@mariozechner/pi-ai 0.70.2 → 0.70.4

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.
@@ -3534,6 +3534,24 @@ export const MODELS = {
3534
3534
  contextWindow: 400000,
3535
3535
  maxTokens: 128000,
3536
3536
  },
3537
+ "gpt-5.5": {
3538
+ id: "gpt-5.5",
3539
+ name: "GPT-5.5",
3540
+ api: "openai-responses",
3541
+ provider: "github-copilot",
3542
+ baseUrl: "https://api.individual.githubcopilot.com",
3543
+ 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" },
3544
+ reasoning: true,
3545
+ input: ["text", "image"],
3546
+ cost: {
3547
+ input: 0,
3548
+ output: 0,
3549
+ cacheRead: 0,
3550
+ cacheWrite: 0,
3551
+ },
3552
+ contextWindow: 400000,
3553
+ maxTokens: 128000,
3554
+ },
3537
3555
  "grok-code-fast-1": {
3538
3556
  id: "grok-code-fast-1",
3539
3557
  name: "Grok Code Fast 1",
@@ -5039,6 +5057,24 @@ export const MODELS = {
5039
5057
  contextWindow: 163840,
5040
5058
  maxTokens: 65536,
5041
5059
  },
5060
+ "deepseek-ai/DeepSeek-V4-Pro": {
5061
+ id: "deepseek-ai/DeepSeek-V4-Pro",
5062
+ name: "DeepSeek V4 Pro",
5063
+ api: "openai-completions",
5064
+ provider: "huggingface",
5065
+ baseUrl: "https://router.huggingface.co/v1",
5066
+ compat: { "supportsDeveloperRole": false },
5067
+ reasoning: true,
5068
+ input: ["text"],
5069
+ cost: {
5070
+ input: 1.74,
5071
+ output: 3.48,
5072
+ cacheRead: 0.145,
5073
+ cacheWrite: 0,
5074
+ },
5075
+ contextWindow: 1048576,
5076
+ maxTokens: 393216,
5077
+ },
5042
5078
  "moonshotai/Kimi-K2-Instruct": {
5043
5079
  id: "moonshotai/Kimi-K2-Instruct",
5044
5080
  name: "Kimi-K2-Instruct",
@@ -6663,23 +6699,6 @@ export const MODELS = {
6663
6699
  contextWindow: 200000,
6664
6700
  maxTokens: 128000,
6665
6701
  },
6666
- "claude-3-5-haiku": {
6667
- id: "claude-3-5-haiku",
6668
- name: "Claude Haiku 3.5",
6669
- api: "anthropic-messages",
6670
- provider: "opencode",
6671
- baseUrl: "https://opencode.ai/zen",
6672
- reasoning: false,
6673
- input: ["text", "image"],
6674
- cost: {
6675
- input: 0.8,
6676
- output: 4,
6677
- cacheRead: 0.08,
6678
- cacheWrite: 1,
6679
- },
6680
- contextWindow: 200000,
6681
- maxTokens: 8192,
6682
- },
6683
6702
  "claude-haiku-4-5": {
6684
6703
  id: "claude-haiku-4-5",
6685
6704
  name: "Claude Haiku 4.5",
@@ -7122,6 +7141,40 @@ export const MODELS = {
7122
7141
  contextWindow: 1050000,
7123
7142
  maxTokens: 128000,
7124
7143
  },
7144
+ "gpt-5.5": {
7145
+ id: "gpt-5.5",
7146
+ name: "GPT-5.5",
7147
+ api: "openai-responses",
7148
+ provider: "opencode",
7149
+ baseUrl: "https://opencode.ai/zen/v1",
7150
+ reasoning: true,
7151
+ input: ["text", "image"],
7152
+ cost: {
7153
+ input: 5,
7154
+ output: 30,
7155
+ cacheRead: 0.5,
7156
+ cacheWrite: 0,
7157
+ },
7158
+ contextWindow: 1050000,
7159
+ maxTokens: 128000,
7160
+ },
7161
+ "gpt-5.5-pro": {
7162
+ id: "gpt-5.5-pro",
7163
+ name: "GPT-5.5 Pro",
7164
+ api: "openai-responses",
7165
+ provider: "opencode",
7166
+ baseUrl: "https://opencode.ai/zen/v1",
7167
+ reasoning: true,
7168
+ input: ["text", "image"],
7169
+ cost: {
7170
+ input: 30,
7171
+ output: 180,
7172
+ cacheRead: 30,
7173
+ cacheWrite: 0,
7174
+ },
7175
+ contextWindow: 1050000,
7176
+ maxTokens: 128000,
7177
+ },
7125
7178
  "hy3-preview-free": {
7126
7179
  id: "hy3-preview-free",
7127
7180
  name: "Hy3 preview Free",
@@ -7294,6 +7347,42 @@ export const MODELS = {
7294
7347
  },
7295
7348
  },
7296
7349
  "opencode-go": {
7350
+ "deepseek-v4-flash": {
7351
+ id: "deepseek-v4-flash",
7352
+ name: "DeepSeek V4 Flash",
7353
+ api: "openai-completions",
7354
+ provider: "opencode-go",
7355
+ baseUrl: "https://opencode.ai/zen/go/v1",
7356
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
7357
+ reasoning: true,
7358
+ input: ["text"],
7359
+ cost: {
7360
+ input: 0.14,
7361
+ output: 0.28,
7362
+ cacheRead: 0.0028,
7363
+ cacheWrite: 0,
7364
+ },
7365
+ contextWindow: 1000000,
7366
+ maxTokens: 384000,
7367
+ },
7368
+ "deepseek-v4-pro": {
7369
+ id: "deepseek-v4-pro",
7370
+ name: "DeepSeek V4 Pro",
7371
+ api: "openai-completions",
7372
+ provider: "opencode-go",
7373
+ baseUrl: "https://opencode.ai/zen/go/v1",
7374
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
7375
+ reasoning: true,
7376
+ input: ["text"],
7377
+ cost: {
7378
+ input: 1.74,
7379
+ output: 3.48,
7380
+ cacheRead: 0.0145,
7381
+ cacheWrite: 0,
7382
+ },
7383
+ contextWindow: 1000000,
7384
+ maxTokens: 384000,
7385
+ },
7297
7386
  "glm-5": {
7298
7387
  id: "glm-5",
7299
7388
  name: "GLM-5",
@@ -7410,7 +7499,7 @@ export const MODELS = {
7410
7499
  cacheRead: 0.08,
7411
7500
  cacheWrite: 0,
7412
7501
  },
7413
- contextWindow: 262144,
7502
+ contextWindow: 1000000,
7414
7503
  maxTokens: 128000,
7415
7504
  },
7416
7505
  "mimo-v2.5-pro": {
@@ -7549,7 +7638,7 @@ export const MODELS = {
7549
7638
  cacheWrite: 0,
7550
7639
  },
7551
7640
  contextWindow: 65536,
7552
- maxTokens: 4096,
7641
+ maxTokens: 16384,
7553
7642
  },
7554
7643
  "amazon/nova-2-lite-v1": {
7555
7644
  id: "amazon/nova-2-lite-v1",
@@ -8110,7 +8199,7 @@ export const MODELS = {
8110
8199
  cacheWrite: 0,
8111
8200
  },
8112
8201
  contextWindow: 163840,
8113
- maxTokens: 163840,
8202
+ maxTokens: 16384,
8114
8203
  },
8115
8204
  "deepseek/deepseek-chat-v3-0324": {
8116
8205
  id: "deepseek/deepseek-chat-v3-0324",
@@ -8127,7 +8216,7 @@ export const MODELS = {
8127
8216
  cacheWrite: 0,
8128
8217
  },
8129
8218
  contextWindow: 163840,
8130
- maxTokens: 4096,
8219
+ maxTokens: 16384,
8131
8220
  },
8132
8221
  "deepseek/deepseek-chat-v3.1": {
8133
8222
  id: "deepseek/deepseek-chat-v3.1",
@@ -8178,7 +8267,7 @@ export const MODELS = {
8178
8267
  cacheWrite: 0,
8179
8268
  },
8180
8269
  contextWindow: 163840,
8181
- maxTokens: 4096,
8270
+ maxTokens: 32768,
8182
8271
  },
8183
8272
  "deepseek/deepseek-v3.1-terminus": {
8184
8273
  id: "deepseek/deepseek-v3.1-terminus",
@@ -8191,11 +8280,11 @@ export const MODELS = {
8191
8280
  cost: {
8192
8281
  input: 0.21,
8193
8282
  output: 0.7899999999999999,
8194
- cacheRead: 0.1300000002,
8283
+ cacheRead: 0.13,
8195
8284
  cacheWrite: 0,
8196
8285
  },
8197
8286
  contextWindow: 163840,
8198
- maxTokens: 4096,
8287
+ maxTokens: 32768,
8199
8288
  },
8200
8289
  "deepseek/deepseek-v3.2": {
8201
8290
  id: "deepseek/deepseek-v3.2",
@@ -8237,12 +8326,13 @@ export const MODELS = {
8237
8326
  api: "openai-completions",
8238
8327
  provider: "openrouter",
8239
8328
  baseUrl: "https://openrouter.ai/api/v1",
8329
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
8240
8330
  reasoning: true,
8241
8331
  input: ["text"],
8242
8332
  cost: {
8243
8333
  input: 0.14,
8244
8334
  output: 0.28,
8245
- cacheRead: 0.028,
8335
+ cacheRead: 0.0028,
8246
8336
  cacheWrite: 0,
8247
8337
  },
8248
8338
  contextWindow: 1048576,
@@ -8254,12 +8344,13 @@ export const MODELS = {
8254
8344
  api: "openai-completions",
8255
8345
  provider: "openrouter",
8256
8346
  baseUrl: "https://openrouter.ai/api/v1",
8347
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
8257
8348
  reasoning: true,
8258
8349
  input: ["text"],
8259
8350
  cost: {
8260
- input: 1.74,
8261
- output: 3.48,
8262
- cacheRead: 0.145,
8351
+ input: 0.435,
8352
+ output: 0.87,
8353
+ cacheRead: 0.003625,
8263
8354
  cacheWrite: 0,
8264
8355
  },
8265
8356
  contextWindow: 1048576,
@@ -8296,7 +8387,7 @@ export const MODELS = {
8296
8387
  cacheRead: 0.024999999999999998,
8297
8388
  cacheWrite: 0.08333333333333334,
8298
8389
  },
8299
- contextWindow: 1048576,
8390
+ contextWindow: 1000000,
8300
8391
  maxTokens: 8192,
8301
8392
  },
8302
8393
  "google/gemini-2.0-flash-lite-001": {
@@ -8486,6 +8577,40 @@ export const MODELS = {
8486
8577
  contextWindow: 1048576,
8487
8578
  maxTokens: 65536,
8488
8579
  },
8580
+ "google/gemma-3-12b-it": {
8581
+ id: "google/gemma-3-12b-it",
8582
+ name: "Google: Gemma 3 12B",
8583
+ api: "openai-completions",
8584
+ provider: "openrouter",
8585
+ baseUrl: "https://openrouter.ai/api/v1",
8586
+ reasoning: false,
8587
+ input: ["text", "image"],
8588
+ cost: {
8589
+ input: 0.04,
8590
+ output: 0.13,
8591
+ cacheRead: 0,
8592
+ cacheWrite: 0,
8593
+ },
8594
+ contextWindow: 131072,
8595
+ maxTokens: 16384,
8596
+ },
8597
+ "google/gemma-3-27b-it": {
8598
+ id: "google/gemma-3-27b-it",
8599
+ name: "Google: Gemma 3 27B",
8600
+ api: "openai-completions",
8601
+ provider: "openrouter",
8602
+ baseUrl: "https://openrouter.ai/api/v1",
8603
+ reasoning: false,
8604
+ input: ["text", "image"],
8605
+ cost: {
8606
+ input: 0.08,
8607
+ output: 0.16,
8608
+ cacheRead: 0,
8609
+ cacheWrite: 0,
8610
+ },
8611
+ contextWindow: 131072,
8612
+ maxTokens: 16384,
8613
+ },
8489
8614
  "google/gemma-4-26b-a4b-it": {
8490
8615
  id: "google/gemma-4-26b-a4b-it",
8491
8616
  name: "Google: Gemma 4 26B A4B ",
@@ -8535,7 +8660,7 @@ export const MODELS = {
8535
8660
  cacheWrite: 0,
8536
8661
  },
8537
8662
  contextWindow: 262144,
8538
- maxTokens: 4096,
8663
+ maxTokens: 16384,
8539
8664
  },
8540
8665
  "google/gemma-4-31b-it:free": {
8541
8666
  id: "google/gemma-4-31b-it:free",
@@ -8654,7 +8779,7 @@ export const MODELS = {
8654
8779
  cacheWrite: 0,
8655
8780
  },
8656
8781
  contextWindow: 131072,
8657
- maxTokens: 4096,
8782
+ maxTokens: 16384,
8658
8783
  },
8659
8784
  "meta-llama/llama-3.1-8b-instruct": {
8660
8785
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8790,7 +8915,7 @@ export const MODELS = {
8790
8915
  cacheWrite: 0,
8791
8916
  },
8792
8917
  contextWindow: 196608,
8793
- maxTokens: 4096,
8918
+ maxTokens: 131072,
8794
8919
  },
8795
8920
  "minimax/minimax-m2.5:free": {
8796
8921
  id: "minimax/minimax-m2.5:free",
@@ -9056,13 +9181,13 @@ export const MODELS = {
9056
9181
  reasoning: false,
9057
9182
  input: ["text"],
9058
9183
  cost: {
9059
- input: 0.01,
9060
- output: 0.03,
9184
+ input: 0.02,
9185
+ output: 0.04,
9061
9186
  cacheRead: 0,
9062
9187
  cacheWrite: 0,
9063
9188
  },
9064
9189
  contextWindow: 131072,
9065
- maxTokens: 4096,
9190
+ maxTokens: 16384,
9066
9191
  },
9067
9192
  "mistralai/mistral-saba": {
9068
9193
  id: "mistralai/mistral-saba",
@@ -9113,7 +9238,7 @@ export const MODELS = {
9113
9238
  cacheWrite: 0,
9114
9239
  },
9115
9240
  contextWindow: 128000,
9116
- maxTokens: 4096,
9241
+ maxTokens: 16384,
9117
9242
  },
9118
9243
  "mistralai/mistral-small-creative": {
9119
9244
  id: "mistralai/mistral-small-creative",
@@ -9334,7 +9459,7 @@ export const MODELS = {
9334
9459
  cacheWrite: 0,
9335
9460
  },
9336
9461
  contextWindow: 131072,
9337
- maxTokens: 4096,
9462
+ maxTokens: 16384,
9338
9463
  },
9339
9464
  "nvidia/nemotron-3-nano-30b-a3b": {
9340
9465
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -9351,7 +9476,7 @@ export const MODELS = {
9351
9476
  cacheWrite: 0,
9352
9477
  },
9353
9478
  contextWindow: 262144,
9354
- maxTokens: 4096,
9479
+ maxTokens: 228000,
9355
9480
  },
9356
9481
  "nvidia/nemotron-3-nano-30b-a3b:free": {
9357
9482
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -9436,7 +9561,7 @@ export const MODELS = {
9436
9561
  cacheWrite: 0,
9437
9562
  },
9438
9563
  contextWindow: 131072,
9439
- maxTokens: 4096,
9564
+ maxTokens: 16384,
9440
9565
  },
9441
9566
  "nvidia/nemotron-nano-9b-v2:free": {
9442
9567
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -10101,6 +10226,40 @@ export const MODELS = {
10101
10226
  contextWindow: 1050000,
10102
10227
  maxTokens: 128000,
10103
10228
  },
10229
+ "openai/gpt-5.5": {
10230
+ id: "openai/gpt-5.5",
10231
+ name: "OpenAI: GPT-5.5",
10232
+ api: "openai-completions",
10233
+ provider: "openrouter",
10234
+ baseUrl: "https://openrouter.ai/api/v1",
10235
+ reasoning: true,
10236
+ input: ["text", "image"],
10237
+ cost: {
10238
+ input: 5,
10239
+ output: 30,
10240
+ cacheRead: 0.5,
10241
+ cacheWrite: 0,
10242
+ },
10243
+ contextWindow: 1050000,
10244
+ maxTokens: 128000,
10245
+ },
10246
+ "openai/gpt-5.5-pro": {
10247
+ id: "openai/gpt-5.5-pro",
10248
+ name: "OpenAI: GPT-5.5 Pro",
10249
+ api: "openai-completions",
10250
+ provider: "openrouter",
10251
+ baseUrl: "https://openrouter.ai/api/v1",
10252
+ reasoning: true,
10253
+ input: ["text", "image"],
10254
+ cost: {
10255
+ input: 30,
10256
+ output: 180,
10257
+ cacheRead: 0,
10258
+ cacheWrite: 0,
10259
+ },
10260
+ contextWindow: 1050000,
10261
+ maxTokens: 128000,
10262
+ },
10104
10263
  "openai/gpt-audio": {
10105
10264
  id: "openai/gpt-audio",
10106
10265
  name: "OpenAI: GPT Audio",
@@ -10150,7 +10309,7 @@ export const MODELS = {
10150
10309
  cacheWrite: 0,
10151
10310
  },
10152
10311
  contextWindow: 131072,
10153
- maxTokens: 4096,
10312
+ maxTokens: 131072,
10154
10313
  },
10155
10314
  "openai/gpt-oss-120b:free": {
10156
10315
  id: "openai/gpt-oss-120b:free",
@@ -10184,7 +10343,7 @@ export const MODELS = {
10184
10343
  cacheWrite: 0,
10185
10344
  },
10186
10345
  contextWindow: 131072,
10187
- maxTokens: 4096,
10346
+ maxTokens: 131072,
10188
10347
  },
10189
10348
  "openai/gpt-oss-20b:free": {
10190
10349
  id: "openai/gpt-oss-20b:free",
@@ -10433,8 +10592,8 @@ export const MODELS = {
10433
10592
  reasoning: false,
10434
10593
  input: ["text"],
10435
10594
  cost: {
10436
- input: 0.12,
10437
- output: 0.39,
10595
+ input: 0.36,
10596
+ output: 0.39999999999999997,
10438
10597
  cacheRead: 0,
10439
10598
  cacheWrite: 0,
10440
10599
  },
@@ -10609,7 +10768,7 @@ export const MODELS = {
10609
10768
  cacheWrite: 0,
10610
10769
  },
10611
10770
  contextWindow: 262144,
10612
- maxTokens: 4096,
10771
+ maxTokens: 16384,
10613
10772
  },
10614
10773
  "qwen/qwen3-235b-a22b-thinking-2507": {
10615
10774
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10643,7 +10802,7 @@ export const MODELS = {
10643
10802
  cacheWrite: 0,
10644
10803
  },
10645
10804
  contextWindow: 40960,
10646
- maxTokens: 40960,
10805
+ maxTokens: 16384,
10647
10806
  },
10648
10807
  "qwen/qwen3-30b-a3b-instruct-2507": {
10649
10808
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10723,12 +10882,12 @@ export const MODELS = {
10723
10882
  input: ["text"],
10724
10883
  cost: {
10725
10884
  input: 0.22,
10726
- output: 1,
10727
- cacheRead: 0.022,
10885
+ output: 1.7999999999999998,
10886
+ cacheRead: 0,
10728
10887
  cacheWrite: 0,
10729
10888
  },
10730
10889
  contextWindow: 262144,
10731
- maxTokens: 4096,
10890
+ maxTokens: 65536,
10732
10891
  },
10733
10892
  "qwen/qwen3-coder-30b-a3b-instruct": {
10734
10893
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10773,9 +10932,9 @@ export const MODELS = {
10773
10932
  reasoning: false,
10774
10933
  input: ["text"],
10775
10934
  cost: {
10776
- input: 0.15,
10935
+ input: 0.14,
10777
10936
  output: 0.7999999999999999,
10778
- cacheRead: 0.11,
10937
+ cacheRead: 0.09,
10779
10938
  cacheWrite: 0,
10780
10939
  },
10781
10940
  contextWindow: 262144,
@@ -10864,7 +11023,7 @@ export const MODELS = {
10864
11023
  cacheWrite: 0,
10865
11024
  },
10866
11025
  contextWindow: 262144,
10867
- maxTokens: 4096,
11026
+ maxTokens: 16384,
10868
11027
  },
10869
11028
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10870
11029
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10915,7 +11074,7 @@ export const MODELS = {
10915
11074
  cacheWrite: 0,
10916
11075
  },
10917
11076
  contextWindow: 262144,
10918
- maxTokens: 4096,
11077
+ maxTokens: 16384,
10919
11078
  },
10920
11079
  "qwen/qwen3-vl-235b-a22b-thinking": {
10921
11080
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -11138,47 +11297,115 @@ export const MODELS = {
11138
11297
  contextWindow: 1000000,
11139
11298
  maxTokens: 65536,
11140
11299
  },
11141
- "qwen/qwen3.6-plus": {
11142
- id: "qwen/qwen3.6-plus",
11143
- name: "Qwen: Qwen3.6 Plus",
11300
+ "qwen/qwen3.5-plus-20260420": {
11301
+ id: "qwen/qwen3.5-plus-20260420",
11302
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
11144
11303
  api: "openai-completions",
11145
11304
  provider: "openrouter",
11146
11305
  baseUrl: "https://openrouter.ai/api/v1",
11147
11306
  reasoning: true,
11148
11307
  input: ["text", "image"],
11149
11308
  cost: {
11150
- input: 0.325,
11151
- output: 1.95,
11309
+ input: 0.39999999999999997,
11310
+ output: 2.4,
11152
11311
  cacheRead: 0,
11153
- cacheWrite: 0.40625,
11312
+ cacheWrite: 0,
11154
11313
  },
11155
11314
  contextWindow: 1000000,
11156
11315
  maxTokens: 65536,
11157
11316
  },
11158
- "qwen/qwq-32b": {
11159
- id: "qwen/qwq-32b",
11160
- name: "Qwen: QwQ 32B",
11317
+ "qwen/qwen3.6-27b": {
11318
+ id: "qwen/qwen3.6-27b",
11319
+ name: "Qwen: Qwen3.6 27B",
11161
11320
  api: "openai-completions",
11162
11321
  provider: "openrouter",
11163
11322
  baseUrl: "https://openrouter.ai/api/v1",
11164
11323
  reasoning: true,
11165
- input: ["text"],
11324
+ input: ["text", "image"],
11166
11325
  cost: {
11167
- input: 0.15,
11168
- output: 0.58,
11169
- cacheRead: 0,
11326
+ input: 0.5,
11327
+ output: 2,
11328
+ cacheRead: 0.25,
11170
11329
  cacheWrite: 0,
11171
11330
  },
11172
- contextWindow: 131072,
11173
- maxTokens: 131072,
11331
+ contextWindow: 262144,
11332
+ maxTokens: 65536,
11174
11333
  },
11175
- "rekaai/reka-edge": {
11176
- id: "rekaai/reka-edge",
11177
- name: "Reka Edge",
11334
+ "qwen/qwen3.6-flash": {
11335
+ id: "qwen/qwen3.6-flash",
11336
+ name: "Qwen: Qwen3.6 Flash",
11178
11337
  api: "openai-completions",
11179
11338
  provider: "openrouter",
11180
11339
  baseUrl: "https://openrouter.ai/api/v1",
11181
- reasoning: false,
11340
+ reasoning: true,
11341
+ input: ["text", "image"],
11342
+ cost: {
11343
+ input: 0.25,
11344
+ output: 1.5,
11345
+ cacheRead: 0,
11346
+ cacheWrite: 0.3125,
11347
+ },
11348
+ contextWindow: 1000000,
11349
+ maxTokens: 65536,
11350
+ },
11351
+ "qwen/qwen3.6-max-preview": {
11352
+ id: "qwen/qwen3.6-max-preview",
11353
+ name: "Qwen: Qwen3.6 Max Preview",
11354
+ api: "openai-completions",
11355
+ provider: "openrouter",
11356
+ baseUrl: "https://openrouter.ai/api/v1",
11357
+ reasoning: true,
11358
+ input: ["text"],
11359
+ cost: {
11360
+ input: 1.3,
11361
+ output: 7.8,
11362
+ cacheRead: 0,
11363
+ cacheWrite: 1.625,
11364
+ },
11365
+ contextWindow: 262144,
11366
+ maxTokens: 65536,
11367
+ },
11368
+ "qwen/qwen3.6-plus": {
11369
+ id: "qwen/qwen3.6-plus",
11370
+ name: "Qwen: Qwen3.6 Plus",
11371
+ api: "openai-completions",
11372
+ provider: "openrouter",
11373
+ baseUrl: "https://openrouter.ai/api/v1",
11374
+ reasoning: true,
11375
+ input: ["text", "image"],
11376
+ cost: {
11377
+ input: 0.325,
11378
+ output: 1.95,
11379
+ cacheRead: 0,
11380
+ cacheWrite: 0.40625,
11381
+ },
11382
+ contextWindow: 1000000,
11383
+ maxTokens: 65536,
11384
+ },
11385
+ "qwen/qwq-32b": {
11386
+ id: "qwen/qwq-32b",
11387
+ name: "Qwen: QwQ 32B",
11388
+ api: "openai-completions",
11389
+ provider: "openrouter",
11390
+ baseUrl: "https://openrouter.ai/api/v1",
11391
+ reasoning: true,
11392
+ input: ["text"],
11393
+ cost: {
11394
+ input: 0.15,
11395
+ output: 0.58,
11396
+ cacheRead: 0,
11397
+ cacheWrite: 0,
11398
+ },
11399
+ contextWindow: 131072,
11400
+ maxTokens: 131072,
11401
+ },
11402
+ "rekaai/reka-edge": {
11403
+ id: "rekaai/reka-edge",
11404
+ name: "Reka Edge",
11405
+ api: "openai-completions",
11406
+ provider: "openrouter",
11407
+ baseUrl: "https://openrouter.ai/api/v1",
11408
+ reasoning: false,
11182
11409
  input: ["text", "image"],
11183
11410
  cost: {
11184
11411
  input: 0.09999999999999999,
@@ -11693,11 +11920,11 @@ export const MODELS = {
11693
11920
  cost: {
11694
11921
  input: 0.3,
11695
11922
  output: 0.8999999999999999,
11696
- cacheRead: 0,
11923
+ cacheRead: 0.049999999999999996,
11697
11924
  cacheWrite: 0,
11698
11925
  },
11699
11926
  contextWindow: 131072,
11700
- maxTokens: 131072,
11927
+ maxTokens: 24000,
11701
11928
  },
11702
11929
  "z-ai/glm-4.7": {
11703
11930
  id: "z-ai/glm-4.7",
@@ -11727,11 +11954,11 @@ export const MODELS = {
11727
11954
  cost: {
11728
11955
  input: 0.06,
11729
11956
  output: 0.39999999999999997,
11730
- cacheRead: 0.0100000002,
11957
+ cacheRead: 0.01,
11731
11958
  cacheWrite: 0,
11732
11959
  },
11733
11960
  contextWindow: 202752,
11734
- maxTokens: 4096,
11961
+ maxTokens: 16384,
11735
11962
  },
11736
11963
  "z-ai/glm-5": {
11737
11964
  id: "z-ai/glm-5",
@@ -11748,7 +11975,7 @@ export const MODELS = {
11748
11975
  cacheWrite: 0,
11749
11976
  },
11750
11977
  contextWindow: 202752,
11751
- maxTokens: 4096,
11978
+ maxTokens: 16384,
11752
11979
  },
11753
11980
  "z-ai/glm-5-turbo": {
11754
11981
  id: "z-ai/glm-5-turbo",
@@ -11801,6 +12028,23 @@ export const MODELS = {
11801
12028
  contextWindow: 202752,
11802
12029
  maxTokens: 131072,
11803
12030
  },
12031
+ "~anthropic/claude-haiku-latest": {
12032
+ id: "~anthropic/claude-haiku-latest",
12033
+ name: "Anthropic Claude Haiku Latest",
12034
+ api: "openai-completions",
12035
+ provider: "openrouter",
12036
+ baseUrl: "https://openrouter.ai/api/v1",
12037
+ reasoning: true,
12038
+ input: ["text", "image"],
12039
+ cost: {
12040
+ input: 1,
12041
+ output: 5,
12042
+ cacheRead: 0.09999999999999999,
12043
+ cacheWrite: 1.25,
12044
+ },
12045
+ contextWindow: 200000,
12046
+ maxTokens: 64000,
12047
+ },
11804
12048
  "~anthropic/claude-opus-latest": {
11805
12049
  id: "~anthropic/claude-opus-latest",
11806
12050
  name: "Anthropic: Claude Opus Latest",
@@ -11818,6 +12062,108 @@ export const MODELS = {
11818
12062
  contextWindow: 1000000,
11819
12063
  maxTokens: 128000,
11820
12064
  },
12065
+ "~anthropic/claude-sonnet-latest": {
12066
+ id: "~anthropic/claude-sonnet-latest",
12067
+ name: "Anthropic Claude Sonnet Latest",
12068
+ api: "openai-completions",
12069
+ provider: "openrouter",
12070
+ baseUrl: "https://openrouter.ai/api/v1",
12071
+ reasoning: true,
12072
+ input: ["text", "image"],
12073
+ cost: {
12074
+ input: 3,
12075
+ output: 15,
12076
+ cacheRead: 0.3,
12077
+ cacheWrite: 3.75,
12078
+ },
12079
+ contextWindow: 1000000,
12080
+ maxTokens: 128000,
12081
+ },
12082
+ "~google/gemini-flash-latest": {
12083
+ id: "~google/gemini-flash-latest",
12084
+ name: "Google Gemini Flash Latest",
12085
+ api: "openai-completions",
12086
+ provider: "openrouter",
12087
+ baseUrl: "https://openrouter.ai/api/v1",
12088
+ reasoning: true,
12089
+ input: ["text", "image"],
12090
+ cost: {
12091
+ input: 0.5,
12092
+ output: 3,
12093
+ cacheRead: 0.049999999999999996,
12094
+ cacheWrite: 0.08333333333333334,
12095
+ },
12096
+ contextWindow: 1048576,
12097
+ maxTokens: 65536,
12098
+ },
12099
+ "~google/gemini-pro-latest": {
12100
+ id: "~google/gemini-pro-latest",
12101
+ name: "Google Gemini Pro Latest",
12102
+ api: "openai-completions",
12103
+ provider: "openrouter",
12104
+ baseUrl: "https://openrouter.ai/api/v1",
12105
+ reasoning: true,
12106
+ input: ["text", "image"],
12107
+ cost: {
12108
+ input: 2,
12109
+ output: 12,
12110
+ cacheRead: 0.19999999999999998,
12111
+ cacheWrite: 0.375,
12112
+ },
12113
+ contextWindow: 1048576,
12114
+ maxTokens: 65536,
12115
+ },
12116
+ "~moonshotai/kimi-latest": {
12117
+ id: "~moonshotai/kimi-latest",
12118
+ name: "MoonshotAI Kimi Latest",
12119
+ api: "openai-completions",
12120
+ provider: "openrouter",
12121
+ baseUrl: "https://openrouter.ai/api/v1",
12122
+ reasoning: true,
12123
+ input: ["text", "image"],
12124
+ cost: {
12125
+ input: 0.7448,
12126
+ output: 4.655,
12127
+ cacheRead: 0.1463,
12128
+ cacheWrite: 0,
12129
+ },
12130
+ contextWindow: 256000,
12131
+ maxTokens: 65536,
12132
+ },
12133
+ "~openai/gpt-latest": {
12134
+ id: "~openai/gpt-latest",
12135
+ name: "OpenAI GPT Latest",
12136
+ api: "openai-completions",
12137
+ provider: "openrouter",
12138
+ baseUrl: "https://openrouter.ai/api/v1",
12139
+ reasoning: true,
12140
+ input: ["text", "image"],
12141
+ cost: {
12142
+ input: 5,
12143
+ output: 30,
12144
+ cacheRead: 0.5,
12145
+ cacheWrite: 0,
12146
+ },
12147
+ contextWindow: 1050000,
12148
+ maxTokens: 128000,
12149
+ },
12150
+ "~openai/gpt-mini-latest": {
12151
+ id: "~openai/gpt-mini-latest",
12152
+ name: "OpenAI GPT Mini Latest",
12153
+ api: "openai-completions",
12154
+ provider: "openrouter",
12155
+ baseUrl: "https://openrouter.ai/api/v1",
12156
+ reasoning: true,
12157
+ input: ["text", "image"],
12158
+ cost: {
12159
+ input: 0.75,
12160
+ output: 4.5,
12161
+ cacheRead: 0.075,
12162
+ cacheWrite: 0,
12163
+ },
12164
+ contextWindow: 400000,
12165
+ maxTokens: 128000,
12166
+ },
11821
12167
  },
11822
12168
  "vercel-ai-gateway": {
11823
12169
  "alibaba/qwen-3-14b": {
@@ -12494,7 +12840,7 @@ export const MODELS = {
12494
12840
  cost: {
12495
12841
  input: 0.14,
12496
12842
  output: 0.28,
12497
- cacheRead: 0.014,
12843
+ cacheRead: 0.028,
12498
12844
  cacheWrite: 0,
12499
12845
  },
12500
12846
  contextWindow: 1000000,
@@ -12509,9 +12855,9 @@ export const MODELS = {
12509
12855
  reasoning: true,
12510
12856
  input: ["text"],
12511
12857
  cost: {
12512
- input: 1.74,
12513
- output: 3.48,
12514
- cacheRead: 0.145,
12858
+ input: 0.435,
12859
+ output: 0.87,
12860
+ cacheRead: 0.0036,
12515
12861
  cacheWrite: 0,
12516
12862
  },
12517
12863
  contextWindow: 1000000,
@@ -13792,6 +14138,40 @@ export const MODELS = {
13792
14138
  contextWindow: 1050000,
13793
14139
  maxTokens: 128000,
13794
14140
  },
14141
+ "openai/gpt-5.5": {
14142
+ id: "openai/gpt-5.5",
14143
+ name: "GPT 5.5",
14144
+ api: "anthropic-messages",
14145
+ provider: "vercel-ai-gateway",
14146
+ baseUrl: "https://ai-gateway.vercel.sh",
14147
+ reasoning: true,
14148
+ input: ["text", "image"],
14149
+ cost: {
14150
+ input: 5,
14151
+ output: 30,
14152
+ cacheRead: 0.5,
14153
+ cacheWrite: 0,
14154
+ },
14155
+ contextWindow: 1000000,
14156
+ maxTokens: 128000,
14157
+ },
14158
+ "openai/gpt-5.5-pro": {
14159
+ id: "openai/gpt-5.5-pro",
14160
+ name: "GPT 5.5 Pro",
14161
+ api: "anthropic-messages",
14162
+ provider: "vercel-ai-gateway",
14163
+ baseUrl: "https://ai-gateway.vercel.sh",
14164
+ reasoning: true,
14165
+ input: ["text", "image"],
14166
+ cost: {
14167
+ input: 30,
14168
+ output: 180,
14169
+ cacheRead: 0,
14170
+ cacheWrite: 0,
14171
+ },
14172
+ contextWindow: 1000000,
14173
+ maxTokens: 128000,
14174
+ },
13795
14175
  "openai/gpt-oss-20b": {
13796
14176
  id: "openai/gpt-oss-20b",
13797
14177
  name: "GPT OSS 120B",
@@ -14918,24 +15298,6 @@ export const MODELS = {
14918
15298
  },
14919
15299
  },
14920
15300
  "zai": {
14921
- "glm-4.5": {
14922
- id: "glm-4.5",
14923
- name: "GLM-4.5",
14924
- api: "openai-completions",
14925
- provider: "zai",
14926
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14927
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14928
- reasoning: true,
14929
- input: ["text"],
14930
- cost: {
14931
- input: 0,
14932
- output: 0,
14933
- cacheRead: 0,
14934
- cacheWrite: 0,
14935
- },
14936
- contextWindow: 131072,
14937
- maxTokens: 98304,
14938
- },
14939
15301
  "glm-4.5-air": {
14940
15302
  id: "glm-4.5-air",
14941
15303
  name: "GLM-4.5-Air",
@@ -14954,78 +15316,6 @@ export const MODELS = {
14954
15316
  contextWindow: 131072,
14955
15317
  maxTokens: 98304,
14956
15318
  },
14957
- "glm-4.5-flash": {
14958
- id: "glm-4.5-flash",
14959
- name: "GLM-4.5-Flash",
14960
- api: "openai-completions",
14961
- provider: "zai",
14962
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14963
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14964
- reasoning: true,
14965
- input: ["text"],
14966
- cost: {
14967
- input: 0,
14968
- output: 0,
14969
- cacheRead: 0,
14970
- cacheWrite: 0,
14971
- },
14972
- contextWindow: 131072,
14973
- maxTokens: 98304,
14974
- },
14975
- "glm-4.5v": {
14976
- id: "glm-4.5v",
14977
- name: "GLM-4.5V",
14978
- api: "openai-completions",
14979
- provider: "zai",
14980
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14981
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14982
- reasoning: true,
14983
- input: ["text", "image"],
14984
- cost: {
14985
- input: 0,
14986
- output: 0,
14987
- cacheRead: 0,
14988
- cacheWrite: 0,
14989
- },
14990
- contextWindow: 64000,
14991
- maxTokens: 16384,
14992
- },
14993
- "glm-4.6": {
14994
- id: "glm-4.6",
14995
- name: "GLM-4.6",
14996
- api: "openai-completions",
14997
- provider: "zai",
14998
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14999
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15000
- reasoning: true,
15001
- input: ["text"],
15002
- cost: {
15003
- input: 0,
15004
- output: 0,
15005
- cacheRead: 0,
15006
- cacheWrite: 0,
15007
- },
15008
- contextWindow: 204800,
15009
- maxTokens: 131072,
15010
- },
15011
- "glm-4.6v": {
15012
- id: "glm-4.6v",
15013
- name: "GLM-4.6V",
15014
- api: "openai-completions",
15015
- provider: "zai",
15016
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
15017
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15018
- reasoning: true,
15019
- input: ["text", "image"],
15020
- cost: {
15021
- input: 0,
15022
- output: 0,
15023
- cacheRead: 0,
15024
- cacheWrite: 0,
15025
- },
15026
- contextWindow: 128000,
15027
- maxTokens: 32768,
15028
- },
15029
15319
  "glm-4.7": {
15030
15320
  id: "glm-4.7",
15031
15321
  name: "GLM-4.7",
@@ -15044,60 +15334,6 @@ export const MODELS = {
15044
15334
  contextWindow: 204800,
15045
15335
  maxTokens: 131072,
15046
15336
  },
15047
- "glm-4.7-flash": {
15048
- id: "glm-4.7-flash",
15049
- name: "GLM-4.7-Flash",
15050
- api: "openai-completions",
15051
- provider: "zai",
15052
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
15053
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15054
- reasoning: true,
15055
- input: ["text"],
15056
- cost: {
15057
- input: 0,
15058
- output: 0,
15059
- cacheRead: 0,
15060
- cacheWrite: 0,
15061
- },
15062
- contextWindow: 200000,
15063
- maxTokens: 131072,
15064
- },
15065
- "glm-4.7-flashx": {
15066
- id: "glm-4.7-flashx",
15067
- name: "GLM-4.7-FlashX",
15068
- api: "openai-completions",
15069
- provider: "zai",
15070
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
15071
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15072
- reasoning: true,
15073
- input: ["text"],
15074
- cost: {
15075
- input: 0.07,
15076
- output: 0.4,
15077
- cacheRead: 0.01,
15078
- cacheWrite: 0,
15079
- },
15080
- contextWindow: 200000,
15081
- maxTokens: 131072,
15082
- },
15083
- "glm-5": {
15084
- id: "glm-5",
15085
- name: "GLM-5",
15086
- api: "openai-completions",
15087
- provider: "zai",
15088
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
15089
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15090
- reasoning: true,
15091
- input: ["text"],
15092
- cost: {
15093
- input: 0,
15094
- output: 0,
15095
- cacheRead: 0,
15096
- cacheWrite: 0,
15097
- },
15098
- contextWindow: 204800,
15099
- maxTokens: 131072,
15100
- },
15101
15337
  "glm-5-turbo": {
15102
15338
  id: "glm-5-turbo",
15103
15339
  name: "GLM-5-Turbo",
@@ -15134,24 +15370,6 @@ export const MODELS = {
15134
15370
  contextWindow: 200000,
15135
15371
  maxTokens: 131072,
15136
15372
  },
15137
- "glm-5v-turbo": {
15138
- id: "glm-5v-turbo",
15139
- name: "glm-5v-turbo",
15140
- api: "openai-completions",
15141
- provider: "zai",
15142
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
15143
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15144
- reasoning: true,
15145
- input: ["text", "image"],
15146
- cost: {
15147
- input: 0,
15148
- output: 0,
15149
- cacheRead: 0,
15150
- cacheWrite: 0,
15151
- },
15152
- contextWindow: 200000,
15153
- maxTokens: 131072,
15154
- },
15155
15373
  },
15156
15374
  };
15157
15375
  //# sourceMappingURL=models.generated.js.map