@hyperspaceng/neural-ai 0.68.2 → 0.70.1

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 (48) hide show
  1. package/README.md +1 -1
  2. package/dist/env-api-keys.d.ts +9 -0
  3. package/dist/env-api-keys.d.ts.map +1 -1
  4. package/dist/env-api-keys.js +41 -31
  5. package/dist/env-api-keys.js.map +1 -1
  6. package/dist/index.d.ts +2 -2
  7. package/dist/index.d.ts.map +1 -1
  8. package/dist/index.js +1 -1
  9. package/dist/index.js.map +1 -1
  10. package/dist/models.d.ts +1 -1
  11. package/dist/models.d.ts.map +1 -1
  12. package/dist/models.generated.d.ts +409 -0
  13. package/dist/models.generated.d.ts.map +1 -1
  14. package/dist/models.generated.js +436 -39
  15. package/dist/models.generated.js.map +1 -1
  16. package/dist/models.js +5 -2
  17. package/dist/models.js.map +1 -1
  18. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  19. package/dist/providers/amazon-bedrock.js.map +1 -1
  20. package/dist/providers/anthropic.d.ts.map +1 -1
  21. package/dist/providers/anthropic.js +28 -11
  22. package/dist/providers/anthropic.js.map +1 -1
  23. package/dist/providers/google-vertex.d.ts.map +1 -1
  24. package/dist/providers/google-vertex.js +34 -13
  25. package/dist/providers/google-vertex.js.map +1 -1
  26. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  27. package/dist/providers/openai-codex-responses.js +8 -7
  28. package/dist/providers/openai-codex-responses.js.map +1 -1
  29. package/dist/providers/openai-completions.d.ts.map +1 -1
  30. package/dist/providers/openai-completions.js +53 -31
  31. package/dist/providers/openai-completions.js.map +1 -1
  32. package/dist/providers/openai-responses.d.ts.map +1 -1
  33. package/dist/providers/openai-responses.js +19 -19
  34. package/dist/providers/openai-responses.js.map +1 -1
  35. package/dist/providers/transform-messages.d.ts.map +1 -1
  36. package/dist/providers/transform-messages.js +2 -0
  37. package/dist/providers/transform-messages.js.map +1 -1
  38. package/dist/types.d.ts +21 -2
  39. package/dist/types.d.ts.map +1 -1
  40. package/dist/types.js.map +1 -1
  41. package/dist/utils/typebox-helpers.d.ts +1 -1
  42. package/dist/utils/typebox-helpers.d.ts.map +1 -1
  43. package/dist/utils/typebox-helpers.js +1 -1
  44. package/dist/utils/typebox-helpers.js.map +1 -1
  45. package/dist/utils/validation.d.ts.map +1 -1
  46. package/dist/utils/validation.js +242 -41
  47. package/dist/utils/validation.js.map +1 -1
  48. package/package.json +2 -4
@@ -325,6 +325,40 @@ export const MODELS = {
325
325
  contextWindow: 1000000,
326
326
  maxTokens: 64000,
327
327
  },
328
+ "au.anthropic.claude-opus-4-6-v1": {
329
+ id: "au.anthropic.claude-opus-4-6-v1",
330
+ name: "AU Anthropic Claude Opus 4.6",
331
+ api: "bedrock-converse-stream",
332
+ provider: "amazon-bedrock",
333
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
334
+ reasoning: true,
335
+ input: ["text", "image"],
336
+ cost: {
337
+ input: 16.5,
338
+ output: 82.5,
339
+ cacheRead: 0.5,
340
+ cacheWrite: 6.25,
341
+ },
342
+ contextWindow: 1000000,
343
+ maxTokens: 128000,
344
+ },
345
+ "au.anthropic.claude-sonnet-4-6": {
346
+ id: "au.anthropic.claude-sonnet-4-6",
347
+ name: "AU Anthropic Claude Sonnet 4.6",
348
+ api: "bedrock-converse-stream",
349
+ provider: "amazon-bedrock",
350
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
351
+ reasoning: true,
352
+ input: ["text", "image"],
353
+ cost: {
354
+ input: 3.3,
355
+ output: 16.5,
356
+ cacheRead: 0.33,
357
+ cacheWrite: 4.125,
358
+ },
359
+ contextWindow: 1000000,
360
+ maxTokens: 128000,
361
+ },
328
362
  "deepseek.r1-v1:0": {
329
363
  id: "deepseek.r1-v1:0",
330
364
  name: "DeepSeek-R1",
@@ -2488,6 +2522,23 @@ export const MODELS = {
2488
2522
  contextWindow: 1050000,
2489
2523
  maxTokens: 128000,
2490
2524
  },
2525
+ "gpt-5.5": {
2526
+ id: "gpt-5.5",
2527
+ name: "GPT-5.5",
2528
+ api: "azure-openai-responses",
2529
+ provider: "azure-openai-responses",
2530
+ baseUrl: "",
2531
+ reasoning: true,
2532
+ input: ["text", "image"],
2533
+ cost: {
2534
+ input: 5,
2535
+ output: 30,
2536
+ cacheRead: 0.5,
2537
+ cacheWrite: 0,
2538
+ },
2539
+ contextWindow: 1050000,
2540
+ maxTokens: 130000,
2541
+ },
2491
2542
  "o1": {
2492
2543
  id: "o1",
2493
2544
  name: "o1",
@@ -3011,6 +3062,7 @@ export const MODELS = {
3011
3062
  provider: "github-copilot",
3012
3063
  baseUrl: "https://api.individual.githubcopilot.com",
3013
3064
  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" },
3065
+ compat: { "supportsEagerToolInputStreaming": false },
3014
3066
  reasoning: true,
3015
3067
  input: ["text", "image"],
3016
3068
  cost: {
@@ -3083,6 +3135,7 @@ export const MODELS = {
3083
3135
  provider: "github-copilot",
3084
3136
  baseUrl: "https://api.individual.githubcopilot.com",
3085
3137
  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" },
3138
+ compat: { "supportsEagerToolInputStreaming": false },
3086
3139
  reasoning: true,
3087
3140
  input: ["text", "image"],
3088
3141
  cost: {
@@ -3101,6 +3154,7 @@ export const MODELS = {
3101
3154
  provider: "github-copilot",
3102
3155
  baseUrl: "https://api.individual.githubcopilot.com",
3103
3156
  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" },
3157
+ compat: { "supportsEagerToolInputStreaming": false },
3104
3158
  reasoning: true,
3105
3159
  input: ["text", "image"],
3106
3160
  cost: {
@@ -4164,6 +4218,23 @@ export const MODELS = {
4164
4218
  contextWindow: 1048576,
4165
4219
  maxTokens: 65535,
4166
4220
  },
4221
+ "gemini-3.1-flash-lite-preview": {
4222
+ id: "gemini-3.1-flash-lite-preview",
4223
+ name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
4224
+ api: "google-gemini-cli",
4225
+ provider: "google-gemini-cli",
4226
+ baseUrl: "https://cloudcode-pa.googleapis.com",
4227
+ reasoning: true,
4228
+ input: ["text", "image"],
4229
+ cost: {
4230
+ input: 0,
4231
+ output: 0,
4232
+ cacheRead: 0,
4233
+ cacheWrite: 0,
4234
+ },
4235
+ contextWindow: 1048576,
4236
+ maxTokens: 65535,
4237
+ },
4167
4238
  "gemini-3.1-pro-preview": {
4168
4239
  id: "gemini-3.1-pro-preview",
4169
4240
  name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
@@ -5100,6 +5171,7 @@ export const MODELS = {
5100
5171
  api: "anthropic-messages",
5101
5172
  provider: "kimi-coding",
5102
5173
  baseUrl: "https://api.kimi.com/coding",
5174
+ headers: { "User-Agent": "KimiCLI/1.5" },
5103
5175
  reasoning: true,
5104
5176
  input: ["text", "image"],
5105
5177
  cost: {
@@ -5117,6 +5189,7 @@ export const MODELS = {
5117
5189
  api: "anthropic-messages",
5118
5190
  provider: "kimi-coding",
5119
5191
  baseUrl: "https://api.kimi.com/coding",
5192
+ headers: { "User-Agent": "KimiCLI/1.5" },
5120
5193
  reasoning: true,
5121
5194
  input: ["text", "image"],
5122
5195
  cost: {
@@ -5134,6 +5207,7 @@ export const MODELS = {
5134
5207
  api: "anthropic-messages",
5135
5208
  provider: "kimi-coding",
5136
5209
  baseUrl: "https://api.kimi.com/coding",
5210
+ headers: { "User-Agent": "KimiCLI/1.5" },
5137
5211
  reasoning: true,
5138
5212
  input: ["text"],
5139
5213
  cost: {
@@ -6207,6 +6281,23 @@ export const MODELS = {
6207
6281
  contextWindow: 1050000,
6208
6282
  maxTokens: 128000,
6209
6283
  },
6284
+ "gpt-5.5": {
6285
+ id: "gpt-5.5",
6286
+ name: "GPT-5.5",
6287
+ api: "openai-responses",
6288
+ provider: "openai",
6289
+ baseUrl: "https://api.openai.com/v1",
6290
+ reasoning: true,
6291
+ input: ["text", "image"],
6292
+ cost: {
6293
+ input: 5,
6294
+ output: 30,
6295
+ cacheRead: 0.5,
6296
+ cacheWrite: 0,
6297
+ },
6298
+ contextWindow: 1050000,
6299
+ maxTokens: 130000,
6300
+ },
6210
6301
  "o1": {
6211
6302
  id: "o1",
6212
6303
  name: "o1",
@@ -6498,6 +6589,23 @@ export const MODELS = {
6498
6589
  contextWindow: 272000,
6499
6590
  maxTokens: 128000,
6500
6591
  },
6592
+ "gpt-5.5": {
6593
+ id: "gpt-5.5",
6594
+ name: "GPT-5.5",
6595
+ api: "openai-codex-responses",
6596
+ provider: "openai-codex",
6597
+ baseUrl: "https://chatgpt.com/backend-api",
6598
+ reasoning: true,
6599
+ input: ["text", "image"],
6600
+ cost: {
6601
+ input: 5,
6602
+ output: 30,
6603
+ cacheRead: 0.5,
6604
+ cacheWrite: 0,
6605
+ },
6606
+ contextWindow: 400000,
6607
+ maxTokens: 128000,
6608
+ },
6501
6609
  },
6502
6610
  "opencode": {
6503
6611
  "big-pickle": {
@@ -6976,6 +7084,57 @@ export const MODELS = {
6976
7084
  contextWindow: 1050000,
6977
7085
  maxTokens: 128000,
6978
7086
  },
7087
+ "gpt-5.5": {
7088
+ id: "gpt-5.5",
7089
+ name: "GPT-5.5",
7090
+ api: "openai-responses",
7091
+ provider: "opencode",
7092
+ baseUrl: "https://opencode.ai/zen/v1",
7093
+ reasoning: true,
7094
+ input: ["text", "image"],
7095
+ cost: {
7096
+ input: 5,
7097
+ output: 30,
7098
+ cacheRead: 0.5,
7099
+ cacheWrite: 0,
7100
+ },
7101
+ contextWindow: 1050000,
7102
+ maxTokens: 130000,
7103
+ },
7104
+ "gpt-5.5-pro": {
7105
+ id: "gpt-5.5-pro",
7106
+ name: "GPT-5.5 Pro",
7107
+ api: "openai-responses",
7108
+ provider: "opencode",
7109
+ baseUrl: "https://opencode.ai/zen/v1",
7110
+ reasoning: true,
7111
+ input: ["text", "image"],
7112
+ cost: {
7113
+ input: 30,
7114
+ output: 180,
7115
+ cacheRead: 30,
7116
+ cacheWrite: 0,
7117
+ },
7118
+ contextWindow: 1050000,
7119
+ maxTokens: 128000,
7120
+ },
7121
+ "hy3-preview-free": {
7122
+ id: "hy3-preview-free",
7123
+ name: "Hy3 preview Free",
7124
+ api: "openai-completions",
7125
+ provider: "opencode",
7126
+ baseUrl: "https://opencode.ai/zen/v1",
7127
+ reasoning: true,
7128
+ input: ["text"],
7129
+ cost: {
7130
+ input: 0,
7131
+ output: 0,
7132
+ cacheRead: 0,
7133
+ cacheWrite: 0,
7134
+ },
7135
+ contextWindow: 256000,
7136
+ maxTokens: 64000,
7137
+ },
6979
7138
  "kimi-k2.5": {
6980
7139
  id: "kimi-k2.5",
6981
7140
  name: "Kimi K2.5",
@@ -7131,6 +7290,40 @@ export const MODELS = {
7131
7290
  },
7132
7291
  },
7133
7292
  "opencode-go": {
7293
+ "deepseek-v4-flash": {
7294
+ id: "deepseek-v4-flash",
7295
+ name: "DeepSeek V4 Flash",
7296
+ api: "openai-completions",
7297
+ provider: "opencode-go",
7298
+ baseUrl: "https://opencode.ai/zen/go/v1",
7299
+ reasoning: true,
7300
+ input: ["text"],
7301
+ cost: {
7302
+ input: 0.14,
7303
+ output: 0.28,
7304
+ cacheRead: 0.028,
7305
+ cacheWrite: 0,
7306
+ },
7307
+ contextWindow: 1000000,
7308
+ maxTokens: 384000,
7309
+ },
7310
+ "deepseek-v4-pro": {
7311
+ id: "deepseek-v4-pro",
7312
+ name: "DeepSeek V4 Pro",
7313
+ api: "openai-completions",
7314
+ provider: "opencode-go",
7315
+ baseUrl: "https://opencode.ai/zen/go/v1",
7316
+ reasoning: true,
7317
+ input: ["text"],
7318
+ cost: {
7319
+ input: 1.74,
7320
+ output: 3.48,
7321
+ cacheRead: 0.145,
7322
+ cacheWrite: 0,
7323
+ },
7324
+ contextWindow: 1000000,
7325
+ maxTokens: 384000,
7326
+ },
7134
7327
  "glm-5": {
7135
7328
  id: "glm-5",
7136
7329
  name: "GLM-5",
@@ -7386,7 +7579,7 @@ export const MODELS = {
7386
7579
  cacheWrite: 0,
7387
7580
  },
7388
7581
  contextWindow: 65536,
7389
- maxTokens: 4096,
7582
+ maxTokens: 16384,
7390
7583
  },
7391
7584
  "amazon/nova-2-lite-v1": {
7392
7585
  id: "amazon/nova-2-lite-v1",
@@ -7947,7 +8140,7 @@ export const MODELS = {
7947
8140
  cacheWrite: 0,
7948
8141
  },
7949
8142
  contextWindow: 163840,
7950
- maxTokens: 163840,
8143
+ maxTokens: 16384,
7951
8144
  },
7952
8145
  "deepseek/deepseek-chat-v3-0324": {
7953
8146
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7964,7 +8157,7 @@ export const MODELS = {
7964
8157
  cacheWrite: 0,
7965
8158
  },
7966
8159
  contextWindow: 163840,
7967
- maxTokens: 4096,
8160
+ maxTokens: 16384,
7968
8161
  },
7969
8162
  "deepseek/deepseek-chat-v3.1": {
7970
8163
  id: "deepseek/deepseek-chat-v3.1",
@@ -8015,7 +8208,7 @@ export const MODELS = {
8015
8208
  cacheWrite: 0,
8016
8209
  },
8017
8210
  contextWindow: 163840,
8018
- maxTokens: 4096,
8211
+ maxTokens: 32768,
8019
8212
  },
8020
8213
  "deepseek/deepseek-v3.1-terminus": {
8021
8214
  id: "deepseek/deepseek-v3.1-terminus",
@@ -8028,11 +8221,11 @@ export const MODELS = {
8028
8221
  cost: {
8029
8222
  input: 0.21,
8030
8223
  output: 0.7899999999999999,
8031
- cacheRead: 0.1300000002,
8224
+ cacheRead: 0.13,
8032
8225
  cacheWrite: 0,
8033
8226
  },
8034
8227
  contextWindow: 163840,
8035
- maxTokens: 4096,
8228
+ maxTokens: 32768,
8036
8229
  },
8037
8230
  "deepseek/deepseek-v3.2": {
8038
8231
  id: "deepseek/deepseek-v3.2",
@@ -8068,6 +8261,40 @@ export const MODELS = {
8068
8261
  contextWindow: 163840,
8069
8262
  maxTokens: 65536,
8070
8263
  },
8264
+ "deepseek/deepseek-v4-flash": {
8265
+ id: "deepseek/deepseek-v4-flash",
8266
+ name: "DeepSeek: DeepSeek V4 Flash",
8267
+ api: "openai-completions",
8268
+ provider: "openrouter",
8269
+ baseUrl: "https://openrouter.ai/api/v1",
8270
+ reasoning: true,
8271
+ input: ["text"],
8272
+ cost: {
8273
+ input: 0.14,
8274
+ output: 0.28,
8275
+ cacheRead: 0.028,
8276
+ cacheWrite: 0,
8277
+ },
8278
+ contextWindow: 1048576,
8279
+ maxTokens: 384000,
8280
+ },
8281
+ "deepseek/deepseek-v4-pro": {
8282
+ id: "deepseek/deepseek-v4-pro",
8283
+ name: "DeepSeek: DeepSeek V4 Pro",
8284
+ api: "openai-completions",
8285
+ provider: "openrouter",
8286
+ baseUrl: "https://openrouter.ai/api/v1",
8287
+ reasoning: true,
8288
+ input: ["text"],
8289
+ cost: {
8290
+ input: 1.74,
8291
+ output: 3.48,
8292
+ cacheRead: 0.145,
8293
+ cacheWrite: 0,
8294
+ },
8295
+ contextWindow: 1048576,
8296
+ maxTokens: 384000,
8297
+ },
8071
8298
  "essentialai/rnj-1-instruct": {
8072
8299
  id: "essentialai/rnj-1-instruct",
8073
8300
  name: "EssentialAI: Rnj 1 Instruct",
@@ -8289,6 +8516,40 @@ export const MODELS = {
8289
8516
  contextWindow: 1048576,
8290
8517
  maxTokens: 65536,
8291
8518
  },
8519
+ "google/gemma-3-12b-it": {
8520
+ id: "google/gemma-3-12b-it",
8521
+ name: "Google: Gemma 3 12B",
8522
+ api: "openai-completions",
8523
+ provider: "openrouter",
8524
+ baseUrl: "https://openrouter.ai/api/v1",
8525
+ reasoning: false,
8526
+ input: ["text", "image"],
8527
+ cost: {
8528
+ input: 0.04,
8529
+ output: 0.13,
8530
+ cacheRead: 0,
8531
+ cacheWrite: 0,
8532
+ },
8533
+ contextWindow: 131072,
8534
+ maxTokens: 16384,
8535
+ },
8536
+ "google/gemma-3-27b-it": {
8537
+ id: "google/gemma-3-27b-it",
8538
+ name: "Google: Gemma 3 27B",
8539
+ api: "openai-completions",
8540
+ provider: "openrouter",
8541
+ baseUrl: "https://openrouter.ai/api/v1",
8542
+ reasoning: false,
8543
+ input: ["text", "image"],
8544
+ cost: {
8545
+ input: 0.08,
8546
+ output: 0.16,
8547
+ cacheRead: 0,
8548
+ cacheWrite: 0,
8549
+ },
8550
+ contextWindow: 131072,
8551
+ maxTokens: 16384,
8552
+ },
8292
8553
  "google/gemma-4-26b-a4b-it": {
8293
8554
  id: "google/gemma-4-26b-a4b-it",
8294
8555
  name: "Google: Gemma 4 26B A4B ",
@@ -8298,8 +8559,8 @@ export const MODELS = {
8298
8559
  reasoning: true,
8299
8560
  input: ["text", "image"],
8300
8561
  cost: {
8301
- input: 0.07,
8302
- output: 0.33999999999999997,
8562
+ input: 0.06,
8563
+ output: 0.33,
8303
8564
  cacheRead: 0,
8304
8565
  cacheWrite: 0,
8305
8566
  },
@@ -8338,7 +8599,7 @@ export const MODELS = {
8338
8599
  cacheWrite: 0,
8339
8600
  },
8340
8601
  contextWindow: 262144,
8341
- maxTokens: 4096,
8602
+ maxTokens: 16384,
8342
8603
  },
8343
8604
  "google/gemma-4-31b-it:free": {
8344
8605
  id: "google/gemma-4-31b-it:free",
@@ -8374,6 +8635,23 @@ export const MODELS = {
8374
8635
  contextWindow: 128000,
8375
8636
  maxTokens: 50000,
8376
8637
  },
8638
+ "inclusionai/ling-2.6-1t:free": {
8639
+ id: "inclusionai/ling-2.6-1t:free",
8640
+ name: "inclusionAI: Ling-2.6-1T (free)",
8641
+ api: "openai-completions",
8642
+ provider: "openrouter",
8643
+ baseUrl: "https://openrouter.ai/api/v1",
8644
+ reasoning: false,
8645
+ input: ["text"],
8646
+ cost: {
8647
+ input: 0,
8648
+ output: 0,
8649
+ cacheRead: 0,
8650
+ cacheWrite: 0,
8651
+ },
8652
+ contextWindow: 262144,
8653
+ maxTokens: 32768,
8654
+ },
8377
8655
  "inclusionai/ling-2.6-flash:free": {
8378
8656
  id: "inclusionai/ling-2.6-flash:free",
8379
8657
  name: "inclusionAI: Ling-2.6-flash (free)",
@@ -8440,7 +8718,7 @@ export const MODELS = {
8440
8718
  cacheWrite: 0,
8441
8719
  },
8442
8720
  contextWindow: 131072,
8443
- maxTokens: 4096,
8721
+ maxTokens: 16384,
8444
8722
  },
8445
8723
  "meta-llama/llama-3.1-8b-instruct": {
8446
8724
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8571,12 +8849,12 @@ export const MODELS = {
8571
8849
  input: ["text"],
8572
8850
  cost: {
8573
8851
  input: 0.15,
8574
- output: 1.2,
8575
- cacheRead: 0.075,
8852
+ output: 1.15,
8853
+ cacheRead: 0.03,
8576
8854
  cacheWrite: 0,
8577
8855
  },
8578
8856
  contextWindow: 196608,
8579
- maxTokens: 65536,
8857
+ maxTokens: 131072,
8580
8858
  },
8581
8859
  "minimax/minimax-m2.5:free": {
8582
8860
  id: "minimax/minimax-m2.5:free",
@@ -8842,13 +9120,13 @@ export const MODELS = {
8842
9120
  reasoning: false,
8843
9121
  input: ["text"],
8844
9122
  cost: {
8845
- input: 0.02,
8846
- output: 0.04,
9123
+ input: 0.01,
9124
+ output: 0.03,
8847
9125
  cacheRead: 0,
8848
9126
  cacheWrite: 0,
8849
9127
  },
8850
9128
  contextWindow: 131072,
8851
- maxTokens: 16384,
9129
+ maxTokens: 4096,
8852
9130
  },
8853
9131
  "mistralai/mistral-saba": {
8854
9132
  id: "mistralai/mistral-saba",
@@ -8899,7 +9177,7 @@ export const MODELS = {
8899
9177
  cacheWrite: 0,
8900
9178
  },
8901
9179
  contextWindow: 128000,
8902
- maxTokens: 4096,
9180
+ maxTokens: 16384,
8903
9181
  },
8904
9182
  "mistralai/mistral-small-creative": {
8905
9183
  id: "mistralai/mistral-small-creative",
@@ -9063,13 +9341,13 @@ export const MODELS = {
9063
9341
  reasoning: true,
9064
9342
  input: ["text", "image"],
9065
9343
  cost: {
9066
- input: 0.75,
9067
- output: 3.5,
9068
- cacheRead: 0.15,
9344
+ input: 0.7448,
9345
+ output: 4.655,
9346
+ cacheRead: 0.1463,
9069
9347
  cacheWrite: 0,
9070
9348
  },
9071
- contextWindow: 262144,
9072
- maxTokens: 4096,
9349
+ contextWindow: 256000,
9350
+ maxTokens: 65536,
9073
9351
  },
9074
9352
  "nex-agi/deepseek-v3.1-nex-n1": {
9075
9353
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9120,7 +9398,7 @@ export const MODELS = {
9120
9398
  cacheWrite: 0,
9121
9399
  },
9122
9400
  contextWindow: 131072,
9123
- maxTokens: 4096,
9401
+ maxTokens: 16384,
9124
9402
  },
9125
9403
  "nvidia/nemotron-3-nano-30b-a3b": {
9126
9404
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -9137,7 +9415,7 @@ export const MODELS = {
9137
9415
  cacheWrite: 0,
9138
9416
  },
9139
9417
  contextWindow: 262144,
9140
- maxTokens: 4096,
9418
+ maxTokens: 228000,
9141
9419
  },
9142
9420
  "nvidia/nemotron-3-nano-30b-a3b:free": {
9143
9421
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -9222,7 +9500,7 @@ export const MODELS = {
9222
9500
  cacheWrite: 0,
9223
9501
  },
9224
9502
  contextWindow: 131072,
9225
- maxTokens: 4096,
9503
+ maxTokens: 16384,
9226
9504
  },
9227
9505
  "nvidia/nemotron-nano-9b-v2:free": {
9228
9506
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9887,6 +10165,40 @@ export const MODELS = {
9887
10165
  contextWindow: 1050000,
9888
10166
  maxTokens: 128000,
9889
10167
  },
10168
+ "openai/gpt-5.5": {
10169
+ id: "openai/gpt-5.5",
10170
+ name: "OpenAI: GPT-5.5",
10171
+ api: "openai-completions",
10172
+ provider: "openrouter",
10173
+ baseUrl: "https://openrouter.ai/api/v1",
10174
+ reasoning: true,
10175
+ input: ["text", "image"],
10176
+ cost: {
10177
+ input: 5,
10178
+ output: 30,
10179
+ cacheRead: 0.5,
10180
+ cacheWrite: 0,
10181
+ },
10182
+ contextWindow: 1050000,
10183
+ maxTokens: 128000,
10184
+ },
10185
+ "openai/gpt-5.5-pro": {
10186
+ id: "openai/gpt-5.5-pro",
10187
+ name: "OpenAI: GPT-5.5 Pro",
10188
+ api: "openai-completions",
10189
+ provider: "openrouter",
10190
+ baseUrl: "https://openrouter.ai/api/v1",
10191
+ reasoning: true,
10192
+ input: ["text", "image"],
10193
+ cost: {
10194
+ input: 30,
10195
+ output: 180,
10196
+ cacheRead: 0,
10197
+ cacheWrite: 0,
10198
+ },
10199
+ contextWindow: 1050000,
10200
+ maxTokens: 128000,
10201
+ },
9890
10202
  "openai/gpt-audio": {
9891
10203
  id: "openai/gpt-audio",
9892
10204
  name: "OpenAI: GPT Audio",
@@ -9936,7 +10248,7 @@ export const MODELS = {
9936
10248
  cacheWrite: 0,
9937
10249
  },
9938
10250
  contextWindow: 131072,
9939
- maxTokens: 4096,
10251
+ maxTokens: 131072,
9940
10252
  },
9941
10253
  "openai/gpt-oss-120b:free": {
9942
10254
  id: "openai/gpt-oss-120b:free",
@@ -9970,7 +10282,7 @@ export const MODELS = {
9970
10282
  cacheWrite: 0,
9971
10283
  },
9972
10284
  contextWindow: 131072,
9973
- maxTokens: 4096,
10285
+ maxTokens: 131072,
9974
10286
  },
9975
10287
  "openai/gpt-oss-20b:free": {
9976
10288
  id: "openai/gpt-oss-20b:free",
@@ -10395,7 +10707,7 @@ export const MODELS = {
10395
10707
  cacheWrite: 0,
10396
10708
  },
10397
10709
  contextWindow: 262144,
10398
- maxTokens: 4096,
10710
+ maxTokens: 16384,
10399
10711
  },
10400
10712
  "qwen/qwen3-235b-a22b-thinking-2507": {
10401
10713
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10429,7 +10741,7 @@ export const MODELS = {
10429
10741
  cacheWrite: 0,
10430
10742
  },
10431
10743
  contextWindow: 40960,
10432
- maxTokens: 40960,
10744
+ maxTokens: 16384,
10433
10745
  },
10434
10746
  "qwen/qwen3-30b-a3b-instruct-2507": {
10435
10747
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10514,7 +10826,7 @@ export const MODELS = {
10514
10826
  cacheWrite: 0,
10515
10827
  },
10516
10828
  contextWindow: 262144,
10517
- maxTokens: 4096,
10829
+ maxTokens: 65536,
10518
10830
  },
10519
10831
  "qwen/qwen3-coder-30b-a3b-instruct": {
10520
10832
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10559,9 +10871,9 @@ export const MODELS = {
10559
10871
  reasoning: false,
10560
10872
  input: ["text"],
10561
10873
  cost: {
10562
- input: 0.15,
10874
+ input: 0.14,
10563
10875
  output: 0.7999999999999999,
10564
- cacheRead: 0.11,
10876
+ cacheRead: 0.09,
10565
10877
  cacheWrite: 0,
10566
10878
  },
10567
10879
  contextWindow: 262144,
@@ -10650,7 +10962,7 @@ export const MODELS = {
10650
10962
  cacheWrite: 0,
10651
10963
  },
10652
10964
  contextWindow: 262144,
10653
- maxTokens: 4096,
10965
+ maxTokens: 16384,
10654
10966
  },
10655
10967
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10656
10968
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10701,7 +11013,7 @@ export const MODELS = {
10701
11013
  cacheWrite: 0,
10702
11014
  },
10703
11015
  contextWindow: 262144,
10704
- maxTokens: 4096,
11016
+ maxTokens: 16384,
10705
11017
  },
10706
11018
  "qwen/qwen3-vl-235b-a22b-thinking": {
10707
11019
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -11043,6 +11355,23 @@ export const MODELS = {
11043
11355
  contextWindow: 262144,
11044
11356
  maxTokens: 65536,
11045
11357
  },
11358
+ "tencent/hy3-preview:free": {
11359
+ id: "tencent/hy3-preview:free",
11360
+ name: "Tencent: Hy3 preview (free)",
11361
+ api: "openai-completions",
11362
+ provider: "openrouter",
11363
+ baseUrl: "https://openrouter.ai/api/v1",
11364
+ reasoning: true,
11365
+ input: ["text"],
11366
+ cost: {
11367
+ input: 0,
11368
+ output: 0,
11369
+ cacheRead: 0,
11370
+ cacheWrite: 0,
11371
+ },
11372
+ contextWindow: 262144,
11373
+ maxTokens: 262144,
11374
+ },
11046
11375
  "thedrummer/rocinante-12b": {
11047
11376
  id: "thedrummer/rocinante-12b",
11048
11377
  name: "TheDrummer: Rocinante 12B",
@@ -11462,11 +11791,11 @@ export const MODELS = {
11462
11791
  cost: {
11463
11792
  input: 0.3,
11464
11793
  output: 0.8999999999999999,
11465
- cacheRead: 0,
11794
+ cacheRead: 0.049999999999999996,
11466
11795
  cacheWrite: 0,
11467
11796
  },
11468
11797
  contextWindow: 131072,
11469
- maxTokens: 131072,
11798
+ maxTokens: 24000,
11470
11799
  },
11471
11800
  "z-ai/glm-4.7": {
11472
11801
  id: "z-ai/glm-4.7",
@@ -11496,11 +11825,11 @@ export const MODELS = {
11496
11825
  cost: {
11497
11826
  input: 0.06,
11498
11827
  output: 0.39999999999999997,
11499
- cacheRead: 0.0100000002,
11828
+ cacheRead: 0.01,
11500
11829
  cacheWrite: 0,
11501
11830
  },
11502
11831
  contextWindow: 202752,
11503
- maxTokens: 4096,
11832
+ maxTokens: 16384,
11504
11833
  },
11505
11834
  "z-ai/glm-5": {
11506
11835
  id: "z-ai/glm-5",
@@ -11517,7 +11846,7 @@ export const MODELS = {
11517
11846
  cacheWrite: 0,
11518
11847
  },
11519
11848
  contextWindow: 202752,
11520
- maxTokens: 4096,
11849
+ maxTokens: 16384,
11521
11850
  },
11522
11851
  "z-ai/glm-5-turbo": {
11523
11852
  id: "z-ai/glm-5-turbo",
@@ -12252,6 +12581,40 @@ export const MODELS = {
12252
12581
  contextWindow: 128000,
12253
12582
  maxTokens: 64000,
12254
12583
  },
12584
+ "deepseek/deepseek-v4-flash": {
12585
+ id: "deepseek/deepseek-v4-flash",
12586
+ name: "DeepSeek V4 Flash",
12587
+ api: "anthropic-messages",
12588
+ provider: "vercel-ai-gateway",
12589
+ baseUrl: "https://ai-gateway.vercel.sh",
12590
+ reasoning: true,
12591
+ input: ["text"],
12592
+ cost: {
12593
+ input: 0.14,
12594
+ output: 0.28,
12595
+ cacheRead: 0.028,
12596
+ cacheWrite: 0,
12597
+ },
12598
+ contextWindow: 1000000,
12599
+ maxTokens: 384000,
12600
+ },
12601
+ "deepseek/deepseek-v4-pro": {
12602
+ id: "deepseek/deepseek-v4-pro",
12603
+ name: "DeepSeek V4 Pro",
12604
+ api: "anthropic-messages",
12605
+ provider: "vercel-ai-gateway",
12606
+ baseUrl: "https://ai-gateway.vercel.sh",
12607
+ reasoning: true,
12608
+ input: ["text"],
12609
+ cost: {
12610
+ input: 1.74,
12611
+ output: 3.48,
12612
+ cacheRead: 0.145,
12613
+ cacheWrite: 0,
12614
+ },
12615
+ contextWindow: 1000000,
12616
+ maxTokens: 384000,
12617
+ },
12255
12618
  "google/gemini-2.0-flash": {
12256
12619
  id: "google/gemini-2.0-flash",
12257
12620
  name: "Gemini 2.0 Flash",
@@ -13527,6 +13890,40 @@ export const MODELS = {
13527
13890
  contextWindow: 1050000,
13528
13891
  maxTokens: 128000,
13529
13892
  },
13893
+ "openai/gpt-5.5": {
13894
+ id: "openai/gpt-5.5",
13895
+ name: "GPT 5.5",
13896
+ api: "anthropic-messages",
13897
+ provider: "vercel-ai-gateway",
13898
+ baseUrl: "https://ai-gateway.vercel.sh",
13899
+ reasoning: true,
13900
+ input: ["text", "image"],
13901
+ cost: {
13902
+ input: 5,
13903
+ output: 30,
13904
+ cacheRead: 0.5,
13905
+ cacheWrite: 0,
13906
+ },
13907
+ contextWindow: 1000000,
13908
+ maxTokens: 128000,
13909
+ },
13910
+ "openai/gpt-5.5-pro": {
13911
+ id: "openai/gpt-5.5-pro",
13912
+ name: "GPT 5.5 Pro",
13913
+ api: "anthropic-messages",
13914
+ provider: "vercel-ai-gateway",
13915
+ baseUrl: "https://ai-gateway.vercel.sh",
13916
+ reasoning: true,
13917
+ input: ["text", "image"],
13918
+ cost: {
13919
+ input: 30,
13920
+ output: 180,
13921
+ cacheRead: 0,
13922
+ cacheWrite: 0,
13923
+ },
13924
+ contextWindow: 1000000,
13925
+ maxTokens: 128000,
13926
+ },
13530
13927
  "openai/gpt-oss-20b": {
13531
13928
  id: "openai/gpt-oss-20b",
13532
13929
  name: "GPT OSS 120B",