@kolisachint/hoocode-ai 0.5.86 → 0.5.88

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.
@@ -1205,6 +1205,23 @@ export const MODELS = {
1205
1205
  contextWindow: 1000000,
1206
1206
  maxTokens: 384000,
1207
1207
  },
1208
+ "accounts/fireworks/models/ember-1": {
1209
+ id: "accounts/fireworks/models/ember-1",
1210
+ name: "Ember-1",
1211
+ api: "anthropic-messages",
1212
+ provider: "fireworks",
1213
+ baseUrl: "https://api.fireworks.ai/inference",
1214
+ reasoning: true,
1215
+ input: ["text", "image"],
1216
+ cost: {
1217
+ input: 3,
1218
+ output: 15,
1219
+ cacheRead: 0.3,
1220
+ cacheWrite: 0,
1221
+ },
1222
+ contextWindow: 1048576,
1223
+ maxTokens: 131072,
1224
+ },
1208
1225
  "accounts/fireworks/models/glm-5p2": {
1209
1226
  id: "accounts/fireworks/models/glm-5p2",
1210
1227
  name: "GLM 5.2",
@@ -2343,8 +2360,8 @@ export const MODELS = {
2343
2360
  cacheRead: 0,
2344
2361
  cacheWrite: 0,
2345
2362
  },
2346
- contextWindow: 131072,
2347
- maxTokens: 65536,
2363
+ contextWindow: 128000,
2364
+ maxTokens: 64000,
2348
2365
  },
2349
2366
  "gemini-2.5-flash": {
2350
2367
  id: "gemini-2.5-flash",
@@ -2449,7 +2466,7 @@ export const MODELS = {
2449
2466
  cacheWrite: 0,
2450
2467
  },
2451
2468
  contextWindow: 65536,
2452
- maxTokens: 65536,
2469
+ maxTokens: 4096,
2453
2470
  },
2454
2471
  "gemini-3.1-flash-lite-preview": {
2455
2472
  id: "gemini-3.1-flash-lite-preview",
@@ -4915,7 +4932,7 @@ export const MODELS = {
4915
4932
  cacheWrite: 0,
4916
4933
  },
4917
4934
  contextWindow: 1048576,
4918
- maxTokens: 131072,
4935
+ maxTokens: 1048576,
4919
4936
  },
4920
4937
  },
4921
4938
  "moonshotai-cn": {
@@ -4989,7 +5006,7 @@ export const MODELS = {
4989
5006
  cacheWrite: 0,
4990
5007
  },
4991
5008
  contextWindow: 1048576,
4992
- maxTokens: 131072,
5009
+ maxTokens: 1048576,
4993
5010
  },
4994
5011
  },
4995
5012
  "nvidia": {
@@ -7170,6 +7187,42 @@ export const MODELS = {
7170
7187
  contextWindow: 272000,
7171
7188
  maxTokens: 128000,
7172
7189
  },
7190
+ "gpt-6-luna": {
7191
+ id: "gpt-6-luna",
7192
+ name: "GPT-6 Luna",
7193
+ api: "openai-codex-responses",
7194
+ provider: "openai-codex",
7195
+ baseUrl: "https://chatgpt.com/backend-api",
7196
+ reasoning: true,
7197
+ thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
7198
+ input: ["text", "image"],
7199
+ cost: {
7200
+ input: 0.1,
7201
+ output: 0.5,
7202
+ cacheRead: 0.01,
7203
+ cacheWrite: 0,
7204
+ },
7205
+ contextWindow: 272000,
7206
+ maxTokens: 128000,
7207
+ },
7208
+ "gpt-6-sol": {
7209
+ id: "gpt-6-sol",
7210
+ name: "GPT-6 Sol",
7211
+ api: "openai-codex-responses",
7212
+ provider: "openai-codex",
7213
+ baseUrl: "https://chatgpt.com/backend-api",
7214
+ reasoning: true,
7215
+ thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
7216
+ input: ["text", "image"],
7217
+ cost: {
7218
+ input: 2,
7219
+ output: 10,
7220
+ cacheRead: 0.2,
7221
+ cacheWrite: 0,
7222
+ },
7223
+ contextWindow: 272000,
7224
+ maxTokens: 128000,
7225
+ },
7173
7226
  },
7174
7227
  "opencode": {
7175
7228
  "big-pickle": {
@@ -8475,6 +8528,23 @@ export const MODELS = {
8475
8528
  contextWindow: 1000000,
8476
8529
  maxTokens: 131072,
8477
8530
  },
8531
+ "space-bunny-free": {
8532
+ id: "space-bunny-free",
8533
+ name: "Space Bunny Free",
8534
+ api: "openai-completions",
8535
+ provider: "opencode",
8536
+ baseUrl: "https://opencode.ai/zen/v1",
8537
+ reasoning: true,
8538
+ input: ["text", "image"],
8539
+ cost: {
8540
+ input: 0,
8541
+ output: 0,
8542
+ cacheRead: 0,
8543
+ cacheWrite: 0,
8544
+ },
8545
+ contextWindow: 1048576,
8546
+ maxTokens: 524288,
8547
+ },
8478
8548
  },
8479
8549
  "opencode-go": {
8480
8550
  "deepseek-v4-flash": {
@@ -8639,6 +8709,24 @@ export const MODELS = {
8639
8709
  contextWindow: 1050000,
8640
8710
  maxTokens: 128000,
8641
8711
  },
8712
+ "gpt-6-luna": {
8713
+ id: "gpt-6-luna",
8714
+ name: "GPT-6 Luna",
8715
+ api: "openai-responses",
8716
+ provider: "opencode-go",
8717
+ baseUrl: "https://opencode.ai/zen/go/v1",
8718
+ reasoning: true,
8719
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8720
+ input: ["text", "image"],
8721
+ cost: {
8722
+ input: 0.1,
8723
+ output: 0.5,
8724
+ cacheRead: 0.01,
8725
+ cacheWrite: 0.125,
8726
+ },
8727
+ contextWindow: 1050000,
8728
+ maxTokens: 128000,
8729
+ },
8642
8730
  "grok-4.6": {
8643
8731
  id: "grok-4.6",
8644
8732
  name: "Grok 4.6",
@@ -9000,6 +9088,23 @@ export const MODELS = {
9000
9088
  contextWindow: 1000000,
9001
9089
  maxTokens: 131072,
9002
9090
  },
9091
+ "space-bunny-free": {
9092
+ id: "space-bunny-free",
9093
+ name: "Space Bunny Free",
9094
+ api: "openai-completions",
9095
+ provider: "opencode-go",
9096
+ baseUrl: "https://opencode.ai/zen/go/v1",
9097
+ reasoning: true,
9098
+ input: ["text", "image"],
9099
+ cost: {
9100
+ input: 0,
9101
+ output: 0,
9102
+ cacheRead: 0,
9103
+ cacheWrite: 0,
9104
+ },
9105
+ contextWindow: 1048576,
9106
+ maxTokens: 524288,
9107
+ },
9003
9108
  },
9004
9109
  "openrouter": {
9005
9110
  "aion-labs/aion-2.0": {
@@ -9053,6 +9158,40 @@ export const MODELS = {
9053
9158
  contextWindow: 131072,
9054
9159
  maxTokens: 32768,
9055
9160
  },
9161
+ "aion-labs/aion-3.5": {
9162
+ id: "aion-labs/aion-3.5",
9163
+ name: "AionLabs: Aion 3.5",
9164
+ api: "openai-completions",
9165
+ provider: "openrouter",
9166
+ baseUrl: "https://openrouter.ai/api/v1",
9167
+ reasoning: true,
9168
+ input: ["text"],
9169
+ cost: {
9170
+ input: 3,
9171
+ output: 6,
9172
+ cacheRead: 0.75,
9173
+ cacheWrite: 0,
9174
+ },
9175
+ contextWindow: 262144,
9176
+ maxTokens: 32768,
9177
+ },
9178
+ "aion-labs/aion-3.5-mini": {
9179
+ id: "aion-labs/aion-3.5-mini",
9180
+ name: "AionLabs: Aion 3.5 Mini",
9181
+ api: "openai-completions",
9182
+ provider: "openrouter",
9183
+ baseUrl: "https://openrouter.ai/api/v1",
9184
+ reasoning: true,
9185
+ input: ["text"],
9186
+ cost: {
9187
+ input: 0.7,
9188
+ output: 1.4,
9189
+ cacheRead: 0.18,
9190
+ cacheWrite: 0,
9191
+ },
9192
+ contextWindow: 262144,
9193
+ maxTokens: 32768,
9194
+ },
9056
9195
  "amazon/nova-2-lite-v1": {
9057
9196
  id: "amazon/nova-2-lite-v1",
9058
9197
  name: "Amazon: Nova 2 Lite",
@@ -9997,8 +10136,8 @@ export const MODELS = {
9997
10136
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9998
10137
  input: ["text"],
9999
10138
  cost: {
10000
- input: 0.04,
10001
- output: 0.64,
10139
+ input: 0.03,
10140
+ output: 0.32,
10002
10141
  cacheRead: 0.016,
10003
10142
  cacheWrite: 0,
10004
10143
  },
@@ -10035,9 +10174,9 @@ export const MODELS = {
10035
10174
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10036
10175
  input: ["text"],
10037
10176
  cost: {
10038
- input: 0.9552599999999999,
10039
- output: 1.9105199999999998,
10040
- cacheRead: 0.07960500000000001,
10177
+ input: 0.9396,
10178
+ output: 1.8792,
10179
+ cacheRead: 0.07830000000000001,
10041
10180
  cacheWrite: 0,
10042
10181
  },
10043
10182
  contextWindow: 1048576,
@@ -10054,9 +10193,9 @@ export const MODELS = {
10054
10193
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10055
10194
  input: ["text"],
10056
10195
  cost: {
10057
- input: 0.498696,
10058
- output: 1.496088,
10059
- cacheRead: 0.0166232,
10196
+ input: 0.46199999999999997,
10197
+ output: 1.386,
10198
+ cacheRead: 0.015399999999999999,
10060
10199
  cacheWrite: 0,
10061
10200
  },
10062
10201
  contextWindow: 1048576,
@@ -10073,13 +10212,13 @@ export const MODELS = {
10073
10212
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10074
10213
  input: ["text", "image"],
10075
10214
  cost: {
10076
- input: 0.15,
10077
- output: 0.6,
10078
- cacheRead: 0.003,
10215
+ input: 0.14,
10216
+ output: 0.42,
10217
+ cacheRead: 0.004200000000000001,
10079
10218
  cacheWrite: 0,
10080
10219
  },
10081
10220
  contextWindow: 1048576,
10082
- maxTokens: 384000,
10221
+ maxTokens: 131072,
10083
10222
  },
10084
10223
  "deepseek/deepseek-v4.1-flash:batch": {
10085
10224
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -10117,6 +10256,23 @@ export const MODELS = {
10117
10256
  contextWindow: 512000,
10118
10257
  maxTokens: 460800,
10119
10258
  },
10259
+ "fireworks/ember-1": {
10260
+ id: "fireworks/ember-1",
10261
+ name: "Fireworks: Ember-1",
10262
+ api: "openai-completions",
10263
+ provider: "openrouter",
10264
+ baseUrl: "https://openrouter.ai/api/v1",
10265
+ reasoning: true,
10266
+ input: ["text", "image"],
10267
+ cost: {
10268
+ input: 3,
10269
+ output: 15,
10270
+ cacheRead: 0.3,
10271
+ cacheWrite: 0,
10272
+ },
10273
+ contextWindow: 1048576,
10274
+ maxTokens: 943718,
10275
+ },
10120
10276
  "google/gemini-2.5-flash": {
10121
10277
  id: "google/gemini-2.5-flash",
10122
10278
  name: "Google: Gemini 2.5 Flash",
@@ -10794,23 +10950,6 @@ export const MODELS = {
10794
10950
  cacheRead: 0.012,
10795
10951
  cacheWrite: 0,
10796
10952
  },
10797
- contextWindow: 131072,
10798
- maxTokens: 32768,
10799
- },
10800
- "inclusionai/ling-3.0-flash-vl:free": {
10801
- id: "inclusionai/ling-3.0-flash-vl:free",
10802
- name: "inclusionAI: Ling 3.0 Flash VL (free)",
10803
- api: "openai-completions",
10804
- provider: "openrouter",
10805
- baseUrl: "https://openrouter.ai/api/v1",
10806
- reasoning: true,
10807
- input: ["text", "image"],
10808
- cost: {
10809
- input: 0,
10810
- output: 0,
10811
- cacheRead: 0,
10812
- cacheWrite: 0,
10813
- },
10814
10953
  contextWindow: 262144,
10815
10954
  maxTokens: 32768,
10816
10955
  },
@@ -11078,13 +11217,13 @@ export const MODELS = {
11078
11217
  reasoning: true,
11079
11218
  input: ["text"],
11080
11219
  cost: {
11081
- input: 0.255,
11082
- output: 1.02,
11220
+ input: 0.3,
11221
+ output: 1.2,
11083
11222
  cacheRead: 0,
11084
11223
  cacheWrite: 0,
11085
11224
  },
11086
11225
  contextWindow: 204800,
11087
- maxTokens: 131072,
11226
+ maxTokens: 176947,
11088
11227
  },
11089
11228
  "minimax/minimax-m2.1": {
11090
11229
  id: "minimax/minimax-m2.1",
@@ -11188,23 +11327,6 @@ export const MODELS = {
11188
11327
  contextWindow: 256000,
11189
11328
  maxTokens: 204800,
11190
11329
  },
11191
- "mistralai/devstral-2512": {
11192
- id: "mistralai/devstral-2512",
11193
- name: "Mistral: Devstral 2 2512",
11194
- api: "openai-completions",
11195
- provider: "openrouter",
11196
- baseUrl: "https://openrouter.ai/api/v1",
11197
- reasoning: false,
11198
- input: ["text"],
11199
- cost: {
11200
- input: 0.39999999999999997,
11201
- output: 2,
11202
- cacheRead: 0.04,
11203
- cacheWrite: 0,
11204
- },
11205
- contextWindow: 262144,
11206
- maxTokens: 209715,
11207
- },
11208
11330
  "mistralai/ministral-14b-2512": {
11209
11331
  id: "mistralai/ministral-14b-2512",
11210
11332
  name: "Mistral: Ministral 3 14B 2512",
@@ -11639,7 +11761,7 @@ export const MODELS = {
11639
11761
  reasoning: true,
11640
11762
  input: ["text", "image"],
11641
11763
  cost: {
11642
- input: 0.7062,
11764
+ input: 0.6562,
11643
11765
  output: 3.3000000000000003,
11644
11766
  cacheRead: 0.18,
11645
11767
  cacheWrite: 0,
@@ -11698,23 +11820,6 @@ export const MODELS = {
11698
11820
  contextWindow: 262144,
11699
11821
  maxTokens: 235929,
11700
11822
  },
11701
- "nex-agi/nex-n2.5-pro": {
11702
- id: "nex-agi/nex-n2.5-pro",
11703
- name: "Nex AGI: Nex-N2.5-Pro",
11704
- api: "openai-completions",
11705
- provider: "openrouter",
11706
- baseUrl: "https://openrouter.ai/api/v1",
11707
- reasoning: true,
11708
- input: ["text", "image"],
11709
- cost: {
11710
- input: 0.075,
11711
- output: 0.25,
11712
- cacheRead: 0.015,
11713
- cacheWrite: 0,
11714
- },
11715
- contextWindow: 262144,
11716
- maxTokens: 235929,
11717
- },
11718
11823
  "nex-agi/nex-n2.5-pro:free": {
11719
11824
  id: "nex-agi/nex-n2.5-pro:free",
11720
11825
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -13276,6 +13381,23 @@ export const MODELS = {
13276
13381
  contextWindow: 131072,
13277
13382
  maxTokens: 65536,
13278
13383
  },
13384
+ "openai/gpt-oss-120b:batch": {
13385
+ id: "openai/gpt-oss-120b:batch",
13386
+ name: "OpenAI: gpt-oss-120b (batch)",
13387
+ api: "openai-completions",
13388
+ provider: "openrouter",
13389
+ baseUrl: "https://openrouter.ai/api/v1",
13390
+ reasoning: true,
13391
+ input: ["text"],
13392
+ cost: {
13393
+ input: 0.0296,
13394
+ output: 0.136,
13395
+ cacheRead: 0,
13396
+ cacheWrite: 0,
13397
+ },
13398
+ contextWindow: 131072,
13399
+ maxTokens: 117964,
13400
+ },
13279
13401
  "openai/gpt-oss-20b": {
13280
13402
  id: "openai/gpt-oss-20b",
13281
13403
  name: "OpenAI: gpt-oss-20b",
@@ -13795,13 +13917,13 @@ export const MODELS = {
13795
13917
  reasoning: false,
13796
13918
  input: ["text"],
13797
13919
  cost: {
13798
- input: 0.04815,
13799
- output: 0.19305,
13920
+ input: 0.09999999999999999,
13921
+ output: 0.3,
13800
13922
  cacheRead: 0,
13801
13923
  cacheWrite: 0,
13802
13924
  },
13803
13925
  contextWindow: 262144,
13804
- maxTokens: 32000,
13926
+ maxTokens: 235929,
13805
13927
  },
13806
13928
  "qwen/qwen3-30b-a3b-thinking-2507": {
13807
13929
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -13982,13 +14104,13 @@ export const MODELS = {
13982
14104
  reasoning: false,
13983
14105
  input: ["text"],
13984
14106
  cost: {
13985
- input: 0.09,
14107
+ input: 0.09999999999999999,
13986
14108
  output: 1.1,
13987
- cacheRead: 0,
14109
+ cacheRead: 0.07,
13988
14110
  cacheWrite: 0,
13989
14111
  },
13990
14112
  contextWindow: 262144,
13991
- maxTokens: 16384,
14113
+ maxTokens: 235929,
13992
14114
  },
13993
14115
  "qwen/qwen3-next-80b-a3b-thinking": {
13994
14116
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14483,6 +14605,23 @@ export const MODELS = {
14483
14605
  contextWindow: 1000000,
14484
14606
  maxTokens: 131072,
14485
14607
  },
14608
+ "qwen/qwen3.8-max-prime": {
14609
+ id: "qwen/qwen3.8-max-prime",
14610
+ name: "Qwen: Qwen3.8 Max Prime",
14611
+ api: "openai-completions",
14612
+ provider: "openrouter",
14613
+ baseUrl: "https://openrouter.ai/api/v1",
14614
+ reasoning: true,
14615
+ input: ["text", "image"],
14616
+ cost: {
14617
+ input: 4,
14618
+ output: 12,
14619
+ cacheRead: 0.5,
14620
+ cacheWrite: 0,
14621
+ },
14622
+ contextWindow: 1000000,
14623
+ maxTokens: 131072,
14624
+ },
14486
14625
  "qwen/qwen3.8-omni-flash": {
14487
14626
  id: "qwen/qwen3.8-omni-flash",
14488
14627
  name: "Qwen: Qwen3.8 Omni Flash",
@@ -14619,6 +14758,23 @@ export const MODELS = {
14619
14758
  contextWindow: 131072,
14620
14759
  maxTokens: 16384,
14621
14760
  },
14761
+ "stealth/space-bunny-alpha": {
14762
+ id: "stealth/space-bunny-alpha",
14763
+ name: "Space Bunny Alpha",
14764
+ api: "openai-completions",
14765
+ provider: "openrouter",
14766
+ baseUrl: "https://openrouter.ai/api/v1",
14767
+ reasoning: true,
14768
+ input: ["text", "image"],
14769
+ cost: {
14770
+ input: 0,
14771
+ output: 0,
14772
+ cacheRead: 0,
14773
+ cacheWrite: 0,
14774
+ },
14775
+ contextWindow: 1000000,
14776
+ maxTokens: 524288,
14777
+ },
14622
14778
  "stepfun/step-3.5-flash": {
14623
14779
  id: "stepfun/step-3.5-flash",
14624
14780
  name: "StepFun: Step 3.5 Flash",
@@ -15293,12 +15449,29 @@ export const MODELS = {
15293
15449
  cost: {
15294
15450
  input: 0.37,
15295
15451
  output: 1.25,
15296
- cacheRead: 0.075,
15452
+ cacheRead: 0.09,
15297
15453
  cacheWrite: 0,
15298
15454
  },
15299
15455
  contextWindow: 1048576,
15300
15456
  maxTokens: 131072,
15301
15457
  },
15458
+ "z-ai/glm-5.3-prime": {
15459
+ id: "z-ai/glm-5.3-prime",
15460
+ name: "Z.ai: GLM 5.3 Prime",
15461
+ api: "openai-completions",
15462
+ provider: "openrouter",
15463
+ baseUrl: "https://openrouter.ai/api/v1",
15464
+ reasoning: true,
15465
+ input: ["text"],
15466
+ cost: {
15467
+ input: 2.8,
15468
+ output: 8.8,
15469
+ cacheRead: 0.56,
15470
+ cacheWrite: 0,
15471
+ },
15472
+ contextWindow: 1000000,
15473
+ maxTokens: 131072,
15474
+ },
15302
15475
  "z-ai/glm-5.3:batch": {
15303
15476
  id: "z-ai/glm-5.3:batch",
15304
15477
  name: "Z.ai: GLM 5.3 (batch)",
@@ -15308,9 +15481,9 @@ export const MODELS = {
15308
15481
  reasoning: true,
15309
15482
  input: ["text"],
15310
15483
  cost: {
15311
- input: 0.72,
15312
- output: 2.4,
15313
- cacheRead: 0.12,
15484
+ input: 0.44999999999999996,
15485
+ output: 2,
15486
+ cacheRead: 0.09999999999999999,
15314
15487
  cacheWrite: 0,
15315
15488
  },
15316
15489
  contextWindow: 1048576,
@@ -15413,8 +15586,8 @@ export const MODELS = {
15413
15586
  reasoning: true,
15414
15587
  input: ["text", "image"],
15415
15588
  cost: {
15416
- input: 0.09999999999999999,
15417
- output: 0.5,
15589
+ input: 0.04,
15590
+ output: 1,
15418
15591
  cacheRead: 0.01,
15419
15592
  cacheWrite: 0,
15420
15593
  },
@@ -15430,13 +15603,13 @@ export const MODELS = {
15430
15603
  reasoning: true,
15431
15604
  input: ["text"],
15432
15605
  cost: {
15433
- input: 0.39999999999999997,
15434
- output: 4.300000000000001,
15435
- cacheRead: 0.032999999999999995,
15606
+ input: 0.39,
15607
+ output: 2.9000000000000004,
15608
+ cacheRead: 0.25,
15436
15609
  cacheWrite: 0,
15437
15610
  },
15438
15611
  contextWindow: 1048576,
15439
- maxTokens: 384000,
15612
+ maxTokens: 943718,
15440
15613
  },
15441
15614
  "~deepseek/deepseek-v4-flash-latest": {
15442
15615
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -15449,9 +15622,9 @@ export const MODELS = {
15449
15622
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15450
15623
  input: ["text"],
15451
15624
  cost: {
15452
- input: 0.038000000000000006,
15453
- output: 0.55,
15454
- cacheRead: 0.022799999999999997,
15625
+ input: 0.03,
15626
+ output: 0.32,
15627
+ cacheRead: 0.016,
15455
15628
  cacheWrite: 0,
15456
15629
  },
15457
15630
  contextWindow: 1310720,
@@ -15500,8 +15673,8 @@ export const MODELS = {
15500
15673
  reasoning: true,
15501
15674
  input: ["text", "image"],
15502
15675
  cost: {
15503
- input: 1.4989,
15504
- output: 10.758,
15676
+ input: 1.4,
15677
+ output: 10.75,
15505
15678
  cacheRead: 0.3,
15506
15679
  cacheWrite: 0,
15507
15680
  },
@@ -15619,13 +15792,13 @@ export const MODELS = {
15619
15792
  reasoning: true,
15620
15793
  input: ["text", "image"],
15621
15794
  cost: {
15622
- input: 0.075,
15623
- output: 0.25,
15624
- cacheRead: 0.015,
15795
+ input: 0.045,
15796
+ output: 0.14,
15797
+ cacheRead: 0.01,
15625
15798
  cacheWrite: 0,
15626
15799
  },
15627
15800
  contextWindow: 1310720,
15628
- maxTokens: 131072,
15801
+ maxTokens: 128000,
15629
15802
  },
15630
15803
  "~z-ai/glm-latest": {
15631
15804
  id: "~z-ai/glm-latest",
@@ -15662,7 +15835,7 @@ export const MODELS = {
15662
15835
  cacheRead: 0.06,
15663
15836
  cacheWrite: 0,
15664
15837
  },
15665
- contextWindow: 202752,
15838
+ contextWindow: 196608,
15666
15839
  maxTokens: 131072,
15667
15840
  },
15668
15841
  "MiniMaxAI/MiniMax-M3": {
@@ -15774,7 +15947,7 @@ export const MODELS = {
15774
15947
  cacheRead: 0.03,
15775
15948
  cacheWrite: 0,
15776
15949
  },
15777
- contextWindow: 1000000,
15950
+ contextWindow: 1048576,
15778
15951
  maxTokens: 384000,
15779
15952
  },
15780
15953
  "deepseek-ai/DeepSeek-V4-Pro": {
@@ -16020,7 +16193,7 @@ export const MODELS = {
16020
16193
  cacheRead: 0.26,
16021
16194
  cacheWrite: 0,
16022
16195
  },
16023
- contextWindow: 512000,
16196
+ contextWindow: 1048575,
16024
16197
  maxTokens: 164000,
16025
16198
  },
16026
16199
  "zai-org/GLM-5.3": {
@@ -16573,6 +16746,23 @@ export const MODELS = {
16573
16746
  contextWindow: 991000,
16574
16747
  maxTokens: 128000,
16575
16748
  },
16749
+ "alibaba/qwen3.8-max-prime": {
16750
+ id: "alibaba/qwen3.8-max-prime",
16751
+ name: "Qwen 3.8 Max Prime",
16752
+ api: "anthropic-messages",
16753
+ provider: "vercel-ai-gateway",
16754
+ baseUrl: "https://ai-gateway.vercel.sh",
16755
+ reasoning: true,
16756
+ input: ["text", "image"],
16757
+ cost: {
16758
+ input: 4,
16759
+ output: 12,
16760
+ cacheRead: 0.5,
16761
+ cacheWrite: 0,
16762
+ },
16763
+ contextWindow: 1000000,
16764
+ maxTokens: 131072,
16765
+ },
16576
16766
  "alibaba/qwen3.8-omni-flash": {
16577
16767
  id: "alibaba/qwen3.8-omni-flash",
16578
16768
  name: "Qwen 3.8 Omni Flash",
@@ -17613,26 +17803,9 @@ export const MODELS = {
17613
17803
  reasoning: true,
17614
17804
  input: ["text", "image"],
17615
17805
  cost: {
17616
- input: 0,
17617
- output: 0,
17618
- cacheRead: 0,
17619
- cacheWrite: 0,
17620
- },
17621
- contextWindow: 256000,
17622
- maxTokens: 32000,
17623
- },
17624
- "inclusionai/ling-3.0-flash-vl-free": {
17625
- id: "inclusionai/ling-3.0-flash-vl-free",
17626
- name: "Ling 3.0 Flash VL (Free)",
17627
- api: "anthropic-messages",
17628
- provider: "vercel-ai-gateway",
17629
- baseUrl: "https://ai-gateway.vercel.sh",
17630
- reasoning: true,
17631
- input: ["text", "image"],
17632
- cost: {
17633
- input: 0,
17634
- output: 0,
17635
- cacheRead: 0,
17806
+ input: 0.075,
17807
+ output: 0.22,
17808
+ cacheRead: 0.015,
17636
17809
  cacheWrite: 0,
17637
17810
  },
17638
17811
  contextWindow: 256000,
@@ -19268,7 +19441,7 @@ export const MODELS = {
19268
19441
  cost: {
19269
19442
  input: 0.09999999999999999,
19270
19443
  output: 0.5,
19271
- cacheRead: 0,
19444
+ cacheRead: 0.09999999999999999,
19272
19445
  cacheWrite: 0,
19273
19446
  },
19274
19447
  contextWindow: 131072,