999999999999999,
22618
+ cacheRead: 0.049999999999999996,
22619
+ cacheWrite: 0,
22620
+ },
22621
+ contextWindow: 1047576,
22622
+ maxTokens: 32768,
22623
+ },
22013
22624
  "openai/gpt-4.1-mini-fast": {
22014
22625
  id: "openai/gpt-4.1-mini-fast",
22015
22626
  name: "GPT-4.1 mini (Fast)",
@@ -22044,6 +22655,23 @@ export const MODELS = {
22044
22655
  contextWindow: 1047576,
22045
22656
  maxTokens: 32768,
22046
22657
  },
22658
+ "openai/gpt-4.1-nano-batch": {
22659
+ id: "openai/gpt-4.1-nano-batch",
22660
+ name: "GPT-4.1 nano (Batch)",
22661
+ api: "anthropic-messages",
22662
+ provider: "vercel-ai-gateway",
22663
+ baseUrl: "https://ai-gateway.vercel.sh",
22664
+ reasoning: false,
22665
+ input: ["text", "image"],
22666
+ cost: {
22667
+ input: 0.049999999999999996,
22668
+ output: 0.19999999999999998,
22669
+ cacheRead: 0.012499999999999999,
22670
+ cacheWrite: 0,
22671
+ },
22672
+ contextWindow: 1047576,
22673
+ maxTokens: 32768,
22674
+ },
22047
22675
  "openai/gpt-4.1-nano-fast": {
22048
22676
  id: "openai/gpt-4.1-nano-fast",
22049
22677
  name: "GPT-4.1 nano (Fast)",
@@ -22078,6 +22706,23 @@ export const MODELS = {
22078
22706
  contextWindow: 128000,
22079
22707
  maxTokens: 16384,
22080
22708
  },
22709
+ "openai/gpt-4o-batch": {
22710
+ id: "openai/gpt-4o-batch",
22711
+ name: "GPT-4o (Batch)",
22712
+ api: "anthropic-messages",
22713
+ provider: "vercel-ai-gateway",
22714
+ baseUrl: "https://ai-gateway.vercel.sh",
22715
+ reasoning: false,
22716
+ input: ["text", "image"],
22717
+ cost: {
22718
+ input: 1.25,
22719
+ output: 5,
22720
+ cacheRead: 0.625,
22721
+ cacheWrite: 0,
22722
+ },
22723
+ contextWindow: 128000,
22724
+ maxTokens: 16384,
22725
+ },
22081
22726
  "openai/gpt-4o-fast": {
22082
22727
  id: "openai/gpt-4o-fast",
22083
22728
  name: "GPT-4o (Fast)",
@@ -22112,6 +22757,23 @@ export const MODELS = {
22112
22757
  contextWindow: 128000,
22113
22758
  maxTokens: 16384,
22114
22759
  },
22760
+ "openai/gpt-4o-mini-batch": {
22761
+ id: "openai/gpt-4o-mini-batch",
22762
+ name: "GPT-4o mini (Batch)",
22763
+ api: "anthropic-messages",
22764
+ provider: "vercel-ai-gateway",
22765
+ baseUrl: "https://ai-gateway.vercel.sh",
22766
+ reasoning: false,
22767
+ input: ["text", "image"],
22768
+ cost: {
22769
+ input: 0.075,
22770
+ output: 0.3,
22771
+ cacheRead: 0.0375,
22772
+ cacheWrite: 0,
22773
+ },
22774
+ contextWindow: 128000,
22775
+ maxTokens: 16384,
22776
+ },
22115
22777
  "openai/gpt-4o-mini-fast": {
22116
22778
  id: "openai/gpt-4o-mini-fast",
22117
22779
  name: "GPT-4o mini (Fast)",
@@ -22146,6 +22808,23 @@ export const MODELS = {
22146
22808
  contextWindow: 400000,
22147
22809
  maxTokens: 128000,
22148
22810
  },
22811
+ "openai/gpt-5-batch": {
22812
+ id: "openai/gpt-5-batch",
22813
+ name: "GPT-5 (Batch)",
22814
+ api: "anthropic-messages",
22815
+ provider: "vercel-ai-gateway",
22816
+ baseUrl: "https://ai-gateway.vercel.sh",
22817
+ reasoning: true,
22818
+ input: ["text", "image"],
22819
+ cost: {
22820
+ input: 0.625,
22821
+ output: 5,
22822
+ cacheRead: 0.0625,
22823
+ cacheWrite: 0,
22824
+ },
22825
+ contextWindow: 400000,
22826
+ maxTokens: 128000,
22827
+ },
22149
22828
  "openai/gpt-5-codex": {
22150
22829
  id: "openai/gpt-5-codex",
22151
22830
  name: "GPT-5-Codex",
@@ -22197,6 +22876,23 @@ export const MODELS = {
22197
22876
  contextWindow: 400000,
22198
22877
  maxTokens: 128000,
22199
22878
  },
22879
+ "openai/gpt-5-mini-batch": {
22880
+ id: "openai/gpt-5-mini-batch",
22881
+ name: "GPT-5 mini (Batch)",
22882
+ api: "anthropic-messages",
22883
+ provider: "vercel-ai-gateway",
22884
+ baseUrl: "https://ai-gateway.vercel.sh",
22885
+ reasoning: true,
22886
+ input: ["text", "image"],
22887
+ cost: {
22888
+ input: 0.125,
22889
+ output: 1,
22890
+ cacheRead: 0.012499999999999999,
22891
+ cacheWrite: 0,
22892
+ },
22893
+ contextWindow: 400000,
22894
+ maxTokens: 128000,
22895
+ },
22200
22896
  "openai/gpt-5-mini-fast": {
22201
22897
  id: "openai/gpt-5-mini-fast",
22202
22898
  name: "GPT-5 mini (Fast)",
@@ -22229,19 +22925,53 @@ export const MODELS = {
22229
22925
  cacheWrite: 0,
22230
22926
  },
22231
22927
  contextWindow: 400000,
22232
- maxTokens: 128000,
22928
+ maxTokens: 128000,
22929
+ },
22930
+ "openai/gpt-5-nano-batch": {
22931
+ id: "openai/gpt-5-nano-batch",
22932
+ name: "GPT-5 nano (Batch)",
22933
+ api: "anthropic-messages",
22934
+ provider: "vercel-ai-gateway",
22935
+ baseUrl: "https://ai-gateway.vercel.sh",
22936
+ reasoning: true,
22937
+ input: ["text", "image"],
22938
+ cost: {
22939
+ input: 0.024999999999999998,
22940
+ output: 0.19999999999999998,
22941
+ cacheRead: 0.0025,
22942
+ cacheWrite: 0,
22943
+ },
22944
+ contextWindow: 400000,
22945
+ maxTokens: 128000,
22946
+ },
22947
+ "openai/gpt-5-pro": {
22948
+ id: "openai/gpt-5-pro",
22949
+ name: "GPT-5 pro",
22950
+ api: "anthropic-messages",
22951
+ provider: "vercel-ai-gateway",
22952
+ baseUrl: "https://ai-gateway.vercel.sh",
22953
+ reasoning: true,
22954
+ input: ["text", "image"],
22955
+ cost: {
22956
+ input: 15,
22957
+ output: 120,
22958
+ cacheRead: 0,
22959
+ cacheWrite: 0,
22960
+ },
22961
+ contextWindow: 400000,
22962
+ maxTokens: 272000,
22233
22963
  },
22234
- "openai/gpt-5-pro": {
22235
- id: "openai/gpt-5-pro",
22236
- name: "GPT-5 pro",
22964
+ "openai/gpt-5-pro-batch": {
22965
+ id: "openai/gpt-5-pro-batch",
22966
+ name: "GPT-5 pro (Batch)",
22237
22967
  api: "anthropic-messages",
22238
22968
  provider: "vercel-ai-gateway",
22239
22969
  baseUrl: "https://ai-gateway.vercel.sh",
22240
22970
  reasoning: true,
22241
22971
  input: ["text", "image"],
22242
22972
  cost: {
22243
- input: 15,
22244
- output: 120,
22973
+ input: 7.5,
22974
+ output: 60,
22245
22975
  cacheRead: 0,
22246
22976
  cacheWrite: 0,
22247
22977
  },
@@ -22351,6 +23081,24 @@ export const MODELS = {
22351
23081
  contextWindow: 400000,
22352
23082
  maxTokens: 128000,
22353
23083
  },
23084
+ "openai/gpt-5.2-batch": {
23085
+ id: "openai/gpt-5.2-batch",
23086
+ name: "GPT 5.2 (Batch)",
23087
+ api: "anthropic-messages",
23088
+ provider: "vercel-ai-gateway",
23089
+ baseUrl: "https://ai-gateway.vercel.sh",
23090
+ reasoning: true,
23091
+ thinkingLevelMap: { "xhigh": "xhigh" },
23092
+ input: ["text", "image"],
23093
+ cost: {
23094
+ input: 0.875,
23095
+ output: 7,
23096
+ cacheRead: 0.0875,
23097
+ cacheWrite: 0,
23098
+ },
23099
+ contextWindow: 400000,
23100
+ maxTokens: 128000,
23101
+ },
22354
23102
  "openai/gpt-5.2-codex": {
22355
23103
  id: "openai/gpt-5.2-codex",
22356
23104
  name: "GPT 5.2 Codex",
@@ -22459,6 +23207,24 @@ export const MODELS = {
22459
23207
  contextWindow: 1050000,
22460
23208
  maxTokens: 128000,
22461
23209
  },
23210
+ "openai/gpt-5.4-batch": {
23211
+ id: "openai/gpt-5.4-batch",
23212
+ name: "GPT 5.4 (Batch)",
23213
+ api: "anthropic-messages",
23214
+ provider: "vercel-ai-gateway",
23215
+ baseUrl: "https://ai-gateway.vercel.sh",
23216
+ reasoning: true,
23217
+ thinkingLevelMap: { "xhigh": "xhigh" },
23218
+ input: ["text", "image"],
23219
+ cost: {
23220
+ input: 1.25,
23221
+ output: 7.5,
23222
+ cacheRead: 0.125,
23223
+ cacheWrite: 0,
23224
+ },
23225
+ contextWindow: 1050000,
23226
+ maxTokens: 128000,
23227
+ },
22462
23228
  "openai/gpt-5.4-fast": {
22463
23229
  id: "openai/gpt-5.4-fast",
22464
23230
  name: "GPT 5.4 (Fast)",
@@ -22495,6 +23261,24 @@ export const MODELS = {
22495
23261
  contextWindow: 400000,
22496
23262
  maxTokens: 128000,
22497
23263
  },
23264
+ "openai/gpt-5.4-mini-batch": {
23265
+ id: "openai/gpt-5.4-mini-batch",
23266
+ name: "GPT 5.4 Mini (Batch)",
23267
+ api: "anthropic-messages",
23268
+ provider: "vercel-ai-gateway",
23269
+ baseUrl: "https://ai-gateway.vercel.sh",
23270
+ reasoning: true,
23271
+ thinkingLevelMap: { "xhigh": "xhigh" },
23272
+ input: ["text", "image"],
23273
+ cost: {
23274
+ input: 0.375,
23275
+ output: 2.25,
23276
+ cacheRead: 0.0375,
23277
+ cacheWrite: 0,
23278
+ },
23279
+ contextWindow: 400000,
23280
+ maxTokens: 128000,
23281
+ },
22498
23282
  "openai/gpt-5.4-mini-fast": {
22499
23283
  id: "openai/gpt-5.4-mini-fast",
22500
23284
  name: "GPT 5.4 Mini (Fast)",
@@ -22531,6 +23315,24 @@ export const MODELS = {
22531
23315
  contextWindow: 400000,
22532
23316
  maxTokens: 128000,
22533
23317
  },
23318
+ "openai/gpt-5.4-nano-batch": {
23319
+ id: "openai/gpt-5.4-nano-batch",
23320
+ name: "GPT 5.4 Nano (Batch)",
23321
+ api: "anthropic-messages",
23322
+ provider: "vercel-ai-gateway",
23323
+ baseUrl: "https://ai-gateway.vercel.sh",
23324
+ reasoning: true,
23325
+ thinkingLevelMap: { "xhigh": "xhigh" },
23326
+ input: ["text", "image"],
23327
+ cost: {
23328
+ input: 0.09999999999999999,
23329
+ output: 0.625,
23330
+ cacheRead: 0.01,
23331
+ cacheWrite: 0,
23332
+ },
23333
+ contextWindow: 400000,
23334
+ maxTokens: 128000,
23335
+ },
22534
23336
  "openai/gpt-5.4-pro": {
22535
23337
  id: "openai/gpt-5.4-pro",
22536
23338
  name: "GPT 5.4 Pro",
@@ -22567,6 +23369,24 @@ export const MODELS = {
22567
23369
  contextWindow: 1000000,
22568
23370
  maxTokens: 128000,
22569
23371
  },
23372
+ "openai/gpt-5.5-batch": {
23373
+ id: "openai/gpt-5.5-batch",
23374
+ name: "GPT 5.5 (Batch)",
23375
+ api: "anthropic-messages",
23376
+ provider: "vercel-ai-gateway",
23377
+ baseUrl: "https://ai-gateway.vercel.sh",
23378
+ reasoning: true,
23379
+ thinkingLevelMap: { "xhigh": "xhigh" },
23380
+ input: ["text", "image"],
23381
+ cost: {
23382
+ input: 2.5,
23383
+ output: 15,
23384
+ cacheRead: 0.25,
23385
+ cacheWrite: 0,
23386
+ },
23387
+ contextWindow: 1000000,
23388
+ maxTokens: 128000,
23389
+ },
22570
23390
  "openai/gpt-5.5-fast": {
22571
23391
  id: "openai/gpt-5.5-fast",
22572
23392
  name: "GPT 5.5 (Fast)",
@@ -22603,6 +23423,24 @@ export const MODELS = {
22603
23423
  contextWindow: 1000000,
22604
23424
  maxTokens: 128000,
22605
23425
  },
23426
+ "openai/gpt-5.5-pro-batch": {
23427
+ id: "openai/gpt-5.5-pro-batch",
23428
+ name: "GPT 5.5 Pro (Batch)",
23429
+ api: "anthropic-messages",
23430
+ provider: "vercel-ai-gateway",
23431
+ baseUrl: "https://ai-gateway.vercel.sh",
23432
+ reasoning: true,
23433
+ thinkingLevelMap: { "xhigh": "xhigh" },
23434
+ input: ["text", "image"],
23435
+ cost: {
23436
+ input: 15,
23437
+ output: 90,
23438
+ cacheRead: 0,
23439
+ cacheWrite: 0,
23440
+ },
23441
+ contextWindow: 1000000,
23442
+ maxTokens: 128000,
23443
+ },
22606
23444
  "openai/gpt-5.6-luna": {
22607
23445
  id: "openai/gpt-5.6-luna",
22608
23446
  name: "GPT 5.6 Luna",
@@ -22620,6 +23458,23 @@ export const MODELS = {
22620
23458
  contextWindow: 1050000,
22621
23459
  maxTokens: 128000,
22622
23460
  },
23461
+ "openai/gpt-5.6-luna-batch": {
23462
+ id: "openai/gpt-5.6-luna-batch",
23463
+ name: "GPT 5.6 Luna (Batch)",
23464
+ api: "anthropic-messages",
23465
+ provider: "vercel-ai-gateway",
23466
+ baseUrl: "https://ai-gateway.vercel.sh",
23467
+ reasoning: true,
23468
+ input: ["text", "image"],
23469
+ cost: {
23470
+ input: 0.09999999999999999,
23471
+ output: 0.6,
23472
+ cacheRead: 0.01,
23473
+ cacheWrite: 0.125,
23474
+ },
23475
+ contextWindow: 1050000,
23476
+ maxTokens: 128000,
23477
+ },
22623
23478
  "openai/gpt-5.6-luna-fast": {
22624
23479
  id: "openai/gpt-5.6-luna-fast",
22625
23480
  name: "GPT 5.6 Luna (Fast)",
@@ -22654,6 +23509,23 @@ export const MODELS = {
22654
23509
  contextWindow: 1050000,
22655
23510
  maxTokens: 128000,
22656
23511
  },
23512
+ "openai/gpt-5.6-sol-batch": {
23513
+ id: "openai/gpt-5.6-sol-batch",
23514
+ name: "GPT 5.6 Sol (Batch)",
23515
+ api: "anthropic-messages",
23516
+ provider: "vercel-ai-gateway",
23517
+ baseUrl: "https://ai-gateway.vercel.sh",
23518
+ reasoning: true,
23519
+ input: ["text", "image"],
23520
+ cost: {
23521
+ input: 2,
23522
+ output: 10,
23523
+ cacheRead: 0.19999999999999998,
23524
+ cacheWrite: 2.5,
23525
+ },
23526
+ contextWindow: 1050000,
23527
+ maxTokens: 128000,
23528
+ },
22657
23529
  "openai/gpt-5.6-sol-fast": {
22658
23530
  id: "openai/gpt-5.6-sol-fast",
22659
23531
  name: "GPT 5.6 Sol (Fast)",
@@ -22688,6 +23560,23 @@ export const MODELS = {
22688
23560
  contextWindow: 1050000,
22689
23561
  maxTokens: 128000,
22690
23562
  },
23563
+ "openai/gpt-5.6-terra-batch": {
23564
+ id: "openai/gpt-5.6-terra-batch",
23565
+ name: "GPT 5.6 Terra (Batch)",
23566
+ api: "anthropic-messages",
23567
+ provider: "vercel-ai-gateway",
23568
+ baseUrl: "https://ai-gateway.vercel.sh",
23569
+ reasoning: true,
23570
+ input: ["text", "image"],
23571
+ cost: {
23572
+ input: 1,
23573
+ output: 6,
23574
+ cacheRead: 0.09999999999999999,
23575
+ cacheWrite: 1.25,
23576
+ },
23577
+ contextWindow: 1050000,
23578
+ maxTokens: 128000,
23579
+ },
22691
23580
  "openai/gpt-5.6-terra-fast": {
22692
23581
  id: "openai/gpt-5.6-terra-fast",
22693
23582
  name: "GPT 5.6 Terra (Fast)",
@@ -22722,6 +23611,23 @@ export const MODELS = {
22722
23611
  contextWindow: 1050000,
22723
23612
  maxTokens: 128000,
22724
23613
  },
23614
+ "openai/gpt-6-astra-batch": {
23615
+ id: "openai/gpt-6-astra-batch",
23616
+ name: "GPT-6 Astra (Batch)",
23617
+ api: "anthropic-messages",
23618
+ provider: "vercel-ai-gateway",
23619
+ baseUrl: "https://ai-gateway.vercel.sh",
23620
+ reasoning: true,
23621
+ input: ["text", "image"],
23622
+ cost: {
23623
+ input: 5,
23624
+ output: 25,
23625
+ cacheRead: 0.5,
23626
+ cacheWrite: 6.25,
23627
+ },
23628
+ contextWindow: 1050000,
23629
+ maxTokens: 128000,
23630
+ },
22725
23631
  "openai/gpt-6-astra-fast": {
22726
23632
  id: "openai/gpt-6-astra-fast",
22727
23633
  name: "GPT-6 Astra (Fast)",
@@ -22756,6 +23662,23 @@ export const MODELS = {
22756
23662
  contextWindow: 1050000,
22757
23663
  maxTokens: 128000,
22758
23664
  },
23665
+ "openai/gpt-6-luna-batch": {
23666
+ id: "openai/gpt-6-luna-batch",
23667
+ name: "GPT-6 Luna (Batch)",
23668
+ api: "anthropic-messages",
23669
+ provider: "vercel-ai-gateway",
23670
+ baseUrl: "https://ai-gateway.vercel.sh",
23671
+ reasoning: true,
23672
+ input: ["text", "image"],
23673
+ cost: {
23674
+ input: 0.049999999999999996,
23675
+ output: 0.25,
23676
+ cacheRead: 0.005,
23677
+ cacheWrite: 0.0625,
23678
+ },
23679
+ contextWindow: 1050000,
23680
+ maxTokens: 128000,
23681
+ },
22759
23682
  "openai/gpt-6-luna-fast": {
22760
23683
  id: "openai/gpt-6-luna-fast",
22761
23684
  name: "GPT-6 Luna (Fast)",
@@ -22790,6 +23713,23 @@ export const MODELS = {
22790
23713
  contextWindow: 1050000,
22791
23714
  maxTokens: 128000,
22792
23715
  },
23716
+ "openai/gpt-6-sol-batch": {
23717
+ id: "openai/gpt-6-sol-batch",
23718
+ name: "GPT-6 Sol (Batch)",
23719
+ api: "anthropic-messages",
23720
+ provider: "vercel-ai-gateway",
23721
+ baseUrl: "https://ai-gateway.vercel.sh",
23722
+ reasoning: true,
23723
+ input: ["text", "image"],
23724
+ cost: {
23725
+ input: 1,
23726
+ output: 5,
23727
+ cacheRead: 0.09999999999999999,
23728
+ cacheWrite: 1.25,
23729
+ },
23730
+ contextWindow: 1050000,
23731
+ maxTokens: 128000,
23732
+ },
22793
23733
  "openai/gpt-6-sol-fast": {
22794
23734
  id: "openai/gpt-6-sol-fast",
22795
23735
  name: "GPT-6 Sol (Fast)",
@@ -22824,6 +23764,23 @@ export const MODELS = {
22824
23764
  contextWindow: 1050000,
22825
23765
  maxTokens: 128000,
22826
23766
  },
23767
+ "openai/gpt-6.1-sol-batch": {
23768
+ id: "openai/gpt-6.1-sol-batch",
23769
+ name: "GPT-6.1 Sol (Batch)",
23770
+ api: "anthropic-messages",
23771
+ provider: "vercel-ai-gateway",
23772
+ baseUrl: "https://ai-gateway.vercel.sh",
23773
+ reasoning: true,
23774
+ input: ["text", "image"],
23775
+ cost: {
23776
+ input: 1,
23777
+ output: 5,
23778
+ cacheRead: 0.049999999999999996,
23779
+ cacheWrite: 1.25,
23780
+ },
23781
+ contextWindow: 1050000,
23782
+ maxTokens: 128000,
23783
+ },
22827
23784
  "openai/gpt-6.1-sol-fast": {
22828
23785
  id: "openai/gpt-6.1-sol-fast",
22829
23786
  name: "GPT-6.1 Sol (Fast)",
@@ -23215,6 +24172,23 @@ export const MODELS = {
23215
24172
  contextWindow: 2000000,
23216
24173
  maxTokens: 2000000,
23217
24174
  },
24175
+ "spacexai/grok-4.20-multi-agent-batch": {
24176
+ id: "spacexai/grok-4.20-multi-agent-batch",
24177
+ name: "Grok 4.20 Multi-Agent (Batch)",
24178
+ api: "anthropic-messages",
24179
+ provider: "vercel-ai-gateway",
24180
+ baseUrl: "https://ai-gateway.vercel.sh",
24181
+ reasoning: true,
24182
+ input: ["text", "image"],
24183
+ cost: {
24184
+ input: 1,
24185
+ output: 2,
24186
+ cacheRead: 0.16,
24187
+ cacheWrite: 0,
24188
+ },
24189
+ contextWindow: 2000000,
24190
+ maxTokens: 2000000,
24191
+ },
23218
24192
  "spacexai/grok-4.20-multi-agent-beta": {
23219
24193
  id: "spacexai/grok-4.20-multi-agent-beta",
23220
24194
  name: "Grok 4.20 Multi Agent Beta",
@@ -23249,6 +24223,23 @@ export const MODELS = {
23249
24223
  contextWindow: 2000000,
23250
24224
  maxTokens: 2000000,
23251
24225
  },
24226
+ "spacexai/grok-4.20-non-reasoning-batch": {
24227
+ id: "spacexai/grok-4.20-non-reasoning-batch",
24228
+ name: "Grok 4.20 Non-Reasoning (Batch)",
24229
+ api: "anthropic-messages",
24230
+ provider: "vercel-ai-gateway",
24231
+ baseUrl: "https://ai-gateway.vercel.sh",
24232
+ reasoning: false,
24233
+ input: ["text", "image"],
24234
+ cost: {
24235
+ input: 1,
24236
+ output: 2,
24237
+ cacheRead: 0.16,
24238
+ cacheWrite: 0,
24239
+ },
24240
+ contextWindow: 2000000,
24241
+ maxTokens: 2000000,
24242
+ },
23252
24243
  "spacexai/grok-4.20-non-reasoning-beta": {
23253
24244
  id: "spacexai/grok-4.20-non-reasoning-beta",
23254
24245
  name: "Grok 4.20 Beta Non-Reasoning",
@@ -23283,6 +24274,23 @@ export const MODELS = {
23283
24274
  contextWindow: 2000000,
23284
24275
  maxTokens: 2000000,
23285
24276
  },
24277
+ "spacexai/grok-4.20-reasoning-batch": {
24278
+ id: "spacexai/grok-4.20-reasoning-batch",
24279
+ name: "Grok 4.20 Reasoning (Batch)",
24280
+ api: "anthropic-messages",
24281
+ provider: "vercel-ai-gateway",
24282
+ baseUrl: "https://ai-gateway.vercel.sh",
24283
+ reasoning: true,
24284
+ input: ["text", "image"],
24285
+ cost: {
24286
+ input: 1,
24287
+ output: 2,
24288
+ cacheRead: 0.16,
24289
+ cacheWrite: 0,
24290
+ },
24291
+ contextWindow: 2000000,
24292
+ maxTokens: 2000000,
24293
+ },
23286
24294
  "spacexai/grok-4.20-reasoning-beta": {
23287
24295
  id: "spacexai/grok-4.20-reasoning-beta",
23288
24296
  name: "Grok 4.20 Beta Reasoning",
@@ -23317,6 +24325,23 @@ export const MODELS = {
23317
24325
  contextWindow: 1000000,
23318
24326
  maxTokens: 1000000,
23319
24327
  },
24328
+ "spacexai/grok-4.3-batch": {
24329
+ id: "spacexai/grok-4.3-batch",
24330
+ name: "Grok 4.3 (Batch)",
24331
+ api: "anthropic-messages",
24332
+ provider: "vercel-ai-gateway",
24333
+ baseUrl: "https://ai-gateway.vercel.sh",
24334
+ reasoning: true,
24335
+ input: ["text", "image"],
24336
+ cost: {
24337
+ input: 1,
24338
+ output: 2,
24339
+ cacheRead: 0.16,
24340
+ cacheWrite: 0,
24341
+ },
24342
+ contextWindow: 1000000,
24343
+ maxTokens: 1000000,
24344
+ },
23320
24345
  "spacexai/grok-4.5": {
23321
24346
  id: "spacexai/grok-4.5",
23322
24347
  name: "Grok 4.5",