@elyracode/ai 0.9.56 → 0.9.57

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.
@@ -78,7 +78,7 @@ export const MODELS = {
78
78
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
79
79
  reasoning: true,
80
80
  thinkingType: "adaptive",
81
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
81
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
82
82
  input: ["text", "image"],
83
83
  cost: {
84
84
  input: 10,
@@ -97,7 +97,7 @@ export const MODELS = {
97
97
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
98
98
  reasoning: true,
99
99
  thinkingType: "adaptive",
100
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
100
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
101
101
  input: ["text", "image"],
102
102
  cost: {
103
103
  input: 10,
@@ -108,6 +108,25 @@ export const MODELS = {
108
108
  contextWindow: 1000000,
109
109
  maxTokens: 128000,
110
110
  },
111
+ "anthropic.claude-fable-5-2": {
112
+ id: "anthropic.claude-fable-5-2",
113
+ name: "Claude Fable 5.2",
114
+ api: "bedrock-converse-stream",
115
+ provider: "amazon-bedrock",
116
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
117
+ reasoning: true,
118
+ thinkingType: "adaptive",
119
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
120
+ input: ["text", "image"],
121
+ cost: {
122
+ input: 8,
123
+ output: 40,
124
+ cacheRead: 0.2,
125
+ cacheWrite: 10,
126
+ },
127
+ contextWindow: 1000000,
128
+ maxTokens: 128000,
129
+ },
111
130
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
112
131
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
113
132
  name: "Claude Haiku 4.5",
@@ -263,6 +282,7 @@ export const MODELS = {
263
282
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
264
283
  reasoning: true,
265
284
  thinkingType: "adaptive",
285
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
266
286
  input: ["text", "image"],
267
287
  cost: {
268
288
  input: 4,
@@ -335,6 +355,7 @@ export const MODELS = {
335
355
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
336
356
  reasoning: true,
337
357
  thinkingType: "adaptive",
358
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
338
359
  input: ["text", "image"],
339
360
  cost: {
340
361
  input: 2,
@@ -533,6 +554,7 @@ export const MODELS = {
533
554
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
534
555
  reasoning: true,
535
556
  thinkingType: "adaptive",
557
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
536
558
  input: ["text", "image"],
537
559
  cost: {
538
560
  input: 4.4,
@@ -605,6 +627,7 @@ export const MODELS = {
605
627
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
606
628
  reasoning: true,
607
629
  thinkingType: "adaptive",
630
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
608
631
  input: ["text", "image"],
609
632
  cost: {
610
633
  input: 2.2,
@@ -742,7 +765,7 @@ export const MODELS = {
742
765
  baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
743
766
  reasoning: true,
744
767
  thinkingType: "adaptive",
745
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
768
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
746
769
  input: ["text", "image"],
747
770
  cost: {
748
771
  input: 11,
@@ -890,6 +913,7 @@ export const MODELS = {
890
913
  baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
891
914
  reasoning: true,
892
915
  thinkingType: "adaptive",
916
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
893
917
  input: ["text", "image"],
894
918
  cost: {
895
919
  input: 4.4,
@@ -980,6 +1004,7 @@ export const MODELS = {
980
1004
  baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
981
1005
  reasoning: true,
982
1006
  thinkingType: "adaptive",
1007
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
983
1008
  input: ["text", "image"],
984
1009
  cost: {
985
1010
  input: 2.2,
@@ -1032,7 +1057,7 @@ export const MODELS = {
1032
1057
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1033
1058
  reasoning: true,
1034
1059
  thinkingType: "adaptive",
1035
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1060
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1036
1061
  input: ["text", "image"],
1037
1062
  cost: {
1038
1063
  input: 10,
@@ -1051,7 +1076,7 @@ export const MODELS = {
1051
1076
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1052
1077
  reasoning: true,
1053
1078
  thinkingType: "adaptive",
1054
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1079
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1055
1080
  input: ["text", "image"],
1056
1081
  cost: {
1057
1082
  input: 10,
@@ -1062,6 +1087,25 @@ export const MODELS = {
1062
1087
  contextWindow: 1000000,
1063
1088
  maxTokens: 128000,
1064
1089
  },
1090
+ "global.anthropic.claude-fable-5-2": {
1091
+ id: "global.anthropic.claude-fable-5-2",
1092
+ name: "Claude Fable 5.2 (Global)",
1093
+ api: "bedrock-converse-stream",
1094
+ provider: "amazon-bedrock",
1095
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1096
+ reasoning: true,
1097
+ thinkingType: "adaptive",
1098
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1099
+ input: ["text", "image"],
1100
+ cost: {
1101
+ input: 8,
1102
+ output: 40,
1103
+ cacheRead: 0.2,
1104
+ cacheWrite: 10,
1105
+ },
1106
+ contextWindow: 1000000,
1107
+ maxTokens: 128000,
1108
+ },
1065
1109
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
1066
1110
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
1067
1111
  name: "Claude Haiku 4.5 (Global)",
@@ -1199,6 +1243,7 @@ export const MODELS = {
1199
1243
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1200
1244
  reasoning: true,
1201
1245
  thinkingType: "adaptive",
1246
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
1202
1247
  input: ["text", "image"],
1203
1248
  cost: {
1204
1249
  input: 4,
@@ -1289,6 +1334,7 @@ export const MODELS = {
1289
1334
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1290
1335
  reasoning: true,
1291
1336
  thinkingType: "adaptive",
1337
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
1292
1338
  input: ["text", "image"],
1293
1339
  cost: {
1294
1340
  input: 2,
@@ -1316,6 +1362,23 @@ export const MODELS = {
1316
1362
  contextWindow: 1048576,
1317
1363
  maxTokens: 128000,
1318
1364
  },
1365
+ "global.moonshotai.kimi-k3.1": {
1366
+ id: "global.moonshotai.kimi-k3.1",
1367
+ name: "Kimi K3.1 Pro Highspeed (Global)",
1368
+ api: "bedrock-converse-stream",
1369
+ provider: "amazon-bedrock",
1370
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1371
+ reasoning: true,
1372
+ input: ["text", "image"],
1373
+ cost: {
1374
+ input: 4,
1375
+ output: 20,
1376
+ cacheRead: 0.2,
1377
+ cacheWrite: 5,
1378
+ },
1379
+ contextWindow: 1048576,
1380
+ maxTokens: 1048576,
1381
+ },
1319
1382
  "global.openai.gpt-5.6-luna": {
1320
1383
  id: "global.openai.gpt-5.6-luna",
1321
1384
  name: "GPT-5.6 Luna (Global)",
@@ -1759,6 +1822,7 @@ export const MODELS = {
1759
1822
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1760
1823
  reasoning: true,
1761
1824
  thinkingType: "adaptive",
1825
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
1762
1826
  input: ["text", "image"],
1763
1827
  cost: {
1764
1828
  input: 4.4,
@@ -2734,7 +2798,7 @@ export const MODELS = {
2734
2798
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2735
2799
  reasoning: true,
2736
2800
  thinkingType: "adaptive",
2737
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2801
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2738
2802
  input: ["text", "image"],
2739
2803
  cost: {
2740
2804
  input: 11,
@@ -2753,7 +2817,7 @@ export const MODELS = {
2753
2817
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2754
2818
  reasoning: true,
2755
2819
  thinkingType: "adaptive",
2756
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2820
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2757
2821
  input: ["text", "image"],
2758
2822
  cost: {
2759
2823
  input: 11,
@@ -2764,6 +2828,25 @@ export const MODELS = {
2764
2828
  contextWindow: 1000000,
2765
2829
  maxTokens: 128000,
2766
2830
  },
2831
+ "us.anthropic.claude-fable-5-2": {
2832
+ id: "us.anthropic.claude-fable-5-2",
2833
+ name: "Claude Fable 5.2 (US)",
2834
+ api: "bedrock-converse-stream",
2835
+ provider: "amazon-bedrock",
2836
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2837
+ reasoning: true,
2838
+ thinkingType: "adaptive",
2839
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2840
+ input: ["text", "image"],
2841
+ cost: {
2842
+ input: 8.8,
2843
+ output: 44,
2844
+ cacheRead: 0.22,
2845
+ cacheWrite: 11,
2846
+ },
2847
+ contextWindow: 1000000,
2848
+ maxTokens: 128000,
2849
+ },
2767
2850
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
2768
2851
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
2769
2852
  name: "Claude Haiku 4.5 (US)",
@@ -2919,6 +3002,7 @@ export const MODELS = {
2919
3002
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2920
3003
  reasoning: true,
2921
3004
  thinkingType: "adaptive",
3005
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
2922
3006
  input: ["text", "image"],
2923
3007
  cost: {
2924
3008
  input: 4.4,
@@ -3009,6 +3093,7 @@ export const MODELS = {
3009
3093
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3010
3094
  reasoning: true,
3011
3095
  thinkingType: "adaptive",
3096
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3012
3097
  input: ["text", "image"],
3013
3098
  cost: {
3014
3099
  input: 2.2,
@@ -3138,6 +3223,23 @@ export const MODELS = {
3138
3223
  contextWindow: 1048576,
3139
3224
  maxTokens: 128000,
3140
3225
  },
3226
+ "us.moonshotai.kimi-k3.1": {
3227
+ id: "us.moonshotai.kimi-k3.1",
3228
+ name: "Kimi K3.1 Pro Highspeed (US)",
3229
+ api: "bedrock-converse-stream",
3230
+ provider: "amazon-bedrock",
3231
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3232
+ reasoning: true,
3233
+ input: ["text", "image"],
3234
+ cost: {
3235
+ input: 4.4,
3236
+ output: 22,
3237
+ cacheRead: 0.22,
3238
+ cacheWrite: 5.5,
3239
+ },
3240
+ contextWindow: 1048576,
3241
+ maxTokens: 1048576,
3242
+ },
3141
3243
  "us.openai.gpt-5.6-luna": {
3142
3244
  id: "us.openai.gpt-5.6-luna",
3143
3245
  name: "GPT-5.6 Luna (US)",
@@ -3488,7 +3590,7 @@ export const MODELS = {
3488
3590
  baseUrl: "https://api.anthropic.com",
3489
3591
  reasoning: true,
3490
3592
  thinkingType: "adaptive",
3491
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3593
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3492
3594
  input: ["text", "image"],
3493
3595
  cost: {
3494
3596
  input: 10,
@@ -3507,7 +3609,7 @@ export const MODELS = {
3507
3609
  baseUrl: "https://api.anthropic.com",
3508
3610
  reasoning: true,
3509
3611
  thinkingType: "adaptive",
3510
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3612
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3511
3613
  input: ["text", "image"],
3512
3614
  cost: {
3513
3615
  input: 10,
@@ -3518,6 +3620,25 @@ export const MODELS = {
3518
3620
  contextWindow: 1000000,
3519
3621
  maxTokens: 128000,
3520
3622
  },
3623
+ "claude-fable-5-2": {
3624
+ id: "claude-fable-5-2",
3625
+ name: "Claude Fable 5.2",
3626
+ api: "anthropic-messages",
3627
+ provider: "anthropic",
3628
+ baseUrl: "https://api.anthropic.com",
3629
+ reasoning: true,
3630
+ thinkingType: "adaptive",
3631
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3632
+ input: ["text", "image"],
3633
+ cost: {
3634
+ input: 8,
3635
+ output: 40,
3636
+ cacheRead: 0.2,
3637
+ cacheWrite: 10,
3638
+ },
3639
+ contextWindow: 1000000,
3640
+ maxTokens: 128000,
3641
+ },
3521
3642
  "claude-haiku-4-5": {
3522
3643
  id: "claude-haiku-4-5",
3523
3644
  name: "Claude Haiku 4.5 (latest)",
@@ -3691,6 +3812,7 @@ export const MODELS = {
3691
3812
  baseUrl: "https://api.anthropic.com",
3692
3813
  reasoning: true,
3693
3814
  thinkingType: "adaptive",
3815
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3694
3816
  input: ["text", "image"],
3695
3817
  cost: {
3696
3818
  input: 4,
@@ -3781,6 +3903,7 @@ export const MODELS = {
3781
3903
  baseUrl: "https://api.anthropic.com",
3782
3904
  reasoning: true,
3783
3905
  thinkingType: "adaptive",
3906
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3784
3907
  input: ["text", "image"],
3785
3908
  cost: {
3786
3909
  input: 2,
@@ -4574,7 +4697,7 @@ export const MODELS = {
4574
4697
  provider: "cloudflare-ai-gateway",
4575
4698
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4576
4699
  reasoning: true,
4577
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4700
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4578
4701
  input: ["text", "image"],
4579
4702
  cost: {
4580
4703
  input: 10,
@@ -4592,7 +4715,7 @@ export const MODELS = {
4592
4715
  provider: "cloudflare-ai-gateway",
4593
4716
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4594
4717
  reasoning: true,
4595
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4718
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4596
4719
  input: ["text", "image"],
4597
4720
  cost: {
4598
4721
  input: 10,
@@ -4732,6 +4855,7 @@ export const MODELS = {
4732
4855
  provider: "cloudflare-ai-gateway",
4733
4856
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4734
4857
  reasoning: true,
4858
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4735
4859
  input: ["text", "image"],
4736
4860
  cost: {
4737
4861
  input: 4,
@@ -4800,6 +4924,7 @@ export const MODELS = {
4800
4924
  provider: "cloudflare-ai-gateway",
4801
4925
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4802
4926
  reasoning: true,
4927
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4803
4928
  input: ["text", "image"],
4804
4929
  cost: {
4805
4930
  input: 2,
@@ -5739,52 +5864,35 @@ export const MODELS = {
5739
5864
  contextWindow: 1048573,
5740
5865
  maxTokens: 131072,
5741
5866
  },
5742
- "accounts/fireworks/models/gpt-oss-120b": {
5743
- id: "accounts/fireworks/models/gpt-oss-120b",
5744
- name: "GPT OSS 120B",
5745
- api: "anthropic-messages",
5746
- provider: "fireworks",
5747
- baseUrl: "https://api.fireworks.ai/inference",
5748
- reasoning: true,
5749
- input: ["text"],
5750
- cost: {
5751
- input: 0.15,
5752
- output: 0.6,
5753
- cacheRead: 0.015,
5754
- cacheWrite: 0,
5755
- },
5756
- contextWindow: 131072,
5757
- maxTokens: 32768,
5758
- },
5759
- "accounts/fireworks/models/inkling": {
5760
- id: "accounts/fireworks/models/inkling",
5761
- name: "Inkling",
5867
+ "accounts/fireworks/models/kimi-k3": {
5868
+ id: "accounts/fireworks/models/kimi-k3",
5869
+ name: "Kimi K3",
5762
5870
  api: "anthropic-messages",
5763
5871
  provider: "fireworks",
5764
5872
  baseUrl: "https://api.fireworks.ai/inference",
5765
5873
  reasoning: true,
5766
5874
  input: ["text", "image"],
5767
5875
  cost: {
5768
- input: 1,
5769
- output: 4.05,
5770
- cacheRead: 0.17,
5876
+ input: 3,
5877
+ output: 15,
5878
+ cacheRead: 0.3,
5771
5879
  cacheWrite: 0,
5772
5880
  },
5773
5881
  contextWindow: 1048576,
5774
- maxTokens: 1048576,
5882
+ maxTokens: 131072,
5775
5883
  },
5776
- "accounts/fireworks/models/kimi-k3": {
5777
- id: "accounts/fireworks/models/kimi-k3",
5778
- name: "Kimi K3",
5884
+ "accounts/fireworks/models/kimi-k3p1-pro": {
5885
+ id: "accounts/fireworks/models/kimi-k3p1-pro",
5886
+ name: "Kimi K3.1 Pro",
5779
5887
  api: "anthropic-messages",
5780
5888
  provider: "fireworks",
5781
5889
  baseUrl: "https://api.fireworks.ai/inference",
5782
5890
  reasoning: true,
5783
5891
  input: ["text", "image"],
5784
5892
  cost: {
5785
- input: 3,
5786
- output: 15,
5787
- cacheRead: 0.3,
5893
+ input: 2,
5894
+ output: 10,
5895
+ cacheRead: 0.2,
5788
5896
  cacheWrite: 0,
5789
5897
  },
5790
5898
  contextWindow: 1048576,
@@ -5841,40 +5949,6 @@ export const MODELS = {
5841
5949
  contextWindow: 1048576,
5842
5950
  maxTokens: 131072,
5843
5951
  },
5844
- "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5845
- id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5846
- name: "Nemotron 3 Ultra 550B A55B",
5847
- api: "anthropic-messages",
5848
- provider: "fireworks",
5849
- baseUrl: "https://api.fireworks.ai/inference",
5850
- reasoning: true,
5851
- input: ["text"],
5852
- cost: {
5853
- input: 0.6,
5854
- output: 2.4,
5855
- cacheRead: 0.12,
5856
- cacheWrite: 0,
5857
- },
5858
- contextWindow: 262144,
5859
- maxTokens: 128000,
5860
- },
5861
- "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
5862
- id: "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
5863
- name: "Nemotron 3.5 Lightning 30B A3B",
5864
- api: "anthropic-messages",
5865
- provider: "fireworks",
5866
- baseUrl: "https://api.fireworks.ai/inference",
5867
- reasoning: true,
5868
- input: ["text"],
5869
- cost: {
5870
- input: 0.05,
5871
- output: 0.2,
5872
- cacheRead: 0.01,
5873
- cacheWrite: 0,
5874
- },
5875
- contextWindow: 262144,
5876
- maxTokens: 262144,
5877
- },
5878
5952
  "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
5879
5953
  id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
5880
5954
  name: "Qwen3.8 2.4T A95B",
@@ -5943,6 +6017,23 @@ export const MODELS = {
5943
6017
  contextWindow: 1000000,
5944
6018
  maxTokens: 384000,
5945
6019
  },
6020
+ "accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast": {
6021
+ id: "accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast",
6022
+ name: "DeepSeek V4.1 Flash 1017 Ultra-fast",
6023
+ api: "anthropic-messages",
6024
+ provider: "fireworks",
6025
+ baseUrl: "https://api.fireworks.ai/inference",
6026
+ reasoning: true,
6027
+ input: ["text", "image"],
6028
+ cost: {
6029
+ input: 2.4,
6030
+ output: 9.6,
6031
+ cacheRead: 0.048,
6032
+ cacheWrite: 0,
6033
+ },
6034
+ contextWindow: 1000000,
6035
+ maxTokens: 384000,
6036
+ },
5946
6037
  "accounts/fireworks/routers/deepseek-v4p1-flash-spot": {
5947
6038
  id: "accounts/fireworks/routers/deepseek-v4p1-flash-spot",
5948
6039
  name: "DeepSeek V4.1 Flash Spot",
@@ -6158,7 +6249,7 @@ export const MODELS = {
6158
6249
  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" },
6159
6250
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6160
6251
  reasoning: true,
6161
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
6252
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
6162
6253
  input: ["text", "image"],
6163
6254
  cost: {
6164
6255
  input: 10,
@@ -6178,7 +6269,7 @@ export const MODELS = {
6178
6269
  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" },
6179
6270
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6180
6271
  reasoning: true,
6181
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
6272
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
6182
6273
  input: ["text", "image"],
6183
6274
  cost: {
6184
6275
  input: 10,
@@ -6274,6 +6365,7 @@ export const MODELS = {
6274
6365
  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" },
6275
6366
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6276
6367
  reasoning: true,
6368
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6277
6369
  input: ["text", "image"],
6278
6370
  cost: {
6279
6371
  input: 4,
@@ -6330,6 +6422,7 @@ export const MODELS = {
6330
6422
  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" },
6331
6423
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6332
6424
  reasoning: true,
6425
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6333
6426
  input: ["text", "image"],
6334
6427
  cost: {
6335
6428
  input: 2,
@@ -6679,7 +6772,7 @@ export const MODELS = {
6679
6772
  cacheRead: 0.2,
6680
6773
  cacheWrite: 0,
6681
6774
  },
6682
- contextWindow: 131072,
6775
+ contextWindow: 1048576,
6683
6776
  maxTokens: 65536,
6684
6777
  },
6685
6778
  "deep-research-preview-04-2026": {
@@ -6696,7 +6789,7 @@ export const MODELS = {
6696
6789
  cacheRead: 0.2,
6697
6790
  cacheWrite: 0,
6698
6791
  },
6699
- contextWindow: 131072,
6792
+ contextWindow: 1048576,
6700
6793
  maxTokens: 65536,
6701
6794
  },
6702
6795
  "gemini-2.5-computer-use-preview-10-2025": {
@@ -10966,7 +11059,7 @@ export const MODELS = {
10966
11059
  provider: "opencode",
10967
11060
  baseUrl: "https://opencode.ai/zen",
10968
11061
  reasoning: true,
10969
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
11062
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10970
11063
  input: ["text", "image"],
10971
11064
  cost: {
10972
11065
  input: 10,
@@ -10984,7 +11077,7 @@ export const MODELS = {
10984
11077
  provider: "opencode",
10985
11078
  baseUrl: "https://opencode.ai/zen",
10986
11079
  reasoning: true,
10987
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
11080
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10988
11081
  input: ["text", "image"],
10989
11082
  cost: {
10990
11083
  input: 10,
@@ -10995,6 +11088,24 @@ export const MODELS = {
10995
11088
  contextWindow: 1000000,
10996
11089
  maxTokens: 128000,
10997
11090
  },
11091
+ "claude-fable-5-2": {
11092
+ id: "claude-fable-5-2",
11093
+ name: "Claude Fable 5.2",
11094
+ api: "anthropic-messages",
11095
+ provider: "opencode",
11096
+ baseUrl: "https://opencode.ai/zen",
11097
+ reasoning: true,
11098
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
11099
+ input: ["text", "image"],
11100
+ cost: {
11101
+ input: 8,
11102
+ output: 40,
11103
+ cacheRead: 0.2,
11104
+ cacheWrite: 10,
11105
+ },
11106
+ contextWindow: 1000000,
11107
+ maxTokens: 128000,
11108
+ },
10998
11109
  "claude-haiku-4-5": {
10999
11110
  id: "claude-haiku-4-5",
11000
11111
  name: "Claude Haiku 4.5",
@@ -11124,6 +11235,7 @@ export const MODELS = {
11124
11235
  provider: "opencode",
11125
11236
  baseUrl: "https://opencode.ai/zen",
11126
11237
  reasoning: true,
11238
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
11127
11239
  input: ["text", "image"],
11128
11240
  cost: {
11129
11241
  input: 4,
@@ -11192,11 +11304,12 @@ export const MODELS = {
11192
11304
  provider: "opencode",
11193
11305
  baseUrl: "https://opencode.ai/zen",
11194
11306
  reasoning: true,
11307
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
11195
11308
  input: ["text", "image"],
11196
11309
  cost: {
11197
11310
  input: 2,
11198
11311
  output: 10,
11199
- cacheRead: 0.2,
11312
+ cacheRead: 0.1,
11200
11313
  cacheWrite: 2.5,
11201
11314
  },
11202
11315
  contextWindow: 1000000,
@@ -11358,9 +11471,9 @@ export const MODELS = {
11358
11471
  thinkingLevelMap: { "off": null },
11359
11472
  input: ["text", "image"],
11360
11473
  cost: {
11361
- input: 1.5,
11362
- output: 7.5,
11363
- cacheRead: 0.15,
11474
+ input: 0.75,
11475
+ output: 3.75,
11476
+ cacheRead: 0.075,
11364
11477
  cacheWrite: 0,
11365
11478
  },
11366
11479
  contextWindow: 1048576,
@@ -11376,9 +11489,9 @@ export const MODELS = {
11376
11489
  thinkingLevelMap: { "off": null },
11377
11490
  input: ["text", "image"],
11378
11491
  cost: {
11379
- input: 1.5,
11380
- output: 7.5,
11381
- cacheRead: 0.15,
11492
+ input: 0.75,
11493
+ output: 3.75,
11494
+ cacheRead: 0.075,
11382
11495
  cacheWrite: 0,
11383
11496
  },
11384
11497
  contextWindow: 1048576,
@@ -11394,9 +11507,9 @@ export const MODELS = {
11394
11507
  thinkingLevelMap: { "off": null },
11395
11508
  input: ["text", "image"],
11396
11509
  cost: {
11397
- input: 1.5,
11398
- output: 7.5,
11399
- cacheRead: 0.15,
11510
+ input: 0.75,
11511
+ output: 3.75,
11512
+ cacheRead: 0.075,
11400
11513
  cacheWrite: 0,
11401
11514
  },
11402
11515
  contextWindow: 1048576,
@@ -11999,6 +12112,40 @@ export const MODELS = {
11999
12112
  contextWindow: 256000,
12000
12113
  maxTokens: 256000,
12001
12114
  },
12115
+ "iceman-free": {
12116
+ id: "iceman-free",
12117
+ name: "Iceman Free",
12118
+ api: "openai-completions",
12119
+ provider: "opencode",
12120
+ baseUrl: "https://opencode.ai/zen/v1",
12121
+ reasoning: true,
12122
+ input: ["text"],
12123
+ cost: {
12124
+ input: 0,
12125
+ output: 0,
12126
+ cacheRead: 0,
12127
+ cacheWrite: 0,
12128
+ },
12129
+ contextWindow: 262144,
12130
+ maxTokens: 131072,
12131
+ },
12132
+ "inkling-2-small-free": {
12133
+ id: "inkling-2-small-free",
12134
+ name: "Inkling 2 Small Free",
12135
+ api: "openai-completions",
12136
+ provider: "opencode",
12137
+ baseUrl: "https://opencode.ai/zen/v1",
12138
+ reasoning: true,
12139
+ input: ["text", "image"],
12140
+ cost: {
12141
+ input: 0,
12142
+ output: 0,
12143
+ cacheRead: 0,
12144
+ cacheWrite: 0,
12145
+ },
12146
+ contextWindow: 1048576,
12147
+ maxTokens: 131072,
12148
+ },
12002
12149
  "kimi-k2.5": {
12003
12150
  id: "kimi-k2.5",
12004
12151
  name: "Kimi K2.5",
@@ -12067,9 +12214,9 @@ export const MODELS = {
12067
12214
  contextWindow: 1048576,
12068
12215
  maxTokens: 131072,
12069
12216
  },
12070
- "mimo-v2.6-flash-free": {
12071
- id: "mimo-v2.6-flash-free",
12072
- name: "MiMo-V2.6-Flash Free",
12217
+ "longcat-2.5-free": {
12218
+ id: "longcat-2.5-free",
12219
+ name: "LongCat 2.5 Free",
12073
12220
  api: "openai-completions",
12074
12221
  provider: "opencode",
12075
12222
  baseUrl: "https://opencode.ai/zen/v1",
@@ -12081,12 +12228,29 @@ export const MODELS = {
12081
12228
  cacheRead: 0,
12082
12229
  cacheWrite: 0,
12083
12230
  },
12084
- contextWindow: 200000,
12085
- maxTokens: 32000,
12231
+ contextWindow: 1000000,
12232
+ maxTokens: 262144,
12086
12233
  },
12087
- "minimax-m2.5": {
12088
- id: "minimax-m2.5",
12089
- name: "MiniMax-M2.5",
12234
+ "mimo-v2.6-flash-free": {
12235
+ id: "mimo-v2.6-flash-free",
12236
+ name: "MiMo-V2.6-Flash Free",
12237
+ api: "openai-completions",
12238
+ provider: "opencode",
12239
+ baseUrl: "https://opencode.ai/zen/v1",
12240
+ reasoning: true,
12241
+ input: ["text", "image"],
12242
+ cost: {
12243
+ input: 0,
12244
+ output: 0,
12245
+ cacheRead: 0,
12246
+ cacheWrite: 0,
12247
+ },
12248
+ contextWindow: 200000,
12249
+ maxTokens: 32000,
12250
+ },
12251
+ "minimax-m2.5": {
12252
+ id: "minimax-m2.5",
12253
+ name: "MiniMax-M2.5",
12090
12254
  api: "openai-completions",
12091
12255
  provider: "opencode",
12092
12256
  baseUrl: "https://opencode.ai/zen/v1",
@@ -12135,6 +12299,23 @@ export const MODELS = {
12135
12299
  contextWindow: 512000,
12136
12300
  maxTokens: 128000,
12137
12301
  },
12302
+ "minimax-m3.1-flash-free": {
12303
+ id: "minimax-m3.1-flash-free",
12304
+ name: "MiniMax M3.1 Flash Free",
12305
+ api: "openai-completions",
12306
+ provider: "opencode",
12307
+ baseUrl: "https://opencode.ai/zen/v1",
12308
+ reasoning: true,
12309
+ input: ["text", "image"],
12310
+ cost: {
12311
+ input: 0,
12312
+ output: 0,
12313
+ cacheRead: 0,
12314
+ cacheWrite: 0,
12315
+ },
12316
+ contextWindow: 1000000,
12317
+ maxTokens: 512000,
12318
+ },
12138
12319
  "mistral-large-4": {
12139
12320
  id: "mistral-large-4",
12140
12321
  name: "Mistral Large 4",
@@ -12152,6 +12333,23 @@ export const MODELS = {
12152
12333
  contextWindow: 524288,
12153
12334
  maxTokens: 262144,
12154
12335
  },
12336
+ "muse-ember-1.0": {
12337
+ id: "muse-ember-1.0",
12338
+ name: "Muse Ember 1.0",
12339
+ api: "openai-responses",
12340
+ provider: "opencode",
12341
+ baseUrl: "https://opencode.ai/zen/v1",
12342
+ reasoning: true,
12343
+ input: ["text", "image"],
12344
+ cost: {
12345
+ input: 0.1,
12346
+ output: 0.5,
12347
+ cacheRead: 0.004,
12348
+ cacheWrite: 0,
12349
+ },
12350
+ contextWindow: 1048576,
12351
+ maxTokens: 270000,
12352
+ },
12155
12353
  "muse-spark-1.2": {
12156
12354
  id: "muse-spark-1.2",
12157
12355
  name: "Muse Spark 1.2",
@@ -12343,7 +12541,7 @@ export const MODELS = {
12343
12541
  },
12344
12542
  "deepseek-v4-pro": {
12345
12543
  id: "deepseek-v4-pro",
12346
- name: "DeepSeek V4 Pro (New)",
12544
+ name: "DeepSeek V4 Pro",
12347
12545
  api: "openai-completions",
12348
12546
  provider: "opencode-go",
12349
12547
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12516,6 +12714,23 @@ export const MODELS = {
12516
12714
  contextWindow: 256000,
12517
12715
  maxTokens: 128000,
12518
12716
  },
12717
+ "hy4": {
12718
+ id: "hy4",
12719
+ name: "Hy4",
12720
+ api: "openai-completions",
12721
+ provider: "opencode-go",
12722
+ baseUrl: "https://opencode.ai/zen/go/v1",
12723
+ reasoning: true,
12724
+ input: ["text", "image"],
12725
+ cost: {
12726
+ input: 0.834,
12727
+ output: 2.501,
12728
+ cacheRead: 0.042,
12729
+ cacheWrite: 0,
12730
+ },
12731
+ contextWindow: 1048576,
12732
+ maxTokens: 65536,
12733
+ },
12519
12734
  "hy4-preview": {
12520
12735
  id: "hy4-preview",
12521
12736
  name: "Hy4 preview",
@@ -12618,6 +12833,23 @@ export const MODELS = {
12618
12833
  contextWindow: 1000000,
12619
12834
  maxTokens: 131072,
12620
12835
  },
12836
+ "longcat-2.5-free": {
12837
+ id: "longcat-2.5-free",
12838
+ name: "LongCat 2.5 Free",
12839
+ api: "openai-completions",
12840
+ provider: "opencode-go",
12841
+ baseUrl: "https://opencode.ai/zen/go/v1",
12842
+ reasoning: true,
12843
+ input: ["text", "image"],
12844
+ cost: {
12845
+ input: 0,
12846
+ output: 0,
12847
+ cacheRead: 0,
12848
+ cacheWrite: 0,
12849
+ },
12850
+ contextWindow: 1000000,
12851
+ maxTokens: 262144,
12852
+ },
12621
12853
  "mimo-v2.5": {
12622
12854
  id: "mimo-v2.5",
12623
12855
  name: "MiMo V2.5",
@@ -13001,7 +13233,7 @@ export const MODELS = {
13001
13233
  provider: "openrouter",
13002
13234
  baseUrl: "https://openrouter.ai/api/v1",
13003
13235
  reasoning: true,
13004
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13236
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13005
13237
  input: ["text", "image"],
13006
13238
  cost: {
13007
13239
  input: 10,
@@ -13019,7 +13251,7 @@ export const MODELS = {
13019
13251
  provider: "openrouter",
13020
13252
  baseUrl: "https://openrouter.ai/api/v1",
13021
13253
  reasoning: true,
13022
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13254
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13023
13255
  input: ["text", "image"],
13024
13256
  cost: {
13025
13257
  input: 10,
@@ -13037,7 +13269,7 @@ export const MODELS = {
13037
13269
  provider: "openrouter",
13038
13270
  baseUrl: "https://openrouter.ai/api/v1",
13039
13271
  reasoning: true,
13040
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13272
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13041
13273
  input: ["text", "image"],
13042
13274
  cost: {
13043
13275
  input: 5,
@@ -13048,6 +13280,42 @@ export const MODELS = {
13048
13280
  contextWindow: 1000000,
13049
13281
  maxTokens: 128000,
13050
13282
  },
13283
+ "anthropic/claude-fable-5.2": {
13284
+ id: "anthropic/claude-fable-5.2",
13285
+ name: "Anthropic: Claude Fable 5.2",
13286
+ api: "openai-completions",
13287
+ provider: "openrouter",
13288
+ baseUrl: "https://openrouter.ai/api/v1",
13289
+ reasoning: true,
13290
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13291
+ input: ["text", "image"],
13292
+ cost: {
13293
+ input: 8,
13294
+ output: 40,
13295
+ cacheRead: 0.19999999999999998,
13296
+ cacheWrite: 10,
13297
+ },
13298
+ contextWindow: 1000000,
13299
+ maxTokens: 128000,
13300
+ },
13301
+ "anthropic/claude-fable-5.2:batch": {
13302
+ id: "anthropic/claude-fable-5.2:batch",
13303
+ name: "Anthropic: Claude Fable 5.2 (batch)",
13304
+ api: "openai-completions",
13305
+ provider: "openrouter",
13306
+ baseUrl: "https://openrouter.ai/api/v1",
13307
+ reasoning: true,
13308
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13309
+ input: ["text", "image"],
13310
+ cost: {
13311
+ input: 4,
13312
+ output: 20,
13313
+ cacheRead: 0.09999999999999999,
13314
+ cacheWrite: 5,
13315
+ },
13316
+ contextWindow: 1000000,
13317
+ maxTokens: 128000,
13318
+ },
13051
13319
  "anthropic/claude-fable-5:batch": {
13052
13320
  id: "anthropic/claude-fable-5:batch",
13053
13321
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -13055,7 +13323,7 @@ export const MODELS = {
13055
13323
  provider: "openrouter",
13056
13324
  baseUrl: "https://openrouter.ai/api/v1",
13057
13325
  reasoning: true,
13058
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13326
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13059
13327
  input: ["text", "image"],
13060
13328
  cost: {
13061
13329
  input: 5,
@@ -13334,6 +13602,7 @@ export const MODELS = {
13334
13602
  provider: "openrouter",
13335
13603
  baseUrl: "https://openrouter.ai/api/v1",
13336
13604
  reasoning: true,
13605
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
13337
13606
  input: ["text", "image"],
13338
13607
  cost: {
13339
13608
  input: 4,
@@ -13351,6 +13620,7 @@ export const MODELS = {
13351
13620
  provider: "openrouter",
13352
13621
  baseUrl: "https://openrouter.ai/api/v1",
13353
13622
  reasoning: true,
13623
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
13354
13624
  input: ["text", "image"],
13355
13625
  cost: {
13356
13626
  input: 2,
@@ -13470,6 +13740,7 @@ export const MODELS = {
13470
13740
  provider: "openrouter",
13471
13741
  baseUrl: "https://openrouter.ai/api/v1",
13472
13742
  reasoning: true,
13743
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
13473
13744
  input: ["text", "image"],
13474
13745
  cost: {
13475
13746
  input: 2,
@@ -13487,6 +13758,7 @@ export const MODELS = {
13487
13758
  provider: "openrouter",
13488
13759
  baseUrl: "https://openrouter.ai/api/v1",
13489
13760
  reasoning: true,
13761
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
13490
13762
  input: ["text", "image"],
13491
13763
  cost: {
13492
13764
  input: 1,
@@ -13633,6 +13905,23 @@ export const MODELS = {
13633
13905
  contextWindow: 262144,
13634
13906
  maxTokens: 131072,
13635
13907
  },
13908
+ "cohere/command-a": {
13909
+ id: "cohere/command-a",
13910
+ name: "Cohere: Command A",
13911
+ api: "openai-completions",
13912
+ provider: "openrouter",
13913
+ baseUrl: "https://openrouter.ai/api/v1",
13914
+ reasoning: false,
13915
+ input: ["text"],
13916
+ cost: {
13917
+ input: 2.5,
13918
+ output: 10,
13919
+ cacheRead: 0,
13920
+ cacheWrite: 0,
13921
+ },
13922
+ contextWindow: 256000,
13923
+ maxTokens: 8192,
13924
+ },
13636
13925
  "cohere/command-a-plus": {
13637
13926
  id: "cohere/command-a-plus",
13638
13927
  name: "Cohere: Command A+",
@@ -13684,6 +13973,23 @@ export const MODELS = {
13684
13973
  contextWindow: 128000,
13685
13974
  maxTokens: 4000,
13686
13975
  },
13976
+ "cohere/command-r7b-12-2024": {
13977
+ id: "cohere/command-r7b-12-2024",
13978
+ name: "Cohere: Command R7B (12-2024)",
13979
+ api: "openai-completions",
13980
+ provider: "openrouter",
13981
+ baseUrl: "https://openrouter.ai/api/v1",
13982
+ reasoning: false,
13983
+ input: ["text"],
13984
+ cost: {
13985
+ input: 0.0375,
13986
+ output: 0.15,
13987
+ cacheRead: 0,
13988
+ cacheWrite: 0,
13989
+ },
13990
+ contextWindow: 128000,
13991
+ maxTokens: 4000,
13992
+ },
13687
13993
  "cohere/north-mini-code:free": {
13688
13994
  id: "cohere/north-mini-code:free",
13689
13995
  name: "Cohere: North Mini Code (free)",
@@ -13710,13 +14016,13 @@ export const MODELS = {
13710
14016
  reasoning: false,
13711
14017
  input: ["text"],
13712
14018
  cost: {
13713
- input: 0.2574,
13714
- output: 1.0287,
14019
+ input: 0.32,
14020
+ output: 0.8899999999999999,
13715
14021
  cacheRead: 0,
13716
14022
  cacheWrite: 0,
13717
14023
  },
13718
14024
  contextWindow: 163840,
13719
- maxTokens: 16000,
14025
+ maxTokens: 16384,
13720
14026
  },
13721
14027
  "deepseek/deepseek-chat-v3-0324": {
13722
14028
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13850,14 +14156,33 @@ export const MODELS = {
13850
14156
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13851
14157
  input: ["text"],
13852
14158
  cost: {
13853
- input: 0.119,
13854
- output: 0.238,
13855
- cacheRead: 0.0238,
14159
+ input: 0.0434,
14160
+ output: 0.3,
14161
+ cacheRead: 0.035,
13856
14162
  cacheWrite: 0,
13857
14163
  },
13858
14164
  contextWindow: 1048576,
13859
14165
  maxTokens: 943718,
13860
14166
  },
14167
+ "deepseek/deepseek-v4-flash-0731:batch": {
14168
+ id: "deepseek/deepseek-v4-flash-0731:batch",
14169
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
14170
+ api: "openai-completions",
14171
+ provider: "openrouter",
14172
+ baseUrl: "https://openrouter.ai/api/v1",
14173
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
14174
+ reasoning: true,
14175
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14176
+ input: ["text"],
14177
+ cost: {
14178
+ input: 0.048,
14179
+ output: 0.144,
14180
+ cacheRead: 0.012,
14181
+ cacheWrite: 0,
14182
+ },
14183
+ contextWindow: 1048576,
14184
+ maxTokens: 384000,
14185
+ },
13861
14186
  "deepseek/deepseek-v4-flash-vision-exp": {
13862
14187
  id: "deepseek/deepseek-v4-flash-vision-exp",
13863
14188
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -13869,13 +14194,13 @@ export const MODELS = {
13869
14194
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13870
14195
  input: ["text", "image"],
13871
14196
  cost: {
13872
- input: 0.21559999999999999,
13873
- output: 0.6468,
13874
- cacheRead: 0.00686,
14197
+ input: 0.44,
14198
+ output: 1.32,
14199
+ cacheRead: 0.014,
13875
14200
  cacheWrite: 0,
13876
14201
  },
13877
14202
  contextWindow: 1048576,
13878
- maxTokens: 262144,
14203
+ maxTokens: 943717,
13879
14204
  },
13880
14205
  "deepseek/deepseek-v4-pro": {
13881
14206
  id: "deepseek/deepseek-v4-pro",
@@ -13888,13 +14213,13 @@ export const MODELS = {
13888
14213
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13889
14214
  input: ["text"],
13890
14215
  cost: {
13891
- input: 1.5999999999999999,
13892
- output: 3.1999999999999997,
13893
- cacheRead: 0.135,
14216
+ input: 0.9552599999999999,
14217
+ output: 1.9105199999999998,
14218
+ cacheRead: 0.07960500000000001,
13894
14219
  cacheWrite: 0,
13895
14220
  },
13896
14221
  contextWindow: 1048576,
13897
- maxTokens: 393216,
14222
+ maxTokens: 384000,
13898
14223
  },
13899
14224
  "deepseek/deepseek-v4-pro-0813": {
13900
14225
  id: "deepseek/deepseek-v4-pro-0813",
@@ -13907,9 +14232,9 @@ export const MODELS = {
13907
14232
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13908
14233
  input: ["text"],
13909
14234
  cost: {
13910
- input: 0.11499999999999999,
13911
- output: 4,
13912
- cacheRead: 0.11,
14235
+ input: 0.111,
14236
+ output: 4.4399999999999995,
14237
+ cacheRead: 0.09699999999999999,
13913
14238
  cacheWrite: 0,
13914
14239
  },
13915
14240
  contextWindow: 1048576,
@@ -13926,9 +14251,9 @@ export const MODELS = {
13926
14251
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13927
14252
  input: ["text", "image"],
13928
14253
  cost: {
13929
- input: 0.045,
14254
+ input: 0.006,
13930
14255
  output: 0.5,
13931
- cacheRead: 0.006,
14256
+ cacheRead: 0.005,
13932
14257
  cacheWrite: 0,
13933
14258
  },
13934
14259
  contextWindow: 1048576,
@@ -13945,13 +14270,32 @@ export const MODELS = {
13945
14270
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13946
14271
  input: ["text", "image"],
13947
14272
  cost: {
13948
- input: 0.15,
13949
- output: 0.6,
13950
- cacheRead: 0.003,
14273
+ input: 0.006,
14274
+ output: 0.5,
14275
+ cacheRead: 0.005,
13951
14276
  cacheWrite: 0,
13952
14277
  },
13953
14278
  contextWindow: 1048576,
13954
- maxTokens: 393216,
14279
+ maxTokens: 943718,
14280
+ },
14281
+ "deepseek/deepseek-v4.1-flash-1017:batch": {
14282
+ id: "deepseek/deepseek-v4.1-flash-1017:batch",
14283
+ name: "DeepSeek: DeepSeek V4.1 Flash 1017 (batch)",
14284
+ api: "openai-completions",
14285
+ provider: "openrouter",
14286
+ baseUrl: "https://openrouter.ai/api/v1",
14287
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
14288
+ reasoning: true,
14289
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14290
+ input: ["text", "image"],
14291
+ cost: {
14292
+ input: 0.011,
14293
+ output: 0.19999999999999998,
14294
+ cacheRead: 0.002,
14295
+ cacheWrite: 0,
14296
+ },
14297
+ contextWindow: 1048576,
14298
+ maxTokens: 943718,
13955
14299
  },
13956
14300
  "deepseek/deepseek-v4.1-flash:batch": {
13957
14301
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -13964,13 +14308,13 @@ export const MODELS = {
13964
14308
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13965
14309
  input: ["text", "image"],
13966
14310
  cost: {
13967
- input: 0.049999999999999996,
13968
- output: 0.15,
13969
- cacheRead: 0.004,
14311
+ input: 0.112,
14312
+ output: 0.33599999999999997,
14313
+ cacheRead: 0.00336,
13970
14314
  cacheWrite: 0,
13971
14315
  },
13972
14316
  contextWindow: 1048576,
13973
- maxTokens: 384000,
14317
+ maxTokens: 131072,
13974
14318
  },
13975
14319
  "dots-studio/dots-3-note-preview:free": {
13976
14320
  id: "dots-studio/dots-3-note-preview:free",
@@ -14492,7 +14836,7 @@ export const MODELS = {
14492
14836
  input: ["text", "image"],
14493
14837
  cost: {
14494
14838
  input: 0.08,
14495
- output: 0.35,
14839
+ output: 0.44999999999999996,
14496
14840
  cacheRead: 0.04,
14497
14841
  cacheWrite: 0,
14498
14842
  },
@@ -14508,13 +14852,13 @@ export const MODELS = {
14508
14852
  reasoning: true,
14509
14853
  input: ["text", "image"],
14510
14854
  cost: {
14511
- input: 0.0675,
14512
- output: 0.22499999999999998,
14513
- cacheRead: 0.0375,
14855
+ input: 0.08,
14856
+ output: 0.09999999999999999,
14857
+ cacheRead: 0.046,
14514
14858
  cacheWrite: 0,
14515
14859
  },
14516
14860
  contextWindow: 262144,
14517
- maxTokens: 235929,
14861
+ maxTokens: 128000,
14518
14862
  },
14519
14863
  "google/gemma-4-26b-a4b-it:free": {
14520
14864
  id: "google/gemma-4-26b-a4b-it:free",
@@ -14577,64 +14921,13 @@ export const MODELS = {
14577
14921
  input: ["text"],
14578
14922
  cost: {
14579
14923
  input: 0.06,
14580
- output: 0.15,
14924
+ output: 0.25,
14581
14925
  cacheRead: 0.015,
14582
14926
  cacheWrite: 0,
14583
14927
  },
14584
14928
  contextWindow: 131072,
14585
14929
  maxTokens: 117964,
14586
14930
  },
14587
- "inception/mercury-2": {
14588
- id: "inception/mercury-2",
14589
- name: "Inception: Mercury 2",
14590
- api: "openai-completions",
14591
- provider: "openrouter",
14592
- baseUrl: "https://openrouter.ai/api/v1",
14593
- reasoning: true,
14594
- input: ["text"],
14595
- cost: {
14596
- input: 0.25,
14597
- output: 0.75,
14598
- cacheRead: 0.024999999999999998,
14599
- cacheWrite: 0,
14600
- },
14601
- contextWindow: 128000,
14602
- maxTokens: 50000,
14603
- },
14604
- "inception/mercury-2.5": {
14605
- id: "inception/mercury-2.5",
14606
- name: "Inception: Mercury 2.5",
14607
- api: "openai-completions",
14608
- provider: "openrouter",
14609
- baseUrl: "https://openrouter.ai/api/v1",
14610
- reasoning: true,
14611
- input: ["text"],
14612
- cost: {
14613
- input: 0.04,
14614
- output: 0.15,
14615
- cacheRead: 0.004,
14616
- cacheWrite: 0,
14617
- },
14618
- contextWindow: 260000,
14619
- maxTokens: 65536,
14620
- },
14621
- "inception/mercury-3": {
14622
- id: "inception/mercury-3",
14623
- name: "Inception: Mercury 3",
14624
- api: "openai-completions",
14625
- provider: "openrouter",
14626
- baseUrl: "https://openrouter.ai/api/v1",
14627
- reasoning: true,
14628
- input: ["text"],
14629
- cost: {
14630
- input: 0.09999999999999999,
14631
- output: 0.35,
14632
- cacheRead: 0.01,
14633
- cacheWrite: 0,
14634
- },
14635
- contextWindow: 1000000,
14636
- maxTokens: 131072,
14637
- },
14638
14931
  "inclusionai/ling-3.0-flash": {
14639
14932
  id: "inclusionai/ling-3.0-flash",
14640
14933
  name: "inclusionAI: Ling 3.0 Flash",
@@ -14669,6 +14962,23 @@ export const MODELS = {
14669
14962
  contextWindow: 131072,
14670
14963
  maxTokens: 32768,
14671
14964
  },
14965
+ "inclusionai/ling-3.0-tiny": {
14966
+ id: "inclusionai/ling-3.0-tiny",
14967
+ name: "inclusionAI: Ling 3.0 Tiny",
14968
+ api: "openai-completions",
14969
+ provider: "openrouter",
14970
+ baseUrl: "https://openrouter.ai/api/v1",
14971
+ reasoning: true,
14972
+ input: ["text"],
14973
+ cost: {
14974
+ input: 0.015,
14975
+ output: 0.045,
14976
+ cacheRead: 0.003,
14977
+ cacheWrite: 0,
14978
+ },
14979
+ contextWindow: 262144,
14980
+ maxTokens: 250000,
14981
+ },
14672
14982
  "inclusionai/ling-3.1-flash": {
14673
14983
  id: "inclusionai/ling-3.1-flash",
14674
14984
  name: "inclusionAI: Ling 3.1 Flash",
@@ -14678,9 +14988,9 @@ export const MODELS = {
14678
14988
  reasoning: true,
14679
14989
  input: ["text"],
14680
14990
  cost: {
14681
- input: 0.075,
14682
- output: 0.22499999999999998,
14683
- cacheRead: 0.015,
14991
+ input: 0.045,
14992
+ output: 0.135,
14993
+ cacheRead: 0.009,
14684
14994
  cacheWrite: 0,
14685
14995
  },
14686
14996
  contextWindow: 1000000,
@@ -14737,39 +15047,56 @@ export const MODELS = {
14737
15047
  contextWindow: 128000,
14738
15048
  maxTokens: 8192,
14739
15049
  },
14740
- "meituan/longcat-2.0": {
14741
- id: "meituan/longcat-2.0",
14742
- name: "Meituan: LongCat 2.0",
15050
+ "liquid/lfm-3-1.7b": {
15051
+ id: "liquid/lfm-3-1.7b",
15052
+ name: "LiquidAI: LFM3-1.7B",
14743
15053
  api: "openai-completions",
14744
15054
  provider: "openrouter",
14745
15055
  baseUrl: "https://openrouter.ai/api/v1",
14746
15056
  reasoning: true,
14747
15057
  input: ["text"],
14748
15058
  cost: {
14749
- input: 0.3,
14750
- output: 1.2,
14751
- cacheRead: 0.006,
15059
+ input: 0.08,
15060
+ output: 0.19999999999999998,
15061
+ cacheRead: 0.02,
14752
15062
  cacheWrite: 0,
14753
15063
  },
14754
- contextWindow: 1048756,
14755
- maxTokens: 262144,
15064
+ contextWindow: 262144,
15065
+ maxTokens: 8192,
14756
15066
  },
14757
- "meta-llama/llama-3.1-70b-instruct": {
14758
- id: "meta-llama/llama-3.1-70b-instruct",
14759
- name: "Meta: Llama 3.1 70B Instruct",
15067
+ "liquid/lfm-3-1.7b:free": {
15068
+ id: "liquid/lfm-3-1.7b:free",
15069
+ name: "LiquidAI: LFM3-1.7B (free)",
14760
15070
  api: "openai-completions",
14761
15071
  provider: "openrouter",
14762
15072
  baseUrl: "https://openrouter.ai/api/v1",
14763
- reasoning: false,
15073
+ reasoning: true,
14764
15074
  input: ["text"],
14765
15075
  cost: {
14766
- input: 0.39999999999999997,
14767
- output: 0.39999999999999997,
15076
+ input: 0,
15077
+ output: 0,
14768
15078
  cacheRead: 0,
14769
15079
  cacheWrite: 0,
14770
15080
  },
14771
- contextWindow: 131072,
14772
- maxTokens: 16384,
15081
+ contextWindow: 262144,
15082
+ maxTokens: 8192,
15083
+ },
15084
+ "meituan/longcat-2.0": {
15085
+ id: "meituan/longcat-2.0",
15086
+ name: "Meituan: LongCat 2.0",
15087
+ api: "openai-completions",
15088
+ provider: "openrouter",
15089
+ baseUrl: "https://openrouter.ai/api/v1",
15090
+ reasoning: true,
15091
+ input: ["text"],
15092
+ cost: {
15093
+ input: 0.3,
15094
+ output: 1.2,
15095
+ cacheRead: 0.006,
15096
+ cacheWrite: 0,
15097
+ },
15098
+ contextWindow: 1048756,
15099
+ maxTokens: 262144,
14773
15100
  },
14774
15101
  "meta-llama/llama-3.1-8b-instruct": {
14775
15102
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -14780,13 +15107,13 @@ export const MODELS = {
14780
15107
  reasoning: false,
14781
15108
  input: ["text"],
14782
15109
  cost: {
14783
- input: 0.049999999999999996,
14784
- output: 0.08,
14785
- cacheRead: 0.024999999999999998,
15110
+ input: 0.02,
15111
+ output: 0.04,
15112
+ cacheRead: 0,
14786
15113
  cacheWrite: 0,
14787
15114
  },
14788
15115
  contextWindow: 131072,
14789
- maxTokens: 117964,
15116
+ maxTokens: 16384,
14790
15117
  },
14791
15118
  "meta-llama/llama-3.3-70b-instruct": {
14792
15119
  id: "meta-llama/llama-3.3-70b-instruct",
@@ -14797,13 +15124,13 @@ export const MODELS = {
14797
15124
  reasoning: false,
14798
15125
  input: ["text"],
14799
15126
  cost: {
14800
- input: 0.09999999999999999,
14801
- output: 0.32,
14802
- cacheRead: 0,
15127
+ input: 0.71,
15128
+ output: 0.71,
15129
+ cacheRead: 0.71,
14803
15130
  cacheWrite: 0,
14804
15131
  },
14805
15132
  contextWindow: 131072,
14806
- maxTokens: 16384,
15133
+ maxTokens: 115200,
14807
15134
  },
14808
15135
  "meta-llama/llama-4-maverick": {
14809
15136
  id: "meta-llama/llama-4-maverick",
@@ -14814,13 +15141,13 @@ export const MODELS = {
14814
15141
  reasoning: false,
14815
15142
  input: ["text", "image"],
14816
15143
  cost: {
14817
- input: 0.1875,
14818
- output: 0.6525,
14819
- cacheRead: 0.049999999999999996,
15144
+ input: 0.35,
15145
+ output: 1,
15146
+ cacheRead: 0.16999999999999998,
14820
15147
  cacheWrite: 0,
14821
15148
  },
14822
15149
  contextWindow: 524288,
14823
- maxTokens: 16384,
15150
+ maxTokens: 32768,
14824
15151
  },
14825
15152
  "meta-llama/llama-4-scout": {
14826
15153
  id: "meta-llama/llama-4-scout",
@@ -14839,6 +15166,23 @@ export const MODELS = {
14839
15166
  contextWindow: 1310720,
14840
15167
  maxTokens: 16384,
14841
15168
  },
15169
+ "meta/muse-ember": {
15170
+ id: "meta/muse-ember",
15171
+ name: "Meta: Muse Ember",
15172
+ api: "openai-completions",
15173
+ provider: "openrouter",
15174
+ baseUrl: "https://openrouter.ai/api/v1",
15175
+ reasoning: true,
15176
+ input: ["text", "image"],
15177
+ cost: {
15178
+ input: 0.09999999999999999,
15179
+ output: 0.5,
15180
+ cacheRead: 0.004,
15181
+ cacheWrite: 0.125,
15182
+ },
15183
+ contextWindow: 1048576,
15184
+ maxTokens: 943718,
15185
+ },
14842
15186
  "meta/muse-glimmer-30b": {
14843
15187
  id: "meta/muse-glimmer-30b",
14844
15188
  name: "Meta: Muse Glimmer 30B",
@@ -14856,6 +15200,23 @@ export const MODELS = {
14856
15200
  contextWindow: 131072,
14857
15201
  maxTokens: 16384,
14858
15202
  },
15203
+ "meta/muse-glimmer-30b:batch": {
15204
+ id: "meta/muse-glimmer-30b:batch",
15205
+ name: "Meta: Muse Glimmer 30B (batch)",
15206
+ api: "openai-completions",
15207
+ provider: "openrouter",
15208
+ baseUrl: "https://openrouter.ai/api/v1",
15209
+ reasoning: true,
15210
+ input: ["text", "image"],
15211
+ cost: {
15212
+ input: 0.24,
15213
+ output: 0.96,
15214
+ cacheRead: 0.032,
15215
+ cacheWrite: 0,
15216
+ },
15217
+ contextWindow: 131072,
15218
+ maxTokens: 16384,
15219
+ },
14859
15220
  "meta/muse-spark-1.1": {
14860
15221
  id: "meta/muse-spark-1.1",
14861
15222
  name: "Meta: Muse Spark 1.1",
@@ -14975,57 +15336,6 @@ export const MODELS = {
14975
15336
  contextWindow: 1048576,
14976
15337
  maxTokens: 943718,
14977
15338
  },
14978
- "minimax/minimax-m1": {
14979
- id: "minimax/minimax-m1",
14980
- name: "MiniMax: MiniMax M1",
14981
- api: "openai-completions",
14982
- provider: "openrouter",
14983
- baseUrl: "https://openrouter.ai/api/v1",
14984
- reasoning: true,
14985
- input: ["text"],
14986
- cost: {
14987
- input: 0.55,
14988
- output: 2.2,
14989
- cacheRead: 0,
14990
- cacheWrite: 0,
14991
- },
14992
- contextWindow: 1000000,
14993
- maxTokens: 40000,
14994
- },
14995
- "minimax/minimax-m2": {
14996
- id: "minimax/minimax-m2",
14997
- name: "MiniMax: MiniMax M2",
14998
- api: "openai-completions",
14999
- provider: "openrouter",
15000
- baseUrl: "https://openrouter.ai/api/v1",
15001
- reasoning: true,
15002
- input: ["text"],
15003
- cost: {
15004
- input: 0.255,
15005
- output: 1.02,
15006
- cacheRead: 0,
15007
- cacheWrite: 0,
15008
- },
15009
- contextWindow: 204800,
15010
- maxTokens: 131072,
15011
- },
15012
- "minimax/minimax-m2.1": {
15013
- id: "minimax/minimax-m2.1",
15014
- name: "MiniMax: MiniMax M2.1",
15015
- api: "openai-completions",
15016
- provider: "openrouter",
15017
- baseUrl: "https://openrouter.ai/api/v1",
15018
- reasoning: true,
15019
- input: ["text"],
15020
- cost: {
15021
- input: 0.3,
15022
- output: 1.2,
15023
- cacheRead: 0.03,
15024
- cacheWrite: 0,
15025
- },
15026
- contextWindow: 204800,
15027
- maxTokens: 131072,
15028
- },
15029
15339
  "minimax/minimax-m2.5": {
15030
15340
  id: "minimax/minimax-m2.5",
15031
15341
  name: "MiniMax: MiniMax M2.5",
@@ -15035,13 +15345,13 @@ export const MODELS = {
15035
15345
  reasoning: true,
15036
15346
  input: ["text"],
15037
15347
  cost: {
15038
- input: 0.27,
15039
- output: 0.95,
15040
- cacheRead: 0.03,
15348
+ input: 0.3,
15349
+ output: 1.2,
15350
+ cacheRead: 0.06,
15041
15351
  cacheWrite: 0,
15042
15352
  },
15043
- contextWindow: 204800,
15044
- maxTokens: 32768,
15353
+ contextWindow: 200000,
15354
+ maxTokens: 58982,
15045
15355
  },
15046
15356
  "minimax/minimax-m2.7": {
15047
15357
  id: "minimax/minimax-m2.7",
@@ -15052,13 +15362,13 @@ export const MODELS = {
15052
15362
  reasoning: true,
15053
15363
  input: ["text"],
15054
15364
  cost: {
15055
- input: 0.3,
15056
- output: 1.2,
15057
- cacheRead: 0.06,
15365
+ input: 0.21,
15366
+ output: 0.84,
15367
+ cacheRead: 0.041999999999999996,
15058
15368
  cacheWrite: 0,
15059
15369
  },
15060
- contextWindow: 204800,
15061
- maxTokens: 131072,
15370
+ contextWindow: 196608,
15371
+ maxTokens: 176947,
15062
15372
  },
15063
15373
  "minimax/minimax-m3": {
15064
15374
  id: "minimax/minimax-m3",
@@ -15086,14 +15396,31 @@ export const MODELS = {
15086
15396
  reasoning: true,
15087
15397
  input: ["text", "image"],
15088
15398
  cost: {
15089
- input: 0.075,
15090
- output: 0.3,
15091
- cacheRead: 0.0075,
15399
+ input: 0.15,
15400
+ output: 0.6,
15401
+ cacheRead: 0.015,
15092
15402
  cacheWrite: 0,
15093
15403
  },
15094
15404
  contextWindow: 1048576,
15095
15405
  maxTokens: 524288,
15096
15406
  },
15407
+ "minimax/minimax-m3:batch": {
15408
+ id: "minimax/minimax-m3:batch",
15409
+ name: "MiniMax: MiniMax M3 (batch)",
15410
+ api: "openai-completions",
15411
+ provider: "openrouter",
15412
+ baseUrl: "https://openrouter.ai/api/v1",
15413
+ reasoning: true,
15414
+ input: ["text", "image"],
15415
+ cost: {
15416
+ input: 0.224,
15417
+ output: 0.88,
15418
+ cacheRead: 0.0448,
15419
+ cacheWrite: 0,
15420
+ },
15421
+ contextWindow: 524288,
15422
+ maxTokens: 512000,
15423
+ },
15097
15424
  "mistralai/codestral-2508": {
15098
15425
  id: "mistralai/codestral-2508",
15099
15426
  name: "Mistral: Codestral 2508",
@@ -15392,13 +15719,13 @@ export const MODELS = {
15392
15719
  reasoning: false,
15393
15720
  input: ["text", "image"],
15394
15721
  cost: {
15395
- input: 0.075,
15396
- output: 0.19999999999999998,
15397
- cacheRead: 0,
15722
+ input: 0.09999999999999999,
15723
+ output: 0.3,
15724
+ cacheRead: 0.01,
15398
15725
  cacheWrite: 0,
15399
15726
  },
15400
15727
  contextWindow: 256000,
15401
- maxTokens: 16384,
15728
+ maxTokens: 26214,
15402
15729
  },
15403
15730
  "mistralai/mixtral-8x22b-instruct": {
15404
15731
  id: "mistralai/mixtral-8x22b-instruct",
@@ -15530,7 +15857,7 @@ export const MODELS = {
15530
15857
  cost: {
15531
15858
  input: 0.6,
15532
15859
  output: 3.5,
15533
- cacheRead: 0.15,
15860
+ cacheRead: 0.16,
15534
15861
  cacheWrite: 0,
15535
15862
  },
15536
15863
  contextWindow: 262144,
@@ -15546,7 +15873,7 @@ export const MODELS = {
15546
15873
  input: ["text", "image"],
15547
15874
  cost: {
15548
15875
  input: 0.192,
15549
- output: 15,
15876
+ output: 16,
15550
15877
  cacheRead: 0.182,
15551
15878
  cacheWrite: 0,
15552
15879
  },
@@ -15604,6 +15931,23 @@ export const MODELS = {
15604
15931
  contextWindow: 262144,
15605
15932
  maxTokens: 235929,
15606
15933
  },
15934
+ "nex-agi/nex-n2.6": {
15935
+ id: "nex-agi/nex-n2.6",
15936
+ name: "Nex AGI: Nex-N2.6",
15937
+ api: "openai-completions",
15938
+ provider: "openrouter",
15939
+ baseUrl: "https://openrouter.ai/api/v1",
15940
+ reasoning: true,
15941
+ input: ["text", "image"],
15942
+ cost: {
15943
+ input: 0.12,
15944
+ output: 0.39999999999999997,
15945
+ cacheRead: 0.024,
15946
+ cacheWrite: 0,
15947
+ },
15948
+ contextWindow: 262144,
15949
+ maxTokens: 235929,
15950
+ },
15607
15951
  "nvidia/nemotron-3-nano-30b-a3b": {
15608
15952
  id: "nvidia/nemotron-3-nano-30b-a3b",
15609
15953
  name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -15647,13 +15991,13 @@ export const MODELS = {
15647
15991
  reasoning: true,
15648
15992
  input: ["text"],
15649
15993
  cost: {
15650
- input: 0.3,
15651
- output: 2.4,
15652
- cacheRead: 0.15,
15994
+ input: 0.075,
15995
+ output: 0.39999999999999997,
15996
+ cacheRead: 0,
15653
15997
  cacheWrite: 0,
15654
15998
  },
15655
15999
  contextWindow: 1048576,
15656
- maxTokens: 262144,
16000
+ maxTokens: 16384,
15657
16001
  },
15658
16002
  "nvidia/nemotron-3-ultra-550b-a55b": {
15659
16003
  id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -15733,12 +16077,12 @@ export const MODELS = {
15733
16077
  input: ["text", "image"],
15734
16078
  cost: {
15735
16079
  input: 0.15,
15736
- output: 0.5,
16080
+ output: 0.47,
15737
16081
  cacheRead: 0.02,
15738
16082
  cacheWrite: 0,
15739
16083
  },
15740
16084
  contextWindow: 1048576,
15741
- maxTokens: 235929,
16085
+ maxTokens: 943718,
15742
16086
  },
15743
16087
  "nvidia/nemotron-3.5-super-vl:free": {
15744
16088
  id: "nvidia/nemotron-3.5-super-vl:free",
@@ -17162,9 +17506,9 @@ export const MODELS = {
17162
17506
  reasoning: true,
17163
17507
  input: ["text"],
17164
17508
  cost: {
17165
- input: 0.014,
17166
- output: 0.051,
17167
- cacheRead: 0,
17509
+ input: 0.15,
17510
+ output: 0.6,
17511
+ cacheRead: 0.075,
17168
17512
  cacheWrite: 0,
17169
17513
  },
17170
17514
  contextWindow: 131072,
@@ -17196,13 +17540,13 @@ export const MODELS = {
17196
17540
  reasoning: true,
17197
17541
  input: ["text"],
17198
17542
  cost: {
17199
- input: 0.03,
17200
- output: 0.13,
17201
- cacheRead: 0.03,
17543
+ input: 0.018,
17544
+ output: 0.09,
17545
+ cacheRead: 0.009,
17202
17546
  cacheWrite: 0,
17203
17547
  },
17204
17548
  contextWindow: 131072,
17205
- maxTokens: 117964,
17549
+ maxTokens: 32768,
17206
17550
  },
17207
17551
  "openai/gpt-oss-20b:batch": {
17208
17552
  id: "openai/gpt-oss-20b:batch",
@@ -17355,7 +17699,24 @@ export const MODELS = {
17355
17699
  cacheWrite: 0,
17356
17700
  },
17357
17701
  contextWindow: 2000000,
17358
- maxTokens: 65536,
17702
+ maxTokens: 64000,
17703
+ },
17704
+ "openrouter/auto-code": {
17705
+ id: "openrouter/auto-code",
17706
+ name: "Auto Code",
17707
+ api: "openai-completions",
17708
+ provider: "openrouter",
17709
+ baseUrl: "https://openrouter.ai/api/v1",
17710
+ reasoning: true,
17711
+ input: ["text", "image"],
17712
+ cost: {
17713
+ input: -1000000,
17714
+ output: -1000000,
17715
+ cacheRead: 0,
17716
+ cacheWrite: 0,
17717
+ },
17718
+ contextWindow: 2000000,
17719
+ maxTokens: 64000,
17359
17720
  },
17360
17721
  "openrouter/free": {
17361
17722
  id: "openrouter/free",
@@ -17519,13 +17880,13 @@ export const MODELS = {
17519
17880
  reasoning: true,
17520
17881
  input: ["text"],
17521
17882
  cost: {
17522
- input: 0.12,
17523
- output: 0.24,
17883
+ input: 0.09999999999999999,
17884
+ output: 0.22,
17524
17885
  cacheRead: 0,
17525
17886
  cacheWrite: 0,
17526
17887
  },
17527
17888
  contextWindow: 40960,
17528
- maxTokens: 16384,
17889
+ maxTokens: 36864,
17529
17890
  },
17530
17891
  "qwen/qwen3-235b-a22b-2507": {
17531
17892
  id: "qwen/qwen3-235b-a22b-2507",
@@ -17536,13 +17897,13 @@ export const MODELS = {
17536
17897
  reasoning: false,
17537
17898
  input: ["text"],
17538
17899
  cost: {
17539
- input: 0.09,
17540
- output: 0.55,
17541
- cacheRead: 0,
17900
+ input: 0.14,
17901
+ output: 0.7999999999999999,
17902
+ cacheRead: 0.049999999999999996,
17542
17903
  cacheWrite: 0,
17543
17904
  },
17544
17905
  contextWindow: 262144,
17545
- maxTokens: 16384,
17906
+ maxTokens: 117964,
17546
17907
  },
17547
17908
  "qwen/qwen3-235b-a22b-thinking-2507": {
17548
17909
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -17638,8 +17999,8 @@ export const MODELS = {
17638
17999
  reasoning: false,
17639
18000
  input: ["text"],
17640
18001
  cost: {
17641
- input: 0.07,
17642
- output: 0.28,
18002
+ input: 0.15,
18003
+ output: 0.6,
17643
18004
  cacheRead: 0,
17644
18005
  cacheWrite: 0,
17645
18006
  },
@@ -17825,13 +18186,13 @@ export const MODELS = {
17825
18186
  reasoning: true,
17826
18187
  input: ["text", "image"],
17827
18188
  cost: {
17828
- input: 0.5,
18189
+ input: 0.6,
17829
18190
  output: 3.5999999999999996,
17830
- cacheRead: 0.3,
18191
+ cacheRead: 0.12,
17831
18192
  cacheWrite: 0,
17832
18193
  },
17833
18194
  contextWindow: 262144,
17834
- maxTokens: 235929,
18195
+ maxTokens: 64000,
17835
18196
  },
17836
18197
  "qwen/qwen3.5-9b": {
17837
18198
  id: "qwen/qwen3.5-9b",
@@ -17910,13 +18271,13 @@ export const MODELS = {
17910
18271
  reasoning: true,
17911
18272
  input: ["text", "image"],
17912
18273
  cost: {
17913
- input: 0.44999999999999996,
17914
- output: 2.7,
18274
+ input: 0.32,
18275
+ output: 3.1999999999999997,
17915
18276
  cacheRead: 0,
17916
18277
  cacheWrite: 0,
17917
18278
  },
17918
18279
  contextWindow: 262144,
17919
- maxTokens: 65536,
18280
+ maxTokens: 81920,
17920
18281
  },
17921
18282
  "qwen/qwen3.6-35b-a3b": {
17922
18283
  id: "qwen/qwen3.6-35b-a3b",
@@ -18068,7 +18429,24 @@ export const MODELS = {
18068
18429
  cacheRead: 0.0375,
18069
18430
  cacheWrite: 0,
18070
18431
  },
18071
- contextWindow: 1000000,
18432
+ contextWindow: 1048575,
18433
+ maxTokens: 235929,
18434
+ },
18435
+ "qwen/qwen3.8-27b:batch": {
18436
+ id: "qwen/qwen3.8-27b:batch",
18437
+ name: "Qwen: Qwen3.8 27B (batch)",
18438
+ api: "openai-completions",
18439
+ provider: "openrouter",
18440
+ baseUrl: "https://openrouter.ai/api/v1",
18441
+ reasoning: true,
18442
+ input: ["text", "image"],
18443
+ cost: {
18444
+ input: 0.16,
18445
+ output: 2,
18446
+ cacheRead: 0.04,
18447
+ cacheWrite: 0,
18448
+ },
18449
+ contextWindow: 262144,
18072
18450
  maxTokens: 235929,
18073
18451
  },
18074
18452
  "qwen/qwen3.8-flash": {
@@ -18105,6 +18483,23 @@ export const MODELS = {
18105
18483
  contextWindow: 1000000,
18106
18484
  maxTokens: 131072,
18107
18485
  },
18486
+ "qwen/qwen3.8-max-0902:batch": {
18487
+ id: "qwen/qwen3.8-max-0902:batch",
18488
+ name: "Qwen: Qwen3.8 Max (0902) (batch)",
18489
+ api: "openai-completions",
18490
+ provider: "openrouter",
18491
+ baseUrl: "https://openrouter.ai/api/v1",
18492
+ reasoning: true,
18493
+ input: ["text", "image"],
18494
+ cost: {
18495
+ input: 1.15,
18496
+ output: 3.45,
18497
+ cacheRead: 0,
18498
+ cacheWrite: 0,
18499
+ },
18500
+ contextWindow: 262144,
18501
+ maxTokens: 131072,
18502
+ },
18108
18503
  "qwen/qwen3.8-max-prime": {
18109
18504
  id: "qwen/qwen3.8-max-prime",
18110
18505
  name: "Qwen: Qwen3.8 Max Prime",
@@ -18165,13 +18560,13 @@ export const MODELS = {
18165
18560
  reasoning: true,
18166
18561
  input: ["text"],
18167
18562
  cost: {
18168
- input: 0.25,
18563
+ input: 0.3,
18169
18564
  output: 1,
18170
- cacheRead: 0.049999999999999996,
18565
+ cacheRead: 0.04,
18171
18566
  cacheWrite: 0,
18172
18567
  },
18173
18568
  contextWindow: 1048576,
18174
- maxTokens: 131072,
18569
+ maxTokens: 943718,
18175
18570
  },
18176
18571
  "rekaai/reka-edge": {
18177
18572
  id: "rekaai/reka-edge",
@@ -18207,6 +18602,23 @@ export const MODELS = {
18207
18602
  contextWindow: 256000,
18208
18603
  maxTokens: 128000,
18209
18604
  },
18605
+ "ricursiveai/ripple-65b-preview": {
18606
+ id: "ricursiveai/ripple-65b-preview",
18607
+ name: "Ricursive: Ripple 65B Preview",
18608
+ api: "openai-completions",
18609
+ provider: "openrouter",
18610
+ baseUrl: "https://openrouter.ai/api/v1",
18611
+ reasoning: true,
18612
+ input: ["text"],
18613
+ cost: {
18614
+ input: 0.19999999999999998,
18615
+ output: 0.6,
18616
+ cacheRead: 0.049999999999999996,
18617
+ cacheWrite: 0,
18618
+ },
18619
+ contextWindow: 1048576,
18620
+ maxTokens: 131072,
18621
+ },
18210
18622
  "sakana/fugu-max": {
18211
18623
  id: "sakana/fugu-max",
18212
18624
  name: "Sakana: Fugu Max",
@@ -18323,7 +18735,7 @@ export const MODELS = {
18323
18735
  cacheRead: 0.09999999999999999,
18324
18736
  cacheWrite: 0,
18325
18737
  },
18326
- contextWindow: 1048576,
18738
+ contextWindow: 1000000,
18327
18739
  maxTokens: 64000,
18328
18740
  },
18329
18741
  "tencent/hy3": {
@@ -18335,14 +18747,31 @@ export const MODELS = {
18335
18747
  reasoning: true,
18336
18748
  input: ["text"],
18337
18749
  cost: {
18338
- input: 0.0825,
18339
- output: 0.33,
18340
- cacheRead: 0.020625,
18750
+ input: 0.13199999999999998,
18751
+ output: 0.5279999999999999,
18752
+ cacheRead: 0.032999999999999995,
18341
18753
  cacheWrite: 0,
18342
18754
  },
18343
18755
  contextWindow: 262144,
18344
18756
  maxTokens: 128000,
18345
18757
  },
18758
+ "tencent/hy4": {
18759
+ id: "tencent/hy4",
18760
+ name: "Tencent: Hy4",
18761
+ api: "openai-completions",
18762
+ provider: "openrouter",
18763
+ baseUrl: "https://openrouter.ai/api/v1",
18764
+ reasoning: true,
18765
+ input: ["text", "image"],
18766
+ cost: {
18767
+ input: 0.417,
18768
+ output: 1.2505,
18769
+ cacheRead: 0.020999999999999998,
18770
+ cacheWrite: 0,
18771
+ },
18772
+ contextWindow: 1048576,
18773
+ maxTokens: 65536,
18774
+ },
18346
18775
  "tencent/hy4-preview": {
18347
18776
  id: "tencent/hy4-preview",
18348
18777
  name: "Tencent: Hy4 preview",
@@ -18352,9 +18781,9 @@ export const MODELS = {
18352
18781
  reasoning: true,
18353
18782
  input: ["text"],
18354
18783
  cost: {
18355
- input: 0.7505999999999999,
18356
- output: 2.2509,
18357
- cacheRead: 0.0378,
18784
+ input: 0.834,
18785
+ output: 2.501,
18786
+ cacheRead: 0.041999999999999996,
18358
18787
  cacheWrite: 0,
18359
18788
  },
18360
18789
  contextWindow: 1048576,
@@ -18377,55 +18806,55 @@ export const MODELS = {
18377
18806
  contextWindow: 524288,
18378
18807
  maxTokens: 471859,
18379
18808
  },
18380
- "thinkingmachines/inkling-small": {
18381
- id: "thinkingmachines/inkling-small",
18382
- name: "Thinking Machines: Inkling Small",
18809
+ "thinkingmachines/inkling-2-small:free": {
18810
+ id: "thinkingmachines/inkling-2-small:free",
18811
+ name: "Thinking Machines: Inkling 2 Small (free)",
18383
18812
  api: "openai-completions",
18384
18813
  provider: "openrouter",
18385
18814
  baseUrl: "https://openrouter.ai/api/v1",
18386
18815
  reasoning: true,
18387
18816
  input: ["text", "image"],
18388
18817
  cost: {
18389
- input: 0.44999999999999996,
18390
- output: 1.2,
18391
- cacheRead: 0.09999999999999999,
18818
+ input: 0,
18819
+ output: 0,
18820
+ cacheRead: 0,
18392
18821
  cacheWrite: 0,
18393
18822
  },
18394
- contextWindow: 524288,
18395
- maxTokens: 262144,
18823
+ contextWindow: 1048576,
18824
+ maxTokens: 131072,
18396
18825
  },
18397
- "thinkingmachines/inkling-small:free": {
18398
- id: "thinkingmachines/inkling-small:free",
18399
- name: "Thinking Machines: Inkling Small (free)",
18826
+ "thinkingmachines/inkling-small": {
18827
+ id: "thinkingmachines/inkling-small",
18828
+ name: "Thinking Machines: Inkling Small",
18400
18829
  api: "openai-completions",
18401
18830
  provider: "openrouter",
18402
18831
  baseUrl: "https://openrouter.ai/api/v1",
18403
18832
  reasoning: true,
18404
18833
  input: ["text", "image"],
18405
18834
  cost: {
18406
- input: 0,
18407
- output: 0,
18408
- cacheRead: 0,
18835
+ input: 0.44999999999999996,
18836
+ output: 1.2,
18837
+ cacheRead: 0.09999999999999999,
18409
18838
  cacheWrite: 0,
18410
18839
  },
18411
- contextWindow: 1048576,
18840
+ contextWindow: 524288,
18412
18841
  maxTokens: 262144,
18413
18842
  },
18414
- "thinkingmachines/inkling:free": {
18415
- id: "thinkingmachines/inkling:free",
18416
- name: "Thinking Machines: Inkling (free)",
18843
+ "thinkingmachines/inkling-small:batch": {
18844
+ id: "thinkingmachines/inkling-small:batch",
18845
+ name: "Thinking Machines: Inkling Small (batch)",
18417
18846
  api: "openai-completions",
18418
18847
  provider: "openrouter",
18419
18848
  baseUrl: "https://openrouter.ai/api/v1",
18420
18849
  reasoning: true,
18421
18850
  input: ["text", "image"],
18422
18851
  cost: {
18423
- input: 0,
18424
- output: 0,
18425
- cacheRead: 0,
18852
+ input: 0.36,
18853
+ output: 0.96,
18854
+ cacheRead: 0.08,
18426
18855
  cacheWrite: 0,
18427
18856
  },
18428
- contextWindow: 1048576,
18857
+ contextWindow: 524288,
18429
18858
  maxTokens: 262144,
18430
18859
  },
18431
18860
  "typesafe/jev-router": {
@@ -18443,7 +18872,7 @@ export const MODELS = {
18443
18872
  cacheWrite: 0,
18444
18873
  },
18445
18874
  contextWindow: 1000000,
18446
- maxTokens: 65536,
18875
+ maxTokens: 64000,
18447
18876
  },
18448
18877
  "unbiased/pareto-26.10": {
18449
18878
  id: "unbiased/pareto-26.10",
@@ -18598,6 +19027,23 @@ export const MODELS = {
18598
19027
  contextWindow: 500000,
18599
19028
  maxTokens: 450000,
18600
19029
  },
19030
+ "x-ai/grok-4.6:batch": {
19031
+ id: "x-ai/grok-4.6:batch",
19032
+ name: "SpaceXAI: Grok 4.6 (batch)",
19033
+ api: "openai-completions",
19034
+ provider: "openrouter",
19035
+ baseUrl: "https://openrouter.ai/api/v1",
19036
+ reasoning: true,
19037
+ input: ["text", "image"],
19038
+ cost: {
19039
+ input: 1.5999999999999999,
19040
+ output: 4.8,
19041
+ cacheRead: 0.39999999999999997,
19042
+ cacheWrite: 0,
19043
+ },
19044
+ contextWindow: 500000,
19045
+ maxTokens: 450000,
19046
+ },
18601
19047
  "x-ai/grok-4.7": {
18602
19048
  id: "x-ai/grok-4.7",
18603
19049
  name: "SpaceXAI: Grok 4.7",
@@ -18615,6 +19061,23 @@ export const MODELS = {
18615
19061
  contextWindow: 500000,
18616
19062
  maxTokens: 450000,
18617
19063
  },
19064
+ "x-ai/grok-4.7:batch": {
19065
+ id: "x-ai/grok-4.7:batch",
19066
+ name: "SpaceXAI: Grok 4.7 (batch)",
19067
+ api: "openai-completions",
19068
+ provider: "openrouter",
19069
+ baseUrl: "https://openrouter.ai/api/v1",
19070
+ reasoning: true,
19071
+ input: ["text", "image"],
19072
+ cost: {
19073
+ input: 1.5999999999999999,
19074
+ output: 4.8,
19075
+ cacheRead: 0.39999999999999997,
19076
+ cacheWrite: 0,
19077
+ },
19078
+ contextWindow: 500000,
19079
+ maxTokens: 450000,
19080
+ },
18618
19081
  "x-ai/grok-build-0.1": {
18619
19082
  id: "x-ai/grok-build-0.1",
18620
19083
  name: "SpaceXAI: Grok Build 0.1",
@@ -18646,7 +19109,7 @@ export const MODELS = {
18646
19109
  cacheRead: 0.08,
18647
19110
  cacheWrite: 0,
18648
19111
  },
18649
- contextWindow: 1050000,
19112
+ contextWindow: 1000000,
18650
19113
  maxTokens: 65536,
18651
19114
  },
18652
19115
  "xiaomi/mimo-v2.5-pro": {
@@ -18663,7 +19126,7 @@ export const MODELS = {
18663
19126
  cacheRead: 0.096,
18664
19127
  cacheWrite: 0,
18665
19128
  },
18666
- contextWindow: 1050000,
19129
+ contextWindow: 1024000,
18667
19130
  maxTokens: 235929,
18668
19131
  },
18669
19132
  "xiaomi/mimo-v2.6-flash": {
@@ -18760,9 +19223,9 @@ export const MODELS = {
18760
19223
  reasoning: true,
18761
19224
  input: ["text"],
18762
19225
  cost: {
18763
- input: 0.13,
18764
- output: 0.85,
18765
- cacheRead: 0.024999999999999998,
19226
+ input: 0.19999999999999998,
19227
+ output: 1.1,
19228
+ cacheRead: 0.03,
18766
19229
  cacheWrite: 0,
18767
19230
  },
18768
19231
  contextWindow: 131072,
@@ -18913,9 +19376,26 @@ export const MODELS = {
18913
19376
  reasoning: true,
18914
19377
  input: ["text"],
18915
19378
  cost: {
18916
- input: 0.006,
19379
+ input: 0.0070999999999999995,
18917
19380
  output: 6.8,
18918
- cacheRead: 0.005,
19381
+ cacheRead: 0.0061,
19382
+ cacheWrite: 0,
19383
+ },
19384
+ contextWindow: 1048576,
19385
+ maxTokens: 943718,
19386
+ },
19387
+ "z-ai/glm-5.2:batch": {
19388
+ id: "z-ai/glm-5.2:batch",
19389
+ name: "Z.ai: GLM 5.2 (batch)",
19390
+ api: "openai-completions",
19391
+ provider: "openrouter",
19392
+ baseUrl: "https://openrouter.ai/api/v1",
19393
+ reasoning: true,
19394
+ input: ["text"],
19395
+ cost: {
19396
+ input: 0.527,
19397
+ output: 1.0750000000000002,
19398
+ cacheRead: 0.17800000000000002,
18919
19399
  cacheWrite: 0,
18920
19400
  },
18921
19401
  contextWindow: 1048576,
@@ -18930,9 +19410,9 @@ export const MODELS = {
18930
19410
  reasoning: true,
18931
19411
  input: ["text"],
18932
19412
  cost: {
18933
- input: 0.08,
18934
- output: 3.5999999999999996,
18935
- cacheRead: 0.07600000000000001,
19413
+ input: 0.0699,
19414
+ output: 1.4,
19415
+ cacheRead: 0.0689,
18936
19416
  cacheWrite: 0,
18937
19417
  },
18938
19418
  contextWindow: 1048576,
@@ -18947,13 +19427,13 @@ export const MODELS = {
18947
19427
  reasoning: true,
18948
19428
  input: ["text", "image"],
18949
19429
  cost: {
18950
- input: 0.0285,
18951
- output: 0.0923,
18952
- cacheRead: 0.0285,
19430
+ input: 0.15,
19431
+ output: 0.5,
19432
+ cacheRead: 0.03,
18953
19433
  cacheWrite: 0,
18954
19434
  },
18955
19435
  contextWindow: 1048576,
18956
- maxTokens: 131072,
19436
+ maxTokens: 943717,
18957
19437
  },
18958
19438
  "z-ai/glm-5.3-flash:batch": {
18959
19439
  id: "z-ai/glm-5.3-flash:batch",
@@ -18964,17 +19444,34 @@ export const MODELS = {
18964
19444
  reasoning: true,
18965
19445
  input: ["text", "image"],
18966
19446
  cost: {
18967
- input: 0.049999999999999996,
18968
- output: 0.18,
18969
- cacheRead: 0.01,
19447
+ input: 0.03,
19448
+ output: 0.061000000000000006,
19449
+ cacheRead: 0.013000000000000001,
19450
+ cacheWrite: 0,
19451
+ },
19452
+ contextWindow: 1048576,
19453
+ maxTokens: 943718,
19454
+ },
19455
+ "z-ai/glm-5.3-flashx": {
19456
+ id: "z-ai/glm-5.3-flashx",
19457
+ name: "Z.ai: GLM 5.3 FlashX",
19458
+ api: "openai-completions",
19459
+ provider: "openrouter",
19460
+ baseUrl: "https://openrouter.ai/api/v1",
19461
+ reasoning: true,
19462
+ input: ["text", "image"],
19463
+ cost: {
19464
+ input: 0.37,
19465
+ output: 1.25,
19466
+ cacheRead: 0.075,
18970
19467
  cacheWrite: 0,
18971
19468
  },
18972
19469
  contextWindow: 1048576,
18973
19470
  maxTokens: 131072,
18974
19471
  },
18975
- "z-ai/glm-5.3-flashx": {
18976
- id: "z-ai/glm-5.3-flashx",
18977
- name: "Z.ai: GLM 5.3 FlashX",
19472
+ "z-ai/glm-5.3-flashx-legal": {
19473
+ id: "z-ai/glm-5.3-flashx-legal",
19474
+ name: "Z.ai: GLM 5.3 FlashX Legal",
18978
19475
  api: "openai-completions",
18979
19476
  provider: "openrouter",
18980
19477
  baseUrl: "https://openrouter.ai/api/v1",
@@ -18983,7 +19480,7 @@ export const MODELS = {
18983
19480
  cost: {
18984
19481
  input: 0.37,
18985
19482
  output: 1.25,
18986
- cacheRead: 0.09,
19483
+ cacheRead: 0.075,
18987
19484
  cacheWrite: 0,
18988
19485
  },
18989
19486
  contextWindow: 1048576,
@@ -19047,13 +19544,13 @@ export const MODELS = {
19047
19544
  provider: "openrouter",
19048
19545
  baseUrl: "https://openrouter.ai/api/v1",
19049
19546
  reasoning: true,
19050
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
19547
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
19051
19548
  input: ["text", "image"],
19052
19549
  cost: {
19053
- input: 10,
19054
- output: 50,
19055
- cacheRead: 0.25,
19056
- cacheWrite: 12.5,
19550
+ input: 8,
19551
+ output: 40,
19552
+ cacheRead: 0.19999999999999998,
19553
+ cacheWrite: 10,
19057
19554
  },
19058
19555
  contextWindow: 1000000,
19059
19556
  maxTokens: 128000,
@@ -19118,7 +19615,7 @@ export const MODELS = {
19118
19615
  reasoning: true,
19119
19616
  input: ["text", "image"],
19120
19617
  cost: {
19121
- input: 0.035,
19618
+ input: 0.006,
19122
19619
  output: 0.5,
19123
19620
  cacheRead: 0.005,
19124
19621
  cacheWrite: 0,
@@ -19135,9 +19632,9 @@ export const MODELS = {
19135
19632
  reasoning: true,
19136
19633
  input: ["text"],
19137
19634
  cost: {
19138
- input: 0.1035,
19635
+ input: 0.0999,
19139
19636
  output: 8,
19140
- cacheRead: 0.09999999999999999,
19637
+ cacheRead: 0.0999,
19141
19638
  cacheWrite: 0,
19142
19639
  },
19143
19640
  contextWindow: 1048576,
@@ -19154,7 +19651,7 @@ export const MODELS = {
19154
19651
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19155
19652
  input: ["text"],
19156
19653
  cost: {
19157
- input: 0.059,
19654
+ input: 0.0434,
19158
19655
  output: 0.3,
19159
19656
  cacheRead: 0.035,
19160
19657
  cacheWrite: 0,
@@ -19205,9 +19702,9 @@ export const MODELS = {
19205
19702
  reasoning: true,
19206
19703
  input: ["text", "image"],
19207
19704
  cost: {
19208
- input: 0.14950000000000002,
19209
- output: 7.15,
19210
- cacheRead: 0.07475000000000001,
19705
+ input: 0.18239999999999998,
19706
+ output: 10.5601,
19707
+ cacheRead: 0.18,
19211
19708
  cacheWrite: 0,
19212
19709
  },
19213
19710
  contextWindow: 1048576,
@@ -19341,9 +19838,9 @@ export const MODELS = {
19341
19838
  reasoning: true,
19342
19839
  input: ["text", "image"],
19343
19840
  cost: {
19344
- input: 0.0285,
19345
- output: 0.0923,
19346
- cacheRead: 0.0285,
19841
+ input: 0.0335,
19842
+ output: 0.083,
19843
+ cacheRead: 0.03,
19347
19844
  cacheWrite: 0,
19348
19845
  },
19349
19846
  contextWindow: 1048576,
@@ -19520,6 +20017,25 @@ export const MODELS = {
19520
20017
  contextWindow: 1048576,
19521
20018
  maxTokens: 131072,
19522
20019
  },
20020
+ "moonshotai/Kimi-K3.1-Pro": {
20021
+ id: "moonshotai/Kimi-K3.1-Pro",
20022
+ name: "Kimi K3.1 Pro",
20023
+ api: "openai-completions",
20024
+ provider: "together",
20025
+ baseUrl: "https://api.together.ai/v1",
20026
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
20027
+ reasoning: true,
20028
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
20029
+ input: ["text", "image"],
20030
+ cost: {
20031
+ input: 2,
20032
+ output: 10,
20033
+ cacheRead: 0.2,
20034
+ cacheWrite: 0,
20035
+ },
20036
+ contextWindow: 1048576,
20037
+ maxTokens: 131072,
20038
+ },
19523
20039
  "nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
19524
20040
  id: "nvidia/NVIDIA-Nemotron-3.5-Super-VL",
19525
20041
  name: "Nemotron 3.5 Super VL 120B A12B",
@@ -19987,13 +20503,13 @@ export const MODELS = {
19987
20503
  reasoning: true,
19988
20504
  input: ["text", "image"],
19989
20505
  cost: {
19990
- input: 0.5,
19991
- output: 3,
19992
- cacheRead: 0.09999999999999999,
19993
- cacheWrite: 0.625,
20506
+ input: 0.06,
20507
+ output: 2.3,
20508
+ cacheRead: 0.059,
20509
+ cacheWrite: 0,
19994
20510
  },
19995
- contextWindow: 1000000,
19996
- maxTokens: 131072,
20511
+ contextWindow: 262144,
20512
+ maxTokens: 262144,
19997
20513
  },
19998
20514
  "alibaba/qwen3.8-flash": {
19999
20515
  id: "alibaba/qwen3.8-flash",
@@ -20155,7 +20671,7 @@ export const MODELS = {
20155
20671
  provider: "vercel-ai-gateway",
20156
20672
  baseUrl: "https://ai-gateway.vercel.sh",
20157
20673
  reasoning: true,
20158
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20674
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20159
20675
  input: ["text", "image"],
20160
20676
  cost: {
20161
20677
  input: 10,
@@ -20173,7 +20689,7 @@ export const MODELS = {
20173
20689
  provider: "vercel-ai-gateway",
20174
20690
  baseUrl: "https://ai-gateway.vercel.sh",
20175
20691
  reasoning: true,
20176
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20692
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20177
20693
  input: ["text", "image"],
20178
20694
  cost: {
20179
20695
  input: 5,
@@ -20191,7 +20707,7 @@ export const MODELS = {
20191
20707
  provider: "vercel-ai-gateway",
20192
20708
  baseUrl: "https://ai-gateway.vercel.sh",
20193
20709
  reasoning: true,
20194
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20710
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20195
20711
  input: ["text", "image"],
20196
20712
  cost: {
20197
20713
  input: 10,
@@ -20209,7 +20725,7 @@ export const MODELS = {
20209
20725
  provider: "vercel-ai-gateway",
20210
20726
  baseUrl: "https://ai-gateway.vercel.sh",
20211
20727
  reasoning: true,
20212
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20728
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20213
20729
  input: ["text", "image"],
20214
20730
  cost: {
20215
20731
  input: 5,
@@ -20220,6 +20736,60 @@ export const MODELS = {
20220
20736
  contextWindow: 1000000,
20221
20737
  maxTokens: 128000,
20222
20738
  },
20739
+ "anthropic/claude-fable-5.2": {
20740
+ id: "anthropic/claude-fable-5.2",
20741
+ name: "Claude Fable 5.2",
20742
+ api: "anthropic-messages",
20743
+ provider: "vercel-ai-gateway",
20744
+ baseUrl: "https://ai-gateway.vercel.sh",
20745
+ reasoning: true,
20746
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20747
+ input: ["text", "image"],
20748
+ cost: {
20749
+ input: 8,
20750
+ output: 40,
20751
+ cacheRead: 0.19999999999999998,
20752
+ cacheWrite: 10,
20753
+ },
20754
+ contextWindow: 1000000,
20755
+ maxTokens: 128000,
20756
+ },
20757
+ "anthropic/claude-fable-5.2-batch": {
20758
+ id: "anthropic/claude-fable-5.2-batch",
20759
+ name: "Claude Fable 5.2 (Batch)",
20760
+ api: "anthropic-messages",
20761
+ provider: "vercel-ai-gateway",
20762
+ baseUrl: "https://ai-gateway.vercel.sh",
20763
+ reasoning: true,
20764
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20765
+ input: ["text", "image"],
20766
+ cost: {
20767
+ input: 4,
20768
+ output: 20,
20769
+ cacheRead: 0.09999999999999999,
20770
+ cacheWrite: 5,
20771
+ },
20772
+ contextWindow: 1000000,
20773
+ maxTokens: 128000,
20774
+ },
20775
+ "anthropic/claude-fable-5.2-fast": {
20776
+ id: "anthropic/claude-fable-5.2-fast",
20777
+ name: "Claude Fable 5.2 (Fast)",
20778
+ api: "anthropic-messages",
20779
+ provider: "vercel-ai-gateway",
20780
+ baseUrl: "https://ai-gateway.vercel.sh",
20781
+ reasoning: true,
20782
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
20783
+ input: ["text", "image"],
20784
+ cost: {
20785
+ input: 16,
20786
+ output: 80,
20787
+ cacheRead: 0.39999999999999997,
20788
+ cacheWrite: 20,
20789
+ },
20790
+ contextWindow: 1000000,
20791
+ maxTokens: 128000,
20792
+ },
20223
20793
  "anthropic/claude-haiku-4.5": {
20224
20794
  id: "anthropic/claude-haiku-4.5",
20225
20795
  name: "Claude Haiku 4.5",
@@ -20506,6 +21076,7 @@ export const MODELS = {
20506
21076
  provider: "vercel-ai-gateway",
20507
21077
  baseUrl: "https://ai-gateway.vercel.sh",
20508
21078
  reasoning: true,
21079
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
20509
21080
  input: ["text", "image"],
20510
21081
  cost: {
20511
21082
  input: 4,
@@ -20523,6 +21094,7 @@ export const MODELS = {
20523
21094
  provider: "vercel-ai-gateway",
20524
21095
  baseUrl: "https://ai-gateway.vercel.sh",
20525
21096
  reasoning: true,
21097
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
20526
21098
  input: ["text", "image"],
20527
21099
  cost: {
20528
21100
  input: 2,
@@ -20540,6 +21112,7 @@ export const MODELS = {
20540
21112
  provider: "vercel-ai-gateway",
20541
21113
  baseUrl: "https://ai-gateway.vercel.sh",
20542
21114
  reasoning: true,
21115
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
20543
21116
  input: ["text", "image"],
20544
21117
  cost: {
20545
21118
  input: 8,
@@ -20659,6 +21232,7 @@ export const MODELS = {
20659
21232
  provider: "vercel-ai-gateway",
20660
21233
  baseUrl: "https://ai-gateway.vercel.sh",
20661
21234
  reasoning: true,
21235
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
20662
21236
  input: ["text", "image"],
20663
21237
  cost: {
20664
21238
  input: 2,
@@ -20676,6 +21250,7 @@ export const MODELS = {
20676
21250
  provider: "vercel-ai-gateway",
20677
21251
  baseUrl: "https://ai-gateway.vercel.sh",
20678
21252
  reasoning: true,
21253
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
20679
21254
  input: ["text", "image"],
20680
21255
  cost: {
20681
21256
  input: 1,
@@ -20865,9 +21440,9 @@ export const MODELS = {
20865
21440
  reasoning: true,
20866
21441
  input: ["text"],
20867
21442
  cost: {
20868
- input: 0.07600000000000001,
20869
- output: 0.153,
20870
- cacheRead: 0.014,
21443
+ input: 0.13,
21444
+ output: 0.26,
21445
+ cacheRead: 0.028,
20871
21446
  cacheWrite: 0,
20872
21447
  },
20873
21448
  contextWindow: 1000000,
@@ -20899,13 +21474,13 @@ export const MODELS = {
20899
21474
  reasoning: true,
20900
21475
  input: ["text"],
20901
21476
  cost: {
20902
- input: 0.66,
20903
- output: 1.9800000000000002,
20904
- cacheRead: 0.022,
21477
+ input: 1.32,
21478
+ output: 3.9600000000000004,
21479
+ cacheRead: 0.13199999999999998,
20905
21480
  cacheWrite: 0,
20906
21481
  },
20907
- contextWindow: 1000000,
20908
- maxTokens: 384000,
21482
+ contextWindow: 1048600,
21483
+ maxTokens: 1048600,
20909
21484
  },
20910
21485
  "deepseek/deepseek-v4-pro-0813": {
20911
21486
  id: "deepseek/deepseek-v4-pro-0813",
@@ -20975,6 +21550,23 @@ export const MODELS = {
20975
21550
  contextWindow: 1048576,
20976
21551
  maxTokens: 262144,
20977
21552
  },
21553
+ "deepseek/deepseek-v4.1-flash-1017-ultrafast": {
21554
+ id: "deepseek/deepseek-v4.1-flash-1017-ultrafast",
21555
+ name: "DeepSeek V4.1 Flash 1017 Ultrafast",
21556
+ api: "anthropic-messages",
21557
+ provider: "vercel-ai-gateway",
21558
+ baseUrl: "https://ai-gateway.vercel.sh",
21559
+ reasoning: true,
21560
+ input: ["text", "image"],
21561
+ cost: {
21562
+ input: 2.4,
21563
+ output: 9.6,
21564
+ cacheRead: 0.048,
21565
+ cacheWrite: 0,
21566
+ },
21567
+ contextWindow: 1048576,
21568
+ maxTokens: 1048576,
21569
+ },
20978
21570
  "deepseek/deepseek-v4.1-flash-fast": {
20979
21571
  id: "deepseek/deepseek-v4.1-flash-fast",
20980
21572
  name: "DeepSeek V4.1 Flash Fast",
@@ -21230,23 +21822,6 @@ export const MODELS = {
21230
21822
  contextWindow: 1000000,
21231
21823
  maxTokens: 64000,
21232
21824
  },
21233
- "google/gemini-3.5-flash-batch": {
21234
- id: "google/gemini-3.5-flash-batch",
21235
- name: "Gemini 3.5 Flash (Batch)",
21236
- api: "anthropic-messages",
21237
- provider: "vercel-ai-gateway",
21238
- baseUrl: "https://ai-gateway.vercel.sh",
21239
- reasoning: true,
21240
- input: ["text", "image"],
21241
- cost: {
21242
- input: 0.75,
21243
- output: 4.5,
21244
- cacheRead: 0.075,
21245
- cacheWrite: 0,
21246
- },
21247
- contextWindow: 1000000,
21248
- maxTokens: 64000,
21249
- },
21250
21825
  "google/gemini-3.5-flash-lite": {
21251
21826
  id: "google/gemini-3.5-flash-lite",
21252
21827
  name: "Gemini 3.5 Flash Lite",
@@ -21332,23 +21907,6 @@ export const MODELS = {
21332
21907
  contextWindow: 1000000,
21333
21908
  maxTokens: 65535,
21334
21909
  },
21335
- "google/gemini-3.7-flash-batch": {
21336
- id: "google/gemini-3.7-flash-batch",
21337
- name: "Gemini 3.7 Flash (Batch)",
21338
- api: "anthropic-messages",
21339
- provider: "vercel-ai-gateway",
21340
- baseUrl: "https://ai-gateway.vercel.sh",
21341
- reasoning: true,
21342
- input: ["text", "image"],
21343
- cost: {
21344
- input: 0.375,
21345
- output: 1.875,
21346
- cacheRead: 0.0375,
21347
- cacheWrite: 0,
21348
- },
21349
- contextWindow: 1000000,
21350
- maxTokens: 65535,
21351
- },
21352
21910
  "google/gemini-3.8-flash": {
21353
21911
  id: "google/gemini-3.8-flash",
21354
21912
  name: "Gemini 3.8 Flash",
@@ -21417,6 +21975,23 @@ export const MODELS = {
21417
21975
  contextWindow: 262144,
21418
21976
  maxTokens: 131072,
21419
21977
  },
21978
+ "humansand/ampersand-v0.1": {
21979
+ id: "humansand/ampersand-v0.1",
21980
+ name: "Ampersand v0.1",
21981
+ api: "anthropic-messages",
21982
+ provider: "vercel-ai-gateway",
21983
+ baseUrl: "https://ai-gateway.vercel.sh",
21984
+ reasoning: true,
21985
+ input: ["text"],
21986
+ cost: {
21987
+ input: 0,
21988
+ output: 0,
21989
+ cacheRead: 0,
21990
+ cacheWrite: 0,
21991
+ },
21992
+ contextWindow: 1000000,
21993
+ maxTokens: 32768,
21994
+ },
21420
21995
  "inception/mercury-2": {
21421
21996
  id: "inception/mercury-2",
21422
21997
  name: "Mercury 2",
@@ -21579,9 +22154,9 @@ export const MODELS = {
21579
22154
  reasoning: true,
21580
22155
  input: ["text"],
21581
22156
  cost: {
21582
- input: 0,
21583
- output: 0,
21584
- cacheRead: 0,
22157
+ input: 0.3,
22158
+ output: 0.8999999999999999,
22159
+ cacheRead: 0.06,
21585
22160
  cacheWrite: 0,
21586
22161
  },
21587
22162
  contextWindow: 1000000,
@@ -21621,9 +22196,9 @@ export const MODELS = {
21621
22196
  contextWindow: 128000,
21622
22197
  maxTokens: 8200,
21623
22198
  },
21624
- "meituan/longcat-2.5-preview": {
21625
- id: "meituan/longcat-2.5-preview",
21626
- name: "LongCat 2.5 Preview",
22199
+ "meituan/longcat-2.5": {
22200
+ id: "meituan/longcat-2.5",
22201
+ name: "LongCat 2.5",
21627
22202
  api: "anthropic-messages",
21628
22203
  provider: "vercel-ai-gateway",
21629
22204
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -21723,6 +22298,23 @@ export const MODELS = {
21723
22298
  contextWindow: 128000,
21724
22299
  maxTokens: 8192,
21725
22300
  },
22301
+ "meta/muse-ember": {
22302
+ id: "meta/muse-ember",
22303
+ name: "Muse Ember",
22304
+ api: "anthropic-messages",
22305
+ provider: "vercel-ai-gateway",
22306
+ baseUrl: "https://ai-gateway.vercel.sh",
22307
+ reasoning: true,
22308
+ input: ["text", "image"],
22309
+ cost: {
22310
+ input: 0.09999999999999999,
22311
+ output: 0.5,
22312
+ cacheRead: 0.004,
22313
+ cacheWrite: 0,
22314
+ },
22315
+ contextWindow: 1048576,
22316
+ maxTokens: 1048576,
22317
+ },
21726
22318
  "meta/muse-glimmer-30b": {
21727
22319
  id: "meta/muse-glimmer-30b",
21728
22320
  name: "Muse Glimmer 30B",
@@ -22313,10 +22905,10 @@ export const MODELS = {
22313
22905
  input: 2,
22314
22906
  output: 10,
22315
22907
  cacheRead: 0.19999999999999998,
22316
- cacheWrite: 2,
22908
+ cacheWrite: 0,
22317
22909
  },
22318
- contextWindow: 1048576,
22319
- maxTokens: 1048576,
22910
+ contextWindow: 1000000,
22911
+ maxTokens: 262144,
22320
22912
  },
22321
22913
  "moonshotai/kimi-k3.1-pro-highspeed": {
22322
22914
  id: "moonshotai/kimi-k3.1-pro-highspeed",
@@ -22395,9 +22987,9 @@ export const MODELS = {
22395
22987
  reasoning: true,
22396
22988
  input: ["text"],
22397
22989
  cost: {
22398
- input: 0.049999999999999996,
22399
- output: 0.19999999999999998,
22400
- cacheRead: 0.01,
22990
+ input: 0.06,
22991
+ output: 0.16,
22992
+ cacheRead: 0.03,
22401
22993
  cacheWrite: 0,
22402
22994
  },
22403
22995
  contextWindow: 262144,
@@ -24398,7 +24990,7 @@ export const MODELS = {
24398
24990
  },
24399
24991
  "tencent/hy3": {
24400
24992
  id: "tencent/hy3",
24401
- name: "Hy3",
24993
+ name: "Tencent Hy3",
24402
24994
  api: "anthropic-messages",
24403
24995
  provider: "vercel-ai-gateway",
24404
24996
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -24413,6 +25005,23 @@ export const MODELS = {
24413
25005
  contextWindow: 262144,
24414
25006
  maxTokens: 262144,
24415
25007
  },
25008
+ "tencent/hy4": {
25009
+ id: "tencent/hy4",
25010
+ name: "Tencent Hy4",
25011
+ api: "anthropic-messages",
25012
+ provider: "vercel-ai-gateway",
25013
+ baseUrl: "https://ai-gateway.vercel.sh",
25014
+ reasoning: true,
25015
+ input: ["text", "image"],
25016
+ cost: {
25017
+ input: 0.417,
25018
+ output: 1.2505,
25019
+ cacheRead: 0.020999999999999998,
25020
+ cacheWrite: 0,
25021
+ },
25022
+ contextWindow: 1024000,
25023
+ maxTokens: 64000,
25024
+ },
24416
25025
  "tencent/hy4-preview": {
24417
25026
  id: "tencent/hy4-preview",
24418
25027
  name: "Tencent Hy4 Preview",
@@ -24464,40 +25073,6 @@ export const MODELS = {
24464
25073
  contextWindow: 1000000,
24465
25074
  maxTokens: 1000000,
24466
25075
  },
24467
- "xiaomi/mimo-v2.5": {
24468
- id: "xiaomi/mimo-v2.5",
24469
- name: "MiMo M2.5",
24470
- api: "anthropic-messages",
24471
- provider: "vercel-ai-gateway",
24472
- baseUrl: "https://ai-gateway.vercel.sh",
24473
- reasoning: true,
24474
- input: ["text", "image"],
24475
- cost: {
24476
- input: 0.119,
24477
- output: 0.238,
24478
- cacheRead: 0.0025,
24479
- cacheWrite: 0,
24480
- },
24481
- contextWindow: 1050000,
24482
- maxTokens: 131100,
24483
- },
24484
- "xiaomi/mimo-v2.5-pro": {
24485
- id: "xiaomi/mimo-v2.5-pro",
24486
- name: "MiMo V2.5 Pro",
24487
- api: "anthropic-messages",
24488
- provider: "vercel-ai-gateway",
24489
- baseUrl: "https://ai-gateway.vercel.sh",
24490
- reasoning: true,
24491
- input: ["text"],
24492
- cost: {
24493
- input: 0.3045,
24494
- output: 0.609,
24495
- cacheRead: 0.0028,
24496
- cacheWrite: 0,
24497
- },
24498
- contextWindow: 1050000,
24499
- maxTokens: 131000,
24500
- },
24501
25076
  "xiaomi/mimo-v2.6-flash": {
24502
25077
  id: "xiaomi/mimo-v2.6-flash",
24503
25078
  name: "MiMo V2.6 Flash",
@@ -24728,9 +25303,9 @@ export const MODELS = {
24728
25303
  reasoning: true,
24729
25304
  input: ["text"],
24730
25305
  cost: {
24731
- input: 0.7999999999999999,
24732
- output: 2.5500000000000003,
24733
- cacheRead: 0.16,
25306
+ input: 1.4,
25307
+ output: 4.4,
25308
+ cacheRead: 0.14,
24734
25309
  cacheWrite: 0,
24735
25310
  },
24736
25311
  contextWindow: 1000000,
@@ -24821,6 +25396,23 @@ export const MODELS = {
24821
25396
  contextWindow: 1000000,
24822
25397
  maxTokens: 131072,
24823
25398
  },
25399
+ "zai/glm-5.3-flashx-legal": {
25400
+ id: "zai/glm-5.3-flashx-legal",
25401
+ name: "GLM 5.3 FlashX Legal",
25402
+ api: "anthropic-messages",
25403
+ provider: "vercel-ai-gateway",
25404
+ baseUrl: "https://ai-gateway.vercel.sh",
25405
+ reasoning: true,
25406
+ input: ["text", "image"],
25407
+ cost: {
25408
+ input: 0.37,
25409
+ output: 1.25,
25410
+ cacheRead: 0.075,
25411
+ cacheWrite: 0,
25412
+ },
25413
+ contextWindow: 1000000,
25414
+ maxTokens: 131072,
25415
+ },
24824
25416
  "zai/glm-5v-turbo": {
24825
25417
  id: "zai/glm-5v-turbo",
24826
25418
  name: "GLM 5V Turbo",