pi-ollama-cloud 0.6.0 → 0.8.0

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 (10) hide show
  1. package/CHANGELOG.md +23 -0
  2. package/README.md +62 -39
  3. package/index.ts +15 -114
  4. package/models.generated.ts +75 -491
  5. package/models.ts +203 -137
  6. package/package.json +10 -4
  7. package/pricing.generated.ts +32 -0
  8. package/thinking-levels.ts +13 -0
  9. package/utils.ts +17 -0
  10. package/web-tools.ts +160 -125
package/models.generated.ts CHANGED
@@ -1,14 +1,14 @@
1
1
  // Auto-generated by scripts/generate-models.ts
2
2
  // Do not edit manually.
3
- // Generated: 2026-06-05T15:26:51.472Z
4
- // Model count: 30
3
+ // Generated: 2026-08-08T04:19:46.959Z
4
+ // Model count: 18
5
5
 
6
6
  import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
7
7
 
8
8
  export const GENERATED_MODELS: ProviderModelConfig[] = [
9
9
  {
10
- id: "deepseek-v3.1:671b",
11
- name: "deepseek-v3.1:671b",
10
+ id: "deepseek-v4-flash:0731",
11
+ name: "deepseek-v4-flash:0731",
12
12
  compat: {
13
13
  maxTokensField: "max_tokens",
14
14
  openRouterRouting: {},
@@ -27,52 +27,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
27
27
  vercelGatewayRouting: {},
28
28
  zaiToolStream: false,
29
29
  },
30
- contextWindow: 163840,
31
- cost: {
32
- cacheRead: 0,
33
- cacheWrite: 0,
34
- input: 0,
35
- output: 0,
36
- },
37
- input: ["text"],
38
- maxTokens: 32768,
39
- reasoning: true,
40
- thinkingLevelMap: {
41
- high: "high",
42
- low: "low",
43
- medium: "medium",
44
- minimal: null,
45
- off: "none",
46
- xhigh: "max",
47
- },
48
- },
49
- {
50
- id: "deepseek-v3.2",
51
- name: "deepseek-v3.2",
52
- compat: {
53
- maxTokensField: "max_tokens",
54
- openRouterRouting: {},
55
- requiresAssistantAfterToolResult: false,
56
- requiresReasoningContentOnAssistantMessages: false,
57
- requiresThinkingAsText: false,
58
- requiresToolResultName: false,
59
- sendSessionAffinityHeaders: false,
60
- supportsDeveloperRole: false,
61
- supportsLongCacheRetention: false,
62
- supportsReasoningEffort: true,
63
- supportsStore: false,
64
- supportsStrictMode: false,
65
- supportsUsageInStreaming: true,
66
- thinkingFormat: "openai",
67
- vercelGatewayRouting: {},
68
- zaiToolStream: false,
69
- },
70
- contextWindow: 163840,
30
+ contextWindow: 1048576,
71
31
  cost: {
72
- cacheRead: 0,
32
+ cacheRead: 0.0028,
73
33
  cacheWrite: 0,
74
- input: 0,
75
- output: 0,
34
+ input: 0.14,
35
+ output: 0.28,
76
36
  },
77
37
  input: ["text"],
78
38
  maxTokens: 32768,
@@ -87,8 +47,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
87
47
  },
88
48
  },
89
49
  {
90
- id: "deepseek-v4-flash",
91
- name: "deepseek-v4-flash",
50
+ id: "deepseek-v4-flash:preview",
51
+ name: "deepseek-v4-flash:preview",
92
52
  compat: {
93
53
  maxTokensField: "max_tokens",
94
54
  openRouterRouting: {},
@@ -109,10 +69,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
109
69
  },
110
70
  contextWindow: 1048576,
111
71
  cost: {
112
- cacheRead: 0,
72
+ cacheRead: 0.0028,
113
73
  cacheWrite: 0,
114
- input: 0,
115
- output: 0,
74
+ input: 0.14,
75
+ output: 0.28,
116
76
  },
117
77
  input: ["text"],
118
78
  maxTokens: 32768,
@@ -147,12 +107,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
147
107
  vercelGatewayRouting: {},
148
108
  zaiToolStream: false,
149
109
  },
150
- contextWindow: 1048576,
110
+ contextWindow: 524288,
151
111
  cost: {
152
- cacheRead: 0,
112
+ cacheRead: 0.003625,
153
113
  cacheWrite: 0,
154
- input: 0,
155
- output: 0,
114
+ input: 0.435,
115
+ output: 0.87,
156
116
  },
157
117
  input: ["text"],
158
118
  maxTokens: 32768,
@@ -166,110 +126,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
166
126
  xhigh: "max",
167
127
  },
168
128
  },
169
- {
170
- id: "devstral-2:123b",
171
- name: "devstral-2:123b",
172
- compat: {
173
- maxTokensField: "max_tokens",
174
- openRouterRouting: {},
175
- requiresAssistantAfterToolResult: false,
176
- requiresReasoningContentOnAssistantMessages: false,
177
- requiresThinkingAsText: false,
178
- requiresToolResultName: false,
179
- sendSessionAffinityHeaders: false,
180
- supportsDeveloperRole: false,
181
- supportsLongCacheRetention: false,
182
- supportsReasoningEffort: true,
183
- supportsStore: false,
184
- supportsStrictMode: false,
185
- supportsUsageInStreaming: true,
186
- thinkingFormat: "openai",
187
- vercelGatewayRouting: {},
188
- zaiToolStream: false,
189
- },
190
- contextWindow: 262144,
191
- cost: {
192
- cacheRead: 0,
193
- cacheWrite: 0,
194
- input: 0,
195
- output: 0,
196
- },
197
- input: ["text"],
198
- maxTokens: 32768,
199
- reasoning: false,
200
- },
201
- {
202
- id: "devstral-small-2:24b",
203
- name: "devstral-small-2:24b",
204
- compat: {
205
- maxTokensField: "max_tokens",
206
- openRouterRouting: {},
207
- requiresAssistantAfterToolResult: false,
208
- requiresReasoningContentOnAssistantMessages: false,
209
- requiresThinkingAsText: false,
210
- requiresToolResultName: false,
211
- sendSessionAffinityHeaders: false,
212
- supportsDeveloperRole: false,
213
- supportsLongCacheRetention: false,
214
- supportsReasoningEffort: true,
215
- supportsStore: false,
216
- supportsStrictMode: false,
217
- supportsUsageInStreaming: true,
218
- thinkingFormat: "openai",
219
- vercelGatewayRouting: {},
220
- zaiToolStream: false,
221
- },
222
- contextWindow: 262144,
223
- cost: {
224
- cacheRead: 0,
225
- cacheWrite: 0,
226
- input: 0,
227
- output: 0,
228
- },
229
- input: ["text", "image"],
230
- maxTokens: 32768,
231
- reasoning: false,
232
- },
233
- {
234
- id: "gemini-3-flash-preview",
235
- name: "gemini-3-flash-preview",
236
- compat: {
237
- maxTokensField: "max_tokens",
238
- openRouterRouting: {},
239
- requiresAssistantAfterToolResult: false,
240
- requiresReasoningContentOnAssistantMessages: false,
241
- requiresThinkingAsText: false,
242
- requiresToolResultName: false,
243
- sendSessionAffinityHeaders: false,
244
- supportsDeveloperRole: false,
245
- supportsLongCacheRetention: false,
246
- supportsReasoningEffort: true,
247
- supportsStore: false,
248
- supportsStrictMode: false,
249
- supportsUsageInStreaming: true,
250
- thinkingFormat: "openai",
251
- vercelGatewayRouting: {},
252
- zaiToolStream: false,
253
- },
254
- contextWindow: 1048576,
255
- cost: {
256
- cacheRead: 0,
257
- cacheWrite: 0,
258
- input: 0,
259
- output: 0,
260
- },
261
- input: ["text", "image"],
262
- maxTokens: 32768,
263
- reasoning: true,
264
- thinkingLevelMap: {
265
- high: "high",
266
- low: "low",
267
- medium: "medium",
268
- minimal: null,
269
- off: "none",
270
- xhigh: "max",
271
- },
272
- },
273
129
  {
274
130
  id: "gemma4:31b",
275
131
  name: "gemma4:31b",
@@ -293,10 +149,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
293
149
  },
294
150
  contextWindow: 262144,
295
151
  cost: {
296
- cacheRead: 0,
152
+ cacheRead: 0.1,
297
153
  cacheWrite: 0,
298
- input: 0,
299
- output: 0,
154
+ input: 0.1,
155
+ output: 0.34,
300
156
  },
301
157
  input: ["text", "image"],
302
158
  maxTokens: 32768,
@@ -311,48 +167,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
311
167
  },
312
168
  },
313
169
  {
314
- id: "glm-4.7",
315
- name: "glm-4.7",
316
- compat: {
317
- maxTokensField: "max_tokens",
318
- openRouterRouting: {},
319
- requiresAssistantAfterToolResult: false,
320
- requiresReasoningContentOnAssistantMessages: false,
321
- requiresThinkingAsText: false,
322
- requiresToolResultName: false,
323
- sendSessionAffinityHeaders: false,
324
- supportsDeveloperRole: false,
325
- supportsLongCacheRetention: false,
326
- supportsReasoningEffort: true,
327
- supportsStore: false,
328
- supportsStrictMode: false,
329
- supportsUsageInStreaming: true,
330
- thinkingFormat: "openai",
331
- vercelGatewayRouting: {},
332
- zaiToolStream: false,
333
- },
334
- contextWindow: 202752,
335
- cost: {
336
- cacheRead: 0,
337
- cacheWrite: 0,
338
- input: 0,
339
- output: 0,
340
- },
341
- input: ["text"],
342
- maxTokens: 32768,
343
- reasoning: true,
344
- thinkingLevelMap: {
345
- high: "high",
346
- low: "low",
347
- medium: "medium",
348
- minimal: null,
349
- off: "none",
350
- xhigh: "max",
351
- },
352
- },
353
- {
354
- id: "glm-5",
355
- name: "glm-5",
170
+ id: "glm-5.1",
171
+ name: "glm-5.1",
356
172
  compat: {
357
173
  maxTokensField: "max_tokens",
358
174
  openRouterRouting: {},
@@ -373,10 +189,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
373
189
  },
374
190
  contextWindow: 202752,
375
191
  cost: {
376
- cacheRead: 0,
192
+ cacheRead: 0.26,
377
193
  cacheWrite: 0,
378
- input: 0,
379
- output: 0,
194
+ input: 1.4,
195
+ output: 4.4,
380
196
  },
381
197
  input: ["text"],
382
198
  maxTokens: 32768,
@@ -391,8 +207,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
391
207
  },
392
208
  },
393
209
  {
394
- id: "glm-5.1",
395
- name: "glm-5.1",
210
+ id: "glm-5.2",
211
+ name: "glm-5.2",
396
212
  compat: {
397
213
  maxTokensField: "max_tokens",
398
214
  openRouterRouting: {},
@@ -411,20 +227,20 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
411
227
  vercelGatewayRouting: {},
412
228
  zaiToolStream: false,
413
229
  },
414
- contextWindow: 202752,
230
+ contextWindow: 1000000,
415
231
  cost: {
416
- cacheRead: 0,
232
+ cacheRead: 0.26,
417
233
  cacheWrite: 0,
418
- input: 0,
419
- output: 0,
234
+ input: 1.4,
235
+ output: 4.4,
420
236
  },
421
237
  input: ["text"],
422
238
  maxTokens: 32768,
423
239
  reasoning: true,
424
240
  thinkingLevelMap: {
425
241
  high: "high",
426
- low: "low",
427
- medium: "medium",
242
+ low: null,
243
+ medium: null,
428
244
  minimal: null,
429
245
  off: "none",
430
246
  xhigh: "max",
@@ -455,8 +271,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
455
271
  cost: {
456
272
  cacheRead: 0,
457
273
  cacheWrite: 0,
458
- input: 0,
459
- output: 0,
274
+ input: 0.037,
275
+ output: 0.17,
460
276
  },
461
277
  input: ["text"],
462
278
  maxTokens: 32768,
@@ -493,10 +309,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
493
309
  },
494
310
  contextWindow: 131072,
495
311
  cost: {
496
- cacheRead: 0,
312
+ cacheRead: 0.03,
497
313
  cacheWrite: 0,
498
- input: 0,
499
- output: 0,
314
+ input: 0.03,
315
+ output: 0.13,
500
316
  },
501
317
  input: ["text"],
502
318
  maxTokens: 32768,
@@ -511,8 +327,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
511
327
  },
512
328
  },
513
329
  {
514
- id: "kimi-k2.5",
515
- name: "kimi-k2.5",
330
+ id: "kimi-k2.6",
331
+ name: "kimi-k2.6",
516
332
  compat: {
517
333
  maxTokensField: "max_tokens",
518
334
  openRouterRouting: {},
@@ -533,10 +349,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
533
349
  },
534
350
  contextWindow: 262144,
535
351
  cost: {
536
- cacheRead: 0,
352
+ cacheRead: 0.16,
537
353
  cacheWrite: 0,
538
- input: 0,
539
- output: 0,
354
+ input: 0.95,
355
+ output: 4,
540
356
  },
541
357
  input: ["text", "image"],
542
358
  maxTokens: 32768,
@@ -551,8 +367,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
551
367
  },
552
368
  },
553
369
  {
554
- id: "kimi-k2.6",
555
- name: "kimi-k2.6",
370
+ id: "kimi-k2.7-code",
371
+ name: "kimi-k2.7-code",
556
372
  compat: {
557
373
  maxTokensField: "max_tokens",
558
374
  openRouterRouting: {},
@@ -573,10 +389,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
573
389
  },
574
390
  contextWindow: 262144,
575
391
  cost: {
576
- cacheRead: 0,
392
+ cacheRead: 0.19,
577
393
  cacheWrite: 0,
578
- input: 0,
579
- output: 0,
394
+ input: 0.95,
395
+ output: 4,
580
396
  },
581
397
  input: ["text", "image"],
582
398
  maxTokens: 32768,
@@ -591,8 +407,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
591
407
  },
592
408
  },
593
409
  {
594
- id: "minimax-m2.1",
595
- name: "minimax-m2.1",
410
+ id: "kimi-k3",
411
+ name: "kimi-k3",
596
412
  compat: {
597
413
  maxTokensField: "max_tokens",
598
414
  openRouterRouting: {},
@@ -611,54 +427,14 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
611
427
  vercelGatewayRouting: {},
612
428
  zaiToolStream: false,
613
429
  },
614
- contextWindow: 204800,
615
- cost: {
616
- cacheRead: 0,
617
- cacheWrite: 0,
618
- input: 0,
619
- output: 0,
620
- },
621
- input: ["text"],
622
- maxTokens: 32768,
623
- reasoning: true,
624
- thinkingLevelMap: {
625
- high: "high",
626
- low: "low",
627
- medium: "medium",
628
- minimal: null,
629
- off: null,
630
- xhigh: "max",
631
- },
632
- },
633
- {
634
- id: "minimax-m2.5",
635
- name: "minimax-m2.5",
636
- compat: {
637
- maxTokensField: "max_tokens",
638
- openRouterRouting: {},
639
- requiresAssistantAfterToolResult: false,
640
- requiresReasoningContentOnAssistantMessages: false,
641
- requiresThinkingAsText: false,
642
- requiresToolResultName: false,
643
- sendSessionAffinityHeaders: false,
644
- supportsDeveloperRole: false,
645
- supportsLongCacheRetention: false,
646
- supportsReasoningEffort: true,
647
- supportsStore: false,
648
- supportsStrictMode: false,
649
- supportsUsageInStreaming: true,
650
- thinkingFormat: "openai",
651
- vercelGatewayRouting: {},
652
- zaiToolStream: false,
653
- },
654
- contextWindow: 196608,
430
+ contextWindow: 1048576,
655
431
  cost: {
656
- cacheRead: 0,
432
+ cacheRead: 0.3,
657
433
  cacheWrite: 0,
658
- input: 0,
659
- output: 0,
434
+ input: 3,
435
+ output: 15,
660
436
  },
661
- input: ["text"],
437
+ input: ["text", "image"],
662
438
  maxTokens: 32768,
663
439
  reasoning: true,
664
440
  thinkingLevelMap: {
@@ -666,7 +442,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
666
442
  low: "low",
667
443
  medium: "medium",
668
444
  minimal: null,
669
- off: null,
445
+ off: "none",
670
446
  xhigh: "max",
671
447
  },
672
448
  },
@@ -693,10 +469,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
693
469
  },
694
470
  contextWindow: 196608,
695
471
  cost: {
696
- cacheRead: 0,
697
- cacheWrite: 0,
698
- input: 0,
699
- output: 0,
472
+ cacheRead: 0.06,
473
+ cacheWrite: 0.375,
474
+ input: 0.3,
475
+ output: 1.2,
700
476
  },
701
477
  input: ["text"],
702
478
  maxTokens: 32768,
@@ -733,10 +509,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
733
509
  },
734
510
  contextWindow: 524288,
735
511
  cost: {
736
- cacheRead: 0,
512
+ cacheRead: 0.06,
737
513
  cacheWrite: 0,
738
- input: 0,
739
- output: 0,
514
+ input: 0.3,
515
+ output: 1.2,
740
516
  },
741
517
  input: ["text", "image"],
742
518
  maxTokens: 32768,
@@ -750,102 +526,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
750
526
  xhigh: "max",
751
527
  },
752
528
  },
753
- {
754
- id: "ministral-3:14b",
755
- name: "ministral-3:14b",
756
- compat: {
757
- maxTokensField: "max_tokens",
758
- openRouterRouting: {},
759
- requiresAssistantAfterToolResult: false,
760
- requiresReasoningContentOnAssistantMessages: false,
761
- requiresThinkingAsText: false,
762
- requiresToolResultName: false,
763
- sendSessionAffinityHeaders: false,
764
- supportsDeveloperRole: false,
765
- supportsLongCacheRetention: false,
766
- supportsReasoningEffort: true,
767
- supportsStore: false,
768
- supportsStrictMode: false,
769
- supportsUsageInStreaming: true,
770
- thinkingFormat: "openai",
771
- vercelGatewayRouting: {},
772
- zaiToolStream: false,
773
- },
774
- contextWindow: 262144,
775
- cost: {
776
- cacheRead: 0,
777
- cacheWrite: 0,
778
- input: 0,
779
- output: 0,
780
- },
781
- input: ["text", "image"],
782
- maxTokens: 32768,
783
- reasoning: false,
784
- },
785
- {
786
- id: "ministral-3:3b",
787
- name: "ministral-3:3b",
788
- compat: {
789
- maxTokensField: "max_tokens",
790
- openRouterRouting: {},
791
- requiresAssistantAfterToolResult: false,
792
- requiresReasoningContentOnAssistantMessages: false,
793
- requiresThinkingAsText: false,
794
- requiresToolResultName: false,
795
- sendSessionAffinityHeaders: false,
796
- supportsDeveloperRole: false,
797
- supportsLongCacheRetention: false,
798
- supportsReasoningEffort: true,
799
- supportsStore: false,
800
- supportsStrictMode: false,
801
- supportsUsageInStreaming: true,
802
- thinkingFormat: "openai",
803
- vercelGatewayRouting: {},
804
- zaiToolStream: false,
805
- },
806
- contextWindow: 262144,
807
- cost: {
808
- cacheRead: 0,
809
- cacheWrite: 0,
810
- input: 0,
811
- output: 0,
812
- },
813
- input: ["text", "image"],
814
- maxTokens: 32768,
815
- reasoning: false,
816
- },
817
- {
818
- id: "ministral-3:8b",
819
- name: "ministral-3:8b",
820
- compat: {
821
- maxTokensField: "max_tokens",
822
- openRouterRouting: {},
823
- requiresAssistantAfterToolResult: false,
824
- requiresReasoningContentOnAssistantMessages: false,
825
- requiresThinkingAsText: false,
826
- requiresToolResultName: false,
827
- sendSessionAffinityHeaders: false,
828
- supportsDeveloperRole: false,
829
- supportsLongCacheRetention: false,
830
- supportsReasoningEffort: true,
831
- supportsStore: false,
832
- supportsStrictMode: false,
833
- supportsUsageInStreaming: true,
834
- thinkingFormat: "openai",
835
- vercelGatewayRouting: {},
836
- zaiToolStream: false,
837
- },
838
- contextWindow: 262144,
839
- cost: {
840
- cacheRead: 0,
841
- cacheWrite: 0,
842
- input: 0,
843
- output: 0,
844
- },
845
- input: ["text", "image"],
846
- maxTokens: 32768,
847
- reasoning: false,
848
- },
849
529
  {
850
530
  id: "mistral-large-3:675b",
851
531
  name: "mistral-large-3:675b",
@@ -871,8 +551,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
871
551
  cost: {
872
552
  cacheRead: 0,
873
553
  cacheWrite: 0,
874
- input: 0,
875
- output: 0,
554
+ input: 0.5,
555
+ output: 1.5,
876
556
  },
877
557
  input: ["text", "image"],
878
558
  maxTokens: 32768,
@@ -901,10 +581,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
901
581
  },
902
582
  contextWindow: 262144,
903
583
  cost: {
904
- cacheRead: 0,
584
+ cacheRead: 0.03,
905
585
  cacheWrite: 0,
906
- input: 0,
907
- output: 0,
586
+ input: 0.05,
587
+ output: 0.2,
908
588
  },
909
589
  input: ["text"],
910
590
  maxTokens: 32768,
@@ -943,8 +623,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
943
623
  cost: {
944
624
  cacheRead: 0,
945
625
  cacheWrite: 0,
946
- input: 0,
947
- output: 0,
626
+ input: 0.2,
627
+ output: 0.8,
948
628
  },
949
629
  input: ["text"],
950
630
  maxTokens: 32768,
@@ -981,10 +661,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
981
661
  },
982
662
  contextWindow: 262144,
983
663
  cost: {
984
- cacheRead: 0,
664
+ cacheRead: 0.15,
985
665
  cacheWrite: 0,
986
- input: 0,
987
- output: 0,
666
+ input: 0.5,
667
+ output: 2.5,
988
668
  },
989
669
  input: ["text"],
990
670
  maxTokens: 32768,
@@ -998,70 +678,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
998
678
  xhigh: "max",
999
679
  },
1000
680
  },
1001
- {
1002
- id: "qwen3-coder-next",
1003
- name: "qwen3-coder-next",
1004
- compat: {
1005
- maxTokensField: "max_tokens",
1006
- openRouterRouting: {},
1007
- requiresAssistantAfterToolResult: false,
1008
- requiresReasoningContentOnAssistantMessages: false,
1009
- requiresThinkingAsText: false,
1010
- requiresToolResultName: false,
1011
- sendSessionAffinityHeaders: false,
1012
- supportsDeveloperRole: false,
1013
- supportsLongCacheRetention: false,
1014
- supportsReasoningEffort: true,
1015
- supportsStore: false,
1016
- supportsStrictMode: false,
1017
- supportsUsageInStreaming: true,
1018
- thinkingFormat: "openai",
1019
- vercelGatewayRouting: {},
1020
- zaiToolStream: false,
1021
- },
1022
- contextWindow: 262144,
1023
- cost: {
1024
- cacheRead: 0,
1025
- cacheWrite: 0,
1026
- input: 0,
1027
- output: 0,
1028
- },
1029
- input: ["text"],
1030
- maxTokens: 32768,
1031
- reasoning: false,
1032
- },
1033
- {
1034
- id: "qwen3-coder:480b",
1035
- name: "qwen3-coder:480b",
1036
- compat: {
1037
- maxTokensField: "max_tokens",
1038
- openRouterRouting: {},
1039
- requiresAssistantAfterToolResult: false,
1040
- requiresReasoningContentOnAssistantMessages: false,
1041
- requiresThinkingAsText: false,
1042
- requiresToolResultName: false,
1043
- sendSessionAffinityHeaders: false,
1044
- supportsDeveloperRole: false,
1045
- supportsLongCacheRetention: false,
1046
- supportsReasoningEffort: true,
1047
- supportsStore: false,
1048
- supportsStrictMode: false,
1049
- supportsUsageInStreaming: true,
1050
- thinkingFormat: "openai",
1051
- vercelGatewayRouting: {},
1052
- zaiToolStream: false,
1053
- },
1054
- contextWindow: 262144,
1055
- cost: {
1056
- cacheRead: 0,
1057
- cacheWrite: 0,
1058
- input: 0,
1059
- output: 0,
1060
- },
1061
- input: ["text"],
1062
- maxTokens: 32768,
1063
- reasoning: false,
1064
- },
1065
681
  {
1066
682
  id: "qwen3.5:397b",
1067
683
  name: "qwen3.5:397b",
@@ -1087,8 +703,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
1087
703
  cost: {
1088
704
  cacheRead: 0,
1089
705
  cacheWrite: 0,
1090
- input: 0,
1091
- output: 0,
706
+ input: 0.6,
707
+ output: 3.6,
1092
708
  },
1093
709
  input: ["text", "image"],
1094
710
  maxTokens: 32768,
@@ -1102,36 +718,4 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
1102
718
  xhigh: null,
1103
719
  },
1104
720
  },
1105
- {
1106
- id: "rnj-1:8b",
1107
- name: "rnj-1:8b",
1108
- compat: {
1109
- maxTokensField: "max_tokens",
1110
- openRouterRouting: {},
1111
- requiresAssistantAfterToolResult: false,
1112
- requiresReasoningContentOnAssistantMessages: false,
1113
- requiresThinkingAsText: false,
1114
- requiresToolResultName: false,
1115
- sendSessionAffinityHeaders: false,
1116
- supportsDeveloperRole: false,
1117
- supportsLongCacheRetention: false,
1118
- supportsReasoningEffort: true,
1119
- supportsStore: false,
1120
- supportsStrictMode: false,
1121
- supportsUsageInStreaming: true,
1122
- thinkingFormat: "openai",
1123
- vercelGatewayRouting: {},
1124
- zaiToolStream: false,
1125
- },
1126
- contextWindow: 32768,
1127
- cost: {
1128
- cacheRead: 0,
1129
- cacheWrite: 0,
1130
- input: 0,
1131
- output: 0,
1132
- },
1133
- input: ["text"],
1134
- maxTokens: 32768,
1135
- reasoning: false,
1136
- },
1137
721
  ];