@elyracode/ai 0.9.47 → 0.9.49

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.
@@ -126,6 +126,24 @@ export const MODELS = {
126
126
  contextWindow: 200000,
127
127
  maxTokens: 64000,
128
128
  },
129
+ "anthropic.claude-haiku-5-5": {
130
+ id: "anthropic.claude-haiku-5-5",
131
+ name: "Claude Haiku 5.5",
132
+ api: "bedrock-converse-stream",
133
+ provider: "amazon-bedrock",
134
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
135
+ reasoning: true,
136
+ thinkingType: "adaptive",
137
+ input: ["text", "image"],
138
+ cost: {
139
+ input: 0.1,
140
+ output: 0.5,
141
+ cacheRead: 0.01,
142
+ cacheWrite: 0.125,
143
+ },
144
+ contextWindow: 1000000,
145
+ maxTokens: 128000,
146
+ },
129
147
  "anthropic.claude-opus-4-1-20250805-v1:0": {
130
148
  id: "anthropic.claude-opus-4-1-20250805-v1:0",
131
149
  name: "Claude Opus 4.1",
@@ -321,7 +339,7 @@ export const MODELS = {
321
339
  cost: {
322
340
  input: 2,
323
341
  output: 10,
324
- cacheRead: 0.2,
342
+ cacheRead: 0.1,
325
343
  cacheWrite: 2.5,
326
344
  },
327
345
  contextWindow: 1000000,
@@ -414,6 +432,24 @@ export const MODELS = {
414
432
  contextWindow: 200000,
415
433
  maxTokens: 64000,
416
434
  },
435
+ "au.anthropic.claude-haiku-5-5": {
436
+ id: "au.anthropic.claude-haiku-5-5",
437
+ name: "Claude Haiku 5.5 (AU)",
438
+ api: "bedrock-converse-stream",
439
+ provider: "amazon-bedrock",
440
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
441
+ reasoning: true,
442
+ thinkingType: "adaptive",
443
+ input: ["text", "image"],
444
+ cost: {
445
+ input: 0.11,
446
+ output: 0.55,
447
+ cacheRead: 0.011,
448
+ cacheWrite: 0.1375,
449
+ },
450
+ contextWindow: 1000000,
451
+ maxTokens: 128000,
452
+ },
417
453
  "au.anthropic.claude-opus-4-6-v1": {
418
454
  id: "au.anthropic.claude-opus-4-6-v1",
419
455
  name: "AU Anthropic Claude Opus 4.6",
@@ -717,6 +753,24 @@ export const MODELS = {
717
753
  contextWindow: 200000,
718
754
  maxTokens: 64000,
719
755
  },
756
+ "eu.anthropic.claude-haiku-5-5": {
757
+ id: "eu.anthropic.claude-haiku-5-5",
758
+ name: "Claude Haiku 5.5 (EU)",
759
+ api: "bedrock-converse-stream",
760
+ provider: "amazon-bedrock",
761
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
762
+ reasoning: true,
763
+ thinkingType: "adaptive",
764
+ input: ["text", "image"],
765
+ cost: {
766
+ input: 0.11,
767
+ output: 0.55,
768
+ cacheRead: 0.011,
769
+ cacheWrite: 0.1375,
770
+ },
771
+ contextWindow: 1000000,
772
+ maxTokens: 128000,
773
+ },
720
774
  "eu.anthropic.claude-opus-4-5-20251101-v1:0": {
721
775
  id: "eu.anthropic.claude-opus-4-5-20251101-v1:0",
722
776
  name: "Claude Opus 4.5 (EU)",
@@ -900,6 +954,24 @@ export const MODELS = {
900
954
  contextWindow: 1000000,
901
955
  maxTokens: 128000,
902
956
  },
957
+ "eu.anthropic.claude-sonnet-5-5": {
958
+ id: "eu.anthropic.claude-sonnet-5-5",
959
+ name: "Claude Sonnet 5.5 (EU)",
960
+ api: "bedrock-converse-stream",
961
+ provider: "amazon-bedrock",
962
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
963
+ reasoning: true,
964
+ thinkingType: "adaptive",
965
+ input: ["text", "image"],
966
+ cost: {
967
+ input: 2.2,
968
+ output: 11,
969
+ cacheRead: 0.11,
970
+ cacheWrite: 2.75,
971
+ },
972
+ contextWindow: 1000000,
973
+ maxTokens: 128000,
974
+ },
903
975
  "eu.mistral.pixtral-large-2502-v1:0": {
904
976
  id: "eu.mistral.pixtral-large-2502-v1:0",
905
977
  name: "Pixtral Large (25.02) (EU)",
@@ -990,6 +1062,24 @@ export const MODELS = {
990
1062
  contextWindow: 200000,
991
1063
  maxTokens: 64000,
992
1064
  },
1065
+ "global.anthropic.claude-haiku-5-5": {
1066
+ id: "global.anthropic.claude-haiku-5-5",
1067
+ name: "Claude Haiku 5.5 (Global)",
1068
+ api: "bedrock-converse-stream",
1069
+ provider: "amazon-bedrock",
1070
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1071
+ reasoning: true,
1072
+ thinkingType: "adaptive",
1073
+ input: ["text", "image"],
1074
+ cost: {
1075
+ input: 0.1,
1076
+ output: 0.5,
1077
+ cacheRead: 0.01,
1078
+ cacheWrite: 0.125,
1079
+ },
1080
+ contextWindow: 1000000,
1081
+ maxTokens: 128000,
1082
+ },
993
1083
  "global.anthropic.claude-opus-4-5-20251101-v1:0": {
994
1084
  id: "global.anthropic.claude-opus-4-5-20251101-v1:0",
995
1085
  name: "Claude Opus 4.5 (Global)",
@@ -1185,7 +1275,7 @@ export const MODELS = {
1185
1275
  cost: {
1186
1276
  input: 2,
1187
1277
  output: 10,
1188
- cacheRead: 0.2,
1278
+ cacheRead: 0.1,
1189
1279
  cacheWrite: 2.5,
1190
1280
  },
1191
1281
  contextWindow: 1000000,
@@ -1361,6 +1451,23 @@ export const MODELS = {
1361
1451
  contextWindow: 500000,
1362
1452
  maxTokens: 500000,
1363
1453
  },
1454
+ "global.zai.glm-5.3": {
1455
+ id: "global.zai.glm-5.3",
1456
+ name: "GLM-5.3 (Global)",
1457
+ api: "bedrock-converse-stream",
1458
+ provider: "amazon-bedrock",
1459
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1460
+ reasoning: true,
1461
+ input: ["text"],
1462
+ cost: {
1463
+ input: 1.68,
1464
+ output: 5.28,
1465
+ cacheRead: 0.312,
1466
+ cacheWrite: 2.1,
1467
+ },
1468
+ contextWindow: 1000000,
1469
+ maxTokens: 128000,
1470
+ },
1364
1471
  "google.gemma-4-26b-a4b": {
1365
1472
  id: "google.gemma-4-26b-a4b",
1366
1473
  name: "Gemma 4 26B A4B IT",
@@ -1535,6 +1642,24 @@ export const MODELS = {
1535
1642
  contextWindow: 200000,
1536
1643
  maxTokens: 64000,
1537
1644
  },
1645
+ "jp.anthropic.claude-haiku-5-5": {
1646
+ id: "jp.anthropic.claude-haiku-5-5",
1647
+ name: "Claude Haiku 5.5 (JP)",
1648
+ api: "bedrock-converse-stream",
1649
+ provider: "amazon-bedrock",
1650
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1651
+ reasoning: true,
1652
+ thinkingType: "adaptive",
1653
+ input: ["text", "image"],
1654
+ cost: {
1655
+ input: 0.11,
1656
+ output: 0.55,
1657
+ cacheRead: 0.011,
1658
+ cacheWrite: 0.1375,
1659
+ },
1660
+ contextWindow: 1000000,
1661
+ maxTokens: 128000,
1662
+ },
1538
1663
  "jp.anthropic.claude-opus-4-7": {
1539
1664
  id: "jp.anthropic.claude-opus-4-7",
1540
1665
  name: "Claude Opus 4.7 (JP)",
@@ -2605,6 +2730,24 @@ export const MODELS = {
2605
2730
  contextWindow: 200000,
2606
2731
  maxTokens: 64000,
2607
2732
  },
2733
+ "us.anthropic.claude-haiku-5-5": {
2734
+ id: "us.anthropic.claude-haiku-5-5",
2735
+ name: "Claude Haiku 5.5 (US)",
2736
+ api: "bedrock-converse-stream",
2737
+ provider: "amazon-bedrock",
2738
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2739
+ reasoning: true,
2740
+ thinkingType: "adaptive",
2741
+ input: ["text", "image"],
2742
+ cost: {
2743
+ input: 0.11,
2744
+ output: 0.55,
2745
+ cacheRead: 0.011,
2746
+ cacheWrite: 0.1375,
2747
+ },
2748
+ contextWindow: 1000000,
2749
+ maxTokens: 128000,
2750
+ },
2608
2751
  "us.anthropic.claude-opus-4-1-20250805-v1:0": {
2609
2752
  id: "us.anthropic.claude-opus-4-1-20250805-v1:0",
2610
2753
  name: "Claude Opus 4.1 (US)",
@@ -2806,6 +2949,24 @@ export const MODELS = {
2806
2949
  contextWindow: 1000000,
2807
2950
  maxTokens: 128000,
2808
2951
  },
2952
+ "us.anthropic.claude-sonnet-5-5": {
2953
+ id: "us.anthropic.claude-sonnet-5-5",
2954
+ name: "Claude Sonnet 5.5 (US)",
2955
+ api: "bedrock-converse-stream",
2956
+ provider: "amazon-bedrock",
2957
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2958
+ reasoning: true,
2959
+ thinkingType: "adaptive",
2960
+ input: ["text", "image"],
2961
+ cost: {
2962
+ input: 2.2,
2963
+ output: 11,
2964
+ cacheRead: 0.11,
2965
+ cacheWrite: 2.75,
2966
+ },
2967
+ contextWindow: 1000000,
2968
+ maxTokens: 128000,
2969
+ },
2809
2970
  "us.meta.llama3-1-70b-instruct-v1:0": {
2810
2971
  id: "us.meta.llama3-1-70b-instruct-v1:0",
2811
2972
  name: "Llama 3.1 70B Instruct (US)",
@@ -3112,6 +3273,23 @@ export const MODELS = {
3112
3273
  contextWindow: 500000,
3113
3274
  maxTokens: 500000,
3114
3275
  },
3276
+ "us.zai.glm-5.3": {
3277
+ id: "us.zai.glm-5.3",
3278
+ name: "GLM-5.3 (US)",
3279
+ api: "bedrock-converse-stream",
3280
+ provider: "amazon-bedrock",
3281
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3282
+ reasoning: true,
3283
+ input: ["text"],
3284
+ cost: {
3285
+ input: 1.848,
3286
+ output: 5.808,
3287
+ cacheRead: 0.3432,
3288
+ cacheWrite: 2.31,
3289
+ },
3290
+ contextWindow: 1000000,
3291
+ maxTokens: 128000,
3292
+ },
3115
3293
  "writer.palmyra-x4-v1:0": {
3116
3294
  id: "writer.palmyra-x4-v1:0",
3117
3295
  name: "Palmyra X4",
@@ -3307,6 +3485,24 @@ export const MODELS = {
3307
3485
  contextWindow: 200000,
3308
3486
  maxTokens: 64000,
3309
3487
  },
3488
+ "claude-haiku-5-5": {
3489
+ id: "claude-haiku-5-5",
3490
+ name: "Claude Haiku 5.5",
3491
+ api: "anthropic-messages",
3492
+ provider: "anthropic",
3493
+ baseUrl: "https://api.anthropic.com",
3494
+ reasoning: true,
3495
+ thinkingType: "adaptive",
3496
+ input: ["text", "image"],
3497
+ cost: {
3498
+ input: 0.1,
3499
+ output: 0.5,
3500
+ cacheRead: 0.01,
3501
+ cacheWrite: 0.125,
3502
+ },
3503
+ contextWindow: 1000000,
3504
+ maxTokens: 128000,
3505
+ },
3310
3506
  "claude-opus-4-5": {
3311
3507
  id: "claude-opus-4-5",
3312
3508
  name: "Claude Opus 4.5 (latest)",
@@ -3451,7 +3647,7 @@ export const MODELS = {
3451
3647
  cacheRead: 0.3,
3452
3648
  cacheWrite: 3.75,
3453
3649
  },
3454
- contextWindow: 1000000,
3650
+ contextWindow: 200000,
3455
3651
  maxTokens: 64000,
3456
3652
  },
3457
3653
  "claude-sonnet-4-5-20250929": {
@@ -3469,7 +3665,7 @@ export const MODELS = {
3469
3665
  cacheRead: 0.3,
3470
3666
  cacheWrite: 3.75,
3471
3667
  },
3472
- contextWindow: 1000000,
3668
+ contextWindow: 200000,
3473
3669
  maxTokens: 64000,
3474
3670
  },
3475
3671
  "claude-sonnet-4-6": {
@@ -3520,7 +3716,7 @@ export const MODELS = {
3520
3716
  cost: {
3521
3717
  input: 2,
3522
3718
  output: 10,
3523
- cacheRead: 0.2,
3719
+ cacheRead: 0.1,
3524
3720
  cacheWrite: 2.5,
3525
3721
  },
3526
3722
  contextWindow: 1000000,
@@ -4530,6 +4726,23 @@ export const MODELS = {
4530
4726
  contextWindow: 1000000,
4531
4727
  maxTokens: 128000,
4532
4728
  },
4729
+ "claude-sonnet-5.5": {
4730
+ id: "claude-sonnet-5.5",
4731
+ name: "Claude Sonnet 5.5",
4732
+ api: "anthropic-messages",
4733
+ provider: "cloudflare-ai-gateway",
4734
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4735
+ reasoning: true,
4736
+ input: ["text", "image"],
4737
+ cost: {
4738
+ input: 2,
4739
+ output: 10,
4740
+ cacheRead: 0.2,
4741
+ cacheWrite: 2.5,
4742
+ },
4743
+ contextWindow: 1000000,
4744
+ maxTokens: 128000,
4745
+ },
4533
4746
  "gpt-4.1": {
4534
4747
  id: "gpt-4.1",
4535
4748
  name: "GPT-4.1",
@@ -4900,6 +5113,23 @@ export const MODELS = {
4900
5113
  contextWindow: 1050000,
4901
5114
  maxTokens: 128000,
4902
5115
  },
5116
+ "gpt-6.1-sol": {
5117
+ id: "gpt-6.1-sol",
5118
+ name: "GPT-6.1 Sol",
5119
+ api: "openai-responses",
5120
+ provider: "cloudflare-ai-gateway",
5121
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
5122
+ reasoning: true,
5123
+ input: ["text", "image"],
5124
+ cost: {
5125
+ input: 2,
5126
+ output: 10,
5127
+ cacheRead: 0.1,
5128
+ cacheWrite: 2.5,
5129
+ },
5130
+ contextWindow: 1050000,
5131
+ maxTokens: 128000,
5132
+ },
4903
5133
  "o3": {
4904
5134
  id: "o3",
4905
5135
  name: "o3",
@@ -5071,7 +5301,7 @@ export const MODELS = {
5071
5301
  baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
5072
5302
  compat: { "sendSessionAffinityHeaders": true },
5073
5303
  reasoning: false,
5074
- input: ["text"],
5304
+ input: ["text", "image"],
5075
5305
  cost: {
5076
5306
  input: 0.351,
5077
5307
  output: 0.555,
@@ -5756,6 +5986,25 @@ export const MODELS = {
5756
5986
  contextWindow: 200000,
5757
5987
  maxTokens: 64000,
5758
5988
  },
5989
+ "claude-haiku-5.5": {
5990
+ id: "claude-haiku-5.5",
5991
+ name: "Claude Haiku 5.5",
5992
+ api: "openai-completions",
5993
+ provider: "github-copilot",
5994
+ baseUrl: "https://api.individual.githubcopilot.com",
5995
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
5996
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5997
+ reasoning: true,
5998
+ input: ["text", "image"],
5999
+ cost: {
6000
+ input: 0.1,
6001
+ output: 0.5,
6002
+ cacheRead: 0.01,
6003
+ cacheWrite: 0.125,
6004
+ },
6005
+ contextWindow: 1000000,
6006
+ maxTokens: 128000,
6007
+ },
5759
6008
  "claude-opus-4.7": {
5760
6009
  id: "claude-opus-4.7",
5761
6010
  name: "Claude Opus 4.7",
@@ -5882,7 +6131,7 @@ export const MODELS = {
5882
6131
  cost: {
5883
6132
  input: 2,
5884
6133
  output: 10,
5885
- cacheRead: 0.2,
6134
+ cacheRead: 0.1,
5886
6135
  cacheWrite: 2.5,
5887
6136
  },
5888
6137
  contextWindow: 1000000,
@@ -7084,6 +7333,24 @@ export const MODELS = {
7084
7333
  },
7085
7334
  },
7086
7335
  "huggingface": {
7336
+ "MiniMaxAI/MiniMax-M1-80k": {
7337
+ id: "MiniMaxAI/MiniMax-M1-80k",
7338
+ name: "MiniMax M1 80K",
7339
+ api: "openai-completions",
7340
+ provider: "huggingface",
7341
+ baseUrl: "https://router.huggingface.co/v1",
7342
+ compat: { "supportsDeveloperRole": false },
7343
+ reasoning: true,
7344
+ input: ["text"],
7345
+ cost: {
7346
+ input: 0.55,
7347
+ output: 2.2,
7348
+ cacheRead: 0,
7349
+ cacheWrite: 0,
7350
+ },
7351
+ contextWindow: 1000000,
7352
+ maxTokens: 80000,
7353
+ },
7087
7354
  "MiniMaxAI/MiniMax-M2": {
7088
7355
  id: "MiniMaxAI/MiniMax-M2",
7089
7356
  name: "MiniMax-M2",
@@ -7408,6 +7675,24 @@ export const MODELS = {
7408
7675
  contextWindow: 131072,
7409
7676
  maxTokens: 32768,
7410
7677
  },
7678
+ "Qwen/Qwen3-VL-30B-A3B-Instruct": {
7679
+ id: "Qwen/Qwen3-VL-30B-A3B-Instruct",
7680
+ name: "Qwen3 VL 30B A3B Instruct",
7681
+ api: "openai-completions",
7682
+ provider: "huggingface",
7683
+ baseUrl: "https://router.huggingface.co/v1",
7684
+ compat: { "supportsDeveloperRole": false },
7685
+ reasoning: false,
7686
+ input: ["text", "image"],
7687
+ cost: {
7688
+ input: 0.2,
7689
+ output: 0.7,
7690
+ cacheRead: 0,
7691
+ cacheWrite: 0,
7692
+ },
7693
+ contextWindow: 131072,
7694
+ maxTokens: 32768,
7695
+ },
7411
7696
  "Qwen/Qwen3.5-122B-A10B": {
7412
7697
  id: "Qwen/Qwen3.5-122B-A10B",
7413
7698
  name: "Qwen3.5 122B-A10B",
@@ -8616,9 +8901,9 @@ export const MODELS = {
8616
8901
  },
8617
8902
  },
8618
8903
  "mistral": {
8619
- "codestral-latest": {
8620
- id: "codestral-latest",
8621
- name: "Codestral (latest)",
8904
+ "codestral-2508": {
8905
+ id: "codestral-2508",
8906
+ name: "Codestral 25.08",
8622
8907
  api: "mistral-conversations",
8623
8908
  provider: "mistral",
8624
8909
  baseUrl: "https://api.mistral.ai",
@@ -8631,10 +8916,27 @@ export const MODELS = {
8631
8916
  cacheWrite: 0,
8632
8917
  },
8633
8918
  contextWindow: 256000,
8634
- maxTokens: 4096,
8919
+ maxTokens: 8192,
8635
8920
  },
8636
- "devstral-2512": {
8637
- id: "devstral-2512",
8921
+ "codestral-latest": {
8922
+ id: "codestral-latest",
8923
+ name: "Codestral (latest)",
8924
+ api: "mistral-conversations",
8925
+ provider: "mistral",
8926
+ baseUrl: "https://api.mistral.ai",
8927
+ reasoning: false,
8928
+ input: ["text"],
8929
+ cost: {
8930
+ input: 0.3,
8931
+ output: 0.9,
8932
+ cacheRead: 0.03,
8933
+ cacheWrite: 0,
8934
+ },
8935
+ contextWindow: 256000,
8936
+ maxTokens: 4096,
8937
+ },
8938
+ "devstral-2512": {
8939
+ id: "devstral-2512",
8638
8940
  name: "Devstral 2",
8639
8941
  api: "mistral-conversations",
8640
8942
  provider: "mistral",
@@ -8735,6 +9037,23 @@ export const MODELS = {
8735
9037
  contextWindow: 128000,
8736
9038
  maxTokens: 128000,
8737
9039
  },
9040
+ "glm-5-2": {
9041
+ id: "glm-5-2",
9042
+ name: "GLM-5.2",
9043
+ api: "mistral-conversations",
9044
+ provider: "mistral",
9045
+ baseUrl: "https://api.mistral.ai",
9046
+ reasoning: true,
9047
+ input: ["text"],
9048
+ cost: {
9049
+ input: 1.4,
9050
+ output: 4.4,
9051
+ cacheRead: 0.14,
9052
+ cacheWrite: 0,
9053
+ },
9054
+ contextWindow: 1048576,
9055
+ maxTokens: 131072,
9056
+ },
8738
9057
  "labs-devstral-small-2512": {
8739
9058
  id: "labs-devstral-small-2512",
8740
9059
  name: "Devstral Small 2",
@@ -8752,6 +9071,23 @@ export const MODELS = {
8752
9071
  contextWindow: 256000,
8753
9072
  maxTokens: 256000,
8754
9073
  },
9074
+ "labs-leanstral-1-5-1": {
9075
+ id: "labs-leanstral-1-5-1",
9076
+ name: "Leanstral 1.5",
9077
+ api: "mistral-conversations",
9078
+ provider: "mistral",
9079
+ baseUrl: "https://api.mistral.ai",
9080
+ reasoning: true,
9081
+ input: ["text", "image"],
9082
+ cost: {
9083
+ input: 0,
9084
+ output: 0,
9085
+ cacheRead: 0,
9086
+ cacheWrite: 0,
9087
+ },
9088
+ contextWindow: 262144,
9089
+ maxTokens: 128000,
9090
+ },
8755
9091
  "magistral-medium-latest": {
8756
9092
  id: "magistral-medium-latest",
8757
9093
  name: "Magistral Medium (latest)",
@@ -8759,16 +9095,50 @@ export const MODELS = {
8759
9095
  provider: "mistral",
8760
9096
  baseUrl: "https://api.mistral.ai",
8761
9097
  reasoning: true,
8762
- input: ["text"],
9098
+ input: ["text", "image"],
8763
9099
  cost: {
8764
9100
  input: 2,
8765
9101
  output: 5,
8766
9102
  cacheRead: 0,
8767
9103
  cacheWrite: 0,
8768
9104
  },
8769
- contextWindow: 128000,
9105
+ contextWindow: 262144,
8770
9106
  maxTokens: 16384,
8771
9107
  },
9108
+ "ministral-14b-2512": {
9109
+ id: "ministral-14b-2512",
9110
+ name: "Ministral 3 14B",
9111
+ api: "mistral-conversations",
9112
+ provider: "mistral",
9113
+ baseUrl: "https://api.mistral.ai",
9114
+ reasoning: false,
9115
+ input: ["text", "image"],
9116
+ cost: {
9117
+ input: 0.2,
9118
+ output: 0.2,
9119
+ cacheRead: 0.02,
9120
+ cacheWrite: 0,
9121
+ },
9122
+ contextWindow: 262144,
9123
+ maxTokens: 262144,
9124
+ },
9125
+ "ministral-3b-2512": {
9126
+ id: "ministral-3b-2512",
9127
+ name: "Ministral 3 3B",
9128
+ api: "mistral-conversations",
9129
+ provider: "mistral",
9130
+ baseUrl: "https://api.mistral.ai",
9131
+ reasoning: false,
9132
+ input: ["text", "image"],
9133
+ cost: {
9134
+ input: 0.1,
9135
+ output: 0.1,
9136
+ cacheRead: 0.01,
9137
+ cacheWrite: 0,
9138
+ },
9139
+ contextWindow: 131072,
9140
+ maxTokens: 262144,
9141
+ },
8772
9142
  "ministral-3b-latest": {
8773
9143
  id: "ministral-3b-latest",
8774
9144
  name: "Ministral 3B (latest)",
@@ -8776,16 +9146,33 @@ export const MODELS = {
8776
9146
  provider: "mistral",
8777
9147
  baseUrl: "https://api.mistral.ai",
8778
9148
  reasoning: false,
8779
- input: ["text"],
9149
+ input: ["text", "image"],
8780
9150
  cost: {
8781
9151
  input: 0.04,
8782
9152
  output: 0.04,
8783
9153
  cacheRead: 0,
8784
9154
  cacheWrite: 0,
8785
9155
  },
8786
- contextWindow: 128000,
9156
+ contextWindow: 131072,
8787
9157
  maxTokens: 128000,
8788
9158
  },
9159
+ "ministral-8b-2512": {
9160
+ id: "ministral-8b-2512",
9161
+ name: "Ministral 3 8B",
9162
+ api: "mistral-conversations",
9163
+ provider: "mistral",
9164
+ baseUrl: "https://api.mistral.ai",
9165
+ reasoning: false,
9166
+ input: ["text", "image"],
9167
+ cost: {
9168
+ input: 0.15,
9169
+ output: 0.15,
9170
+ cacheRead: 0.015,
9171
+ cacheWrite: 0,
9172
+ },
9173
+ contextWindow: 262144,
9174
+ maxTokens: 262144,
9175
+ },
8789
9176
  "ministral-8b-latest": {
8790
9177
  id: "ministral-8b-latest",
8791
9178
  name: "Ministral 8B (latest)",
@@ -8793,14 +9180,14 @@ export const MODELS = {
8793
9180
  provider: "mistral",
8794
9181
  baseUrl: "https://api.mistral.ai",
8795
9182
  reasoning: false,
8796
- input: ["text"],
9183
+ input: ["text", "image"],
8797
9184
  cost: {
8798
9185
  input: 0.1,
8799
9186
  output: 0.1,
8800
9187
  cacheRead: 0,
8801
9188
  cacheWrite: 0,
8802
9189
  },
8803
- contextWindow: 128000,
9190
+ contextWindow: 262144,
8804
9191
  maxTokens: 128000,
8805
9192
  },
8806
9193
  "mistral-large-2411": {
@@ -8837,6 +9224,23 @@ export const MODELS = {
8837
9224
  contextWindow: 262144,
8838
9225
  maxTokens: 262144,
8839
9226
  },
9227
+ "mistral-large-4": {
9228
+ id: "mistral-large-4",
9229
+ name: "Mistral Large 4",
9230
+ api: "mistral-conversations",
9231
+ provider: "mistral",
9232
+ baseUrl: "https://api.mistral.ai",
9233
+ reasoning: true,
9234
+ input: ["text", "image"],
9235
+ cost: {
9236
+ input: 0.68,
9237
+ output: 2.09,
9238
+ cacheRead: 0.07,
9239
+ cacheWrite: 0,
9240
+ },
9241
+ contextWindow: 1048576,
9242
+ maxTokens: 262144,
9243
+ },
8840
9244
  "mistral-large-latest": {
8841
9245
  id: "mistral-large-latest",
8842
9246
  name: "Mistral Large (latest)",
@@ -8987,7 +9391,7 @@ export const MODELS = {
8987
9391
  cacheRead: 0.015,
8988
9392
  cacheWrite: 0,
8989
9393
  },
8990
- contextWindow: 256000,
9394
+ contextWindow: 262144,
8991
9395
  maxTokens: 256000,
8992
9396
  },
8993
9397
  "mistral-small-latest": {
@@ -9004,7 +9408,7 @@ export const MODELS = {
9004
9408
  cacheRead: 0.015,
9005
9409
  cacheWrite: 0,
9006
9410
  },
9007
- contextWindow: 256000,
9411
+ contextWindow: 262144,
9008
9412
  maxTokens: 256000,
9009
9413
  },
9010
9414
  "open-mistral-7b": {
@@ -9109,6 +9513,23 @@ export const MODELS = {
9109
9513
  contextWindow: 128000,
9110
9514
  maxTokens: 128000,
9111
9515
  },
9516
+ "voxtral-small-2507": {
9517
+ id: "voxtral-small-2507",
9518
+ name: "Voxtral Small",
9519
+ api: "mistral-conversations",
9520
+ provider: "mistral",
9521
+ baseUrl: "https://api.mistral.ai",
9522
+ reasoning: false,
9523
+ input: ["text"],
9524
+ cost: {
9525
+ input: 0.1,
9526
+ output: 0.4,
9527
+ cacheRead: 0,
9528
+ cacheWrite: 0,
9529
+ },
9530
+ contextWindow: 32768,
9531
+ maxTokens: 32000,
9532
+ },
9112
9533
  "voxtral-small-latest": {
9113
9534
  id: "voxtral-small-latest",
9114
9535
  name: "Voxtral Small (latest)",
@@ -9123,7 +9544,7 @@ export const MODELS = {
9123
9544
  cacheRead: 0,
9124
9545
  cacheWrite: 0,
9125
9546
  },
9126
- contextWindow: 32000,
9547
+ contextWindow: 32768,
9127
9548
  maxTokens: 32000,
9128
9549
  },
9129
9550
  "zai-glm-5-2": {
@@ -9140,7 +9561,7 @@ export const MODELS = {
9140
9561
  cacheRead: 0.14,
9141
9562
  cacheWrite: 0,
9142
9563
  },
9143
- contextWindow: 1000000,
9564
+ contextWindow: 1048576,
9144
9565
  maxTokens: 131072,
9145
9566
  },
9146
9567
  "zai-glm-5-3": {
@@ -9157,7 +9578,7 @@ export const MODELS = {
9157
9578
  cacheRead: 0.14,
9158
9579
  cacheWrite: 0,
9159
9580
  },
9160
- contextWindow: 1000000,
9581
+ contextWindow: 1048576,
9161
9582
  maxTokens: 131072,
9162
9583
  },
9163
9584
  },
@@ -9229,7 +9650,7 @@ export const MODELS = {
9229
9650
  input: 3,
9230
9651
  output: 15,
9231
9652
  cacheRead: 0.3,
9232
- cacheWrite: 0,
9653
+ cacheWrite: 3,
9233
9654
  },
9234
9655
  contextWindow: 1048576,
9235
9656
  maxTokens: 1048576,
@@ -9303,7 +9724,7 @@ export const MODELS = {
9303
9724
  input: 3,
9304
9725
  output: 15,
9305
9726
  cacheRead: 0.3,
9306
- cacheWrite: 0,
9727
+ cacheWrite: 3,
9307
9728
  },
9308
9729
  contextWindow: 1048576,
9309
9730
  maxTokens: 1048576,
@@ -10317,6 +10738,23 @@ export const MODELS = {
10317
10738
  contextWindow: 200000,
10318
10739
  maxTokens: 64000,
10319
10740
  },
10741
+ "claude-haiku-5-5": {
10742
+ id: "claude-haiku-5-5",
10743
+ name: "Claude Haiku 5.5",
10744
+ api: "anthropic-messages",
10745
+ provider: "opencode",
10746
+ baseUrl: "https://opencode.ai/zen",
10747
+ reasoning: true,
10748
+ input: ["text", "image"],
10749
+ cost: {
10750
+ input: 0.1,
10751
+ output: 0.5,
10752
+ cacheRead: 0.01,
10753
+ cacheWrite: 0.125,
10754
+ },
10755
+ contextWindow: 1000000,
10756
+ maxTokens: 128000,
10757
+ },
10320
10758
  "claude-opus-4-5": {
10321
10759
  id: "claude-opus-4-5",
10322
10760
  name: "Claude Opus 4.5",
@@ -10583,9 +11021,9 @@ export const MODELS = {
10583
11021
  contextWindow: 1000000,
10584
11022
  maxTokens: 384000,
10585
11023
  },
10586
- "fledge-alpha-free": {
10587
- id: "fledge-alpha-free",
10588
- name: "Fledge Alpha Free",
11024
+ "exo-free": {
11025
+ id: "exo-free",
11026
+ name: "Exo Free",
10589
11027
  api: "openai-completions",
10590
11028
  provider: "opencode",
10591
11029
  baseUrl: "https://opencode.ai/zen/v1",
@@ -11476,6 +11914,23 @@ export const MODELS = {
11476
11914
  contextWindow: 512000,
11477
11915
  maxTokens: 128000,
11478
11916
  },
11917
+ "mistral-large-4": {
11918
+ id: "mistral-large-4",
11919
+ name: "Mistral Large 4",
11920
+ api: "openai-completions",
11921
+ provider: "opencode",
11922
+ baseUrl: "https://opencode.ai/zen/v1",
11923
+ reasoning: true,
11924
+ input: ["text", "image"],
11925
+ cost: {
11926
+ input: 0.68,
11927
+ output: 2.09,
11928
+ cacheRead: 0.07,
11929
+ cacheWrite: 0,
11930
+ },
11931
+ contextWindow: 524288,
11932
+ maxTokens: 262144,
11933
+ },
11479
11934
  "muse-spark-1.2": {
11480
11935
  id: "muse-spark-1.2",
11481
11936
  name: "Muse Spark 1.2",
@@ -11646,8 +12101,42 @@ export const MODELS = {
11646
12101
  contextWindow: 1048576,
11647
12102
  maxTokens: 524288,
11648
12103
  },
12104
+ "step-5-preview-free": {
12105
+ id: "step-5-preview-free",
12106
+ name: "Step 5 Preview Free",
12107
+ api: "openai-completions",
12108
+ provider: "opencode",
12109
+ baseUrl: "https://opencode.ai/zen/v1",
12110
+ reasoning: true,
12111
+ input: ["text", "image"],
12112
+ cost: {
12113
+ input: 0,
12114
+ output: 0,
12115
+ cacheRead: 0,
12116
+ cacheWrite: 0,
12117
+ },
12118
+ contextWindow: 1000000,
12119
+ maxTokens: 65536,
12120
+ },
11649
12121
  },
11650
12122
  "opencode-go": {
12123
+ "claude-haiku-5-5": {
12124
+ id: "claude-haiku-5-5",
12125
+ name: "Claude Haiku 5.5",
12126
+ api: "anthropic-messages",
12127
+ provider: "opencode-go",
12128
+ baseUrl: "https://opencode.ai/zen/go",
12129
+ reasoning: true,
12130
+ input: ["text", "image"],
12131
+ cost: {
12132
+ input: 0.1,
12133
+ output: 0.5,
12134
+ cacheRead: 0.01,
12135
+ cacheWrite: 0.125,
12136
+ },
12137
+ contextWindow: 1000000,
12138
+ maxTokens: 128000,
12139
+ },
11651
12140
  "deepseek-v4-flash": {
11652
12141
  id: "deepseek-v4-flash",
11653
12142
  name: "DeepSeek V4 Flash",
@@ -12085,9 +12574,9 @@ export const MODELS = {
12085
12574
  "qwen3.7-plus": {
12086
12575
  id: "qwen3.7-plus",
12087
12576
  name: "Qwen3.7 Plus",
12088
- api: "openai-completions",
12577
+ api: "anthropic-messages",
12089
12578
  provider: "opencode-go",
12090
- baseUrl: "https://opencode.ai/zen/go/v1",
12579
+ baseUrl: "https://opencode.ai/zen/go",
12091
12580
  reasoning: true,
12092
12581
  input: ["text", "image"],
12093
12582
  cost: {
@@ -12119,9 +12608,9 @@ export const MODELS = {
12119
12608
  "qwen3.8-max": {
12120
12609
  id: "qwen3.8-max",
12121
12610
  name: "Qwen3.8 Max",
12122
- api: "openai-completions",
12611
+ api: "anthropic-messages",
12123
12612
  provider: "opencode-go",
12124
- baseUrl: "https://opencode.ai/zen/go/v1",
12613
+ baseUrl: "https://opencode.ai/zen/go",
12125
12614
  reasoning: true,
12126
12615
  input: ["text", "image"],
12127
12616
  cost: {
@@ -12133,9 +12622,26 @@ export const MODELS = {
12133
12622
  contextWindow: 1000000,
12134
12623
  maxTokens: 131072,
12135
12624
  },
12136
- "space-bunny-free": {
12137
- id: "space-bunny-free",
12138
- name: "Space Bunny Free",
12625
+ "space-bunny": {
12626
+ id: "space-bunny",
12627
+ name: "Space Bunny",
12628
+ api: "openai-completions",
12629
+ provider: "opencode-go",
12630
+ baseUrl: "https://opencode.ai/zen/go/v1",
12631
+ reasoning: true,
12632
+ input: ["text", "image"],
12633
+ cost: {
12634
+ input: 0.15,
12635
+ output: 0.6,
12636
+ cacheRead: 0.03,
12637
+ cacheWrite: 0,
12638
+ },
12639
+ contextWindow: 1048576,
12640
+ maxTokens: 524288,
12641
+ },
12642
+ "step-5-preview-free": {
12643
+ id: "step-5-preview-free",
12644
+ name: "Step 5 Preview Free",
12139
12645
  api: "openai-completions",
12140
12646
  provider: "opencode-go",
12141
12647
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12147,8 +12653,8 @@ export const MODELS = {
12147
12653
  cacheRead: 0,
12148
12654
  cacheWrite: 0,
12149
12655
  },
12150
- contextWindow: 1048576,
12151
- maxTokens: 524288,
12656
+ contextWindow: 1000000,
12657
+ maxTokens: 65536,
12152
12658
  },
12153
12659
  },
12154
12660
  "openrouter": {
@@ -12428,6 +12934,40 @@ export const MODELS = {
12428
12934
  contextWindow: 200000,
12429
12935
  maxTokens: 64000,
12430
12936
  },
12937
+ "anthropic/claude-haiku-5.5": {
12938
+ id: "anthropic/claude-haiku-5.5",
12939
+ name: "Anthropic: Claude Haiku 5.5",
12940
+ api: "openai-completions",
12941
+ provider: "openrouter",
12942
+ baseUrl: "https://openrouter.ai/api/v1",
12943
+ reasoning: true,
12944
+ input: ["text", "image"],
12945
+ cost: {
12946
+ input: 0.09999999999999999,
12947
+ output: 0.5,
12948
+ cacheRead: 0.01,
12949
+ cacheWrite: 0.125,
12950
+ },
12951
+ contextWindow: 1000000,
12952
+ maxTokens: 128000,
12953
+ },
12954
+ "anthropic/claude-haiku-5.5:batch": {
12955
+ id: "anthropic/claude-haiku-5.5:batch",
12956
+ name: "Anthropic: Claude Haiku 5.5 (batch)",
12957
+ api: "openai-completions",
12958
+ provider: "openrouter",
12959
+ baseUrl: "https://openrouter.ai/api/v1",
12960
+ reasoning: true,
12961
+ input: ["text", "image"],
12962
+ cost: {
12963
+ input: 0.049999999999999996,
12964
+ output: 0.25,
12965
+ cacheRead: 0.005,
12966
+ cacheWrite: 0.0625,
12967
+ },
12968
+ contextWindow: 1000000,
12969
+ maxTokens: 128000,
12970
+ },
12431
12971
  "anthropic/claude-opus-4.1": {
12432
12972
  id: "anthropic/claude-opus-4.1",
12433
12973
  name: "Anthropic: Claude Opus 4.1",
@@ -12785,7 +13325,7 @@ export const MODELS = {
12785
13325
  cost: {
12786
13326
  input: 2,
12787
13327
  output: 10,
12788
- cacheRead: 0.19999999999999998,
13328
+ cacheRead: 0.09999999999999999,
12789
13329
  cacheWrite: 2.5,
12790
13330
  },
12791
13331
  contextWindow: 1000000,
@@ -12802,7 +13342,7 @@ export const MODELS = {
12802
13342
  cost: {
12803
13343
  input: 1,
12804
13344
  output: 5,
12805
- cacheRead: 0.09999999999999999,
13345
+ cacheRead: 0.049999999999999996,
12806
13346
  cacheWrite: 1.25,
12807
13347
  },
12808
13348
  contextWindow: 1000000,
@@ -13055,13 +13595,13 @@ export const MODELS = {
13055
13595
  reasoning: false,
13056
13596
  input: ["text"],
13057
13597
  cost: {
13058
- input: 0.2574,
13059
- output: 1.0287,
13598
+ input: 0.32,
13599
+ output: 0.8899999999999999,
13060
13600
  cacheRead: 0,
13061
13601
  cacheWrite: 0,
13062
13602
  },
13063
13603
  contextWindow: 163840,
13064
- maxTokens: 16000,
13604
+ maxTokens: 16384,
13065
13605
  },
13066
13606
  "deepseek/deepseek-chat-v3-0324": {
13067
13607
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13157,13 +13697,13 @@ export const MODELS = {
13157
13697
  reasoning: true,
13158
13698
  input: ["text"],
13159
13699
  cost: {
13160
- input: 0.28,
13161
- output: 0.42,
13162
- cacheRead: 0.028,
13700
+ input: 0.25899999999999995,
13701
+ output: 0.7999999999999999,
13702
+ cacheRead: 0.14,
13163
13703
  cacheWrite: 0,
13164
13704
  },
13165
13705
  contextWindow: 163840,
13166
- maxTokens: 65536,
13706
+ maxTokens: 147456,
13167
13707
  },
13168
13708
  "deepseek/deepseek-v3.2-exp": {
13169
13709
  id: "deepseek/deepseek-v3.2-exp",
@@ -13193,13 +13733,13 @@ export const MODELS = {
13193
13733
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13194
13734
  input: ["text"],
13195
13735
  cost: {
13196
- input: 0.028,
13197
- output: 0.056,
13198
- cacheRead: 0.0056,
13736
+ input: 0.012100000000000001,
13737
+ output: 1.28,
13738
+ cacheRead: 0.012100000000000001,
13199
13739
  cacheWrite: 0,
13200
13740
  },
13201
13741
  contextWindow: 1048576,
13202
- maxTokens: 384000,
13742
+ maxTokens: 943718,
13203
13743
  },
13204
13744
  "deepseek/deepseek-v4-flash-0731": {
13205
13745
  id: "deepseek/deepseek-v4-flash-0731",
@@ -13212,9 +13752,9 @@ export const MODELS = {
13212
13752
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13213
13753
  input: ["text"],
13214
13754
  cost: {
13215
- input: 0.0188,
13755
+ input: 0.0068,
13216
13756
  output: 1.28,
13217
- cacheRead: 0.0188,
13757
+ cacheRead: 0.0068,
13218
13758
  cacheWrite: 0,
13219
13759
  },
13220
13760
  contextWindow: 1048576,
@@ -13250,9 +13790,9 @@ export const MODELS = {
13250
13790
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13251
13791
  input: ["text"],
13252
13792
  cost: {
13253
- input: 0.20879999999999999,
13254
- output: 0.41759999999999997,
13255
- cacheRead: 0.0174,
13793
+ input: 0.9483,
13794
+ output: 1.8966,
13795
+ cacheRead: 0.079025,
13256
13796
  cacheWrite: 0,
13257
13797
  },
13258
13798
  contextWindow: 1048576,
@@ -13269,13 +13809,13 @@ export const MODELS = {
13269
13809
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13270
13810
  input: ["text"],
13271
13811
  cost: {
13272
- input: 0.22,
13273
- output: 4.199999999999999,
13274
- cacheRead: 0.14,
13812
+ input: 0.66,
13813
+ output: 1.9800000000000002,
13814
+ cacheRead: 0.022,
13275
13815
  cacheWrite: 0,
13276
13816
  },
13277
13817
  contextWindow: 1048576,
13278
- maxTokens: 943718,
13818
+ maxTokens: 393216,
13279
13819
  },
13280
13820
  "deepseek/deepseek-v4.1-flash": {
13281
13821
  id: "deepseek/deepseek-v4.1-flash",
@@ -13791,6 +14331,23 @@ export const MODELS = {
13791
14331
  contextWindow: 1048576,
13792
14332
  maxTokens: 65536,
13793
14333
  },
14334
+ "google/gemini-nano-banana-2.1": {
14335
+ id: "google/gemini-nano-banana-2.1",
14336
+ name: "Google: Nano Banana 2.1",
14337
+ api: "openai-completions",
14338
+ provider: "openrouter",
14339
+ baseUrl: "https://openrouter.ai/api/v1",
14340
+ reasoning: true,
14341
+ input: ["text", "image"],
14342
+ cost: {
14343
+ input: 1.5,
14344
+ output: 7.5,
14345
+ cacheRead: 0,
14346
+ cacheWrite: 0,
14347
+ },
14348
+ contextWindow: 65536,
14349
+ maxTokens: 58982,
14350
+ },
13794
14351
  "google/gemma-3-12b-it": {
13795
14352
  id: "google/gemma-3-12b-it",
13796
14353
  name: "Google: Gemma 3 12B",
@@ -13978,18 +14535,18 @@ export const MODELS = {
13978
14535
  contextWindow: 262144,
13979
14536
  maxTokens: 32768,
13980
14537
  },
13981
- "inclusionai/ling-3.0-flash-sante:free": {
13982
- id: "inclusionai/ling-3.0-flash-sante:free",
13983
- name: "inclusionAI: Ling 3.0 Flash Sante (free)",
14538
+ "inclusionai/ling-3.0-flash-sante": {
14539
+ id: "inclusionai/ling-3.0-flash-sante",
14540
+ name: "inclusionAI: Ling 3.0 Flash Sante",
13984
14541
  api: "openai-completions",
13985
14542
  provider: "openrouter",
13986
14543
  baseUrl: "https://openrouter.ai/api/v1",
13987
14544
  reasoning: true,
13988
14545
  input: ["text"],
13989
14546
  cost: {
13990
- input: 0,
13991
- output: 0,
13992
- cacheRead: 0,
14547
+ input: 0.041999999999999996,
14548
+ output: 0.12319999999999999,
14549
+ cacheRead: 0.008400000000000001,
13993
14550
  cacheWrite: 0,
13994
14551
  },
13995
14552
  contextWindow: 262144,
@@ -14029,23 +14586,6 @@ export const MODELS = {
14029
14586
  contextWindow: 262144,
14030
14587
  maxTokens: 32768,
14031
14588
  },
14032
- "kwaipilot/kat-coder-pro-v2.5": {
14033
- id: "kwaipilot/kat-coder-pro-v2.5",
14034
- name: "Kwaipilot: KAT-Coder-Pro V2.5",
14035
- api: "openai-completions",
14036
- provider: "openrouter",
14037
- baseUrl: "https://openrouter.ai/api/v1",
14038
- reasoning: false,
14039
- input: ["text"],
14040
- cost: {
14041
- input: 0.74,
14042
- output: 2.96,
14043
- cacheRead: 0.15,
14044
- cacheWrite: 0,
14045
- },
14046
- contextWindow: 262144,
14047
- maxTokens: 235929,
14048
- },
14049
14589
  "liquid/lfm-2.5-2.6b:free": {
14050
14590
  id: "liquid/lfm-2.5-2.6b:free",
14051
14591
  name: "LiquidAI: LFM2.5-2.6B (free)",
@@ -14123,9 +14663,9 @@ export const MODELS = {
14123
14663
  reasoning: false,
14124
14664
  input: ["text"],
14125
14665
  cost: {
14126
- input: 0.09999999999999999,
14127
- output: 0.32,
14128
- cacheRead: 0,
14666
+ input: 0.22,
14667
+ output: 0.5,
14668
+ cacheRead: 0.11,
14129
14669
  cacheWrite: 0,
14130
14670
  },
14131
14671
  contextWindow: 131072,
@@ -14142,7 +14682,7 @@ export const MODELS = {
14142
14682
  cost: {
14143
14683
  input: 0.1875,
14144
14684
  output: 0.6525,
14145
- cacheRead: 0,
14685
+ cacheRead: 0.049999999999999996,
14146
14686
  cacheWrite: 0,
14147
14687
  },
14148
14688
  contextWindow: 1048576,
@@ -14174,13 +14714,13 @@ export const MODELS = {
14174
14714
  reasoning: true,
14175
14715
  input: ["text", "image"],
14176
14716
  cost: {
14177
- input: 0.35,
14178
- output: 1.5,
14717
+ input: 0.3,
14718
+ output: 1.2,
14179
14719
  cacheRead: 0.04,
14180
14720
  cacheWrite: 0,
14181
14721
  },
14182
14722
  contextWindow: 131072,
14183
- maxTokens: 117964,
14723
+ maxTokens: 16384,
14184
14724
  },
14185
14725
  "meta/muse-spark-1.1": {
14186
14726
  id: "meta/muse-spark-1.1",
@@ -14556,6 +15096,23 @@ export const MODELS = {
14556
15096
  contextWindow: 262144,
14557
15097
  maxTokens: 209715,
14558
15098
  },
15099
+ "mistralai/mistral-large-4-0": {
15100
+ id: "mistralai/mistral-large-4-0",
15101
+ name: "Mistral: Mistral Large 4",
15102
+ api: "openai-completions",
15103
+ provider: "openrouter",
15104
+ baseUrl: "https://openrouter.ai/api/v1",
15105
+ reasoning: true,
15106
+ input: ["text", "image"],
15107
+ cost: {
15108
+ input: 0.6799999999999999,
15109
+ output: 2.09,
15110
+ cacheRead: 0.07,
15111
+ cacheWrite: 0,
15112
+ },
15113
+ contextWindow: 1048576,
15114
+ maxTokens: 262144,
15115
+ },
14559
15116
  "mistralai/mistral-medium-3": {
14560
15117
  id: "mistralai/mistral-medium-3",
14561
15118
  name: "Mistral: Mistral Medium 3",
@@ -14650,7 +15207,7 @@ export const MODELS = {
14650
15207
  reasoning: false,
14651
15208
  input: ["text"],
14652
15209
  cost: {
14653
- input: 0.019000000000000003,
15210
+ input: 0.029,
14654
15211
  output: 0.03,
14655
15212
  cacheRead: 0,
14656
15213
  cacheWrite: 0,
@@ -14822,11 +15379,11 @@ export const MODELS = {
14822
15379
  cost: {
14823
15380
  input: 0.6,
14824
15381
  output: 2.5,
14825
- cacheRead: 0,
15382
+ cacheRead: 0.15,
14826
15383
  cacheWrite: 0,
14827
15384
  },
14828
15385
  contextWindow: 262144,
14829
- maxTokens: 235929,
15386
+ maxTokens: 98304,
14830
15387
  },
14831
15388
  "moonshotai/kimi-k2.5": {
14832
15389
  id: "moonshotai/kimi-k2.5",
@@ -14854,9 +15411,9 @@ export const MODELS = {
14854
15411
  reasoning: true,
14855
15412
  input: ["text", "image"],
14856
15413
  cost: {
14857
- input: 0.95,
14858
- output: 4,
14859
- cacheRead: 0.16,
15414
+ input: 0.46499999999999997,
15415
+ output: 2.4499999999999997,
15416
+ cacheRead: 0.0875,
14860
15417
  cacheWrite: 0,
14861
15418
  },
14862
15419
  contextWindow: 262144,
@@ -14888,9 +15445,9 @@ export const MODELS = {
14888
15445
  reasoning: true,
14889
15446
  input: ["text", "image"],
14890
15447
  cost: {
14891
- input: 0.9900000000000001,
14892
- output: 13,
14893
- cacheRead: 0.7999999999999999,
15448
+ input: 0.64,
15449
+ output: 13.5,
15450
+ cacheRead: 0.28,
14894
15451
  cacheWrite: 0,
14895
15452
  },
14896
15453
  contextWindow: 1048576,
@@ -14939,9 +15496,9 @@ export const MODELS = {
14939
15496
  reasoning: true,
14940
15497
  input: ["text"],
14941
15498
  cost: {
14942
- input: 0.049999999999999996,
14943
- output: 0.19999999999999998,
14944
- cacheRead: 0.03,
15499
+ input: 0.06,
15500
+ output: 0.24,
15501
+ cacheRead: 0,
14945
15502
  cacheWrite: 0,
14946
15503
  },
14947
15504
  contextWindow: 262144,
@@ -15041,13 +15598,13 @@ export const MODELS = {
15041
15598
  reasoning: true,
15042
15599
  input: ["text"],
15043
15600
  cost: {
15044
- input: 0.0595,
15045
- output: 0.16999999999999998,
15046
- cacheRead: 0.02975,
15601
+ input: 0.07,
15602
+ output: 0.19999999999999998,
15603
+ cacheRead: 0.04,
15047
15604
  cacheWrite: 0,
15048
15605
  },
15049
15606
  contextWindow: 262144,
15050
- maxTokens: 131072,
15607
+ maxTokens: 235929,
15051
15608
  },
15052
15609
  "nvidia/nemotron-3.5-lightning:free": {
15053
15610
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15978,10 +16535,10 @@ export const MODELS = {
15978
16535
  reasoning: true,
15979
16536
  input: ["text", "image"],
15980
16537
  cost: {
15981
- input: 4,
15982
- output: 20,
15983
- cacheRead: 0.39999999999999997,
15984
- cacheWrite: 5,
16538
+ input: 2,
16539
+ output: 10,
16540
+ cacheRead: 0.19999999999999998,
16541
+ cacheWrite: 2.5,
15985
16542
  },
15986
16543
  contextWindow: 1050000,
15987
16544
  maxTokens: 128000,
@@ -16343,6 +16900,40 @@ export const MODELS = {
16343
16900
  contextWindow: 1050000,
16344
16901
  maxTokens: 128000,
16345
16902
  },
16903
+ "openai/gpt-6.1-sol-pro:batch": {
16904
+ id: "openai/gpt-6.1-sol-pro:batch",
16905
+ name: "OpenAI: GPT-6.1 Sol Pro (batch)",
16906
+ api: "openai-completions",
16907
+ provider: "openrouter",
16908
+ baseUrl: "https://openrouter.ai/api/v1",
16909
+ reasoning: true,
16910
+ input: ["text", "image"],
16911
+ cost: {
16912
+ input: 1,
16913
+ output: 5,
16914
+ cacheRead: 0.049999999999999996,
16915
+ cacheWrite: 1.25,
16916
+ },
16917
+ contextWindow: 1050000,
16918
+ maxTokens: 128000,
16919
+ },
16920
+ "openai/gpt-6.1-sol:batch": {
16921
+ id: "openai/gpt-6.1-sol:batch",
16922
+ name: "OpenAI: GPT-6.1 Sol (batch)",
16923
+ api: "openai-completions",
16924
+ provider: "openrouter",
16925
+ baseUrl: "https://openrouter.ai/api/v1",
16926
+ reasoning: true,
16927
+ input: ["text", "image"],
16928
+ cost: {
16929
+ input: 1,
16930
+ output: 5,
16931
+ cacheRead: 0.049999999999999996,
16932
+ cacheWrite: 1.25,
16933
+ },
16934
+ contextWindow: 1050000,
16935
+ maxTokens: 128000,
16936
+ },
16346
16937
  "openai/gpt-audio": {
16347
16938
  id: "openai/gpt-audio",
16348
16939
  name: "OpenAI: GPT Audio",
@@ -16853,23 +17444,6 @@ export const MODELS = {
16853
17444
  contextWindow: 1000000,
16854
17445
  maxTokens: 32768,
16855
17446
  },
16856
- "qwen/qwen-plus-2025-07-28": {
16857
- id: "qwen/qwen-plus-2025-07-28",
16858
- name: "Qwen: Qwen Plus 0728",
16859
- api: "openai-completions",
16860
- provider: "openrouter",
16861
- baseUrl: "https://openrouter.ai/api/v1",
16862
- reasoning: false,
16863
- input: ["text"],
16864
- cost: {
16865
- input: 0.26,
16866
- output: 0.78,
16867
- cacheRead: 0,
16868
- cacheWrite: 0,
16869
- },
16870
- contextWindow: 1000000,
16871
- maxTokens: 32768,
16872
- },
16873
17447
  "qwen/qwen3-14b": {
16874
17448
  id: "qwen/qwen3-14b",
16875
17449
  name: "Qwen: Qwen3 14B",
@@ -16879,30 +17453,13 @@ export const MODELS = {
16879
17453
  reasoning: true,
16880
17454
  input: ["text"],
16881
17455
  cost: {
16882
- input: 0.12,
16883
- output: 0.24,
16884
- cacheRead: 0,
16885
- cacheWrite: 0,
16886
- },
16887
- contextWindow: 131072,
16888
- maxTokens: 16384,
16889
- },
16890
- "qwen/qwen3-235b-a22b": {
16891
- id: "qwen/qwen3-235b-a22b",
16892
- name: "Qwen: Qwen3 235B A22B",
16893
- api: "openai-completions",
16894
- provider: "openrouter",
16895
- baseUrl: "https://openrouter.ai/api/v1",
16896
- reasoning: true,
16897
- input: ["text"],
16898
- cost: {
16899
- input: 0.45499999999999996,
16900
- output: 1.8199999999999998,
17456
+ input: 0.09999999999999999,
17457
+ output: 0.22,
16901
17458
  cacheRead: 0,
16902
17459
  cacheWrite: 0,
16903
17460
  },
16904
- contextWindow: 131072,
16905
- maxTokens: 8192,
17461
+ contextWindow: 40960,
17462
+ maxTokens: 36864,
16906
17463
  },
16907
17464
  "qwen/qwen3-235b-a22b-2507": {
16908
17465
  id: "qwen/qwen3-235b-a22b-2507",
@@ -16913,13 +17470,13 @@ export const MODELS = {
16913
17470
  reasoning: false,
16914
17471
  input: ["text"],
16915
17472
  cost: {
16916
- input: 0.0875,
16917
- output: 0.35,
16918
- cacheRead: 0.0175,
17473
+ input: 0.09,
17474
+ output: 0.55,
17475
+ cacheRead: 0,
16919
17476
  cacheWrite: 0,
16920
17477
  },
16921
17478
  contextWindow: 262144,
16922
- maxTokens: 235929,
17479
+ maxTokens: 16384,
16923
17480
  },
16924
17481
  "qwen/qwen3-235b-a22b-thinking-2507": {
16925
17482
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -16930,13 +17487,13 @@ export const MODELS = {
16930
17487
  reasoning: true,
16931
17488
  input: ["text"],
16932
17489
  cost: {
16933
- input: 0.22999999999999998,
16934
- output: 2.3,
17490
+ input: 0.44999999999999996,
17491
+ output: 3.5,
16935
17492
  cacheRead: 0,
16936
17493
  cacheWrite: 0,
16937
17494
  },
16938
- contextWindow: 131072,
16939
- maxTokens: 117964,
17495
+ contextWindow: 128000,
17496
+ maxTokens: 16384,
16940
17497
  },
16941
17498
  "qwen/qwen3-30b-a3b": {
16942
17499
  id: "qwen/qwen3-30b-a3b",
@@ -16952,7 +17509,7 @@ export const MODELS = {
16952
17509
  cacheRead: 0,
16953
17510
  cacheWrite: 0,
16954
17511
  },
16955
- contextWindow: 131072,
17512
+ contextWindow: 40960,
16956
17513
  maxTokens: 16384,
16957
17514
  },
16958
17515
  "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -16964,30 +17521,13 @@ export const MODELS = {
16964
17521
  reasoning: false,
16965
17522
  input: ["text"],
16966
17523
  cost: {
16967
- input: 0.04815,
16968
- output: 0.19305,
17524
+ input: 0.09999999999999999,
17525
+ output: 0.3,
16969
17526
  cacheRead: 0,
16970
17527
  cacheWrite: 0,
16971
17528
  },
16972
17529
  contextWindow: 262144,
16973
- maxTokens: 32000,
16974
- },
16975
- "qwen/qwen3-30b-a3b-thinking-2507": {
16976
- id: "qwen/qwen3-30b-a3b-thinking-2507",
16977
- name: "Qwen: Qwen3 30B A3B Thinking 2507",
16978
- api: "openai-completions",
16979
- provider: "openrouter",
16980
- baseUrl: "https://openrouter.ai/api/v1",
16981
- reasoning: true,
16982
- input: ["text"],
16983
- cost: {
16984
- input: 0.19999999999999998,
16985
- output: 2.4,
16986
- cacheRead: 0,
16987
- cacheWrite: 0,
16988
- },
16989
- contextWindow: 81920,
16990
- maxTokens: 32768,
17530
+ maxTokens: 235929,
16991
17531
  },
16992
17532
  "qwen/qwen3-32b": {
16993
17533
  id: "qwen/qwen3-32b",
@@ -17006,23 +17546,6 @@ export const MODELS = {
17006
17546
  contextWindow: 131072,
17007
17547
  maxTokens: 16384,
17008
17548
  },
17009
- "qwen/qwen3-8b": {
17010
- id: "qwen/qwen3-8b",
17011
- name: "Qwen: Qwen3 8B",
17012
- api: "openai-completions",
17013
- provider: "openrouter",
17014
- baseUrl: "https://openrouter.ai/api/v1",
17015
- reasoning: true,
17016
- input: ["text"],
17017
- cost: {
17018
- input: 0.117,
17019
- output: 0.45499999999999996,
17020
- cacheRead: 0,
17021
- cacheWrite: 0,
17022
- },
17023
- contextWindow: 131072,
17024
- maxTokens: 8192,
17025
- },
17026
17549
  "qwen/qwen3-coder": {
17027
17550
  id: "qwen/qwen3-coder",
17028
17551
  name: "Qwen: Qwen3 Coder 480B A35B",
@@ -17091,57 +17614,6 @@ export const MODELS = {
17091
17614
  contextWindow: 262144,
17092
17615
  maxTokens: 235929,
17093
17616
  },
17094
- "qwen/qwen3-coder-plus": {
17095
- id: "qwen/qwen3-coder-plus",
17096
- name: "Qwen: Qwen3 Coder Plus",
17097
- api: "openai-completions",
17098
- provider: "openrouter",
17099
- baseUrl: "https://openrouter.ai/api/v1",
17100
- reasoning: false,
17101
- input: ["text"],
17102
- cost: {
17103
- input: 0.65,
17104
- output: 3.25,
17105
- cacheRead: 0.13,
17106
- cacheWrite: 0.8125,
17107
- },
17108
- contextWindow: 1000000,
17109
- maxTokens: 65536,
17110
- },
17111
- "qwen/qwen3-max": {
17112
- id: "qwen/qwen3-max",
17113
- name: "Qwen: Qwen3 Max",
17114
- api: "openai-completions",
17115
- provider: "openrouter",
17116
- baseUrl: "https://openrouter.ai/api/v1",
17117
- reasoning: false,
17118
- input: ["text"],
17119
- cost: {
17120
- input: 0.78,
17121
- output: 3.9,
17122
- cacheRead: 0.156,
17123
- cacheWrite: 0.975,
17124
- },
17125
- contextWindow: 262144,
17126
- maxTokens: 65536,
17127
- },
17128
- "qwen/qwen3-max-thinking": {
17129
- id: "qwen/qwen3-max-thinking",
17130
- name: "Qwen: Qwen3 Max Thinking",
17131
- api: "openai-completions",
17132
- provider: "openrouter",
17133
- baseUrl: "https://openrouter.ai/api/v1",
17134
- reasoning: true,
17135
- input: ["text"],
17136
- cost: {
17137
- input: 0.78,
17138
- output: 3.9,
17139
- cacheRead: 0,
17140
- cacheWrite: 0,
17141
- },
17142
- contextWindow: 262144,
17143
- maxTokens: 65536,
17144
- },
17145
17617
  "qwen/qwen3-next-80b-a3b-instruct": {
17146
17618
  id: "qwen/qwen3-next-80b-a3b-instruct",
17147
17619
  name: "Qwen: Qwen3 Next 80B A3B Instruct",
@@ -17174,7 +17646,7 @@ export const MODELS = {
17174
17646
  cacheWrite: 0,
17175
17647
  },
17176
17648
  contextWindow: 262144,
17177
- maxTokens: 32768,
17649
+ maxTokens: 235929,
17178
17650
  },
17179
17651
  "qwen/qwen3-vl-235b-a22b-instruct": {
17180
17652
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -17193,23 +17665,6 @@ export const MODELS = {
17193
17665
  contextWindow: 262144,
17194
17666
  maxTokens: 32768,
17195
17667
  },
17196
- "qwen/qwen3-vl-235b-a22b-thinking": {
17197
- id: "qwen/qwen3-vl-235b-a22b-thinking",
17198
- name: "Qwen: Qwen3 VL 235B A22B Thinking",
17199
- api: "openai-completions",
17200
- provider: "openrouter",
17201
- baseUrl: "https://openrouter.ai/api/v1",
17202
- reasoning: true,
17203
- input: ["text", "image"],
17204
- cost: {
17205
- input: 0.39999999999999997,
17206
- output: 4,
17207
- cacheRead: 0,
17208
- cacheWrite: 0,
17209
- },
17210
- contextWindow: 131072,
17211
- maxTokens: 32768,
17212
- },
17213
17668
  "qwen/qwen3-vl-30b-a3b-instruct": {
17214
17669
  id: "qwen/qwen3-vl-30b-a3b-instruct",
17215
17670
  name: "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -17236,30 +17691,13 @@ export const MODELS = {
17236
17691
  reasoning: true,
17237
17692
  input: ["text", "image"],
17238
17693
  cost: {
17239
- input: 0.19999999999999998,
17240
- output: 2.4,
17694
+ input: 0.29,
17695
+ output: 1,
17241
17696
  cacheRead: 0,
17242
17697
  cacheWrite: 0,
17243
17698
  },
17244
17699
  contextWindow: 262144,
17245
- maxTokens: 32768,
17246
- },
17247
- "qwen/qwen3-vl-32b-instruct": {
17248
- id: "qwen/qwen3-vl-32b-instruct",
17249
- name: "Qwen: Qwen3 VL 32B Instruct",
17250
- api: "openai-completions",
17251
- provider: "openrouter",
17252
- baseUrl: "https://openrouter.ai/api/v1",
17253
- reasoning: false,
17254
- input: ["text", "image"],
17255
- cost: {
17256
- input: 0.10400000000000001,
17257
- output: 0.41600000000000004,
17258
- cacheRead: 0,
17259
- cacheWrite: 0,
17260
- },
17261
- contextWindow: 131072,
17262
- maxTokens: 32768,
17700
+ maxTokens: 235929,
17263
17701
  },
17264
17702
  "qwen/qwen3-vl-8b-instruct": {
17265
17703
  id: "qwen/qwen3-vl-8b-instruct",
@@ -17270,30 +17708,13 @@ export const MODELS = {
17270
17708
  reasoning: false,
17271
17709
  input: ["text", "image"],
17272
17710
  cost: {
17273
- input: 0.117,
17274
- output: 0.45499999999999996,
17275
- cacheRead: 0,
17711
+ input: 0.25,
17712
+ output: 0.75,
17713
+ cacheRead: 0.12,
17276
17714
  cacheWrite: 0,
17277
17715
  },
17278
17716
  contextWindow: 262144,
17279
- maxTokens: 32768,
17280
- },
17281
- "qwen/qwen3-vl-8b-thinking": {
17282
- id: "qwen/qwen3-vl-8b-thinking",
17283
- name: "Qwen: Qwen3 VL 8B Thinking",
17284
- api: "openai-completions",
17285
- provider: "openrouter",
17286
- baseUrl: "https://openrouter.ai/api/v1",
17287
- reasoning: true,
17288
- input: ["text", "image"],
17289
- cost: {
17290
- input: 0.18,
17291
- output: 2.0999999999999996,
17292
- cacheRead: 0,
17293
- cacheWrite: 0,
17294
- },
17295
- contextWindow: 131072,
17296
- maxTokens: 32768,
17717
+ maxTokens: 235929,
17297
17718
  },
17298
17719
  "qwen/qwen3.5-122b-a10b": {
17299
17720
  id: "qwen/qwen3.5-122b-a10b",
@@ -17321,13 +17742,13 @@ export const MODELS = {
17321
17742
  reasoning: true,
17322
17743
  input: ["text", "image"],
17323
17744
  cost: {
17324
- input: 0.195,
17325
- output: 1.56,
17745
+ input: 0.26,
17746
+ output: 2.6,
17326
17747
  cacheRead: 0,
17327
17748
  cacheWrite: 0,
17328
17749
  },
17329
17750
  contextWindow: 262144,
17330
- maxTokens: 65536,
17751
+ maxTokens: 81920,
17331
17752
  },
17332
17753
  "qwen/qwen3.5-35b-a3b": {
17333
17754
  id: "qwen/qwen3.5-35b-a3b",
@@ -17338,13 +17759,13 @@ export const MODELS = {
17338
17759
  reasoning: true,
17339
17760
  input: ["text", "image"],
17340
17761
  cost: {
17341
- input: 0.15,
17342
- output: 1,
17343
- cacheRead: 0.049999999999999996,
17762
+ input: 0.08,
17763
+ output: 0.75,
17764
+ cacheRead: 0.04,
17344
17765
  cacheWrite: 0,
17345
17766
  },
17346
17767
  contextWindow: 262144,
17347
- maxTokens: 235929,
17768
+ maxTokens: 32768,
17348
17769
  },
17349
17770
  "qwen/qwen3.5-397b-a17b": {
17350
17771
  id: "qwen/qwen3.5-397b-a17b",
@@ -17482,23 +17903,6 @@ export const MODELS = {
17482
17903
  contextWindow: 1000000,
17483
17904
  maxTokens: 65536,
17484
17905
  },
17485
- "qwen/qwen3.6-max-preview": {
17486
- id: "qwen/qwen3.6-max-preview",
17487
- name: "Qwen: Qwen3.6 Max Preview",
17488
- api: "openai-completions",
17489
- provider: "openrouter",
17490
- baseUrl: "https://openrouter.ai/api/v1",
17491
- reasoning: true,
17492
- input: ["text"],
17493
- cost: {
17494
- input: 1.0270000000000001,
17495
- output: 6.162,
17496
- cacheRead: 0,
17497
- cacheWrite: 1.28375,
17498
- },
17499
- contextWindow: 262144,
17500
- maxTokens: 65536,
17501
- },
17502
17906
  "qwen/qwen3.6-plus": {
17503
17907
  id: "qwen/qwen3.6-plus",
17504
17908
  name: "Qwen: Qwen3.6 Plus",
@@ -17586,37 +17990,20 @@ export const MODELS = {
17586
17990
  },
17587
17991
  "qwen/qwen3.8-27b": {
17588
17992
  id: "qwen/qwen3.8-27b",
17589
- name: "Qwen: Qwen3.8 27B",
17590
- api: "openai-completions",
17591
- provider: "openrouter",
17592
- baseUrl: "https://openrouter.ai/api/v1",
17593
- reasoning: true,
17594
- input: ["text", "image"],
17595
- cost: {
17596
- input: 0.42,
17597
- output: 3,
17598
- cacheRead: 0.08499999999999999,
17599
- cacheWrite: 0,
17600
- },
17601
- contextWindow: 1000000,
17602
- maxTokens: 131072,
17603
- },
17604
- "qwen/qwen3.8-27b:free": {
17605
- id: "qwen/qwen3.8-27b:free",
17606
- name: "Qwen: Qwen3.8 27B (free)",
17993
+ name: "Qwen: Qwen3.8 27B",
17607
17994
  api: "openai-completions",
17608
17995
  provider: "openrouter",
17609
17996
  baseUrl: "https://openrouter.ai/api/v1",
17610
17997
  reasoning: true,
17611
17998
  input: ["text", "image"],
17612
17999
  cost: {
17613
- input: 0,
17614
- output: 0,
17615
- cacheRead: 0,
17616
- cacheWrite: 0,
18000
+ input: 0.425,
18001
+ output: 2.5500000000000003,
18002
+ cacheRead: 0.08499999999999999,
18003
+ cacheWrite: 0.53125,
17617
18004
  },
17618
- contextWindow: 262144,
17619
- maxTokens: 235929,
18005
+ contextWindow: 1000000,
18006
+ maxTokens: 131072,
17620
18007
  },
17621
18008
  "qwen/qwen3.8-flash": {
17622
18009
  id: "qwen/qwen3.8-flash",
@@ -17630,7 +18017,7 @@ export const MODELS = {
17630
18017
  input: 0.15,
17631
18018
  output: 0.47,
17632
18019
  cacheRead: 0.016,
17633
- cacheWrite: 0.19999999999999998,
18020
+ cacheWrite: 0,
17634
18021
  },
17635
18022
  contextWindow: 1000000,
17636
18023
  maxTokens: 131072,
@@ -17647,7 +18034,7 @@ export const MODELS = {
17647
18034
  input: 2,
17648
18035
  output: 6,
17649
18036
  cacheRead: 0.25,
17650
- cacheWrite: 2.5,
18037
+ cacheWrite: 0,
17651
18038
  },
17652
18039
  contextWindow: 1000000,
17653
18040
  maxTokens: 131072,
@@ -17788,40 +18175,6 @@ export const MODELS = {
17788
18175
  contextWindow: 262144,
17789
18176
  maxTokens: 65536,
17790
18177
  },
17791
- "sao10k/l3.1-euryale-70b": {
17792
- id: "sao10k/l3.1-euryale-70b",
17793
- name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
17794
- api: "openai-completions",
17795
- provider: "openrouter",
17796
- baseUrl: "https://openrouter.ai/api/v1",
17797
- reasoning: false,
17798
- input: ["text"],
17799
- cost: {
17800
- input: 0.85,
17801
- output: 0.85,
17802
- cacheRead: 0,
17803
- cacheWrite: 0,
17804
- },
17805
- contextWindow: 131072,
17806
- maxTokens: 16384,
17807
- },
17808
- "stealth/space-bunny-alpha": {
17809
- id: "stealth/space-bunny-alpha",
17810
- name: "Space Bunny Alpha",
17811
- api: "openai-completions",
17812
- provider: "openrouter",
17813
- baseUrl: "https://openrouter.ai/api/v1",
17814
- reasoning: true,
17815
- input: ["text", "image"],
17816
- cost: {
17817
- input: 0,
17818
- output: 0,
17819
- cacheRead: 0,
17820
- cacheWrite: 0,
17821
- },
17822
- contextWindow: 1000000,
17823
- maxTokens: 524288,
17824
- },
17825
18178
  "stepfun/step-3.5-flash": {
17826
18179
  id: "stepfun/step-3.5-flash",
17827
18180
  name: "StepFun: Step 3.5 Flash",
@@ -17856,6 +18209,23 @@ export const MODELS = {
17856
18209
  contextWindow: 262144,
17857
18210
  maxTokens: 230400,
17858
18211
  },
18212
+ "stepfun/step-5-preview": {
18213
+ id: "stepfun/step-5-preview",
18214
+ name: "StepFun: Step 5 Preview",
18215
+ api: "openai-completions",
18216
+ provider: "openrouter",
18217
+ baseUrl: "https://openrouter.ai/api/v1",
18218
+ reasoning: true,
18219
+ input: ["text", "image"],
18220
+ cost: {
18221
+ input: 1,
18222
+ output: 2.7,
18223
+ cacheRead: 0.049999999999999996,
18224
+ cacheWrite: 0,
18225
+ },
18226
+ contextWindow: 1000000,
18227
+ maxTokens: 64000,
18228
+ },
17859
18229
  "tencent/hy3": {
17860
18230
  id: "tencent/hy3",
17861
18231
  name: "Tencent: Hy3",
@@ -17899,13 +18269,13 @@ export const MODELS = {
17899
18269
  reasoning: true,
17900
18270
  input: ["text", "image"],
17901
18271
  cost: {
17902
- input: 0.95,
18272
+ input: 1,
17903
18273
  output: 4.05,
17904
- cacheRead: 0.16,
18274
+ cacheRead: 0.16999999999999998,
17905
18275
  cacheWrite: 0,
17906
18276
  },
17907
18277
  contextWindow: 524288,
17908
- maxTokens: 262144,
18278
+ maxTokens: 471859,
17909
18279
  },
17910
18280
  "thinkingmachines/inkling-small": {
17911
18281
  id: "thinkingmachines/inkling-small",
@@ -18324,13 +18694,13 @@ export const MODELS = {
18324
18694
  reasoning: true,
18325
18695
  input: ["text"],
18326
18696
  cost: {
18327
- input: 0.43,
18328
- output: 1.75,
18329
- cacheRead: 0.08,
18697
+ input: 0.5,
18698
+ output: 2,
18699
+ cacheRead: 0.09999999999999999,
18330
18700
  cacheWrite: 0,
18331
18701
  },
18332
18702
  contextWindow: 204800,
18333
- maxTokens: 16384,
18703
+ maxTokens: 131072,
18334
18704
  },
18335
18705
  "z-ai/glm-4.6v": {
18336
18706
  id: "z-ai/glm-4.6v",
@@ -18343,7 +18713,7 @@ export const MODELS = {
18343
18713
  cost: {
18344
18714
  input: 0.3,
18345
18715
  output: 0.8999999999999999,
18346
- cacheRead: 0.049999999999999996,
18716
+ cacheRead: 0.055,
18347
18717
  cacheWrite: 0,
18348
18718
  },
18349
18719
  contextWindow: 131072,
@@ -18426,13 +18796,13 @@ export const MODELS = {
18426
18796
  reasoning: true,
18427
18797
  input: ["text"],
18428
18798
  cost: {
18429
- input: 1.4,
18430
- output: 4.4,
18431
- cacheRead: 0.26,
18799
+ input: 0.966,
18800
+ output: 3.036,
18801
+ cacheRead: 0.1794,
18432
18802
  cacheWrite: 0,
18433
18803
  },
18434
18804
  contextWindow: 204800,
18435
- maxTokens: 131072,
18805
+ maxTokens: 128000,
18436
18806
  },
18437
18807
  "z-ai/glm-5.2": {
18438
18808
  id: "z-ai/glm-5.2",
@@ -18443,9 +18813,9 @@ export const MODELS = {
18443
18813
  reasoning: true,
18444
18814
  input: ["text"],
18445
18815
  cost: {
18446
- input: 0.41,
18447
- output: 3.9899999999999998,
18448
- cacheRead: 0.26,
18816
+ input: 0.06,
18817
+ output: 7,
18818
+ cacheRead: 0.059,
18449
18819
  cacheWrite: 0,
18450
18820
  },
18451
18821
  contextWindow: 1048576,
@@ -18460,13 +18830,13 @@ export const MODELS = {
18460
18830
  reasoning: true,
18461
18831
  input: ["text"],
18462
18832
  cost: {
18463
- input: 1.4,
18464
- output: 4.4,
18465
- cacheRead: 0.14,
18833
+ input: 0.039,
18834
+ output: 4.8,
18835
+ cacheRead: 0.038000000000000006,
18466
18836
  cacheWrite: 0,
18467
18837
  },
18468
18838
  contextWindow: 1048576,
18469
- maxTokens: 131072,
18839
+ maxTokens: 943718,
18470
18840
  },
18471
18841
  "z-ai/glm-5.3-flash": {
18472
18842
  id: "z-ai/glm-5.3-flash",
@@ -18597,13 +18967,13 @@ export const MODELS = {
18597
18967
  reasoning: true,
18598
18968
  input: ["text", "image"],
18599
18969
  cost: {
18600
- input: 1,
18601
- output: 5,
18602
- cacheRead: 0.09999999999999999,
18603
- cacheWrite: 1.25,
18970
+ input: 0.09999999999999999,
18971
+ output: 0.5,
18972
+ cacheRead: 0.01,
18973
+ cacheWrite: 0.125,
18604
18974
  },
18605
- contextWindow: 200000,
18606
- maxTokens: 64000,
18975
+ contextWindow: 1000000,
18976
+ maxTokens: 128000,
18607
18977
  },
18608
18978
  "~anthropic/claude-opus-latest": {
18609
18979
  id: "~anthropic/claude-opus-latest",
@@ -18633,7 +19003,7 @@ export const MODELS = {
18633
19003
  cost: {
18634
19004
  input: 2,
18635
19005
  output: 10,
18636
- cacheRead: 0.19999999999999998,
19006
+ cacheRead: 0.09999999999999999,
18637
19007
  cacheWrite: 2.5,
18638
19008
  },
18639
19009
  contextWindow: 1000000,
@@ -18648,9 +19018,9 @@ export const MODELS = {
18648
19018
  reasoning: true,
18649
19019
  input: ["text", "image"],
18650
19020
  cost: {
18651
- input: 0.02,
19021
+ input: 0.0015,
18652
19022
  output: 0.6,
18653
- cacheRead: 0.01,
19023
+ cacheRead: 0.005,
18654
19024
  cacheWrite: 0,
18655
19025
  },
18656
19026
  contextWindow: 1048576,
@@ -18665,9 +19035,9 @@ export const MODELS = {
18665
19035
  reasoning: true,
18666
19036
  input: ["text"],
18667
19037
  cost: {
18668
- input: 0.22,
18669
- output: 4.199999999999999,
18670
- cacheRead: 0.14,
19038
+ input: 0.3,
19039
+ output: 5,
19040
+ cacheRead: 0.219,
18671
19041
  cacheWrite: 0,
18672
19042
  },
18673
19043
  contextWindow: 1048576,
@@ -18684,9 +19054,9 @@ export const MODELS = {
18684
19054
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18685
19055
  input: ["text"],
18686
19056
  cost: {
18687
- input: 0.0188,
19057
+ input: 0.0068,
18688
19058
  output: 1.28,
18689
- cacheRead: 0.0188,
19059
+ cacheRead: 0.0068,
18690
19060
  cacheWrite: 0,
18691
19061
  },
18692
19062
  contextWindow: 1048576,
@@ -18735,9 +19105,9 @@ export const MODELS = {
18735
19105
  reasoning: true,
18736
19106
  input: ["text", "image"],
18737
19107
  cost: {
18738
- input: 0.9895,
18739
- output: 13,
18740
- cacheRead: 0.44999999999999996,
19108
+ input: 0.39999999999999997,
19109
+ output: 15,
19110
+ cacheRead: 0.3,
18741
19111
  cacheWrite: 0,
18742
19112
  },
18743
19113
  contextWindow: 1048576,
@@ -18854,9 +19224,9 @@ export const MODELS = {
18854
19224
  reasoning: true,
18855
19225
  input: ["text", "image"],
18856
19226
  cost: {
18857
- input: 0.035,
19227
+ input: 0.04,
18858
19228
  output: 0.5,
18859
- cacheRead: 0.035,
19229
+ cacheRead: 0.012499999999999999,
18860
19230
  cacheWrite: 0,
18861
19231
  },
18862
19232
  contextWindow: 1048576,
@@ -18871,13 +19241,13 @@ export const MODELS = {
18871
19241
  reasoning: true,
18872
19242
  input: ["text"],
18873
19243
  cost: {
18874
- input: 0.12,
18875
- output: 4,
18876
- cacheRead: 0.08,
19244
+ input: 0.039,
19245
+ output: 4.8,
19246
+ cacheRead: 0.038000000000000006,
18877
19247
  cacheWrite: 0,
18878
19248
  },
18879
19249
  contextWindow: 1048576,
18880
- maxTokens: 131072,
19250
+ maxTokens: 943718,
18881
19251
  },
18882
19252
  },
18883
19253
  "together": {
@@ -19226,7 +19596,7 @@ export const MODELS = {
19226
19596
  api: "anthropic-messages",
19227
19597
  provider: "vercel-ai-gateway",
19228
19598
  baseUrl: "https://ai-gateway.vercel.sh",
19229
- reasoning: true,
19599
+ reasoning: false,
19230
19600
  input: ["text"],
19231
19601
  cost: {
19232
19602
  input: 0.22,
@@ -19885,6 +20255,23 @@ export const MODELS = {
19885
20255
  contextWindow: 200000,
19886
20256
  maxTokens: 64000,
19887
20257
  },
20258
+ "anthropic/claude-haiku-5.5": {
20259
+ id: "anthropic/claude-haiku-5.5",
20260
+ name: "Claude Haiku 5.5",
20261
+ api: "anthropic-messages",
20262
+ provider: "vercel-ai-gateway",
20263
+ baseUrl: "https://ai-gateway.vercel.sh",
20264
+ reasoning: true,
20265
+ input: ["text", "image"],
20266
+ cost: {
20267
+ input: 0.09999999999999999,
20268
+ output: 0.5,
20269
+ cacheRead: 0.01,
20270
+ cacheWrite: 0.125,
20271
+ },
20272
+ contextWindow: 1000000,
20273
+ maxTokens: 128000,
20274
+ },
19888
20275
  "anthropic/claude-opus-4": {
19889
20276
  id: "anthropic/claude-opus-4",
19890
20277
  name: "Claude Opus 4",
@@ -20138,7 +20525,7 @@ export const MODELS = {
20138
20525
  cost: {
20139
20526
  input: 2,
20140
20527
  output: 10,
20141
- cacheRead: 0.19999999999999998,
20528
+ cacheRead: 0.09999999999999999,
20142
20529
  cacheWrite: 2.5,
20143
20530
  },
20144
20531
  contextWindow: 1000000,
@@ -20154,7 +20541,7 @@ export const MODELS = {
20154
20541
  input: ["text"],
20155
20542
  cost: {
20156
20543
  input: 0.25,
20157
- output: 0.8999999999999999,
20544
+ output: 0.7999999999999999,
20158
20545
  cacheRead: 0,
20159
20546
  cacheWrite: 0,
20160
20547
  },
@@ -20212,6 +20599,23 @@ export const MODELS = {
20212
20599
  contextWindow: 262144,
20213
20600
  maxTokens: 262144,
20214
20601
  },
20602
+ "callstack/apex": {
20603
+ id: "callstack/apex",
20604
+ name: "Apex",
20605
+ api: "anthropic-messages",
20606
+ provider: "vercel-ai-gateway",
20607
+ baseUrl: "https://ai-gateway.vercel.sh",
20608
+ reasoning: true,
20609
+ input: ["text", "image"],
20610
+ cost: {
20611
+ input: 0.5,
20612
+ output: 3,
20613
+ cacheRead: 0.19999999999999998,
20614
+ cacheWrite: 0,
20615
+ },
20616
+ contextWindow: 262144,
20617
+ maxTokens: 131072,
20618
+ },
20215
20619
  "cohere/command-a": {
20216
20620
  id: "cohere/command-a",
20217
20621
  name: "Command A",
@@ -20263,23 +20667,6 @@ export const MODELS = {
20263
20667
  contextWindow: 163840,
20264
20668
  maxTokens: 128000,
20265
20669
  },
20266
- "deepseek/deepseek-v3.1-terminus": {
20267
- id: "deepseek/deepseek-v3.1-terminus",
20268
- name: "DeepSeek V3.1 Terminus",
20269
- api: "anthropic-messages",
20270
- provider: "vercel-ai-gateway",
20271
- baseUrl: "https://ai-gateway.vercel.sh",
20272
- reasoning: true,
20273
- input: ["text"],
20274
- cost: {
20275
- input: 0.27,
20276
- output: 1,
20277
- cacheRead: 0.135,
20278
- cacheWrite: 0,
20279
- },
20280
- contextWindow: 131072,
20281
- maxTokens: 65536,
20282
- },
20283
20670
  "deepseek/deepseek-v3.2": {
20284
20671
  id: "deepseek/deepseek-v3.2",
20285
20672
  name: "DeepSeek V3.2",
@@ -20416,23 +20803,6 @@ export const MODELS = {
20416
20803
  contextWindow: 1048576,
20417
20804
  maxTokens: 32768,
20418
20805
  },
20419
- "deepseek/deepseek-v4.1-flash-fast": {
20420
- id: "deepseek/deepseek-v4.1-flash-fast",
20421
- name: "DeepSeek V4.1 Flash Fast",
20422
- api: "anthropic-messages",
20423
- provider: "vercel-ai-gateway",
20424
- baseUrl: "https://ai-gateway.vercel.sh",
20425
- reasoning: true,
20426
- input: ["text", "image"],
20427
- cost: {
20428
- input: 0.3,
20429
- output: 1.2,
20430
- cacheRead: 0.006,
20431
- cacheWrite: 0,
20432
- },
20433
- contextWindow: 1048576,
20434
- maxTokens: 1000000,
20435
- },
20436
20806
  "fireworks/ember-1": {
20437
20807
  id: "fireworks/ember-1",
20438
20808
  name: "Ember-1",
@@ -20765,26 +21135,9 @@ export const MODELS = {
20765
21135
  reasoning: true,
20766
21136
  input: ["text"],
20767
21137
  cost: {
20768
- input: 0,
20769
- output: 0,
20770
- cacheRead: 0,
20771
- cacheWrite: 0,
20772
- },
20773
- contextWindow: 256000,
20774
- maxTokens: 32000,
20775
- },
20776
- "inclusionai/ling-3.0-flash-sante-free": {
20777
- id: "inclusionai/ling-3.0-flash-sante-free",
20778
- name: "Ling 3.0 Flash Sante (Free)",
20779
- api: "anthropic-messages",
20780
- provider: "vercel-ai-gateway",
20781
- baseUrl: "https://ai-gateway.vercel.sh",
20782
- reasoning: true,
20783
- input: ["text"],
20784
- cost: {
20785
- input: 0,
20786
- output: 0,
20787
- cacheRead: 0,
21138
+ input: 0.075,
21139
+ output: 0.22,
21140
+ cacheRead: 0.015,
20788
21141
  cacheWrite: 0,
20789
21142
  },
20790
21143
  contextWindow: 256000,
@@ -21283,6 +21636,23 @@ export const MODELS = {
21283
21636
  contextWindow: 262144,
21284
21637
  maxTokens: 256000,
21285
21638
  },
21639
+ "mistral/mistral-large-4": {
21640
+ id: "mistral/mistral-large-4",
21641
+ name: "Mistral Large 4",
21642
+ api: "anthropic-messages",
21643
+ provider: "vercel-ai-gateway",
21644
+ baseUrl: "https://ai-gateway.vercel.sh",
21645
+ reasoning: true,
21646
+ input: ["text", "image"],
21647
+ cost: {
21648
+ input: 0.6799999999999999,
21649
+ output: 2.09,
21650
+ cacheRead: 0.07,
21651
+ cacheWrite: 0,
21652
+ },
21653
+ contextWindow: 524288,
21654
+ maxTokens: 262144,
21655
+ },
21286
21656
  "mistral/mistral-medium-3.5": {
21287
21657
  id: "mistral/mistral-medium-3.5",
21288
21658
  name: "Mistral Medium Latest",
@@ -21309,13 +21679,13 @@ export const MODELS = {
21309
21679
  reasoning: false,
21310
21680
  input: ["text"],
21311
21681
  cost: {
21312
- input: 0.04,
21313
- output: 0.16999999999999998,
21682
+ input: 0.029,
21683
+ output: 0.03,
21314
21684
  cacheRead: 0,
21315
21685
  cacheWrite: 0,
21316
21686
  },
21317
- contextWindow: 60288,
21318
- maxTokens: 16000,
21687
+ contextWindow: 131072,
21688
+ maxTokens: 131072,
21319
21689
  },
21320
21690
  "mistral/mistral-small": {
21321
21691
  id: "mistral/mistral-small",
@@ -21368,23 +21738,6 @@ export const MODELS = {
21368
21738
  contextWindow: 131072,
21369
21739
  maxTokens: 131072,
21370
21740
  },
21371
- "moonshotai/kimi-k2-thinking": {
21372
- id: "moonshotai/kimi-k2-thinking",
21373
- name: "Kimi K2 Thinking",
21374
- api: "anthropic-messages",
21375
- provider: "vercel-ai-gateway",
21376
- baseUrl: "https://ai-gateway.vercel.sh",
21377
- reasoning: true,
21378
- input: ["text"],
21379
- cost: {
21380
- input: 0.47,
21381
- output: 2,
21382
- cacheRead: 0.14100000000000001,
21383
- cacheWrite: 0,
21384
- },
21385
- contextWindow: 216144,
21386
- maxTokens: 216144,
21387
- },
21388
21741
  "moonshotai/kimi-k2.5": {
21389
21742
  id: "moonshotai/kimi-k2.5",
21390
21743
  name: "Kimi K2.5",
@@ -22684,9 +23037,9 @@ export const MODELS = {
22684
23037
  reasoning: true,
22685
23038
  input: ["text"],
22686
23039
  cost: {
22687
- input: 0.09999999999999999,
22688
- output: 0.19999999999999998,
22689
- cacheRead: 0.01,
23040
+ input: 0.09,
23041
+ output: 0.18,
23042
+ cacheRead: 0.009,
22690
23043
  cacheWrite: 0,
22691
23044
  },
22692
23045
  contextWindow: 1000000,
@@ -23032,22 +23385,22 @@ export const MODELS = {
23032
23385
  contextWindow: 256000,
23033
23386
  maxTokens: 256000,
23034
23387
  },
23035
- "stepfun/step-3.5-flash": {
23036
- id: "stepfun/step-3.5-flash",
23037
- name: "StepFun 3.5 Flash",
23388
+ "stealth/glyph-cluster": {
23389
+ id: "stealth/glyph-cluster",
23390
+ name: "Glyph Cluster",
23038
23391
  api: "anthropic-messages",
23039
23392
  provider: "vercel-ai-gateway",
23040
23393
  baseUrl: "https://ai-gateway.vercel.sh",
23041
23394
  reasoning: true,
23042
- input: ["text", "image"],
23395
+ input: ["text"],
23043
23396
  cost: {
23044
- input: 0.09,
23045
- output: 0.3,
23046
- cacheRead: 0.02,
23397
+ input: 0,
23398
+ output: 0,
23399
+ cacheRead: 0,
23047
23400
  cacheWrite: 0,
23048
23401
  },
23049
- contextWindow: 262114,
23050
- maxTokens: 262114,
23402
+ contextWindow: 256000,
23403
+ maxTokens: 256000,
23051
23404
  },
23052
23405
  "stepfun/step-3.7-flash": {
23053
23406
  id: "stepfun/step-3.7-flash",
@@ -23177,9 +23530,9 @@ export const MODELS = {
23177
23530
  reasoning: true,
23178
23531
  input: ["text", "image"],
23179
23532
  cost: {
23180
- input: 0.04,
23181
- output: 1.28,
23182
- cacheRead: 0.04,
23533
+ input: 0.14,
23534
+ output: 0.28,
23535
+ cacheRead: 0.0028,
23183
23536
  cacheWrite: 0,
23184
23537
  },
23185
23538
  contextWindow: 1048576,