@earendil-works/pi-ai 0.74.0 → 0.74.1

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.
Files changed (63) hide show
  1. package/README.md +76 -6
  2. package/dist/env-api-keys.d.ts.map +1 -1
  3. package/dist/env-api-keys.js +2 -1
  4. package/dist/env-api-keys.js.map +1 -1
  5. package/dist/image-models.d.ts +10 -0
  6. package/dist/image-models.d.ts.map +1 -0
  7. package/dist/image-models.generated.d.ts +425 -0
  8. package/dist/image-models.generated.d.ts.map +1 -0
  9. package/dist/image-models.generated.js +427 -0
  10. package/dist/image-models.generated.js.map +1 -0
  11. package/dist/image-models.js +23 -0
  12. package/dist/image-models.js.map +1 -0
  13. package/dist/images-api-registry.d.ts +14 -0
  14. package/dist/images-api-registry.d.ts.map +1 -0
  15. package/dist/images-api-registry.js +22 -0
  16. package/dist/images-api-registry.js.map +1 -0
  17. package/dist/images.d.ts +4 -0
  18. package/dist/images.d.ts.map +1 -0
  19. package/dist/images.js +14 -0
  20. package/dist/images.js.map +1 -0
  21. package/dist/index.d.ts +4 -0
  22. package/dist/index.d.ts.map +1 -1
  23. package/dist/index.js +4 -0
  24. package/dist/index.js.map +1 -1
  25. package/dist/models.generated.d.ts +1023 -1176
  26. package/dist/models.generated.d.ts.map +1 -1
  27. package/dist/models.generated.js +949 -1362
  28. package/dist/models.generated.js.map +1 -1
  29. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  30. package/dist/providers/amazon-bedrock.js +7 -16
  31. package/dist/providers/amazon-bedrock.js.map +1 -1
  32. package/dist/providers/anthropic.d.ts.map +1 -1
  33. package/dist/providers/anthropic.js +15 -6
  34. package/dist/providers/anthropic.js.map +1 -1
  35. package/dist/providers/images/openrouter.d.ts +3 -0
  36. package/dist/providers/images/openrouter.d.ts.map +1 -0
  37. package/dist/providers/images/openrouter.js +129 -0
  38. package/dist/providers/images/openrouter.js.map +1 -0
  39. package/dist/providers/images/register-builtins.d.ts +4 -0
  40. package/dist/providers/images/register-builtins.d.ts.map +1 -0
  41. package/dist/providers/images/register-builtins.js +34 -0
  42. package/dist/providers/images/register-builtins.js.map +1 -0
  43. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  44. package/dist/providers/openai-codex-responses.js +49 -3
  45. package/dist/providers/openai-codex-responses.js.map +1 -1
  46. package/dist/providers/openai-completions.d.ts.map +1 -1
  47. package/dist/providers/openai-completions.js +32 -14
  48. package/dist/providers/openai-completions.js.map +1 -1
  49. package/dist/providers/simple-options.d.ts.map +1 -1
  50. package/dist/providers/simple-options.js +1 -1
  51. package/dist/providers/simple-options.js.map +1 -1
  52. package/dist/types.d.ts +86 -3
  53. package/dist/types.d.ts.map +1 -1
  54. package/dist/types.js.map +1 -1
  55. package/dist/utils/node-http-proxy.d.ts +10 -0
  56. package/dist/utils/node-http-proxy.d.ts.map +1 -0
  57. package/dist/utils/node-http-proxy.js +97 -0
  58. package/dist/utils/node-http-proxy.js.map +1 -0
  59. package/dist/utils/overflow.d.ts +2 -1
  60. package/dist/utils/overflow.d.ts.map +1 -1
  61. package/dist/utils/overflow.js +6 -1
  62. package/dist/utils/overflow.js.map +1 -1
  63. package/package.json +6 -7
@@ -53,23 +53,6 @@ export const MODELS = {
53
53
  contextWindow: 128000,
54
54
  maxTokens: 8192,
55
55
  },
56
- "amazon.nova-premier-v1:0": {
57
- id: "amazon.nova-premier-v1:0",
58
- name: "Nova Premier",
59
- api: "bedrock-converse-stream",
60
- provider: "amazon-bedrock",
61
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
62
- reasoning: true,
63
- input: ["text", "image"],
64
- cost: {
65
- input: 2.5,
66
- output: 12.5,
67
- cacheRead: 0,
68
- cacheWrite: 0,
69
- },
70
- contextWindow: 1000000,
71
- maxTokens: 16384,
72
- },
73
56
  "amazon.nova-pro-v1:0": {
74
57
  id: "amazon.nova-pro-v1:0",
75
58
  name: "Nova Pro",
@@ -87,91 +70,6 @@ export const MODELS = {
87
70
  contextWindow: 300000,
88
71
  maxTokens: 8192,
89
72
  },
90
- "anthropic.claude-3-5-haiku-20241022-v1:0": {
91
- id: "anthropic.claude-3-5-haiku-20241022-v1:0",
92
- name: "Claude Haiku 3.5",
93
- api: "bedrock-converse-stream",
94
- provider: "amazon-bedrock",
95
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
96
- reasoning: false,
97
- input: ["text", "image"],
98
- cost: {
99
- input: 0.8,
100
- output: 4,
101
- cacheRead: 0.08,
102
- cacheWrite: 1,
103
- },
104
- contextWindow: 200000,
105
- maxTokens: 8192,
106
- },
107
- "anthropic.claude-3-5-sonnet-20240620-v1:0": {
108
- id: "anthropic.claude-3-5-sonnet-20240620-v1:0",
109
- name: "Claude Sonnet 3.5",
110
- api: "bedrock-converse-stream",
111
- provider: "amazon-bedrock",
112
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
113
- reasoning: false,
114
- input: ["text", "image"],
115
- cost: {
116
- input: 3,
117
- output: 15,
118
- cacheRead: 0.3,
119
- cacheWrite: 3.75,
120
- },
121
- contextWindow: 200000,
122
- maxTokens: 8192,
123
- },
124
- "anthropic.claude-3-5-sonnet-20241022-v2:0": {
125
- id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
126
- name: "Claude Sonnet 3.5 v2",
127
- api: "bedrock-converse-stream",
128
- provider: "amazon-bedrock",
129
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
130
- reasoning: false,
131
- input: ["text", "image"],
132
- cost: {
133
- input: 3,
134
- output: 15,
135
- cacheRead: 0.3,
136
- cacheWrite: 3.75,
137
- },
138
- contextWindow: 200000,
139
- maxTokens: 8192,
140
- },
141
- "anthropic.claude-3-7-sonnet-20250219-v1:0": {
142
- id: "anthropic.claude-3-7-sonnet-20250219-v1:0",
143
- name: "Claude Sonnet 3.7",
144
- api: "bedrock-converse-stream",
145
- provider: "amazon-bedrock",
146
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
147
- reasoning: false,
148
- input: ["text", "image"],
149
- cost: {
150
- input: 3,
151
- output: 15,
152
- cacheRead: 0.3,
153
- cacheWrite: 3.75,
154
- },
155
- contextWindow: 200000,
156
- maxTokens: 8192,
157
- },
158
- "anthropic.claude-3-haiku-20240307-v1:0": {
159
- id: "anthropic.claude-3-haiku-20240307-v1:0",
160
- name: "Claude Haiku 3",
161
- api: "bedrock-converse-stream",
162
- provider: "amazon-bedrock",
163
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
164
- reasoning: false,
165
- input: ["text", "image"],
166
- cost: {
167
- input: 0.25,
168
- output: 1.25,
169
- cacheRead: 0,
170
- cacheWrite: 0,
171
- },
172
- contextWindow: 200000,
173
- maxTokens: 4096,
174
- },
175
73
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
176
74
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
177
75
  name: "Claude Haiku 4.5",
@@ -206,23 +104,6 @@ export const MODELS = {
206
104
  contextWindow: 200000,
207
105
  maxTokens: 32000,
208
106
  },
209
- "anthropic.claude-opus-4-20250514-v1:0": {
210
- id: "anthropic.claude-opus-4-20250514-v1:0",
211
- name: "Claude Opus 4",
212
- api: "bedrock-converse-stream",
213
- provider: "amazon-bedrock",
214
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
215
- reasoning: true,
216
- input: ["text", "image"],
217
- cost: {
218
- input: 15,
219
- output: 75,
220
- cacheRead: 1.5,
221
- cacheWrite: 18.75,
222
- },
223
- contextWindow: 200000,
224
- maxTokens: 32000,
225
- },
226
107
  "anthropic.claude-opus-4-5-20251101-v1:0": {
227
108
  id: "anthropic.claude-opus-4-5-20251101-v1:0",
228
109
  name: "Claude Opus 4.5",
@@ -276,9 +157,9 @@ export const MODELS = {
276
157
  contextWindow: 1000000,
277
158
  maxTokens: 128000,
278
159
  },
279
- "anthropic.claude-sonnet-4-20250514-v1:0": {
280
- id: "anthropic.claude-sonnet-4-20250514-v1:0",
281
- name: "Claude Sonnet 4",
160
+ "anthropic.claude-sonnet-4-5-20250929-v1:0": {
161
+ id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
162
+ name: "Claude Sonnet 4.5",
282
163
  api: "bedrock-converse-stream",
283
164
  provider: "amazon-bedrock",
284
165
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -293,9 +174,9 @@ export const MODELS = {
293
174
  contextWindow: 200000,
294
175
  maxTokens: 64000,
295
176
  },
296
- "anthropic.claude-sonnet-4-5-20250929-v1:0": {
297
- id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
298
- name: "Claude Sonnet 4.5",
177
+ "anthropic.claude-sonnet-4-6": {
178
+ id: "anthropic.claude-sonnet-4-6",
179
+ name: "Claude Sonnet 4.6",
299
180
  api: "bedrock-converse-stream",
300
181
  provider: "amazon-bedrock",
301
182
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -307,24 +188,24 @@ export const MODELS = {
307
188
  cacheRead: 0.3,
308
189
  cacheWrite: 3.75,
309
190
  },
310
- contextWindow: 200000,
191
+ contextWindow: 1000000,
311
192
  maxTokens: 64000,
312
193
  },
313
- "anthropic.claude-sonnet-4-6": {
314
- id: "anthropic.claude-sonnet-4-6",
315
- name: "Claude Sonnet 4.6",
194
+ "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
195
+ id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
196
+ name: "Claude Haiku 4.5 (AU)",
316
197
  api: "bedrock-converse-stream",
317
198
  provider: "amazon-bedrock",
318
199
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
319
200
  reasoning: true,
320
201
  input: ["text", "image"],
321
202
  cost: {
322
- input: 3,
323
- output: 15,
324
- cacheRead: 0.3,
325
- cacheWrite: 3.75,
203
+ input: 1,
204
+ output: 5,
205
+ cacheRead: 0.1,
206
+ cacheWrite: 1.25,
326
207
  },
327
- contextWindow: 1000000,
208
+ contextWindow: 200000,
328
209
  maxTokens: 64000,
329
210
  },
330
211
  "au.anthropic.claude-opus-4-6-v1": {
@@ -345,6 +226,23 @@ export const MODELS = {
345
226
  contextWindow: 1000000,
346
227
  maxTokens: 128000,
347
228
  },
229
+ "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
230
+ id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
231
+ name: "Claude Sonnet 4.5 (AU)",
232
+ api: "bedrock-converse-stream",
233
+ provider: "amazon-bedrock",
234
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
235
+ reasoning: true,
236
+ input: ["text", "image"],
237
+ cost: {
238
+ input: 3,
239
+ output: 15,
240
+ cacheRead: 0.3,
241
+ cacheWrite: 3.75,
242
+ },
243
+ contextWindow: 200000,
244
+ maxTokens: 64000,
245
+ },
348
246
  "au.anthropic.claude-sonnet-4-6": {
349
247
  id: "au.anthropic.claude-sonnet-4-6",
350
248
  name: "AU Anthropic Claude Sonnet 4.6",
@@ -483,23 +381,6 @@ export const MODELS = {
483
381
  contextWindow: 1000000,
484
382
  maxTokens: 128000,
485
383
  },
486
- "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
487
- id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
488
- name: "Claude Sonnet 4 (EU)",
489
- api: "bedrock-converse-stream",
490
- provider: "amazon-bedrock",
491
- baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
492
- reasoning: true,
493
- input: ["text", "image"],
494
- cost: {
495
- input: 3,
496
- output: 15,
497
- cacheRead: 0.3,
498
- cacheWrite: 3.75,
499
- },
500
- contextWindow: 200000,
501
- maxTokens: 64000,
502
- },
503
384
  "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
504
385
  id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
505
386
  name: "Claude Sonnet 4.5 (EU)",
@@ -604,23 +485,6 @@ export const MODELS = {
604
485
  contextWindow: 1000000,
605
486
  maxTokens: 128000,
606
487
  },
607
- "global.anthropic.claude-sonnet-4-20250514-v1:0": {
608
- id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
609
- name: "Claude Sonnet 4 (Global)",
610
- api: "bedrock-converse-stream",
611
- provider: "amazon-bedrock",
612
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
613
- reasoning: true,
614
- input: ["text", "image"],
615
- cost: {
616
- input: 3,
617
- output: 15,
618
- cacheRead: 0.3,
619
- cacheWrite: 3.75,
620
- },
621
- contextWindow: 200000,
622
- maxTokens: 64000,
623
- },
624
488
  "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
625
489
  id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
626
490
  name: "Claude Sonnet 4.5 (Global)",
@@ -689,22 +553,57 @@ export const MODELS = {
689
553
  contextWindow: 128000,
690
554
  maxTokens: 4096,
691
555
  },
692
- "meta.llama3-1-405b-instruct-v1:0": {
693
- id: "meta.llama3-1-405b-instruct-v1:0",
694
- name: "Llama 3.1 405B Instruct",
556
+ "jp.anthropic.claude-opus-4-7": {
557
+ id: "jp.anthropic.claude-opus-4-7",
558
+ name: "Claude Opus 4.7 (JP)",
695
559
  api: "bedrock-converse-stream",
696
560
  provider: "amazon-bedrock",
697
561
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
698
- reasoning: false,
699
- input: ["text"],
562
+ reasoning: true,
563
+ thinkingLevelMap: { "xhigh": "xhigh" },
564
+ input: ["text", "image"],
700
565
  cost: {
701
- input: 2.4,
702
- output: 2.4,
703
- cacheRead: 0,
704
- cacheWrite: 0,
566
+ input: 5,
567
+ output: 25,
568
+ cacheRead: 0.5,
569
+ cacheWrite: 6.25,
705
570
  },
706
- contextWindow: 128000,
707
- maxTokens: 4096,
571
+ contextWindow: 1000000,
572
+ maxTokens: 128000,
573
+ },
574
+ "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
575
+ id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
576
+ name: "Claude Sonnet 4.5 (JP)",
577
+ api: "bedrock-converse-stream",
578
+ provider: "amazon-bedrock",
579
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
580
+ reasoning: true,
581
+ input: ["text", "image"],
582
+ cost: {
583
+ input: 3,
584
+ output: 15,
585
+ cacheRead: 0.3,
586
+ cacheWrite: 3.75,
587
+ },
588
+ contextWindow: 200000,
589
+ maxTokens: 64000,
590
+ },
591
+ "jp.anthropic.claude-sonnet-4-6": {
592
+ id: "jp.anthropic.claude-sonnet-4-6",
593
+ name: "Claude Sonnet 4.6 (JP)",
594
+ api: "bedrock-converse-stream",
595
+ provider: "amazon-bedrock",
596
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
597
+ reasoning: true,
598
+ input: ["text", "image"],
599
+ cost: {
600
+ input: 3,
601
+ output: 15,
602
+ cacheRead: 0.3,
603
+ cacheWrite: 3.75,
604
+ },
605
+ contextWindow: 1000000,
606
+ maxTokens: 64000,
708
607
  },
709
608
  "meta.llama3-1-70b-instruct-v1:0": {
710
609
  id: "meta.llama3-1-70b-instruct-v1:0",
@@ -740,128 +639,60 @@ export const MODELS = {
740
639
  contextWindow: 128000,
741
640
  maxTokens: 4096,
742
641
  },
743
- "meta.llama3-2-11b-instruct-v1:0": {
744
- id: "meta.llama3-2-11b-instruct-v1:0",
745
- name: "Llama 3.2 11B Instruct",
642
+ "meta.llama3-3-70b-instruct-v1:0": {
643
+ id: "meta.llama3-3-70b-instruct-v1:0",
644
+ name: "Llama 3.3 70B Instruct",
746
645
  api: "bedrock-converse-stream",
747
646
  provider: "amazon-bedrock",
748
647
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
749
648
  reasoning: false,
750
- input: ["text", "image"],
649
+ input: ["text"],
751
650
  cost: {
752
- input: 0.16,
753
- output: 0.16,
651
+ input: 0.72,
652
+ output: 0.72,
754
653
  cacheRead: 0,
755
654
  cacheWrite: 0,
756
655
  },
757
656
  contextWindow: 128000,
758
657
  maxTokens: 4096,
759
658
  },
760
- "meta.llama3-2-1b-instruct-v1:0": {
761
- id: "meta.llama3-2-1b-instruct-v1:0",
762
- name: "Llama 3.2 1B Instruct",
659
+ "meta.llama4-maverick-17b-instruct-v1:0": {
660
+ id: "meta.llama4-maverick-17b-instruct-v1:0",
661
+ name: "Llama 4 Maverick 17B Instruct",
763
662
  api: "bedrock-converse-stream",
764
663
  provider: "amazon-bedrock",
765
664
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
766
665
  reasoning: false,
767
- input: ["text"],
666
+ input: ["text", "image"],
768
667
  cost: {
769
- input: 0.1,
770
- output: 0.1,
668
+ input: 0.24,
669
+ output: 0.97,
771
670
  cacheRead: 0,
772
671
  cacheWrite: 0,
773
672
  },
774
- contextWindow: 131000,
775
- maxTokens: 4096,
673
+ contextWindow: 1000000,
674
+ maxTokens: 16384,
776
675
  },
777
- "meta.llama3-2-3b-instruct-v1:0": {
778
- id: "meta.llama3-2-3b-instruct-v1:0",
779
- name: "Llama 3.2 3B Instruct",
676
+ "meta.llama4-scout-17b-instruct-v1:0": {
677
+ id: "meta.llama4-scout-17b-instruct-v1:0",
678
+ name: "Llama 4 Scout 17B Instruct",
780
679
  api: "bedrock-converse-stream",
781
680
  provider: "amazon-bedrock",
782
681
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
783
682
  reasoning: false,
784
- input: ["text"],
683
+ input: ["text", "image"],
785
684
  cost: {
786
- input: 0.15,
787
- output: 0.15,
685
+ input: 0.17,
686
+ output: 0.66,
788
687
  cacheRead: 0,
789
688
  cacheWrite: 0,
790
689
  },
791
- contextWindow: 131000,
792
- maxTokens: 4096,
690
+ contextWindow: 3500000,
691
+ maxTokens: 16384,
793
692
  },
794
- "meta.llama3-2-90b-instruct-v1:0": {
795
- id: "meta.llama3-2-90b-instruct-v1:0",
796
- name: "Llama 3.2 90B Instruct",
797
- api: "bedrock-converse-stream",
798
- provider: "amazon-bedrock",
799
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
800
- reasoning: false,
801
- input: ["text", "image"],
802
- cost: {
803
- input: 0.72,
804
- output: 0.72,
805
- cacheRead: 0,
806
- cacheWrite: 0,
807
- },
808
- contextWindow: 128000,
809
- maxTokens: 4096,
810
- },
811
- "meta.llama3-3-70b-instruct-v1:0": {
812
- id: "meta.llama3-3-70b-instruct-v1:0",
813
- name: "Llama 3.3 70B Instruct",
814
- api: "bedrock-converse-stream",
815
- provider: "amazon-bedrock",
816
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
817
- reasoning: false,
818
- input: ["text"],
819
- cost: {
820
- input: 0.72,
821
- output: 0.72,
822
- cacheRead: 0,
823
- cacheWrite: 0,
824
- },
825
- contextWindow: 128000,
826
- maxTokens: 4096,
827
- },
828
- "meta.llama4-maverick-17b-instruct-v1:0": {
829
- id: "meta.llama4-maverick-17b-instruct-v1:0",
830
- name: "Llama 4 Maverick 17B Instruct",
831
- api: "bedrock-converse-stream",
832
- provider: "amazon-bedrock",
833
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
834
- reasoning: false,
835
- input: ["text", "image"],
836
- cost: {
837
- input: 0.24,
838
- output: 0.97,
839
- cacheRead: 0,
840
- cacheWrite: 0,
841
- },
842
- contextWindow: 1000000,
843
- maxTokens: 16384,
844
- },
845
- "meta.llama4-scout-17b-instruct-v1:0": {
846
- id: "meta.llama4-scout-17b-instruct-v1:0",
847
- name: "Llama 4 Scout 17B Instruct",
848
- api: "bedrock-converse-stream",
849
- provider: "amazon-bedrock",
850
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
851
- reasoning: false,
852
- input: ["text", "image"],
853
- cost: {
854
- input: 0.17,
855
- output: 0.66,
856
- cacheRead: 0,
857
- cacheWrite: 0,
858
- },
859
- contextWindow: 3500000,
860
- maxTokens: 16384,
861
- },
862
- "minimax.minimax-m2": {
863
- id: "minimax.minimax-m2",
864
- name: "MiniMax M2",
693
+ "minimax.minimax-m2": {
694
+ id: "minimax.minimax-m2",
695
+ name: "MiniMax M2",
865
696
  api: "bedrock-converse-stream",
866
697
  provider: "amazon-bedrock",
867
698
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1180,7 +1011,7 @@ export const MODELS = {
1180
1011
  cacheWrite: 0,
1181
1012
  },
1182
1013
  contextWindow: 128000,
1183
- maxTokens: 4096,
1014
+ maxTokens: 16384,
1184
1015
  },
1185
1016
  "openai.gpt-oss-20b-1:0": {
1186
1017
  id: "openai.gpt-oss-20b-1:0",
@@ -1197,7 +1028,7 @@ export const MODELS = {
1197
1028
  cacheWrite: 0,
1198
1029
  },
1199
1030
  contextWindow: 128000,
1200
- maxTokens: 4096,
1031
+ maxTokens: 16384,
1201
1032
  },
1202
1033
  "openai.gpt-oss-safeguard-120b": {
1203
1034
  id: "openai.gpt-oss-safeguard-120b",
@@ -1214,7 +1045,7 @@ export const MODELS = {
1214
1045
  cacheWrite: 0,
1215
1046
  },
1216
1047
  contextWindow: 128000,
1217
- maxTokens: 4096,
1048
+ maxTokens: 16384,
1218
1049
  },
1219
1050
  "openai.gpt-oss-safeguard-20b": {
1220
1051
  id: "openai.gpt-oss-safeguard-20b",
@@ -1231,7 +1062,7 @@ export const MODELS = {
1231
1062
  cacheWrite: 0,
1232
1063
  },
1233
1064
  contextWindow: 128000,
1234
- maxTokens: 4096,
1065
+ maxTokens: 16384,
1235
1066
  },
1236
1067
  "qwen.qwen3-235b-a22b-2507-v1:0": {
1237
1068
  id: "qwen.qwen3-235b-a22b-2507-v1:0",
@@ -1386,23 +1217,6 @@ export const MODELS = {
1386
1217
  contextWindow: 200000,
1387
1218
  maxTokens: 32000,
1388
1219
  },
1389
- "us.anthropic.claude-opus-4-20250514-v1:0": {
1390
- id: "us.anthropic.claude-opus-4-20250514-v1:0",
1391
- name: "Claude Opus 4 (US)",
1392
- api: "bedrock-converse-stream",
1393
- provider: "amazon-bedrock",
1394
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1395
- reasoning: true,
1396
- input: ["text", "image"],
1397
- cost: {
1398
- input: 15,
1399
- output: 75,
1400
- cacheRead: 1.5,
1401
- cacheWrite: 18.75,
1402
- },
1403
- contextWindow: 200000,
1404
- maxTokens: 32000,
1405
- },
1406
1220
  "us.anthropic.claude-opus-4-5-20251101-v1:0": {
1407
1221
  id: "us.anthropic.claude-opus-4-5-20251101-v1:0",
1408
1222
  name: "Claude Opus 4.5 (US)",
@@ -1456,9 +1270,9 @@ export const MODELS = {
1456
1270
  contextWindow: 1000000,
1457
1271
  maxTokens: 128000,
1458
1272
  },
1459
- "us.anthropic.claude-sonnet-4-20250514-v1:0": {
1460
- id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
1461
- name: "Claude Sonnet 4 (US)",
1273
+ "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1274
+ id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1275
+ name: "Claude Sonnet 4.5 (US)",
1462
1276
  api: "bedrock-converse-stream",
1463
1277
  provider: "amazon-bedrock",
1464
1278
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1473,9 +1287,9 @@ export const MODELS = {
1473
1287
  contextWindow: 200000,
1474
1288
  maxTokens: 64000,
1475
1289
  },
1476
- "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1477
- id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1478
- name: "Claude Sonnet 4.5 (US)",
1290
+ "us.anthropic.claude-sonnet-4-6": {
1291
+ id: "us.anthropic.claude-sonnet-4-6",
1292
+ name: "Claude Sonnet 4.6 (US)",
1479
1293
  api: "bedrock-converse-stream",
1480
1294
  provider: "amazon-bedrock",
1481
1295
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1487,25 +1301,59 @@ export const MODELS = {
1487
1301
  cacheRead: 0.3,
1488
1302
  cacheWrite: 3.75,
1489
1303
  },
1490
- contextWindow: 200000,
1304
+ contextWindow: 1000000,
1491
1305
  maxTokens: 64000,
1492
1306
  },
1493
- "us.anthropic.claude-sonnet-4-6": {
1494
- id: "us.anthropic.claude-sonnet-4-6",
1495
- name: "Claude Sonnet 4.6 (US)",
1307
+ "us.deepseek.r1-v1:0": {
1308
+ id: "us.deepseek.r1-v1:0",
1309
+ name: "DeepSeek-R1 (US)",
1496
1310
  api: "bedrock-converse-stream",
1497
1311
  provider: "amazon-bedrock",
1498
1312
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1499
1313
  reasoning: true,
1314
+ input: ["text"],
1315
+ cost: {
1316
+ input: 1.35,
1317
+ output: 5.4,
1318
+ cacheRead: 0,
1319
+ cacheWrite: 0,
1320
+ },
1321
+ contextWindow: 128000,
1322
+ maxTokens: 32768,
1323
+ },
1324
+ "us.meta.llama4-maverick-17b-instruct-v1:0": {
1325
+ id: "us.meta.llama4-maverick-17b-instruct-v1:0",
1326
+ name: "Llama 4 Maverick 17B Instruct (US)",
1327
+ api: "bedrock-converse-stream",
1328
+ provider: "amazon-bedrock",
1329
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1330
+ reasoning: false,
1500
1331
  input: ["text", "image"],
1501
1332
  cost: {
1502
- input: 3,
1503
- output: 15,
1504
- cacheRead: 0.3,
1505
- cacheWrite: 3.75,
1333
+ input: 0.24,
1334
+ output: 0.97,
1335
+ cacheRead: 0,
1336
+ cacheWrite: 0,
1506
1337
  },
1507
1338
  contextWindow: 1000000,
1508
- maxTokens: 64000,
1339
+ maxTokens: 16384,
1340
+ },
1341
+ "us.meta.llama4-scout-17b-instruct-v1:0": {
1342
+ id: "us.meta.llama4-scout-17b-instruct-v1:0",
1343
+ name: "Llama 4 Scout 17B Instruct (US)",
1344
+ api: "bedrock-converse-stream",
1345
+ provider: "amazon-bedrock",
1346
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1347
+ reasoning: false,
1348
+ input: ["text", "image"],
1349
+ cost: {
1350
+ input: 0.17,
1351
+ output: 0.66,
1352
+ cacheRead: 0,
1353
+ cacheWrite: 0,
1354
+ },
1355
+ contextWindow: 3500000,
1356
+ maxTokens: 16384,
1509
1357
  },
1510
1358
  "writer.palmyra-x4-v1:0": {
1511
1359
  id: "writer.palmyra-x4-v1:0",
@@ -3601,6 +3449,7 @@ export const MODELS = {
3601
3449
  api: "anthropic-messages",
3602
3450
  provider: "fireworks",
3603
3451
  baseUrl: "https://api.fireworks.ai/inference",
3452
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3604
3453
  reasoning: true,
3605
3454
  input: ["text"],
3606
3455
  cost: {
@@ -3618,6 +3467,7 @@ export const MODELS = {
3618
3467
  api: "anthropic-messages",
3619
3468
  provider: "fireworks",
3620
3469
  baseUrl: "https://api.fireworks.ai/inference",
3470
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3621
3471
  reasoning: true,
3622
3472
  input: ["text"],
3623
3473
  cost: {
@@ -3635,6 +3485,7 @@ export const MODELS = {
3635
3485
  api: "anthropic-messages",
3636
3486
  provider: "fireworks",
3637
3487
  baseUrl: "https://api.fireworks.ai/inference",
3488
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3638
3489
  reasoning: true,
3639
3490
  input: ["text"],
3640
3491
  cost: {
@@ -3652,6 +3503,7 @@ export const MODELS = {
3652
3503
  api: "anthropic-messages",
3653
3504
  provider: "fireworks",
3654
3505
  baseUrl: "https://api.fireworks.ai/inference",
3506
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3655
3507
  reasoning: true,
3656
3508
  input: ["text"],
3657
3509
  cost: {
@@ -3669,6 +3521,7 @@ export const MODELS = {
3669
3521
  api: "anthropic-messages",
3670
3522
  provider: "fireworks",
3671
3523
  baseUrl: "https://api.fireworks.ai/inference",
3524
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3672
3525
  reasoning: true,
3673
3526
  input: ["text"],
3674
3527
  cost: {
@@ -3686,6 +3539,7 @@ export const MODELS = {
3686
3539
  api: "anthropic-messages",
3687
3540
  provider: "fireworks",
3688
3541
  baseUrl: "https://api.fireworks.ai/inference",
3542
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3689
3543
  reasoning: true,
3690
3544
  input: ["text"],
3691
3545
  cost: {
@@ -3703,6 +3557,7 @@ export const MODELS = {
3703
3557
  api: "anthropic-messages",
3704
3558
  provider: "fireworks",
3705
3559
  baseUrl: "https://api.fireworks.ai/inference",
3560
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3706
3561
  reasoning: true,
3707
3562
  input: ["text"],
3708
3563
  cost: {
@@ -3720,6 +3575,7 @@ export const MODELS = {
3720
3575
  api: "anthropic-messages",
3721
3576
  provider: "fireworks",
3722
3577
  baseUrl: "https://api.fireworks.ai/inference",
3578
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3723
3579
  reasoning: true,
3724
3580
  input: ["text"],
3725
3581
  cost: {
@@ -3737,6 +3593,7 @@ export const MODELS = {
3737
3593
  api: "anthropic-messages",
3738
3594
  provider: "fireworks",
3739
3595
  baseUrl: "https://api.fireworks.ai/inference",
3596
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3740
3597
  reasoning: true,
3741
3598
  input: ["text"],
3742
3599
  cost: {
@@ -3754,6 +3611,7 @@ export const MODELS = {
3754
3611
  api: "anthropic-messages",
3755
3612
  provider: "fireworks",
3756
3613
  baseUrl: "https://api.fireworks.ai/inference",
3614
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3757
3615
  reasoning: true,
3758
3616
  input: ["text"],
3759
3617
  cost: {
@@ -3771,6 +3629,7 @@ export const MODELS = {
3771
3629
  api: "anthropic-messages",
3772
3630
  provider: "fireworks",
3773
3631
  baseUrl: "https://api.fireworks.ai/inference",
3632
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3774
3633
  reasoning: false,
3775
3634
  input: ["text"],
3776
3635
  cost: {
@@ -3788,6 +3647,7 @@ export const MODELS = {
3788
3647
  api: "anthropic-messages",
3789
3648
  provider: "fireworks",
3790
3649
  baseUrl: "https://api.fireworks.ai/inference",
3650
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3791
3651
  reasoning: true,
3792
3652
  input: ["text"],
3793
3653
  cost: {
@@ -3805,6 +3665,7 @@ export const MODELS = {
3805
3665
  api: "anthropic-messages",
3806
3666
  provider: "fireworks",
3807
3667
  baseUrl: "https://api.fireworks.ai/inference",
3668
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3808
3669
  reasoning: true,
3809
3670
  input: ["text", "image"],
3810
3671
  cost: {
@@ -3822,6 +3683,7 @@ export const MODELS = {
3822
3683
  api: "anthropic-messages",
3823
3684
  provider: "fireworks",
3824
3685
  baseUrl: "https://api.fireworks.ai/inference",
3686
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3825
3687
  reasoning: true,
3826
3688
  input: ["text", "image"],
3827
3689
  cost: {
@@ -3839,6 +3701,7 @@ export const MODELS = {
3839
3701
  api: "anthropic-messages",
3840
3702
  provider: "fireworks",
3841
3703
  baseUrl: "https://api.fireworks.ai/inference",
3704
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3842
3705
  reasoning: true,
3843
3706
  input: ["text"],
3844
3707
  cost: {
@@ -3856,6 +3719,7 @@ export const MODELS = {
3856
3719
  api: "anthropic-messages",
3857
3720
  provider: "fireworks",
3858
3721
  baseUrl: "https://api.fireworks.ai/inference",
3722
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3859
3723
  reasoning: true,
3860
3724
  input: ["text"],
3861
3725
  cost: {
@@ -3873,6 +3737,7 @@ export const MODELS = {
3873
3737
  api: "anthropic-messages",
3874
3738
  provider: "fireworks",
3875
3739
  baseUrl: "https://api.fireworks.ai/inference",
3740
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3876
3741
  reasoning: true,
3877
3742
  input: ["text"],
3878
3743
  cost: {
@@ -3890,6 +3755,7 @@ export const MODELS = {
3890
3755
  api: "anthropic-messages",
3891
3756
  provider: "fireworks",
3892
3757
  baseUrl: "https://api.fireworks.ai/inference",
3758
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3893
3759
  reasoning: true,
3894
3760
  input: ["text", "image"],
3895
3761
  cost: {
@@ -3907,6 +3773,7 @@ export const MODELS = {
3907
3773
  api: "anthropic-messages",
3908
3774
  provider: "fireworks",
3909
3775
  baseUrl: "https://api.fireworks.ai/inference",
3776
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3910
3777
  reasoning: true,
3911
3778
  input: ["text", "image"],
3912
3779
  cost: {
@@ -3995,25 +3862,6 @@ export const MODELS = {
3995
3862
  contextWindow: 144000,
3996
3863
  maxTokens: 64000,
3997
3864
  },
3998
- "claude-sonnet-4": {
3999
- id: "claude-sonnet-4",
4000
- name: "Claude Sonnet 4",
4001
- api: "anthropic-messages",
4002
- provider: "github-copilot",
4003
- baseUrl: "https://api.individual.githubcopilot.com",
4004
- 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" },
4005
- compat: { "supportsEagerToolInputStreaming": false },
4006
- reasoning: true,
4007
- input: ["text", "image"],
4008
- cost: {
4009
- input: 0,
4010
- output: 0,
4011
- cacheRead: 0,
4012
- cacheWrite: 0,
4013
- },
4014
- contextWindow: 216000,
4015
- maxTokens: 16000,
4016
- },
4017
3865
  "claude-sonnet-4.5": {
4018
3866
  id: "claude-sonnet-4.5",
4019
3867
  name: "Claude Sonnet 4.5",
@@ -4089,25 +3937,6 @@ export const MODELS = {
4089
3937
  contextWindow: 128000,
4090
3938
  maxTokens: 64000,
4091
3939
  },
4092
- "gemini-3-pro-preview": {
4093
- id: "gemini-3-pro-preview",
4094
- name: "Gemini 3 Pro Preview",
4095
- api: "openai-completions",
4096
- provider: "github-copilot",
4097
- baseUrl: "https://api.individual.githubcopilot.com",
4098
- 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" },
4099
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4100
- reasoning: true,
4101
- input: ["text", "image"],
4102
- cost: {
4103
- input: 0,
4104
- output: 0,
4105
- cacheRead: 0,
4106
- cacheWrite: 0,
4107
- },
4108
- contextWindow: 128000,
4109
- maxTokens: 64000,
4110
- },
4111
3940
  "gemini-3.1-pro-preview": {
4112
3941
  id: "gemini-3.1-pro-preview",
4113
3942
  name: "Gemini 3.1 Pro Preview",
@@ -4165,25 +3994,6 @@ export const MODELS = {
4165
3994
  contextWindow: 128000,
4166
3995
  maxTokens: 4096,
4167
3996
  },
4168
- "gpt-5": {
4169
- id: "gpt-5",
4170
- name: "GPT-5",
4171
- api: "openai-responses",
4172
- provider: "github-copilot",
4173
- baseUrl: "https://api.individual.githubcopilot.com",
4174
- 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" },
4175
- reasoning: true,
4176
- thinkingLevelMap: { "off": null },
4177
- input: ["text", "image"],
4178
- cost: {
4179
- input: 0,
4180
- output: 0,
4181
- cacheRead: 0,
4182
- cacheWrite: 0,
4183
- },
4184
- contextWindow: 128000,
4185
- maxTokens: 128000,
4186
- },
4187
3997
  "gpt-5-mini": {
4188
3998
  id: "gpt-5-mini",
4189
3999
  name: "GPT-5-mini",
@@ -4203,15 +4013,15 @@ export const MODELS = {
4203
4013
  contextWindow: 264000,
4204
4014
  maxTokens: 64000,
4205
4015
  },
4206
- "gpt-5.1": {
4207
- id: "gpt-5.1",
4208
- name: "GPT-5.1",
4016
+ "gpt-5.2": {
4017
+ id: "gpt-5.2",
4018
+ name: "GPT-5.2",
4209
4019
  api: "openai-responses",
4210
4020
  provider: "github-copilot",
4211
4021
  baseUrl: "https://api.individual.githubcopilot.com",
4212
4022
  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" },
4213
4023
  reasoning: true,
4214
- thinkingLevelMap: { "off": null },
4024
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4215
4025
  input: ["text", "image"],
4216
4026
  cost: {
4217
4027
  input: 0,
@@ -4222,15 +4032,15 @@ export const MODELS = {
4222
4032
  contextWindow: 264000,
4223
4033
  maxTokens: 64000,
4224
4034
  },
4225
- "gpt-5.1-codex": {
4226
- id: "gpt-5.1-codex",
4227
- name: "GPT-5.1-Codex",
4035
+ "gpt-5.2-codex": {
4036
+ id: "gpt-5.2-codex",
4037
+ name: "GPT-5.2-Codex",
4228
4038
  api: "openai-responses",
4229
4039
  provider: "github-copilot",
4230
4040
  baseUrl: "https://api.individual.githubcopilot.com",
4231
4041
  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" },
4232
4042
  reasoning: true,
4233
- thinkingLevelMap: { "off": null },
4043
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4234
4044
  input: ["text", "image"],
4235
4045
  cost: {
4236
4046
  input: 0,
@@ -4241,15 +4051,15 @@ export const MODELS = {
4241
4051
  contextWindow: 400000,
4242
4052
  maxTokens: 128000,
4243
4053
  },
4244
- "gpt-5.1-codex-max": {
4245
- id: "gpt-5.1-codex-max",
4246
- name: "GPT-5.1-Codex-max",
4054
+ "gpt-5.3-codex": {
4055
+ id: "gpt-5.3-codex",
4056
+ name: "GPT-5.3-Codex",
4247
4057
  api: "openai-responses",
4248
4058
  provider: "github-copilot",
4249
4059
  baseUrl: "https://api.individual.githubcopilot.com",
4250
4060
  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" },
4251
4061
  reasoning: true,
4252
- thinkingLevelMap: { "off": null },
4062
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4253
4063
  input: ["text", "image"],
4254
4064
  cost: {
4255
4065
  input: 0,
@@ -4260,15 +4070,15 @@ export const MODELS = {
4260
4070
  contextWindow: 400000,
4261
4071
  maxTokens: 128000,
4262
4072
  },
4263
- "gpt-5.1-codex-mini": {
4264
- id: "gpt-5.1-codex-mini",
4265
- name: "GPT-5.1-Codex-mini",
4073
+ "gpt-5.4": {
4074
+ id: "gpt-5.4",
4075
+ name: "GPT-5.4",
4266
4076
  api: "openai-responses",
4267
4077
  provider: "github-copilot",
4268
4078
  baseUrl: "https://api.individual.githubcopilot.com",
4269
4079
  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" },
4270
4080
  reasoning: true,
4271
- thinkingLevelMap: { "off": null },
4081
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4272
4082
  input: ["text", "image"],
4273
4083
  cost: {
4274
4084
  input: 0,
@@ -4279,9 +4089,9 @@ export const MODELS = {
4279
4089
  contextWindow: 400000,
4280
4090
  maxTokens: 128000,
4281
4091
  },
4282
- "gpt-5.2": {
4283
- id: "gpt-5.2",
4284
- name: "GPT-5.2",
4092
+ "gpt-5.4-mini": {
4093
+ id: "gpt-5.4-mini",
4094
+ name: "GPT-5.4 Mini",
4285
4095
  api: "openai-responses",
4286
4096
  provider: "github-copilot",
4287
4097
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -4295,12 +4105,12 @@ export const MODELS = {
4295
4105
  cacheRead: 0,
4296
4106
  cacheWrite: 0,
4297
4107
  },
4298
- contextWindow: 264000,
4299
- maxTokens: 64000,
4108
+ contextWindow: 400000,
4109
+ maxTokens: 128000,
4300
4110
  },
4301
- "gpt-5.2-codex": {
4302
- id: "gpt-5.2-codex",
4303
- name: "GPT-5.2-Codex",
4111
+ "gpt-5.5": {
4112
+ id: "gpt-5.5",
4113
+ name: "GPT-5.5",
4304
4114
  api: "openai-responses",
4305
4115
  provider: "github-copilot",
4306
4116
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -4317,92 +4127,16 @@ export const MODELS = {
4317
4127
  contextWindow: 400000,
4318
4128
  maxTokens: 128000,
4319
4129
  },
4320
- "gpt-5.3-codex": {
4321
- id: "gpt-5.3-codex",
4322
- name: "GPT-5.3-Codex",
4323
- api: "openai-responses",
4130
+ "grok-code-fast-1": {
4131
+ id: "grok-code-fast-1",
4132
+ name: "Grok Code Fast 1",
4133
+ api: "openai-completions",
4324
4134
  provider: "github-copilot",
4325
4135
  baseUrl: "https://api.individual.githubcopilot.com",
4326
4136
  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" },
4137
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4327
4138
  reasoning: true,
4328
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4329
- input: ["text", "image"],
4330
- cost: {
4331
- input: 0,
4332
- output: 0,
4333
- cacheRead: 0,
4334
- cacheWrite: 0,
4335
- },
4336
- contextWindow: 400000,
4337
- maxTokens: 128000,
4338
- },
4339
- "gpt-5.4": {
4340
- id: "gpt-5.4",
4341
- name: "GPT-5.4",
4342
- api: "openai-responses",
4343
- provider: "github-copilot",
4344
- baseUrl: "https://api.individual.githubcopilot.com",
4345
- 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" },
4346
- reasoning: true,
4347
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4348
- input: ["text", "image"],
4349
- cost: {
4350
- input: 0,
4351
- output: 0,
4352
- cacheRead: 0,
4353
- cacheWrite: 0,
4354
- },
4355
- contextWindow: 400000,
4356
- maxTokens: 128000,
4357
- },
4358
- "gpt-5.4-mini": {
4359
- id: "gpt-5.4-mini",
4360
- name: "GPT-5.4 Mini",
4361
- api: "openai-responses",
4362
- provider: "github-copilot",
4363
- baseUrl: "https://api.individual.githubcopilot.com",
4364
- 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" },
4365
- reasoning: true,
4366
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4367
- input: ["text", "image"],
4368
- cost: {
4369
- input: 0,
4370
- output: 0,
4371
- cacheRead: 0,
4372
- cacheWrite: 0,
4373
- },
4374
- contextWindow: 400000,
4375
- maxTokens: 128000,
4376
- },
4377
- "gpt-5.5": {
4378
- id: "gpt-5.5",
4379
- name: "GPT-5.5",
4380
- api: "openai-responses",
4381
- provider: "github-copilot",
4382
- baseUrl: "https://api.individual.githubcopilot.com",
4383
- 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" },
4384
- reasoning: true,
4385
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4386
- input: ["text", "image"],
4387
- cost: {
4388
- input: 0,
4389
- output: 0,
4390
- cacheRead: 0,
4391
- cacheWrite: 0,
4392
- },
4393
- contextWindow: 400000,
4394
- maxTokens: 128000,
4395
- },
4396
- "grok-code-fast-1": {
4397
- id: "grok-code-fast-1",
4398
- name: "Grok Code Fast 1",
4399
- api: "openai-completions",
4400
- provider: "github-copilot",
4401
- baseUrl: "https://api.individual.githubcopilot.com",
4402
- 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" },
4403
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4404
- reasoning: true,
4405
- input: ["text"],
4139
+ input: ["text"],
4406
4140
  cost: {
4407
4141
  input: 0,
4408
4142
  output: 0,
@@ -4527,7 +4261,7 @@ export const MODELS = {
4527
4261
  cost: {
4528
4262
  input: 0.1,
4529
4263
  output: 0.4,
4530
- cacheRead: 0.025,
4264
+ cacheRead: 0.01,
4531
4265
  cacheWrite: 0,
4532
4266
  },
4533
4267
  contextWindow: 1048576,
@@ -4705,6 +4439,24 @@ export const MODELS = {
4705
4439
  contextWindow: 1000000,
4706
4440
  maxTokens: 64000,
4707
4441
  },
4442
+ "gemini-3.1-flash-lite": {
4443
+ id: "gemini-3.1-flash-lite",
4444
+ name: "Gemini 3.1 Flash Lite",
4445
+ api: "google-generative-ai",
4446
+ provider: "google",
4447
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4448
+ reasoning: true,
4449
+ thinkingLevelMap: { "off": null },
4450
+ input: ["text", "image"],
4451
+ cost: {
4452
+ input: 0.25,
4453
+ output: 1.5,
4454
+ cacheRead: 0.025,
4455
+ cacheWrite: 0,
4456
+ },
4457
+ contextWindow: 1048576,
4458
+ maxTokens: 65536,
4459
+ },
4708
4460
  "gemini-3.1-flash-lite-preview": {
4709
4461
  id: "gemini-3.1-flash-lite-preview",
4710
4462
  name: "Gemini 3.1 Flash Lite Preview",
@@ -4718,7 +4470,7 @@ export const MODELS = {
4718
4470
  input: 0.25,
4719
4471
  output: 1.5,
4720
4472
  cacheRead: 0.025,
4721
- cacheWrite: 1,
4473
+ cacheWrite: 0,
4722
4474
  },
4723
4475
  contextWindow: 1048576,
4724
4476
  maxTokens: 65536,
@@ -6945,7 +6697,7 @@ export const MODELS = {
6945
6697
  provider: "openai",
6946
6698
  baseUrl: "https://api.openai.com/v1",
6947
6699
  reasoning: true,
6948
- thinkingLevelMap: { "off": null },
6700
+ thinkingLevelMap: { "off": "none" },
6949
6701
  input: ["text", "image"],
6950
6702
  cost: {
6951
6703
  input: 1.25,
@@ -7035,7 +6787,7 @@ export const MODELS = {
7035
6787
  provider: "openai",
7036
6788
  baseUrl: "https://api.openai.com/v1",
7037
6789
  reasoning: true,
7038
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6790
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7039
6791
  input: ["text", "image"],
7040
6792
  cost: {
7041
6793
  input: 1.75,
@@ -7125,7 +6877,7 @@ export const MODELS = {
7125
6877
  provider: "openai",
7126
6878
  baseUrl: "https://api.openai.com/v1",
7127
6879
  reasoning: true,
7128
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6880
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7129
6881
  input: ["text", "image"],
7130
6882
  cost: {
7131
6883
  input: 1.75,
@@ -7161,7 +6913,7 @@ export const MODELS = {
7161
6913
  provider: "openai",
7162
6914
  baseUrl: "https://api.openai.com/v1",
7163
6915
  reasoning: true,
7164
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6916
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7165
6917
  input: ["text", "image"],
7166
6918
  cost: {
7167
6919
  input: 2.5,
@@ -7179,7 +6931,7 @@ export const MODELS = {
7179
6931
  provider: "openai",
7180
6932
  baseUrl: "https://api.openai.com/v1",
7181
6933
  reasoning: true,
7182
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6934
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7183
6935
  input: ["text", "image"],
7184
6936
  cost: {
7185
6937
  input: 0.75,
@@ -7197,7 +6949,7 @@ export const MODELS = {
7197
6949
  provider: "openai",
7198
6950
  baseUrl: "https://api.openai.com/v1",
7199
6951
  reasoning: true,
7200
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6952
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7201
6953
  input: ["text", "image"],
7202
6954
  cost: {
7203
6955
  input: 0.2,
@@ -7233,7 +6985,7 @@ export const MODELS = {
7233
6985
  provider: "openai",
7234
6986
  baseUrl: "https://api.openai.com/v1",
7235
6987
  reasoning: true,
7236
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6988
+ thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
7237
6989
  input: ["text", "image"],
7238
6990
  cost: {
7239
6991
  input: 5,
@@ -7735,6 +7487,25 @@ export const MODELS = {
7735
7487
  contextWindow: 1000000,
7736
7488
  maxTokens: 64000,
7737
7489
  },
7490
+ "deepseek-v4-flash-free": {
7491
+ id: "deepseek-v4-flash-free",
7492
+ name: "DeepSeek V4 Flash Free",
7493
+ api: "openai-completions",
7494
+ provider: "opencode",
7495
+ baseUrl: "https://opencode.ai/zen/v1",
7496
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
7497
+ reasoning: true,
7498
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7499
+ input: ["text"],
7500
+ cost: {
7501
+ input: 0,
7502
+ output: 0,
7503
+ cacheRead: 0,
7504
+ cacheWrite: 0,
7505
+ },
7506
+ contextWindow: 200000,
7507
+ maxTokens: 128000,
7508
+ },
7738
7509
  "gemini-3-flash": {
7739
7510
  id: "gemini-3-flash",
7740
7511
  name: "Gemini 3 Flash",
@@ -8093,23 +7864,6 @@ export const MODELS = {
8093
7864
  contextWindow: 1050000,
8094
7865
  maxTokens: 128000,
8095
7866
  },
8096
- "hy3-preview-free": {
8097
- id: "hy3-preview-free",
8098
- name: "Hy3 preview Free",
8099
- api: "openai-completions",
8100
- provider: "opencode",
8101
- baseUrl: "https://opencode.ai/zen/v1",
8102
- reasoning: true,
8103
- input: ["text"],
8104
- cost: {
8105
- input: 0,
8106
- output: 0,
8107
- cacheRead: 0,
8108
- cacheWrite: 0,
8109
- },
8110
- contextWindow: 256000,
8111
- maxTokens: 64000,
8112
- },
8113
7867
  "kimi-k2.5": {
8114
7868
  id: "kimi-k2.5",
8115
7869
  name: "Kimi K2.5",
@@ -8246,6 +8000,23 @@ export const MODELS = {
8246
8000
  contextWindow: 262144,
8247
8001
  maxTokens: 65536,
8248
8002
  },
8003
+ "qwen3.6-plus-free": {
8004
+ id: "qwen3.6-plus-free",
8005
+ name: "Qwen3.6 Plus Free",
8006
+ api: "anthropic-messages",
8007
+ provider: "opencode",
8008
+ baseUrl: "https://opencode.ai/zen",
8009
+ reasoning: true,
8010
+ input: ["text", "image"],
8011
+ cost: {
8012
+ input: 0,
8013
+ output: 0,
8014
+ cacheRead: 0,
8015
+ cacheWrite: 0,
8016
+ },
8017
+ contextWindow: 262144,
8018
+ maxTokens: 65536,
8019
+ },
8249
8020
  },
8250
8021
  "opencode-go": {
8251
8022
  "deepseek-v4-flash": {
@@ -8391,9 +8162,9 @@ export const MODELS = {
8391
8162
  "minimax-m2.5": {
8392
8163
  id: "minimax-m2.5",
8393
8164
  name: "MiniMax M2.5",
8394
- api: "openai-completions",
8165
+ api: "anthropic-messages",
8395
8166
  provider: "opencode-go",
8396
- baseUrl: "https://opencode.ai/zen/go/v1",
8167
+ baseUrl: "https://opencode.ai/zen/go",
8397
8168
  reasoning: true,
8398
8169
  input: ["text"],
8399
8170
  cost: {
@@ -8613,40 +8384,6 @@ export const MODELS = {
8613
8384
  contextWindow: 200000,
8614
8385
  maxTokens: 8192,
8615
8386
  },
8616
- "anthropic/claude-3.7-sonnet": {
8617
- id: "anthropic/claude-3.7-sonnet",
8618
- name: "Anthropic: Claude 3.7 Sonnet",
8619
- api: "openai-completions",
8620
- provider: "openrouter",
8621
- baseUrl: "https://openrouter.ai/api/v1",
8622
- reasoning: true,
8623
- input: ["text", "image"],
8624
- cost: {
8625
- input: 3,
8626
- output: 15,
8627
- cacheRead: 0.3,
8628
- cacheWrite: 3.75,
8629
- },
8630
- contextWindow: 200000,
8631
- maxTokens: 64000,
8632
- },
8633
- "anthropic/claude-3.7-sonnet:thinking": {
8634
- id: "anthropic/claude-3.7-sonnet:thinking",
8635
- name: "Anthropic: Claude 3.7 Sonnet (thinking)",
8636
- api: "openai-completions",
8637
- provider: "openrouter",
8638
- baseUrl: "https://openrouter.ai/api/v1",
8639
- reasoning: true,
8640
- input: ["text", "image"],
8641
- cost: {
8642
- input: 3,
8643
- output: 15,
8644
- cacheRead: 0.3,
8645
- cacheWrite: 3.75,
8646
- },
8647
- contextWindow: 200000,
8648
- maxTokens: 64000,
8649
- },
8650
8387
  "anthropic/claude-haiku-4.5": {
8651
8388
  id: "anthropic/claude-haiku-4.5",
8652
8389
  name: "Anthropic: Claude Haiku 4.5",
@@ -8769,6 +8506,24 @@ export const MODELS = {
8769
8506
  contextWindow: 1000000,
8770
8507
  maxTokens: 128000,
8771
8508
  },
8509
+ "anthropic/claude-opus-4.7-fast": {
8510
+ id: "anthropic/claude-opus-4.7-fast",
8511
+ name: "Anthropic: Claude Opus 4.7 (Fast)",
8512
+ api: "openai-completions",
8513
+ provider: "openrouter",
8514
+ baseUrl: "https://openrouter.ai/api/v1",
8515
+ reasoning: true,
8516
+ thinkingLevelMap: { "xhigh": "xhigh" },
8517
+ input: ["text", "image"],
8518
+ cost: {
8519
+ input: 30,
8520
+ output: 150,
8521
+ cacheRead: 3,
8522
+ cacheWrite: 37.5,
8523
+ },
8524
+ contextWindow: 1000000,
8525
+ maxTokens: 128000,
8526
+ },
8772
8527
  "anthropic/claude-sonnet-4": {
8773
8528
  id: "anthropic/claude-sonnet-4",
8774
8529
  name: "Anthropic: Claude Sonnet 4",
@@ -8854,6 +8609,23 @@ export const MODELS = {
8854
8609
  contextWindow: 262144,
8855
8610
  maxTokens: 262144,
8856
8611
  },
8612
+ "arcee-ai/trinity-large-thinking:free": {
8613
+ id: "arcee-ai/trinity-large-thinking:free",
8614
+ name: "Arcee AI: Trinity Large Thinking (free)",
8615
+ api: "openai-completions",
8616
+ provider: "openrouter",
8617
+ baseUrl: "https://openrouter.ai/api/v1",
8618
+ reasoning: true,
8619
+ input: ["text"],
8620
+ cost: {
8621
+ input: 0,
8622
+ output: 0,
8623
+ cacheRead: 0,
8624
+ cacheWrite: 0,
8625
+ },
8626
+ contextWindow: 262144,
8627
+ maxTokens: 80000,
8628
+ },
8857
8629
  "arcee-ai/trinity-mini": {
8858
8630
  id: "arcee-ai/trinity-mini",
8859
8631
  name: "Arcee AI: Trinity Mini",
@@ -8936,7 +8708,7 @@ export const MODELS = {
8936
8708
  cacheRead: 0,
8937
8709
  cacheWrite: 0,
8938
8710
  },
8939
- contextWindow: 120000,
8711
+ contextWindow: 131072,
8940
8712
  maxTokens: 8000,
8941
8713
  },
8942
8714
  "baidu/ernie-4.5-vl-28b-a3b": {
@@ -8953,7 +8725,7 @@ export const MODELS = {
8953
8725
  cacheRead: 0,
8954
8726
  cacheWrite: 0,
8955
8727
  },
8956
- contextWindow: 30000,
8728
+ contextWindow: 131072,
8957
8729
  maxTokens: 8000,
8958
8730
  },
8959
8731
  "bytedance-seed/seed-1.6": {
@@ -9101,13 +8873,13 @@ export const MODELS = {
9101
8873
  reasoning: true,
9102
8874
  input: ["text"],
9103
8875
  cost: {
9104
- input: 0.15,
9105
- output: 0.75,
9106
- cacheRead: 0,
8876
+ input: 0.21,
8877
+ output: 0.7899999999999999,
8878
+ cacheRead: 0.13,
9107
8879
  cacheWrite: 0,
9108
8880
  },
9109
- contextWindow: 32768,
9110
- maxTokens: 7168,
8881
+ contextWindow: 163840,
8882
+ maxTokens: 32768,
9111
8883
  },
9112
8884
  "deepseek/deepseek-r1": {
9113
8885
  id: "deepseek/deepseek-r1",
@@ -9123,7 +8895,7 @@ export const MODELS = {
9123
8895
  cacheRead: 0,
9124
8896
  cacheWrite: 0,
9125
8897
  },
9126
- contextWindow: 64000,
8898
+ contextWindow: 163840,
9127
8899
  maxTokens: 16000,
9128
8900
  },
9129
8901
  "deepseek/deepseek-r1-0528": {
@@ -9205,9 +8977,28 @@ export const MODELS = {
9205
8977
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9206
8978
  input: ["text"],
9207
8979
  cost: {
9208
- input: 0.14,
9209
- output: 0.28,
9210
- cacheRead: 0.0028,
8980
+ input: 0.112,
8981
+ output: 0.224,
8982
+ cacheRead: 0.022,
8983
+ cacheWrite: 0,
8984
+ },
8985
+ contextWindow: 1048576,
8986
+ maxTokens: 4096,
8987
+ },
8988
+ "deepseek/deepseek-v4-flash:free": {
8989
+ id: "deepseek/deepseek-v4-flash:free",
8990
+ name: "DeepSeek: DeepSeek V4 Flash (free)",
8991
+ api: "openai-completions",
8992
+ provider: "openrouter",
8993
+ baseUrl: "https://openrouter.ai/api/v1",
8994
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
8995
+ reasoning: true,
8996
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8997
+ input: ["text"],
8998
+ cost: {
8999
+ input: 0,
9000
+ output: 0,
9001
+ cacheRead: 0,
9211
9002
  cacheWrite: 0,
9212
9003
  },
9213
9004
  contextWindow: 1048576,
@@ -9402,6 +9193,23 @@ export const MODELS = {
9402
9193
  contextWindow: 1048576,
9403
9194
  maxTokens: 65536,
9404
9195
  },
9196
+ "google/gemini-3.1-flash-lite": {
9197
+ id: "google/gemini-3.1-flash-lite",
9198
+ name: "Google: Gemini 3.1 Flash Lite",
9199
+ api: "openai-completions",
9200
+ provider: "openrouter",
9201
+ baseUrl: "https://openrouter.ai/api/v1",
9202
+ reasoning: true,
9203
+ input: ["text", "image"],
9204
+ cost: {
9205
+ input: 0.25,
9206
+ output: 1.5,
9207
+ cacheRead: 0.024999999999999998,
9208
+ cacheWrite: 0.08333333333333334,
9209
+ },
9210
+ contextWindow: 1048576,
9211
+ maxTokens: 65536,
9212
+ },
9405
9213
  "google/gemini-3.1-flash-lite-preview": {
9406
9214
  id: "google/gemini-3.1-flash-lite-preview",
9407
9215
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -9450,7 +9258,7 @@ export const MODELS = {
9450
9258
  cacheRead: 0.19999999999999998,
9451
9259
  cacheWrite: 0.375,
9452
9260
  },
9453
- contextWindow: 1048576,
9261
+ contextWindow: 1048756,
9454
9262
  maxTokens: 65536,
9455
9263
  },
9456
9264
  "google/gemma-3-12b-it": {
@@ -9496,13 +9304,13 @@ export const MODELS = {
9496
9304
  reasoning: true,
9497
9305
  input: ["text", "image"],
9498
9306
  cost: {
9499
- input: 0.06,
9500
- output: 0.33,
9307
+ input: 0.07,
9308
+ output: 0.33999999999999997,
9501
9309
  cacheRead: 0,
9502
9310
  cacheWrite: 0,
9503
9311
  },
9504
9312
  contextWindow: 262144,
9505
- maxTokens: 4096,
9313
+ maxTokens: 16384,
9506
9314
  },
9507
9315
  "google/gemma-4-26b-a4b-it:free": {
9508
9316
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9530,8 +9338,8 @@ export const MODELS = {
9530
9338
  reasoning: true,
9531
9339
  input: ["text", "image"],
9532
9340
  cost: {
9533
- input: 0.13,
9534
- output: 0.38,
9341
+ input: 0.12,
9342
+ output: 0.37,
9535
9343
  cacheRead: 0,
9536
9344
  cacheWrite: 0,
9537
9345
  },
@@ -9579,6 +9387,7 @@ export const MODELS = {
9579
9387
  provider: "openrouter",
9580
9388
  baseUrl: "https://openrouter.ai/api/v1",
9581
9389
  reasoning: true,
9390
+ thinkingLevelMap: { "off": null },
9582
9391
  input: ["text"],
9583
9392
  cost: {
9584
9393
  input: 0.25,
@@ -9615,14 +9424,31 @@ export const MODELS = {
9615
9424
  reasoning: false,
9616
9425
  input: ["text"],
9617
9426
  cost: {
9618
- input: 0.08,
9619
- output: 0.24,
9620
- cacheRead: 0.016,
9427
+ input: 0.01,
9428
+ output: 0.03,
9429
+ cacheRead: 0.002,
9621
9430
  cacheWrite: 0,
9622
9431
  },
9623
9432
  contextWindow: 262144,
9624
9433
  maxTokens: 32768,
9625
9434
  },
9435
+ "inclusionai/ring-2.6-1t": {
9436
+ id: "inclusionai/ring-2.6-1t",
9437
+ name: "inclusionAI: Ring-2.6-1T",
9438
+ api: "openai-completions",
9439
+ provider: "openrouter",
9440
+ baseUrl: "https://openrouter.ai/api/v1",
9441
+ reasoning: true,
9442
+ input: ["text"],
9443
+ cost: {
9444
+ input: 0.075,
9445
+ output: 0.625,
9446
+ cacheRead: 0.015,
9447
+ cacheWrite: 0,
9448
+ },
9449
+ contextWindow: 262144,
9450
+ maxTokens: 65536,
9451
+ },
9626
9452
  "kwaipilot/kat-coder-pro-v2": {
9627
9453
  id: "kwaipilot/kat-coder-pro-v2",
9628
9454
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9671,7 +9497,7 @@ export const MODELS = {
9671
9497
  cacheRead: 0,
9672
9498
  cacheWrite: 0,
9673
9499
  },
9674
- contextWindow: 16384,
9500
+ contextWindow: 131072,
9675
9501
  maxTokens: 16384,
9676
9502
  },
9677
9503
  "meta-llama/llama-3.3-70b-instruct": {
@@ -9705,7 +9531,7 @@ export const MODELS = {
9705
9531
  cacheRead: 0,
9706
9532
  cacheWrite: 0,
9707
9533
  },
9708
- contextWindow: 65536,
9534
+ contextWindow: 131072,
9709
9535
  maxTokens: 4096,
9710
9536
  },
9711
9537
  "meta-llama/llama-4-scout": {
@@ -9722,7 +9548,7 @@ export const MODELS = {
9722
9548
  cacheRead: 0,
9723
9549
  cacheWrite: 0,
9724
9550
  },
9725
- contextWindow: 327680,
9551
+ contextWindow: 10000000,
9726
9552
  maxTokens: 16384,
9727
9553
  },
9728
9554
  "minimax/minimax-m1": {
@@ -9756,7 +9582,7 @@ export const MODELS = {
9756
9582
  cacheRead: 0.03,
9757
9583
  cacheWrite: 0,
9758
9584
  },
9759
- contextWindow: 196608,
9585
+ contextWindow: 204800,
9760
9586
  maxTokens: 196608,
9761
9587
  },
9762
9588
  "minimax/minimax-m2.1": {
@@ -9773,7 +9599,7 @@ export const MODELS = {
9773
9599
  cacheRead: 0.03,
9774
9600
  cacheWrite: 0,
9775
9601
  },
9776
- contextWindow: 196608,
9602
+ contextWindow: 204800,
9777
9603
  maxTokens: 196608,
9778
9604
  },
9779
9605
  "minimax/minimax-m2.5": {
@@ -9787,11 +9613,11 @@ export const MODELS = {
9787
9613
  cost: {
9788
9614
  input: 0.15,
9789
9615
  output: 1.15,
9790
- cacheRead: 0.03,
9616
+ cacheRead: 0,
9791
9617
  cacheWrite: 0,
9792
9618
  },
9793
- contextWindow: 196608,
9794
- maxTokens: 131072,
9619
+ contextWindow: 204800,
9620
+ maxTokens: 196608,
9795
9621
  },
9796
9622
  "minimax/minimax-m2.5:free": {
9797
9623
  id: "minimax/minimax-m2.5:free",
@@ -9807,7 +9633,7 @@ export const MODELS = {
9807
9633
  cacheRead: 0,
9808
9634
  cacheWrite: 0,
9809
9635
  },
9810
- contextWindow: 196608,
9636
+ contextWindow: 204800,
9811
9637
  maxTokens: 8192,
9812
9638
  },
9813
9639
  "minimax/minimax-m2.7": {
@@ -9819,13 +9645,13 @@ export const MODELS = {
9819
9645
  reasoning: true,
9820
9646
  input: ["text"],
9821
9647
  cost: {
9822
- input: 0.3,
9648
+ input: 0.27899999999999997,
9823
9649
  output: 1.2,
9824
- cacheRead: 0.059,
9650
+ cacheRead: 0,
9825
9651
  cacheWrite: 0,
9826
9652
  },
9827
- contextWindow: 196608,
9828
- maxTokens: 4096,
9653
+ contextWindow: 204800,
9654
+ maxTokens: 131072,
9829
9655
  },
9830
9656
  "mistralai/codestral-2508": {
9831
9657
  id: "mistralai/codestral-2508",
@@ -10075,12 +9901,12 @@ export const MODELS = {
10075
9901
  input: ["text"],
10076
9902
  cost: {
10077
9903
  input: 0.02,
10078
- output: 0.03,
9904
+ output: 0.04,
10079
9905
  cacheRead: 0,
10080
9906
  cacheWrite: 0,
10081
9907
  },
10082
9908
  contextWindow: 131072,
10083
- maxTokens: 4096,
9909
+ maxTokens: 16384,
10084
9910
  },
10085
9911
  "mistralai/mistral-saba": {
10086
9912
  id: "mistralai/mistral-saba",
@@ -10150,23 +9976,6 @@ export const MODELS = {
10150
9976
  contextWindow: 65536,
10151
9977
  maxTokens: 4096,
10152
9978
  },
10153
- "mistralai/mixtral-8x7b-instruct": {
10154
- id: "mistralai/mixtral-8x7b-instruct",
10155
- name: "Mistral: Mixtral 8x7B Instruct",
10156
- api: "openai-completions",
10157
- provider: "openrouter",
10158
- baseUrl: "https://openrouter.ai/api/v1",
10159
- reasoning: false,
10160
- input: ["text"],
10161
- cost: {
10162
- input: 0.54,
10163
- output: 0.54,
10164
- cacheRead: 0,
10165
- cacheWrite: 0,
10166
- },
10167
- contextWindow: 32768,
10168
- maxTokens: 16384,
10169
- },
10170
9979
  "mistralai/pixtral-large-2411": {
10171
9980
  id: "mistralai/pixtral-large-2411",
10172
9981
  name: "Mistral: Pixtral Large 2411",
@@ -10227,8 +10036,8 @@ export const MODELS = {
10227
10036
  reasoning: false,
10228
10037
  input: ["text"],
10229
10038
  cost: {
10230
- input: 0.39999999999999997,
10231
- output: 2,
10039
+ input: 0.6,
10040
+ output: 2.5,
10232
10041
  cacheRead: 0,
10233
10042
  cacheWrite: 0,
10234
10043
  },
@@ -10246,7 +10055,7 @@ export const MODELS = {
10246
10055
  cost: {
10247
10056
  input: 0.6,
10248
10057
  output: 2.5,
10249
- cacheRead: 0.15,
10058
+ cacheRead: 0,
10250
10059
  cacheWrite: 0,
10251
10060
  },
10252
10061
  contextWindow: 262144,
@@ -10278,13 +10087,13 @@ export const MODELS = {
10278
10087
  reasoning: true,
10279
10088
  input: ["text", "image"],
10280
10089
  cost: {
10281
- input: 0.75,
10282
- output: 3.5,
10283
- cacheRead: 0.15,
10090
+ input: 0.73,
10091
+ output: 3.49,
10092
+ cacheRead: 0.25,
10284
10093
  cacheWrite: 0,
10285
10094
  },
10286
10095
  contextWindow: 262144,
10287
- maxTokens: 16384,
10096
+ maxTokens: 262142,
10288
10097
  },
10289
10098
  "nex-agi/deepseek-v3.1-nex-n1": {
10290
10099
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10303,23 +10112,6 @@ export const MODELS = {
10303
10112
  contextWindow: 131072,
10304
10113
  maxTokens: 163840,
10305
10114
  },
10306
- "nvidia/llama-3.1-nemotron-70b-instruct": {
10307
- id: "nvidia/llama-3.1-nemotron-70b-instruct",
10308
- name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
10309
- api: "openai-completions",
10310
- provider: "openrouter",
10311
- baseUrl: "https://openrouter.ai/api/v1",
10312
- reasoning: false,
10313
- input: ["text"],
10314
- cost: {
10315
- input: 1.2,
10316
- output: 1.2,
10317
- cacheRead: 0,
10318
- cacheWrite: 0,
10319
- },
10320
- contextWindow: 131072,
10321
- maxTokens: 16384,
10322
- },
10323
10115
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
10324
10116
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
10325
10117
  name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -10397,13 +10189,13 @@ export const MODELS = {
10397
10189
  reasoning: true,
10398
10190
  input: ["text"],
10399
10191
  cost: {
10400
- input: 0.09,
10401
- output: 0.44999999999999996,
10192
+ input: 0.09999999999999999,
10193
+ output: 0.5,
10402
10194
  cacheRead: 0,
10403
10195
  cacheWrite: 0,
10404
10196
  },
10405
- contextWindow: 262144,
10406
- maxTokens: 4096,
10197
+ contextWindow: 1000000,
10198
+ maxTokens: 16384,
10407
10199
  },
10408
10200
  "nvidia/nemotron-3-super-120b-a12b:free": {
10409
10201
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -10419,7 +10211,7 @@ export const MODELS = {
10419
10211
  cacheRead: 0,
10420
10212
  cacheWrite: 0,
10421
10213
  },
10422
- contextWindow: 262144,
10214
+ contextWindow: 1000000,
10423
10215
  maxTokens: 262144,
10424
10216
  },
10425
10217
  "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -11226,12 +11018,12 @@ export const MODELS = {
11226
11018
  input: ["text"],
11227
11019
  cost: {
11228
11020
  input: 0.039,
11229
- output: 0.18,
11021
+ output: 0.19,
11230
11022
  cacheRead: 0,
11231
11023
  cacheWrite: 0,
11232
11024
  },
11233
11025
  contextWindow: 131072,
11234
- maxTokens: 4096,
11026
+ maxTokens: 131072,
11235
11027
  },
11236
11028
  "openai/gpt-oss-120b:free": {
11237
11029
  id: "openai/gpt-oss-120b:free",
@@ -11570,7 +11362,7 @@ export const MODELS = {
11570
11362
  cacheRead: 0,
11571
11363
  cacheWrite: 0,
11572
11364
  },
11573
- contextWindow: 32768,
11365
+ contextWindow: 131072,
11574
11366
  maxTokens: 16384,
11575
11367
  },
11576
11368
  "qwen/qwen-2.5-7b-instruct": {
@@ -11587,26 +11379,9 @@ export const MODELS = {
11587
11379
  cacheRead: 0,
11588
11380
  cacheWrite: 0,
11589
11381
  },
11590
- contextWindow: 32768,
11382
+ contextWindow: 131072,
11591
11383
  maxTokens: 32768,
11592
11384
  },
11593
- "qwen/qwen-max": {
11594
- id: "qwen/qwen-max",
11595
- name: "Qwen: Qwen-Max ",
11596
- api: "openai-completions",
11597
- provider: "openrouter",
11598
- baseUrl: "https://openrouter.ai/api/v1",
11599
- reasoning: false,
11600
- input: ["text"],
11601
- cost: {
11602
- input: 1.04,
11603
- output: 4.16,
11604
- cacheRead: 0.20800000000000002,
11605
- cacheWrite: 0,
11606
- },
11607
- contextWindow: 32768,
11608
- maxTokens: 8192,
11609
- },
11610
11385
  "qwen/qwen-plus": {
11611
11386
  id: "qwen/qwen-plus",
11612
11387
  name: "Qwen: Qwen-Plus",
@@ -11658,40 +11433,6 @@ export const MODELS = {
11658
11433
  contextWindow: 1000000,
11659
11434
  maxTokens: 32768,
11660
11435
  },
11661
- "qwen/qwen-turbo": {
11662
- id: "qwen/qwen-turbo",
11663
- name: "Qwen: Qwen-Turbo",
11664
- api: "openai-completions",
11665
- provider: "openrouter",
11666
- baseUrl: "https://openrouter.ai/api/v1",
11667
- reasoning: false,
11668
- input: ["text"],
11669
- cost: {
11670
- input: 0.0325,
11671
- output: 0.13,
11672
- cacheRead: 0.006500000000000001,
11673
- cacheWrite: 0,
11674
- },
11675
- contextWindow: 131072,
11676
- maxTokens: 8192,
11677
- },
11678
- "qwen/qwen-vl-max": {
11679
- id: "qwen/qwen-vl-max",
11680
- name: "Qwen: Qwen VL Max",
11681
- api: "openai-completions",
11682
- provider: "openrouter",
11683
- baseUrl: "https://openrouter.ai/api/v1",
11684
- reasoning: false,
11685
- input: ["text", "image"],
11686
- cost: {
11687
- input: 0.52,
11688
- output: 2.08,
11689
- cacheRead: 0,
11690
- cacheWrite: 0,
11691
- },
11692
- contextWindow: 131072,
11693
- maxTokens: 32768,
11694
- },
11695
11436
  "qwen/qwen3-14b": {
11696
11437
  id: "qwen/qwen3-14b",
11697
11438
  name: "Qwen: Qwen3 14B",
@@ -11701,12 +11442,12 @@ export const MODELS = {
11701
11442
  reasoning: true,
11702
11443
  input: ["text"],
11703
11444
  cost: {
11704
- input: 0.06,
11445
+ input: 0.09999999999999999,
11705
11446
  output: 0.24,
11706
11447
  cacheRead: 0,
11707
11448
  cacheWrite: 0,
11708
11449
  },
11709
- contextWindow: 40960,
11450
+ contextWindow: 131702,
11710
11451
  maxTokens: 40960,
11711
11452
  },
11712
11453
  "qwen/qwen3-235b-a22b": {
@@ -11757,7 +11498,7 @@ export const MODELS = {
11757
11498
  cacheRead: 0,
11758
11499
  cacheWrite: 0,
11759
11500
  },
11760
- contextWindow: 131072,
11501
+ contextWindow: 262144,
11761
11502
  maxTokens: 4096,
11762
11503
  },
11763
11504
  "qwen/qwen3-30b-a3b": {
@@ -11774,7 +11515,7 @@ export const MODELS = {
11774
11515
  cacheRead: 0,
11775
11516
  cacheWrite: 0,
11776
11517
  },
11777
- contextWindow: 40960,
11518
+ contextWindow: 131072,
11778
11519
  maxTokens: 20000,
11779
11520
  },
11780
11521
  "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -11821,12 +11562,12 @@ export const MODELS = {
11821
11562
  input: ["text"],
11822
11563
  cost: {
11823
11564
  input: 0.08,
11824
- output: 0.24,
11825
- cacheRead: 0.04,
11565
+ output: 0.28,
11566
+ cacheRead: 0,
11826
11567
  cacheWrite: 0,
11827
11568
  },
11828
- contextWindow: 40960,
11829
- maxTokens: 40960,
11569
+ contextWindow: 131072,
11570
+ maxTokens: 16384,
11830
11571
  },
11831
11572
  "qwen/qwen3-8b": {
11832
11573
  id: "qwen/qwen3-8b",
@@ -11842,7 +11583,7 @@ export const MODELS = {
11842
11583
  cacheRead: 0.049999999999999996,
11843
11584
  cacheWrite: 0,
11844
11585
  },
11845
- contextWindow: 40960,
11586
+ contextWindow: 131072,
11846
11587
  maxTokens: 8192,
11847
11588
  },
11848
11589
  "qwen/qwen3-coder": {
@@ -11859,7 +11600,7 @@ export const MODELS = {
11859
11600
  cacheRead: 0,
11860
11601
  cacheWrite: 0,
11861
11602
  },
11862
- contextWindow: 262144,
11603
+ contextWindow: 1048576,
11863
11604
  maxTokens: 65536,
11864
11605
  },
11865
11606
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -11944,7 +11685,7 @@ export const MODELS = {
11944
11685
  cacheRead: 0,
11945
11686
  cacheWrite: 0,
11946
11687
  },
11947
- contextWindow: 262000,
11688
+ contextWindow: 1048576,
11948
11689
  maxTokens: 262000,
11949
11690
  },
11950
11691
  "qwen/qwen3-max": {
@@ -12029,7 +11770,7 @@ export const MODELS = {
12029
11770
  cacheRead: 0,
12030
11771
  cacheWrite: 0,
12031
11772
  },
12032
- contextWindow: 131072,
11773
+ contextWindow: 262144,
12033
11774
  maxTokens: 32768,
12034
11775
  },
12035
11776
  "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -12080,7 +11821,7 @@ export const MODELS = {
12080
11821
  cacheRead: 0,
12081
11822
  cacheWrite: 0,
12082
11823
  },
12083
- contextWindow: 131072,
11824
+ contextWindow: 262144,
12084
11825
  maxTokens: 32768,
12085
11826
  },
12086
11827
  "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -12114,7 +11855,7 @@ export const MODELS = {
12114
11855
  cacheRead: 0,
12115
11856
  cacheWrite: 0,
12116
11857
  },
12117
- contextWindow: 131072,
11858
+ contextWindow: 262144,
12118
11859
  maxTokens: 32768,
12119
11860
  },
12120
11861
  "qwen/qwen3-vl-8b-instruct": {
@@ -12131,7 +11872,7 @@ export const MODELS = {
12131
11872
  cacheRead: 0,
12132
11873
  cacheWrite: 0,
12133
11874
  },
12134
- contextWindow: 131072,
11875
+ contextWindow: 256000,
12135
11876
  maxTokens: 32768,
12136
11877
  },
12137
11878
  "qwen/qwen3-vl-8b-thinking": {
@@ -12148,7 +11889,7 @@ export const MODELS = {
12148
11889
  cacheRead: 0,
12149
11890
  cacheWrite: 0,
12150
11891
  },
12151
- contextWindow: 131072,
11892
+ contextWindow: 256000,
12152
11893
  maxTokens: 32768,
12153
11894
  },
12154
11895
  "qwen/qwen3.5-122b-a10b": {
@@ -12279,8 +12020,8 @@ export const MODELS = {
12279
12020
  reasoning: true,
12280
12021
  input: ["text", "image"],
12281
12022
  cost: {
12282
- input: 0.39999999999999997,
12283
- output: 2.4,
12023
+ input: 0.3,
12024
+ output: 1.7999999999999998,
12284
12025
  cacheRead: 0,
12285
12026
  cacheWrite: 0,
12286
12027
  },
@@ -12330,10 +12071,10 @@ export const MODELS = {
12330
12071
  reasoning: true,
12331
12072
  input: ["text", "image"],
12332
12073
  cost: {
12333
- input: 0.25,
12334
- output: 1.5,
12074
+ input: 0.1875,
12075
+ output: 1.125,
12335
12076
  cacheRead: 0,
12336
- cacheWrite: 0.3125,
12077
+ cacheWrite: 0.234375,
12337
12078
  },
12338
12079
  contextWindow: 1000000,
12339
12080
  maxTokens: 65536,
@@ -12457,18 +12198,18 @@ export const MODELS = {
12457
12198
  contextWindow: 262144,
12458
12199
  maxTokens: 65536,
12459
12200
  },
12460
- "tencent/hy3-preview:free": {
12461
- id: "tencent/hy3-preview:free",
12462
- name: "Tencent: Hy3 preview (free)",
12201
+ "tencent/hy3-preview": {
12202
+ id: "tencent/hy3-preview",
12203
+ name: "Tencent: Hy3 preview",
12463
12204
  api: "openai-completions",
12464
12205
  provider: "openrouter",
12465
12206
  baseUrl: "https://openrouter.ai/api/v1",
12466
12207
  reasoning: true,
12467
12208
  input: ["text"],
12468
12209
  cost: {
12469
- input: 0,
12470
- output: 0,
12471
- cacheRead: 0,
12210
+ input: 0.06599999999999999,
12211
+ output: 0.26,
12212
+ cacheRead: 0.029,
12472
12213
  cacheWrite: 0,
12473
12214
  },
12474
12215
  contextWindow: 262144,
@@ -12508,23 +12249,6 @@ export const MODELS = {
12508
12249
  contextWindow: 32768,
12509
12250
  maxTokens: 32768,
12510
12251
  },
12511
- "tngtech/deepseek-r1t2-chimera": {
12512
- id: "tngtech/deepseek-r1t2-chimera",
12513
- name: "TNG: DeepSeek R1T2 Chimera",
12514
- api: "openai-completions",
12515
- provider: "openrouter",
12516
- baseUrl: "https://openrouter.ai/api/v1",
12517
- reasoning: true,
12518
- input: ["text"],
12519
- cost: {
12520
- input: 0.3,
12521
- output: 1.1,
12522
- cacheRead: 0.15,
12523
- cacheWrite: 0,
12524
- },
12525
- contextWindow: 163840,
12526
- maxTokens: 163840,
12527
- },
12528
12252
  "upstage/solar-pro-3": {
12529
12253
  id: "upstage/solar-pro-3",
12530
12254
  name: "Upstage: Solar Pro 3",
@@ -12542,222 +12266,86 @@ export const MODELS = {
12542
12266
  contextWindow: 128000,
12543
12267
  maxTokens: 4096,
12544
12268
  },
12545
- "x-ai/grok-3": {
12546
- id: "x-ai/grok-3",
12547
- name: "xAI: Grok 3",
12269
+ "x-ai/grok-4.20": {
12270
+ id: "x-ai/grok-4.20",
12271
+ name: "xAI: Grok 4.20",
12548
12272
  api: "openai-completions",
12549
12273
  provider: "openrouter",
12550
12274
  baseUrl: "https://openrouter.ai/api/v1",
12551
- reasoning: false,
12552
- input: ["text"],
12275
+ reasoning: true,
12276
+ input: ["text", "image"],
12553
12277
  cost: {
12554
- input: 3,
12555
- output: 15,
12556
- cacheRead: 0.75,
12278
+ input: 1.25,
12279
+ output: 2.5,
12280
+ cacheRead: 0.19999999999999998,
12557
12281
  cacheWrite: 0,
12558
12282
  },
12559
- contextWindow: 131072,
12283
+ contextWindow: 2000000,
12560
12284
  maxTokens: 4096,
12561
12285
  },
12562
- "x-ai/grok-3-beta": {
12563
- id: "x-ai/grok-3-beta",
12564
- name: "xAI: Grok 3 Beta",
12286
+ "x-ai/grok-4.3": {
12287
+ id: "x-ai/grok-4.3",
12288
+ name: "xAI: Grok 4.3",
12565
12289
  api: "openai-completions",
12566
12290
  provider: "openrouter",
12567
12291
  baseUrl: "https://openrouter.ai/api/v1",
12568
- reasoning: false,
12569
- input: ["text"],
12292
+ reasoning: true,
12293
+ input: ["text", "image"],
12570
12294
  cost: {
12571
- input: 3,
12572
- output: 15,
12573
- cacheRead: 0.75,
12295
+ input: 1.25,
12296
+ output: 2.5,
12297
+ cacheRead: 0.19999999999999998,
12574
12298
  cacheWrite: 0,
12575
12299
  },
12576
- contextWindow: 131072,
12300
+ contextWindow: 1000000,
12577
12301
  maxTokens: 4096,
12578
12302
  },
12579
- "x-ai/grok-3-mini": {
12580
- id: "x-ai/grok-3-mini",
12581
- name: "xAI: Grok 3 Mini",
12303
+ "xiaomi/mimo-v2-flash": {
12304
+ id: "xiaomi/mimo-v2-flash",
12305
+ name: "Xiaomi: MiMo-V2-Flash",
12582
12306
  api: "openai-completions",
12583
12307
  provider: "openrouter",
12584
12308
  baseUrl: "https://openrouter.ai/api/v1",
12585
12309
  reasoning: true,
12586
12310
  input: ["text"],
12587
12311
  cost: {
12588
- input: 0.3,
12589
- output: 0.5,
12590
- cacheRead: 0.075,
12312
+ input: 0.09999999999999999,
12313
+ output: 0.3,
12314
+ cacheRead: 0.01,
12591
12315
  cacheWrite: 0,
12592
12316
  },
12593
- contextWindow: 131072,
12594
- maxTokens: 4096,
12317
+ contextWindow: 262144,
12318
+ maxTokens: 65536,
12595
12319
  },
12596
- "x-ai/grok-3-mini-beta": {
12597
- id: "x-ai/grok-3-mini-beta",
12598
- name: "xAI: Grok 3 Mini Beta",
12320
+ "xiaomi/mimo-v2-omni": {
12321
+ id: "xiaomi/mimo-v2-omni",
12322
+ name: "Xiaomi: MiMo-V2-Omni",
12599
12323
  api: "openai-completions",
12600
12324
  provider: "openrouter",
12601
12325
  baseUrl: "https://openrouter.ai/api/v1",
12602
12326
  reasoning: true,
12603
- input: ["text"],
12327
+ input: ["text", "image"],
12604
12328
  cost: {
12605
- input: 0.3,
12606
- output: 0.5,
12607
- cacheRead: 0.075,
12329
+ input: 0.39999999999999997,
12330
+ output: 2,
12331
+ cacheRead: 0.08,
12608
12332
  cacheWrite: 0,
12609
12333
  },
12610
- contextWindow: 131072,
12611
- maxTokens: 4096,
12334
+ contextWindow: 262144,
12335
+ maxTokens: 65536,
12612
12336
  },
12613
- "x-ai/grok-4": {
12614
- id: "x-ai/grok-4",
12615
- name: "xAI: Grok 4",
12337
+ "xiaomi/mimo-v2-pro": {
12338
+ id: "xiaomi/mimo-v2-pro",
12339
+ name: "Xiaomi: MiMo-V2-Pro",
12616
12340
  api: "openai-completions",
12617
12341
  provider: "openrouter",
12618
12342
  baseUrl: "https://openrouter.ai/api/v1",
12619
12343
  reasoning: true,
12620
- input: ["text", "image"],
12344
+ input: ["text"],
12621
12345
  cost: {
12622
- input: 3,
12623
- output: 15,
12624
- cacheRead: 0.75,
12625
- cacheWrite: 0,
12626
- },
12627
- contextWindow: 256000,
12628
- maxTokens: 4096,
12629
- },
12630
- "x-ai/grok-4-fast": {
12631
- id: "x-ai/grok-4-fast",
12632
- name: "xAI: Grok 4 Fast",
12633
- api: "openai-completions",
12634
- provider: "openrouter",
12635
- baseUrl: "https://openrouter.ai/api/v1",
12636
- reasoning: true,
12637
- input: ["text", "image"],
12638
- cost: {
12639
- input: 0.19999999999999998,
12640
- output: 0.5,
12641
- cacheRead: 0.049999999999999996,
12642
- cacheWrite: 0,
12643
- },
12644
- contextWindow: 2000000,
12645
- maxTokens: 30000,
12646
- },
12647
- "x-ai/grok-4.1-fast": {
12648
- id: "x-ai/grok-4.1-fast",
12649
- name: "xAI: Grok 4.1 Fast",
12650
- api: "openai-completions",
12651
- provider: "openrouter",
12652
- baseUrl: "https://openrouter.ai/api/v1",
12653
- reasoning: true,
12654
- input: ["text", "image"],
12655
- cost: {
12656
- input: 0.19999999999999998,
12657
- output: 0.5,
12658
- cacheRead: 0.049999999999999996,
12659
- cacheWrite: 0,
12660
- },
12661
- contextWindow: 2000000,
12662
- maxTokens: 30000,
12663
- },
12664
- "x-ai/grok-4.20": {
12665
- id: "x-ai/grok-4.20",
12666
- name: "xAI: Grok 4.20",
12667
- api: "openai-completions",
12668
- provider: "openrouter",
12669
- baseUrl: "https://openrouter.ai/api/v1",
12670
- reasoning: true,
12671
- input: ["text", "image"],
12672
- cost: {
12673
- input: 1.25,
12674
- output: 2.5,
12675
- cacheRead: 0.19999999999999998,
12676
- cacheWrite: 0,
12677
- },
12678
- contextWindow: 2000000,
12679
- maxTokens: 4096,
12680
- },
12681
- "x-ai/grok-4.3": {
12682
- id: "x-ai/grok-4.3",
12683
- name: "xAI: Grok 4.3",
12684
- api: "openai-completions",
12685
- provider: "openrouter",
12686
- baseUrl: "https://openrouter.ai/api/v1",
12687
- reasoning: true,
12688
- input: ["text", "image"],
12689
- cost: {
12690
- input: 1.25,
12691
- output: 2.5,
12692
- cacheRead: 0.19999999999999998,
12693
- cacheWrite: 0,
12694
- },
12695
- contextWindow: 1000000,
12696
- maxTokens: 4096,
12697
- },
12698
- "x-ai/grok-code-fast-1": {
12699
- id: "x-ai/grok-code-fast-1",
12700
- name: "xAI: Grok Code Fast 1",
12701
- api: "openai-completions",
12702
- provider: "openrouter",
12703
- baseUrl: "https://openrouter.ai/api/v1",
12704
- reasoning: true,
12705
- input: ["text"],
12706
- cost: {
12707
- input: 0.19999999999999998,
12708
- output: 1.5,
12709
- cacheRead: 0.02,
12710
- cacheWrite: 0,
12711
- },
12712
- contextWindow: 256000,
12713
- maxTokens: 10000,
12714
- },
12715
- "xiaomi/mimo-v2-flash": {
12716
- id: "xiaomi/mimo-v2-flash",
12717
- name: "Xiaomi: MiMo-V2-Flash",
12718
- api: "openai-completions",
12719
- provider: "openrouter",
12720
- baseUrl: "https://openrouter.ai/api/v1",
12721
- reasoning: true,
12722
- input: ["text"],
12723
- cost: {
12724
- input: 0.09,
12725
- output: 0.29,
12726
- cacheRead: 0.045,
12727
- cacheWrite: 0,
12728
- },
12729
- contextWindow: 262144,
12730
- maxTokens: 65536,
12731
- },
12732
- "xiaomi/mimo-v2-omni": {
12733
- id: "xiaomi/mimo-v2-omni",
12734
- name: "Xiaomi: MiMo-V2-Omni",
12735
- api: "openai-completions",
12736
- provider: "openrouter",
12737
- baseUrl: "https://openrouter.ai/api/v1",
12738
- reasoning: true,
12739
- input: ["text", "image"],
12740
- cost: {
12741
- input: 0.39999999999999997,
12742
- output: 2,
12743
- cacheRead: 0.08,
12744
- cacheWrite: 0,
12745
- },
12746
- contextWindow: 262144,
12747
- maxTokens: 65536,
12748
- },
12749
- "xiaomi/mimo-v2-pro": {
12750
- id: "xiaomi/mimo-v2-pro",
12751
- name: "Xiaomi: MiMo-V2-Pro",
12752
- api: "openai-completions",
12753
- provider: "openrouter",
12754
- baseUrl: "https://openrouter.ai/api/v1",
12755
- reasoning: true,
12756
- input: ["text"],
12757
- cost: {
12758
- input: 1,
12759
- output: 3,
12760
- cacheRead: 0.19999999999999998,
12346
+ input: 1,
12347
+ output: 3,
12348
+ cacheRead: 0.19999999999999998,
12761
12349
  cacheWrite: 0,
12762
12350
  },
12763
12351
  contextWindow: 1048576,
@@ -12795,7 +12383,7 @@ export const MODELS = {
12795
12383
  cacheWrite: 0,
12796
12384
  },
12797
12385
  contextWindow: 1048576,
12798
- maxTokens: 131072,
12386
+ maxTokens: 16384,
12799
12387
  },
12800
12388
  "z-ai/glm-4-32b": {
12801
12389
  id: "z-ai/glm-4-32b",
@@ -12891,13 +12479,13 @@ export const MODELS = {
12891
12479
  reasoning: true,
12892
12480
  input: ["text"],
12893
12481
  cost: {
12894
- input: 0.39,
12895
- output: 1.9,
12896
- cacheRead: 0,
12482
+ input: 0.43,
12483
+ output: 1.74,
12484
+ cacheRead: 0.08,
12897
12485
  cacheWrite: 0,
12898
12486
  },
12899
- contextWindow: 204800,
12900
- maxTokens: 204800,
12487
+ contextWindow: 202752,
12488
+ maxTokens: 131072,
12901
12489
  },
12902
12490
  "z-ai/glm-4.6v": {
12903
12491
  id: "z-ai/glm-4.6v",
@@ -12925,13 +12513,13 @@ export const MODELS = {
12925
12513
  reasoning: true,
12926
12514
  input: ["text"],
12927
12515
  cost: {
12928
- input: 0.38,
12929
- output: 1.74,
12930
- cacheRead: 0,
12516
+ input: 0.39999999999999997,
12517
+ output: 1.75,
12518
+ cacheRead: 0.08,
12931
12519
  cacheWrite: 0,
12932
12520
  },
12933
12521
  contextWindow: 202752,
12934
- maxTokens: 4096,
12522
+ maxTokens: 131072,
12935
12523
  },
12936
12524
  "z-ai/glm-4.7-flash": {
12937
12525
  id: "z-ai/glm-4.7-flash",
@@ -12993,13 +12581,13 @@ export const MODELS = {
12993
12581
  reasoning: true,
12994
12582
  input: ["text"],
12995
12583
  cost: {
12996
- input: 1.0499999999999998,
12997
- output: 3.5,
12998
- cacheRead: 0.5249999999999999,
12584
+ input: 0.98,
12585
+ output: 3.08,
12586
+ cacheRead: 0.182,
12999
12587
  cacheWrite: 0,
13000
12588
  },
13001
12589
  contextWindow: 202752,
13002
- maxTokens: 65535,
12590
+ maxTokens: 4096,
13003
12591
  },
13004
12592
  "z-ai/glm-5v-turbo": {
13005
12593
  id: "z-ai/glm-5v-turbo",
@@ -13056,103 +12644,425 @@ export const MODELS = {
13056
12644
  id: "~anthropic/claude-sonnet-latest",
13057
12645
  name: "Anthropic Claude Sonnet Latest",
13058
12646
  api: "openai-completions",
13059
- provider: "openrouter",
13060
- baseUrl: "https://openrouter.ai/api/v1",
12647
+ provider: "openrouter",
12648
+ baseUrl: "https://openrouter.ai/api/v1",
12649
+ reasoning: true,
12650
+ input: ["text", "image"],
12651
+ cost: {
12652
+ input: 3,
12653
+ output: 15,
12654
+ cacheRead: 0.3,
12655
+ cacheWrite: 3.75,
12656
+ },
12657
+ contextWindow: 1000000,
12658
+ maxTokens: 128000,
12659
+ },
12660
+ "~google/gemini-flash-latest": {
12661
+ id: "~google/gemini-flash-latest",
12662
+ name: "Google Gemini Flash Latest",
12663
+ api: "openai-completions",
12664
+ provider: "openrouter",
12665
+ baseUrl: "https://openrouter.ai/api/v1",
12666
+ reasoning: true,
12667
+ input: ["text", "image"],
12668
+ cost: {
12669
+ input: 0.5,
12670
+ output: 3,
12671
+ cacheRead: 0.049999999999999996,
12672
+ cacheWrite: 0.08333333333333334,
12673
+ },
12674
+ contextWindow: 1048576,
12675
+ maxTokens: 65536,
12676
+ },
12677
+ "~google/gemini-pro-latest": {
12678
+ id: "~google/gemini-pro-latest",
12679
+ name: "Google Gemini Pro Latest",
12680
+ api: "openai-completions",
12681
+ provider: "openrouter",
12682
+ baseUrl: "https://openrouter.ai/api/v1",
12683
+ reasoning: true,
12684
+ input: ["text", "image"],
12685
+ cost: {
12686
+ input: 2,
12687
+ output: 12,
12688
+ cacheRead: 0.19999999999999998,
12689
+ cacheWrite: 0.375,
12690
+ },
12691
+ contextWindow: 1048576,
12692
+ maxTokens: 65536,
12693
+ },
12694
+ "~moonshotai/kimi-latest": {
12695
+ id: "~moonshotai/kimi-latest",
12696
+ name: "MoonshotAI Kimi Latest",
12697
+ api: "openai-completions",
12698
+ provider: "openrouter",
12699
+ baseUrl: "https://openrouter.ai/api/v1",
12700
+ reasoning: true,
12701
+ input: ["text", "image"],
12702
+ cost: {
12703
+ input: 0.73,
12704
+ output: 3.49,
12705
+ cacheRead: 0.25,
12706
+ cacheWrite: 0,
12707
+ },
12708
+ contextWindow: 262144,
12709
+ maxTokens: 262142,
12710
+ },
12711
+ "~openai/gpt-latest": {
12712
+ id: "~openai/gpt-latest",
12713
+ name: "OpenAI GPT Latest",
12714
+ api: "openai-completions",
12715
+ provider: "openrouter",
12716
+ baseUrl: "https://openrouter.ai/api/v1",
12717
+ reasoning: true,
12718
+ input: ["text", "image"],
12719
+ cost: {
12720
+ input: 5,
12721
+ output: 30,
12722
+ cacheRead: 0.5,
12723
+ cacheWrite: 0,
12724
+ },
12725
+ contextWindow: 1050000,
12726
+ maxTokens: 128000,
12727
+ },
12728
+ "~openai/gpt-mini-latest": {
12729
+ id: "~openai/gpt-mini-latest",
12730
+ name: "OpenAI GPT Mini Latest",
12731
+ api: "openai-completions",
12732
+ provider: "openrouter",
12733
+ baseUrl: "https://openrouter.ai/api/v1",
12734
+ reasoning: true,
12735
+ input: ["text", "image"],
12736
+ cost: {
12737
+ input: 0.75,
12738
+ output: 4.5,
12739
+ cacheRead: 0.075,
12740
+ cacheWrite: 0,
12741
+ },
12742
+ contextWindow: 400000,
12743
+ maxTokens: 128000,
12744
+ },
12745
+ },
12746
+ "together": {
12747
+ "MiniMaxAI/MiniMax-M2.5": {
12748
+ id: "MiniMaxAI/MiniMax-M2.5",
12749
+ name: "MiniMax-M2.5",
12750
+ api: "openai-completions",
12751
+ provider: "together",
12752
+ baseUrl: "https://api.together.ai/v1",
12753
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12754
+ reasoning: true,
12755
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
12756
+ input: ["text"],
12757
+ cost: {
12758
+ input: 0.3,
12759
+ output: 1.2,
12760
+ cacheRead: 0.06,
12761
+ cacheWrite: 0,
12762
+ },
12763
+ contextWindow: 204800,
12764
+ maxTokens: 131072,
12765
+ },
12766
+ "MiniMaxAI/MiniMax-M2.7": {
12767
+ id: "MiniMaxAI/MiniMax-M2.7",
12768
+ name: "MiniMax-M2.7",
12769
+ api: "openai-completions",
12770
+ provider: "together",
12771
+ baseUrl: "https://api.together.ai/v1",
12772
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12773
+ reasoning: true,
12774
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
12775
+ input: ["text"],
12776
+ cost: {
12777
+ input: 0.3,
12778
+ output: 1.2,
12779
+ cacheRead: 0.06,
12780
+ cacheWrite: 0,
12781
+ },
12782
+ contextWindow: 202752,
12783
+ maxTokens: 131072,
12784
+ },
12785
+ "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
12786
+ id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
12787
+ name: "Qwen3 235B A22B Instruct 2507 FP8",
12788
+ api: "openai-completions",
12789
+ provider: "together",
12790
+ baseUrl: "https://api.together.ai/v1",
12791
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12792
+ reasoning: true,
12793
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12794
+ input: ["text"],
12795
+ cost: {
12796
+ input: 0.2,
12797
+ output: 0.6,
12798
+ cacheRead: 0,
12799
+ cacheWrite: 0,
12800
+ },
12801
+ contextWindow: 262144,
12802
+ maxTokens: 262144,
12803
+ },
12804
+ "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
12805
+ id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
12806
+ name: "Qwen3 Coder 480B A35B Instruct",
12807
+ api: "openai-completions",
12808
+ provider: "together",
12809
+ baseUrl: "https://api.together.ai/v1",
12810
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12811
+ reasoning: false,
12812
+ input: ["text"],
12813
+ cost: {
12814
+ input: 2,
12815
+ output: 2,
12816
+ cacheRead: 0,
12817
+ cacheWrite: 0,
12818
+ },
12819
+ contextWindow: 262144,
12820
+ maxTokens: 262144,
12821
+ },
12822
+ "Qwen/Qwen3-Coder-Next-FP8": {
12823
+ id: "Qwen/Qwen3-Coder-Next-FP8",
12824
+ name: "Qwen3 Coder Next FP8",
12825
+ api: "openai-completions",
12826
+ provider: "together",
12827
+ baseUrl: "https://api.together.ai/v1",
12828
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12829
+ reasoning: true,
12830
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12831
+ input: ["text"],
12832
+ cost: {
12833
+ input: 0.5,
12834
+ output: 1.2,
12835
+ cacheRead: 0,
12836
+ cacheWrite: 0,
12837
+ },
12838
+ contextWindow: 262144,
12839
+ maxTokens: 262144,
12840
+ },
12841
+ "Qwen/Qwen3.5-397B-A17B": {
12842
+ id: "Qwen/Qwen3.5-397B-A17B",
12843
+ name: "Qwen3.5 397B A17B",
12844
+ api: "openai-completions",
12845
+ provider: "together",
12846
+ baseUrl: "https://api.together.ai/v1",
12847
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12848
+ reasoning: true,
12849
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12850
+ input: ["text", "image"],
12851
+ cost: {
12852
+ input: 0.6,
12853
+ output: 3.6,
12854
+ cacheRead: 0,
12855
+ cacheWrite: 0,
12856
+ },
12857
+ contextWindow: 262144,
12858
+ maxTokens: 130000,
12859
+ },
12860
+ "Qwen/Qwen3.6-Plus": {
12861
+ id: "Qwen/Qwen3.6-Plus",
12862
+ name: "Qwen3.6 Plus",
12863
+ api: "openai-completions",
12864
+ provider: "together",
12865
+ baseUrl: "https://api.together.ai/v1",
12866
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12867
+ reasoning: true,
12868
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12869
+ input: ["text"],
12870
+ cost: {
12871
+ input: 0.5,
12872
+ output: 3,
12873
+ cacheRead: 0,
12874
+ cacheWrite: 0,
12875
+ },
12876
+ contextWindow: 1000000,
12877
+ maxTokens: 500000,
12878
+ },
12879
+ "deepseek-ai/DeepSeek-V3": {
12880
+ id: "deepseek-ai/DeepSeek-V3",
12881
+ name: "DeepSeek V3",
12882
+ api: "openai-completions",
12883
+ provider: "together",
12884
+ baseUrl: "https://api.together.ai/v1",
12885
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12886
+ reasoning: true,
12887
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12888
+ input: ["text"],
12889
+ cost: {
12890
+ input: 1.25,
12891
+ output: 1.25,
12892
+ cacheRead: 0,
12893
+ cacheWrite: 0,
12894
+ },
12895
+ contextWindow: 131072,
12896
+ maxTokens: 131072,
12897
+ },
12898
+ "deepseek-ai/DeepSeek-V3-1": {
12899
+ id: "deepseek-ai/DeepSeek-V3-1",
12900
+ name: "DeepSeek V3.1",
12901
+ api: "openai-completions",
12902
+ provider: "together",
12903
+ baseUrl: "https://api.together.ai/v1",
12904
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12905
+ reasoning: true,
12906
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12907
+ input: ["text"],
12908
+ cost: {
12909
+ input: 0.6,
12910
+ output: 1.7,
12911
+ cacheRead: 0,
12912
+ cacheWrite: 0,
12913
+ },
12914
+ contextWindow: 131072,
12915
+ maxTokens: 131072,
12916
+ },
12917
+ "deepseek-ai/DeepSeek-V4-Pro": {
12918
+ id: "deepseek-ai/DeepSeek-V4-Pro",
12919
+ name: "DeepSeek V4 Pro",
12920
+ api: "openai-completions",
12921
+ provider: "together",
12922
+ baseUrl: "https://api.together.ai/v1",
12923
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12924
+ reasoning: true,
12925
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
12926
+ input: ["text"],
12927
+ cost: {
12928
+ input: 2.1,
12929
+ output: 4.4,
12930
+ cacheRead: 0.2,
12931
+ cacheWrite: 0,
12932
+ },
12933
+ contextWindow: 512000,
12934
+ maxTokens: 384000,
12935
+ },
12936
+ "essentialai/Rnj-1-Instruct": {
12937
+ id: "essentialai/Rnj-1-Instruct",
12938
+ name: "Rnj-1 Instruct",
12939
+ api: "openai-completions",
12940
+ provider: "together",
12941
+ baseUrl: "https://api.together.ai/v1",
12942
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12943
+ reasoning: false,
12944
+ input: ["text"],
12945
+ cost: {
12946
+ input: 0.15,
12947
+ output: 0.15,
12948
+ cacheRead: 0,
12949
+ cacheWrite: 0,
12950
+ },
12951
+ contextWindow: 32768,
12952
+ maxTokens: 32768,
12953
+ },
12954
+ "google/gemma-4-31B-it": {
12955
+ id: "google/gemma-4-31B-it",
12956
+ name: "Gemma 4 31B Instruct",
12957
+ api: "openai-completions",
12958
+ provider: "together",
12959
+ baseUrl: "https://api.together.ai/v1",
12960
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13061
12961
  reasoning: true,
12962
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13062
12963
  input: ["text", "image"],
13063
12964
  cost: {
13064
- input: 3,
13065
- output: 15,
13066
- cacheRead: 0.3,
13067
- cacheWrite: 3.75,
12965
+ input: 0.2,
12966
+ output: 0.5,
12967
+ cacheRead: 0,
12968
+ cacheWrite: 0,
13068
12969
  },
13069
- contextWindow: 1000000,
13070
- maxTokens: 128000,
12970
+ contextWindow: 262144,
12971
+ maxTokens: 131072,
13071
12972
  },
13072
- "~google/gemini-flash-latest": {
13073
- id: "~google/gemini-flash-latest",
13074
- name: "Google Gemini Flash Latest",
12973
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
12974
+ id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
12975
+ name: "Llama 3.3 70B",
13075
12976
  api: "openai-completions",
13076
- provider: "openrouter",
13077
- baseUrl: "https://openrouter.ai/api/v1",
13078
- reasoning: true,
13079
- input: ["text", "image"],
12977
+ provider: "together",
12978
+ baseUrl: "https://api.together.ai/v1",
12979
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12980
+ reasoning: false,
12981
+ input: ["text"],
13080
12982
  cost: {
13081
- input: 0.5,
13082
- output: 3,
13083
- cacheRead: 0.049999999999999996,
13084
- cacheWrite: 0.08333333333333334,
12983
+ input: 0.88,
12984
+ output: 0.88,
12985
+ cacheRead: 0,
12986
+ cacheWrite: 0,
13085
12987
  },
13086
- contextWindow: 1048576,
13087
- maxTokens: 65536,
12988
+ contextWindow: 131072,
12989
+ maxTokens: 131072,
13088
12990
  },
13089
- "~google/gemini-pro-latest": {
13090
- id: "~google/gemini-pro-latest",
13091
- name: "Google Gemini Pro Latest",
12991
+ "moonshotai/Kimi-K2.5": {
12992
+ id: "moonshotai/Kimi-K2.5",
12993
+ name: "Kimi K2.5",
13092
12994
  api: "openai-completions",
13093
- provider: "openrouter",
13094
- baseUrl: "https://openrouter.ai/api/v1",
12995
+ provider: "together",
12996
+ baseUrl: "https://api.together.ai/v1",
12997
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13095
12998
  reasoning: true,
12999
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13096
13000
  input: ["text", "image"],
13097
13001
  cost: {
13098
- input: 2,
13099
- output: 12,
13100
- cacheRead: 0.19999999999999998,
13101
- cacheWrite: 0.375,
13002
+ input: 0.5,
13003
+ output: 2.8,
13004
+ cacheRead: 0,
13005
+ cacheWrite: 0,
13102
13006
  },
13103
- contextWindow: 1048576,
13104
- maxTokens: 65536,
13007
+ contextWindow: 262144,
13008
+ maxTokens: 262144,
13105
13009
  },
13106
- "~moonshotai/kimi-latest": {
13107
- id: "~moonshotai/kimi-latest",
13108
- name: "MoonshotAI Kimi Latest",
13010
+ "moonshotai/Kimi-K2.6": {
13011
+ id: "moonshotai/Kimi-K2.6",
13012
+ name: "Kimi K2.6",
13109
13013
  api: "openai-completions",
13110
- provider: "openrouter",
13111
- baseUrl: "https://openrouter.ai/api/v1",
13014
+ provider: "together",
13015
+ baseUrl: "https://api.together.ai/v1",
13016
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13112
13017
  reasoning: true,
13018
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13113
13019
  input: ["text", "image"],
13114
13020
  cost: {
13115
- input: 0.75,
13116
- output: 3.5,
13117
- cacheRead: 0.15,
13021
+ input: 1.2,
13022
+ output: 4.5,
13023
+ cacheRead: 0.2,
13118
13024
  cacheWrite: 0,
13119
13025
  },
13120
13026
  contextWindow: 262144,
13121
- maxTokens: 16384,
13027
+ maxTokens: 131000,
13122
13028
  },
13123
- "~openai/gpt-latest": {
13124
- id: "~openai/gpt-latest",
13125
- name: "OpenAI GPT Latest",
13029
+ "openai/gpt-oss-120b": {
13030
+ id: "openai/gpt-oss-120b",
13031
+ name: "GPT OSS 120B",
13126
13032
  api: "openai-completions",
13127
- provider: "openrouter",
13128
- baseUrl: "https://openrouter.ai/api/v1",
13033
+ provider: "together",
13034
+ baseUrl: "https://api.together.ai/v1",
13035
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
13129
13036
  reasoning: true,
13130
- input: ["text", "image"],
13037
+ thinkingLevelMap: { "off": null, "minimal": null },
13038
+ input: ["text"],
13131
13039
  cost: {
13132
- input: 5,
13133
- output: 30,
13134
- cacheRead: 0.5,
13040
+ input: 0.15,
13041
+ output: 0.6,
13042
+ cacheRead: 0,
13135
13043
  cacheWrite: 0,
13136
13044
  },
13137
- contextWindow: 1050000,
13138
- maxTokens: 128000,
13045
+ contextWindow: 131072,
13046
+ maxTokens: 131072,
13139
13047
  },
13140
- "~openai/gpt-mini-latest": {
13141
- id: "~openai/gpt-mini-latest",
13142
- name: "OpenAI GPT Mini Latest",
13048
+ "zai-org/GLM-5.1": {
13049
+ id: "zai-org/GLM-5.1",
13050
+ name: "GLM-5.1",
13143
13051
  api: "openai-completions",
13144
- provider: "openrouter",
13145
- baseUrl: "https://openrouter.ai/api/v1",
13052
+ provider: "together",
13053
+ baseUrl: "https://api.together.ai/v1",
13054
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13146
13055
  reasoning: true,
13147
- input: ["text", "image"],
13056
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13057
+ input: ["text"],
13148
13058
  cost: {
13149
- input: 0.75,
13150
- output: 4.5,
13151
- cacheRead: 0.075,
13059
+ input: 1.4,
13060
+ output: 4.4,
13061
+ cacheRead: 0,
13152
13062
  cacheWrite: 0,
13153
13063
  },
13154
- contextWindow: 400000,
13155
- maxTokens: 128000,
13064
+ contextWindow: 202752,
13065
+ maxTokens: 131072,
13156
13066
  },
13157
13067
  },
13158
13068
  "vercel-ai-gateway": {
@@ -13496,23 +13406,6 @@ export const MODELS = {
13496
13406
  contextWindow: 200000,
13497
13407
  maxTokens: 8192,
13498
13408
  },
13499
- "anthropic/claude-3.7-sonnet": {
13500
- id: "anthropic/claude-3.7-sonnet",
13501
- name: "Claude 3.7 Sonnet",
13502
- api: "anthropic-messages",
13503
- provider: "vercel-ai-gateway",
13504
- baseUrl: "https://ai-gateway.vercel.sh",
13505
- reasoning: true,
13506
- input: ["text", "image"],
13507
- cost: {
13508
- input: 3,
13509
- output: 15,
13510
- cacheRead: 0.3,
13511
- cacheWrite: 3.75,
13512
- },
13513
- contextWindow: 200000,
13514
- maxTokens: 8192,
13515
- },
13516
13409
  "anthropic/claude-haiku-4.5": {
13517
13410
  id: "anthropic/claude-haiku-4.5",
13518
13411
  name: "Claude Haiku 4.5",
@@ -13991,6 +13884,23 @@ export const MODELS = {
13991
13884
  contextWindow: 1000000,
13992
13885
  maxTokens: 64000,
13993
13886
  },
13887
+ "google/gemini-3.1-flash-lite": {
13888
+ id: "google/gemini-3.1-flash-lite",
13889
+ name: "Gemini 3.1 Flash Lite",
13890
+ api: "anthropic-messages",
13891
+ provider: "vercel-ai-gateway",
13892
+ baseUrl: "https://ai-gateway.vercel.sh",
13893
+ reasoning: true,
13894
+ input: ["text", "image"],
13895
+ cost: {
13896
+ input: 0.25,
13897
+ output: 1.5,
13898
+ cacheRead: 0.03,
13899
+ cacheWrite: 0,
13900
+ },
13901
+ contextWindow: 1000000,
13902
+ maxTokens: 65000,
13903
+ },
13994
13904
  "google/gemini-3.1-flash-lite-preview": {
13995
13905
  id: "google/gemini-3.1-flash-lite-preview",
13996
13906
  name: "Gemini 3.1 Flash Lite Preview",
@@ -15178,7 +15088,7 @@ export const MODELS = {
15178
15088
  },
15179
15089
  "openai/gpt-oss-20b": {
15180
15090
  id: "openai/gpt-oss-20b",
15181
- name: "GPT OSS 120B",
15091
+ name: "GPT OSS 20B",
15182
15092
  api: "anthropic-messages",
15183
15093
  provider: "vercel-ai-gateway",
15184
15094
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -15257,213 +15167,94 @@ export const MODELS = {
15257
15167
  output: 40,
15258
15168
  cacheRead: 2.5,
15259
15169
  cacheWrite: 0,
15260
- },
15261
- contextWindow: 200000,
15262
- maxTokens: 100000,
15263
- },
15264
- "openai/o3-mini": {
15265
- id: "openai/o3-mini",
15266
- name: "o3-mini",
15267
- api: "anthropic-messages",
15268
- provider: "vercel-ai-gateway",
15269
- baseUrl: "https://ai-gateway.vercel.sh",
15270
- reasoning: true,
15271
- input: ["text"],
15272
- cost: {
15273
- input: 1.1,
15274
- output: 4.4,
15275
- cacheRead: 0.55,
15276
- cacheWrite: 0,
15277
- },
15278
- contextWindow: 200000,
15279
- maxTokens: 100000,
15280
- },
15281
- "openai/o3-pro": {
15282
- id: "openai/o3-pro",
15283
- name: "o3 Pro",
15284
- api: "anthropic-messages",
15285
- provider: "vercel-ai-gateway",
15286
- baseUrl: "https://ai-gateway.vercel.sh",
15287
- reasoning: true,
15288
- input: ["text", "image"],
15289
- cost: {
15290
- input: 20,
15291
- output: 80,
15292
- cacheRead: 0,
15293
- cacheWrite: 0,
15294
- },
15295
- contextWindow: 200000,
15296
- maxTokens: 100000,
15297
- },
15298
- "openai/o4-mini": {
15299
- id: "openai/o4-mini",
15300
- name: "o4-mini",
15301
- api: "anthropic-messages",
15302
- provider: "vercel-ai-gateway",
15303
- baseUrl: "https://ai-gateway.vercel.sh",
15304
- reasoning: true,
15305
- input: ["text", "image"],
15306
- cost: {
15307
- input: 1.1,
15308
- output: 4.4,
15309
- cacheRead: 0.275,
15310
- cacheWrite: 0,
15311
- },
15312
- contextWindow: 200000,
15313
- maxTokens: 100000,
15314
- },
15315
- "perplexity/sonar": {
15316
- id: "perplexity/sonar",
15317
- name: "Sonar",
15318
- api: "anthropic-messages",
15319
- provider: "vercel-ai-gateway",
15320
- baseUrl: "https://ai-gateway.vercel.sh",
15321
- reasoning: false,
15322
- input: ["text", "image"],
15323
- cost: {
15324
- input: 0,
15325
- output: 0,
15326
- cacheRead: 0,
15327
- cacheWrite: 0,
15328
- },
15329
- contextWindow: 127000,
15330
- maxTokens: 8000,
15331
- },
15332
- "perplexity/sonar-pro": {
15333
- id: "perplexity/sonar-pro",
15334
- name: "Sonar Pro",
15335
- api: "anthropic-messages",
15336
- provider: "vercel-ai-gateway",
15337
- baseUrl: "https://ai-gateway.vercel.sh",
15338
- reasoning: false,
15339
- input: ["text", "image"],
15340
- cost: {
15341
- input: 0,
15342
- output: 0,
15343
- cacheRead: 0,
15344
- cacheWrite: 0,
15345
- },
15346
- contextWindow: 200000,
15347
- maxTokens: 8000,
15348
- },
15349
- "xai/grok-3": {
15350
- id: "xai/grok-3",
15351
- name: "Grok 3 Beta",
15352
- api: "anthropic-messages",
15353
- provider: "vercel-ai-gateway",
15354
- baseUrl: "https://ai-gateway.vercel.sh",
15355
- reasoning: false,
15356
- input: ["text"],
15357
- cost: {
15358
- input: 3,
15359
- output: 15,
15360
- cacheRead: 0.75,
15361
- cacheWrite: 0,
15362
- },
15363
- contextWindow: 131072,
15364
- maxTokens: 131072,
15365
- },
15366
- "xai/grok-3-fast": {
15367
- id: "xai/grok-3-fast",
15368
- name: "Grok 3 Fast Beta",
15369
- api: "anthropic-messages",
15370
- provider: "vercel-ai-gateway",
15371
- baseUrl: "https://ai-gateway.vercel.sh",
15372
- reasoning: false,
15373
- input: ["text"],
15374
- cost: {
15375
- input: 5,
15376
- output: 25,
15377
- cacheRead: 1.25,
15378
- cacheWrite: 0,
15379
- },
15380
- contextWindow: 131072,
15381
- maxTokens: 131072,
15170
+ },
15171
+ contextWindow: 200000,
15172
+ maxTokens: 100000,
15382
15173
  },
15383
- "xai/grok-3-mini": {
15384
- id: "xai/grok-3-mini",
15385
- name: "Grok 3 Mini Beta",
15174
+ "openai/o3-mini": {
15175
+ id: "openai/o3-mini",
15176
+ name: "o3-mini",
15386
15177
  api: "anthropic-messages",
15387
15178
  provider: "vercel-ai-gateway",
15388
15179
  baseUrl: "https://ai-gateway.vercel.sh",
15389
- reasoning: false,
15180
+ reasoning: true,
15390
15181
  input: ["text"],
15391
15182
  cost: {
15392
- input: 0.3,
15393
- output: 0.5,
15394
- cacheRead: 0.075,
15183
+ input: 1.1,
15184
+ output: 4.4,
15185
+ cacheRead: 0.55,
15395
15186
  cacheWrite: 0,
15396
15187
  },
15397
- contextWindow: 131072,
15398
- maxTokens: 131072,
15188
+ contextWindow: 200000,
15189
+ maxTokens: 100000,
15399
15190
  },
15400
- "xai/grok-3-mini-fast": {
15401
- id: "xai/grok-3-mini-fast",
15402
- name: "Grok 3 Mini Fast Beta",
15191
+ "openai/o3-pro": {
15192
+ id: "openai/o3-pro",
15193
+ name: "o3 Pro",
15403
15194
  api: "anthropic-messages",
15404
15195
  provider: "vercel-ai-gateway",
15405
15196
  baseUrl: "https://ai-gateway.vercel.sh",
15406
- reasoning: false,
15407
- input: ["text"],
15197
+ reasoning: true,
15198
+ input: ["text", "image"],
15408
15199
  cost: {
15409
- input: 0.6,
15410
- output: 4,
15200
+ input: 20,
15201
+ output: 80,
15411
15202
  cacheRead: 0,
15412
15203
  cacheWrite: 0,
15413
15204
  },
15414
- contextWindow: 131072,
15415
- maxTokens: 131072,
15205
+ contextWindow: 200000,
15206
+ maxTokens: 100000,
15416
15207
  },
15417
- "xai/grok-4": {
15418
- id: "xai/grok-4",
15419
- name: "Grok 4",
15208
+ "openai/o4-mini": {
15209
+ id: "openai/o4-mini",
15210
+ name: "o4-mini",
15420
15211
  api: "anthropic-messages",
15421
15212
  provider: "vercel-ai-gateway",
15422
15213
  baseUrl: "https://ai-gateway.vercel.sh",
15423
15214
  reasoning: true,
15424
15215
  input: ["text", "image"],
15425
15216
  cost: {
15426
- input: 3,
15427
- output: 15,
15428
- cacheRead: 0.75,
15217
+ input: 1.1,
15218
+ output: 4.4,
15219
+ cacheRead: 0.275,
15429
15220
  cacheWrite: 0,
15430
15221
  },
15431
- contextWindow: 256000,
15432
- maxTokens: 256000,
15222
+ contextWindow: 200000,
15223
+ maxTokens: 100000,
15433
15224
  },
15434
- "xai/grok-4-fast-non-reasoning": {
15435
- id: "xai/grok-4-fast-non-reasoning",
15436
- name: "Grok 4 Fast Non-Reasoning",
15225
+ "perplexity/sonar": {
15226
+ id: "perplexity/sonar",
15227
+ name: "Sonar",
15437
15228
  api: "anthropic-messages",
15438
15229
  provider: "vercel-ai-gateway",
15439
15230
  baseUrl: "https://ai-gateway.vercel.sh",
15440
15231
  reasoning: false,
15441
15232
  input: ["text", "image"],
15442
15233
  cost: {
15443
- input: 0.19999999999999998,
15444
- output: 0.5,
15445
- cacheRead: 0.049999999999999996,
15234
+ input: 0,
15235
+ output: 0,
15236
+ cacheRead: 0,
15446
15237
  cacheWrite: 0,
15447
15238
  },
15448
- contextWindow: 2000000,
15449
- maxTokens: 256000,
15239
+ contextWindow: 127000,
15240
+ maxTokens: 8000,
15450
15241
  },
15451
- "xai/grok-4-fast-reasoning": {
15452
- id: "xai/grok-4-fast-reasoning",
15453
- name: "Grok 4 Fast Reasoning",
15242
+ "perplexity/sonar-pro": {
15243
+ id: "perplexity/sonar-pro",
15244
+ name: "Sonar Pro",
15454
15245
  api: "anthropic-messages",
15455
15246
  provider: "vercel-ai-gateway",
15456
15247
  baseUrl: "https://ai-gateway.vercel.sh",
15457
- reasoning: true,
15248
+ reasoning: false,
15458
15249
  input: ["text", "image"],
15459
15250
  cost: {
15460
- input: 0.19999999999999998,
15461
- output: 0.5,
15462
- cacheRead: 0.049999999999999996,
15251
+ input: 0,
15252
+ output: 0,
15253
+ cacheRead: 0,
15463
15254
  cacheWrite: 0,
15464
15255
  },
15465
- contextWindow: 2000000,
15466
- maxTokens: 256000,
15256
+ contextWindow: 200000,
15257
+ maxTokens: 8000,
15467
15258
  },
15468
15259
  "xai/grok-4.1-fast-non-reasoning": {
15469
15260
  id: "xai/grok-4.1-fast-non-reasoning",
@@ -15479,8 +15270,8 @@ export const MODELS = {
15479
15270
  cacheRead: 0.049999999999999996,
15480
15271
  cacheWrite: 0,
15481
15272
  },
15482
- contextWindow: 2000000,
15483
- maxTokens: 30000,
15273
+ contextWindow: 1000000,
15274
+ maxTokens: 1000000,
15484
15275
  },
15485
15276
  "xai/grok-4.1-fast-reasoning": {
15486
15277
  id: "xai/grok-4.1-fast-reasoning",
@@ -15496,8 +15287,8 @@ export const MODELS = {
15496
15287
  cacheRead: 0.049999999999999996,
15497
15288
  cacheWrite: 0,
15498
15289
  },
15499
- contextWindow: 2000000,
15500
- maxTokens: 30000,
15290
+ contextWindow: 1000000,
15291
+ maxTokens: 1000000,
15501
15292
  },
15502
15293
  "xai/grok-4.20-multi-agent": {
15503
15294
  id: "xai/grok-4.20-multi-agent",
@@ -15618,23 +15409,6 @@ export const MODELS = {
15618
15409
  contextWindow: 1000000,
15619
15410
  maxTokens: 1000000,
15620
15411
  },
15621
- "xai/grok-code-fast-1": {
15622
- id: "xai/grok-code-fast-1",
15623
- name: "Grok Code Fast 1",
15624
- api: "anthropic-messages",
15625
- provider: "vercel-ai-gateway",
15626
- baseUrl: "https://ai-gateway.vercel.sh",
15627
- reasoning: true,
15628
- input: ["text"],
15629
- cost: {
15630
- input: 0.19999999999999998,
15631
- output: 1.5,
15632
- cacheRead: 0.02,
15633
- cacheWrite: 0,
15634
- },
15635
- contextWindow: 256000,
15636
- maxTokens: 256000,
15637
- },
15638
15412
  "xiaomi/mimo-v2-flash": {
15639
15413
  id: "xiaomi/mimo-v2-flash",
15640
15414
  name: "MiMo V2 Flash",
@@ -16062,193 +15836,6 @@ export const MODELS = {
16062
15836
  contextWindow: 131072,
16063
15837
  maxTokens: 8192,
16064
15838
  },
16065
- "grok-3-fast-latest": {
16066
- id: "grok-3-fast-latest",
16067
- name: "Grok 3 Fast Latest",
16068
- api: "openai-completions",
16069
- provider: "xai",
16070
- baseUrl: "https://api.x.ai/v1",
16071
- reasoning: false,
16072
- input: ["text"],
16073
- cost: {
16074
- input: 5,
16075
- output: 25,
16076
- cacheRead: 1.25,
16077
- cacheWrite: 0,
16078
- },
16079
- contextWindow: 131072,
16080
- maxTokens: 8192,
16081
- },
16082
- "grok-3-latest": {
16083
- id: "grok-3-latest",
16084
- name: "Grok 3 Latest",
16085
- api: "openai-completions",
16086
- provider: "xai",
16087
- baseUrl: "https://api.x.ai/v1",
16088
- reasoning: false,
16089
- input: ["text"],
16090
- cost: {
16091
- input: 3,
16092
- output: 15,
16093
- cacheRead: 0.75,
16094
- cacheWrite: 0,
16095
- },
16096
- contextWindow: 131072,
16097
- maxTokens: 8192,
16098
- },
16099
- "grok-3-mini": {
16100
- id: "grok-3-mini",
16101
- name: "Grok 3 Mini",
16102
- api: "openai-completions",
16103
- provider: "xai",
16104
- baseUrl: "https://api.x.ai/v1",
16105
- reasoning: true,
16106
- input: ["text"],
16107
- cost: {
16108
- input: 0.3,
16109
- output: 0.5,
16110
- cacheRead: 0.075,
16111
- cacheWrite: 0,
16112
- },
16113
- contextWindow: 131072,
16114
- maxTokens: 8192,
16115
- },
16116
- "grok-3-mini-fast": {
16117
- id: "grok-3-mini-fast",
16118
- name: "Grok 3 Mini Fast",
16119
- api: "openai-completions",
16120
- provider: "xai",
16121
- baseUrl: "https://api.x.ai/v1",
16122
- reasoning: true,
16123
- input: ["text"],
16124
- cost: {
16125
- input: 0.6,
16126
- output: 4,
16127
- cacheRead: 0.15,
16128
- cacheWrite: 0,
16129
- },
16130
- contextWindow: 131072,
16131
- maxTokens: 8192,
16132
- },
16133
- "grok-3-mini-fast-latest": {
16134
- id: "grok-3-mini-fast-latest",
16135
- name: "Grok 3 Mini Fast Latest",
16136
- api: "openai-completions",
16137
- provider: "xai",
16138
- baseUrl: "https://api.x.ai/v1",
16139
- reasoning: true,
16140
- input: ["text"],
16141
- cost: {
16142
- input: 0.6,
16143
- output: 4,
16144
- cacheRead: 0.15,
16145
- cacheWrite: 0,
16146
- },
16147
- contextWindow: 131072,
16148
- maxTokens: 8192,
16149
- },
16150
- "grok-3-mini-latest": {
16151
- id: "grok-3-mini-latest",
16152
- name: "Grok 3 Mini Latest",
16153
- api: "openai-completions",
16154
- provider: "xai",
16155
- baseUrl: "https://api.x.ai/v1",
16156
- reasoning: true,
16157
- input: ["text"],
16158
- cost: {
16159
- input: 0.3,
16160
- output: 0.5,
16161
- cacheRead: 0.075,
16162
- cacheWrite: 0,
16163
- },
16164
- contextWindow: 131072,
16165
- maxTokens: 8192,
16166
- },
16167
- "grok-4": {
16168
- id: "grok-4",
16169
- name: "Grok 4",
16170
- api: "openai-completions",
16171
- provider: "xai",
16172
- baseUrl: "https://api.x.ai/v1",
16173
- reasoning: true,
16174
- input: ["text"],
16175
- cost: {
16176
- input: 3,
16177
- output: 15,
16178
- cacheRead: 0.75,
16179
- cacheWrite: 0,
16180
- },
16181
- contextWindow: 256000,
16182
- maxTokens: 64000,
16183
- },
16184
- "grok-4-1-fast": {
16185
- id: "grok-4-1-fast",
16186
- name: "Grok 4.1 Fast",
16187
- api: "openai-completions",
16188
- provider: "xai",
16189
- baseUrl: "https://api.x.ai/v1",
16190
- reasoning: true,
16191
- input: ["text", "image"],
16192
- cost: {
16193
- input: 0.2,
16194
- output: 0.5,
16195
- cacheRead: 0.05,
16196
- cacheWrite: 0,
16197
- },
16198
- contextWindow: 2000000,
16199
- maxTokens: 30000,
16200
- },
16201
- "grok-4-1-fast-non-reasoning": {
16202
- id: "grok-4-1-fast-non-reasoning",
16203
- name: "Grok 4.1 Fast (Non-Reasoning)",
16204
- api: "openai-completions",
16205
- provider: "xai",
16206
- baseUrl: "https://api.x.ai/v1",
16207
- reasoning: false,
16208
- input: ["text", "image"],
16209
- cost: {
16210
- input: 0.2,
16211
- output: 0.5,
16212
- cacheRead: 0.05,
16213
- cacheWrite: 0,
16214
- },
16215
- contextWindow: 2000000,
16216
- maxTokens: 30000,
16217
- },
16218
- "grok-4-fast": {
16219
- id: "grok-4-fast",
16220
- name: "Grok 4 Fast",
16221
- api: "openai-completions",
16222
- provider: "xai",
16223
- baseUrl: "https://api.x.ai/v1",
16224
- reasoning: true,
16225
- input: ["text", "image"],
16226
- cost: {
16227
- input: 0.2,
16228
- output: 0.5,
16229
- cacheRead: 0.05,
16230
- cacheWrite: 0,
16231
- },
16232
- contextWindow: 2000000,
16233
- maxTokens: 30000,
16234
- },
16235
- "grok-4-fast-non-reasoning": {
16236
- id: "grok-4-fast-non-reasoning",
16237
- name: "Grok 4 Fast (Non-Reasoning)",
16238
- api: "openai-completions",
16239
- provider: "xai",
16240
- baseUrl: "https://api.x.ai/v1",
16241
- reasoning: false,
16242
- input: ["text", "image"],
16243
- cost: {
16244
- input: 0.2,
16245
- output: 0.5,
16246
- cacheRead: 0.05,
16247
- cacheWrite: 0,
16248
- },
16249
- contextWindow: 2000000,
16250
- maxTokens: 30000,
16251
- },
16252
15839
  "grok-4.20-0309-non-reasoning": {
16253
15840
  id: "grok-4.20-0309-non-reasoning",
16254
15841
  name: "Grok 4.20 (Non-Reasoning)",
@@ -16323,7 +15910,7 @@ export const MODELS = {
16323
15910
  api: "openai-completions",
16324
15911
  provider: "xai",
16325
15912
  baseUrl: "https://api.x.ai/v1",
16326
- reasoning: true,
15913
+ reasoning: false,
16327
15914
  input: ["text"],
16328
15915
  cost: {
16329
15916
  input: 0.2,
@@ -16331,8 +15918,8 @@ export const MODELS = {
16331
15918
  cacheRead: 0.02,
16332
15919
  cacheWrite: 0,
16333
15920
  },
16334
- contextWindow: 256000,
16335
- maxTokens: 10000,
15921
+ contextWindow: 32768,
15922
+ maxTokens: 8192,
16336
15923
  },
16337
15924
  "grok-vision-beta": {
16338
15925
  id: "grok-vision-beta",