@mariozechner/pi-ai 0.68.1 → 0.70.0

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 (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 +212 -19
  13. package/dist/models.generated.d.ts.map +1 -1
  14. package/dist/models.generated.js +238 -49
  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
@@ -2488,6 +2488,23 @@ export const MODELS = {
2488
2488
  contextWindow: 1050000,
2489
2489
  maxTokens: 128000,
2490
2490
  },
2491
+ "gpt-5.5": {
2492
+ id: "gpt-5.5",
2493
+ name: "GPT-5.5",
2494
+ api: "azure-openai-responses",
2495
+ provider: "azure-openai-responses",
2496
+ baseUrl: "",
2497
+ reasoning: true,
2498
+ input: ["text", "image"],
2499
+ cost: {
2500
+ input: 5,
2501
+ output: 30,
2502
+ cacheRead: 0.5,
2503
+ cacheWrite: 0,
2504
+ },
2505
+ contextWindow: 1050000,
2506
+ maxTokens: 130000,
2507
+ },
2491
2508
  "o1": {
2492
2509
  id: "o1",
2493
2510
  name: "o1",
@@ -3011,6 +3028,7 @@ export const MODELS = {
3011
3028
  provider: "github-copilot",
3012
3029
  baseUrl: "https://api.individual.githubcopilot.com",
3013
3030
  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" },
3031
+ compat: { "supportsEagerToolInputStreaming": false },
3014
3032
  reasoning: true,
3015
3033
  input: ["text", "image"],
3016
3034
  cost: {
@@ -3083,6 +3101,7 @@ export const MODELS = {
3083
3101
  provider: "github-copilot",
3084
3102
  baseUrl: "https://api.individual.githubcopilot.com",
3085
3103
  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" },
3104
+ compat: { "supportsEagerToolInputStreaming": false },
3086
3105
  reasoning: true,
3087
3106
  input: ["text", "image"],
3088
3107
  cost: {
@@ -3101,6 +3120,7 @@ export const MODELS = {
3101
3120
  provider: "github-copilot",
3102
3121
  baseUrl: "https://api.individual.githubcopilot.com",
3103
3122
  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" },
3123
+ compat: { "supportsEagerToolInputStreaming": false },
3104
3124
  reasoning: true,
3105
3125
  input: ["text", "image"],
3106
3126
  cost: {
@@ -3888,8 +3908,8 @@ export const MODELS = {
3888
3908
  contextWindow: 131072,
3889
3909
  maxTokens: 8192,
3890
3910
  },
3891
- "gemma-4-26b-it": {
3892
- id: "gemma-4-26b-it",
3911
+ "gemma-4-26b-a4b-it": {
3912
+ id: "gemma-4-26b-a4b-it",
3893
3913
  name: "Gemma 4 26B",
3894
3914
  api: "google-generative-ai",
3895
3915
  provider: "google",
@@ -4164,6 +4184,23 @@ export const MODELS = {
4164
4184
  contextWindow: 1048576,
4165
4185
  maxTokens: 65535,
4166
4186
  },
4187
+ "gemini-3.1-flash-lite-preview": {
4188
+ id: "gemini-3.1-flash-lite-preview",
4189
+ name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
4190
+ api: "google-gemini-cli",
4191
+ provider: "google-gemini-cli",
4192
+ baseUrl: "https://cloudcode-pa.googleapis.com",
4193
+ reasoning: true,
4194
+ input: ["text", "image"],
4195
+ cost: {
4196
+ input: 0,
4197
+ output: 0,
4198
+ cacheRead: 0,
4199
+ cacheWrite: 0,
4200
+ },
4201
+ contextWindow: 1048576,
4202
+ maxTokens: 65535,
4203
+ },
4167
4204
  "gemini-3.1-pro-preview": {
4168
4205
  id: "gemini-3.1-pro-preview",
4169
4206
  name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
@@ -5100,6 +5137,7 @@ export const MODELS = {
5100
5137
  api: "anthropic-messages",
5101
5138
  provider: "kimi-coding",
5102
5139
  baseUrl: "https://api.kimi.com/coding",
5140
+ headers: { "User-Agent": "KimiCLI/1.5" },
5103
5141
  reasoning: true,
5104
5142
  input: ["text", "image"],
5105
5143
  cost: {
@@ -5117,6 +5155,7 @@ export const MODELS = {
5117
5155
  api: "anthropic-messages",
5118
5156
  provider: "kimi-coding",
5119
5157
  baseUrl: "https://api.kimi.com/coding",
5158
+ headers: { "User-Agent": "KimiCLI/1.5" },
5120
5159
  reasoning: true,
5121
5160
  input: ["text", "image"],
5122
5161
  cost: {
@@ -5134,6 +5173,7 @@ export const MODELS = {
5134
5173
  api: "anthropic-messages",
5135
5174
  provider: "kimi-coding",
5136
5175
  baseUrl: "https://api.kimi.com/coding",
5176
+ headers: { "User-Agent": "KimiCLI/1.5" },
5137
5177
  reasoning: true,
5138
5178
  input: ["text"],
5139
5179
  cost: {
@@ -6207,6 +6247,23 @@ export const MODELS = {
6207
6247
  contextWindow: 1050000,
6208
6248
  maxTokens: 128000,
6209
6249
  },
6250
+ "gpt-5.5": {
6251
+ id: "gpt-5.5",
6252
+ name: "GPT-5.5",
6253
+ api: "openai-responses",
6254
+ provider: "openai",
6255
+ baseUrl: "https://api.openai.com/v1",
6256
+ reasoning: true,
6257
+ input: ["text", "image"],
6258
+ cost: {
6259
+ input: 5,
6260
+ output: 30,
6261
+ cacheRead: 0.5,
6262
+ cacheWrite: 0,
6263
+ },
6264
+ contextWindow: 1050000,
6265
+ maxTokens: 130000,
6266
+ },
6210
6267
  "o1": {
6211
6268
  id: "o1",
6212
6269
  name: "o1",
@@ -6498,6 +6555,23 @@ export const MODELS = {
6498
6555
  contextWindow: 272000,
6499
6556
  maxTokens: 128000,
6500
6557
  },
6558
+ "gpt-5.5": {
6559
+ id: "gpt-5.5",
6560
+ name: "GPT-5.5",
6561
+ api: "openai-codex-responses",
6562
+ provider: "openai-codex",
6563
+ baseUrl: "https://chatgpt.com/backend-api",
6564
+ reasoning: true,
6565
+ input: ["text", "image"],
6566
+ cost: {
6567
+ input: 5,
6568
+ output: 30,
6569
+ cacheRead: 0.5,
6570
+ cacheWrite: 0,
6571
+ },
6572
+ contextWindow: 400000,
6573
+ maxTokens: 128000,
6574
+ },
6501
6575
  },
6502
6576
  "opencode": {
6503
6577
  "big-pickle": {
@@ -6976,6 +7050,23 @@ export const MODELS = {
6976
7050
  contextWindow: 1050000,
6977
7051
  maxTokens: 128000,
6978
7052
  },
7053
+ "hy3-preview-free": {
7054
+ id: "hy3-preview-free",
7055
+ name: "Hy3 preview Free",
7056
+ api: "openai-completions",
7057
+ provider: "opencode",
7058
+ baseUrl: "https://opencode.ai/zen/v1",
7059
+ reasoning: true,
7060
+ input: ["text"],
7061
+ cost: {
7062
+ input: 0,
7063
+ output: 0,
7064
+ cacheRead: 0,
7065
+ cacheWrite: 0,
7066
+ },
7067
+ contextWindow: 256000,
7068
+ maxTokens: 64000,
7069
+ },
6979
7070
  "kimi-k2.5": {
6980
7071
  id: "kimi-k2.5",
6981
7072
  name: "Kimi K2.5",
@@ -7098,10 +7189,9 @@ export const MODELS = {
7098
7189
  "qwen3.5-plus": {
7099
7190
  id: "qwen3.5-plus",
7100
7191
  name: "Qwen3.5 Plus",
7101
- api: "openai-completions",
7192
+ api: "anthropic-messages",
7102
7193
  provider: "opencode",
7103
- baseUrl: "https://opencode.ai/zen/v1",
7104
- compat: { "cacheControlFormat": "anthropic" },
7194
+ baseUrl: "https://opencode.ai/zen",
7105
7195
  reasoning: true,
7106
7196
  input: ["text", "image"],
7107
7197
  cost: {
@@ -7116,10 +7206,9 @@ export const MODELS = {
7116
7206
  "qwen3.6-plus": {
7117
7207
  id: "qwen3.6-plus",
7118
7208
  name: "Qwen3.6 Plus",
7119
- api: "openai-completions",
7209
+ api: "anthropic-messages",
7120
7210
  provider: "opencode",
7121
- baseUrl: "https://opencode.ai/zen/v1",
7122
- compat: { "cacheControlFormat": "anthropic" },
7211
+ baseUrl: "https://opencode.ai/zen",
7123
7212
  reasoning: true,
7124
7213
  input: ["text", "image"],
7125
7214
  cost: {
@@ -7216,7 +7305,7 @@ export const MODELS = {
7216
7305
  cacheWrite: 0,
7217
7306
  },
7218
7307
  contextWindow: 262144,
7219
- maxTokens: 64000,
7308
+ maxTokens: 128000,
7220
7309
  },
7221
7310
  "mimo-v2-pro": {
7222
7311
  id: "mimo-v2-pro",
@@ -7233,7 +7322,41 @@ export const MODELS = {
7233
7322
  cacheWrite: 0,
7234
7323
  },
7235
7324
  contextWindow: 1048576,
7236
- maxTokens: 64000,
7325
+ maxTokens: 128000,
7326
+ },
7327
+ "mimo-v2.5": {
7328
+ id: "mimo-v2.5",
7329
+ name: "MiMo V2.5",
7330
+ api: "openai-completions",
7331
+ provider: "opencode-go",
7332
+ baseUrl: "https://opencode.ai/zen/go/v1",
7333
+ reasoning: true,
7334
+ input: ["text", "image"],
7335
+ cost: {
7336
+ input: 0.4,
7337
+ output: 2,
7338
+ cacheRead: 0.08,
7339
+ cacheWrite: 0,
7340
+ },
7341
+ contextWindow: 262144,
7342
+ maxTokens: 128000,
7343
+ },
7344
+ "mimo-v2.5-pro": {
7345
+ id: "mimo-v2.5-pro",
7346
+ name: "MiMo V2.5 Pro",
7347
+ api: "openai-completions",
7348
+ provider: "opencode-go",
7349
+ baseUrl: "https://opencode.ai/zen/go/v1",
7350
+ reasoning: true,
7351
+ input: ["text"],
7352
+ cost: {
7353
+ input: 1,
7354
+ output: 3,
7355
+ cacheRead: 0.2,
7356
+ cacheWrite: 0,
7357
+ },
7358
+ contextWindow: 1048576,
7359
+ maxTokens: 128000,
7237
7360
  },
7238
7361
  "minimax-m2.5": {
7239
7362
  id: "minimax-m2.5",
@@ -7272,10 +7395,9 @@ export const MODELS = {
7272
7395
  "qwen3.5-plus": {
7273
7396
  id: "qwen3.5-plus",
7274
7397
  name: "Qwen3.5 Plus",
7275
- api: "openai-completions",
7398
+ api: "anthropic-messages",
7276
7399
  provider: "opencode-go",
7277
- baseUrl: "https://opencode.ai/zen/go/v1",
7278
- compat: { "cacheControlFormat": "anthropic" },
7400
+ baseUrl: "https://opencode.ai/zen/go",
7279
7401
  reasoning: true,
7280
7402
  input: ["text", "image"],
7281
7403
  cost: {
@@ -7290,10 +7412,9 @@ export const MODELS = {
7290
7412
  "qwen3.6-plus": {
7291
7413
  id: "qwen3.6-plus",
7292
7414
  name: "Qwen3.6 Plus",
7293
- api: "openai-completions",
7415
+ api: "anthropic-messages",
7294
7416
  provider: "opencode-go",
7295
- baseUrl: "https://opencode.ai/zen/go/v1",
7296
- compat: { "cacheControlFormat": "anthropic" },
7417
+ baseUrl: "https://opencode.ai/zen/go",
7297
7418
  reasoning: true,
7298
7419
  input: ["text", "image"],
7299
7420
  cost: {
@@ -7681,17 +7802,17 @@ export const MODELS = {
7681
7802
  contextWindow: 1000000,
7682
7803
  maxTokens: 128000,
7683
7804
  },
7684
- "arcee-ai/trinity-large-preview:free": {
7685
- id: "arcee-ai/trinity-large-preview:free",
7686
- name: "Arcee AI: Trinity Large Preview (free)",
7805
+ "arcee-ai/trinity-large-preview": {
7806
+ id: "arcee-ai/trinity-large-preview",
7807
+ name: "Arcee AI: Trinity Large Preview",
7687
7808
  api: "openai-completions",
7688
7809
  provider: "openrouter",
7689
7810
  baseUrl: "https://openrouter.ai/api/v1",
7690
7811
  reasoning: false,
7691
7812
  input: ["text"],
7692
7813
  cost: {
7693
- input: 0,
7694
- output: 0,
7814
+ input: 0.15,
7815
+ output: 0.44999999999999996,
7695
7816
  cacheRead: 0,
7696
7817
  cacheWrite: 0,
7697
7818
  },
@@ -8019,7 +8140,7 @@ export const MODELS = {
8019
8140
  cacheWrite: 0,
8020
8141
  },
8021
8142
  contextWindow: 131072,
8022
- maxTokens: 32768,
8143
+ maxTokens: 65536,
8023
8144
  },
8024
8145
  "deepseek/deepseek-v3.2-exp": {
8025
8146
  id: "deepseek/deepseek-v3.2-exp",
@@ -8268,13 +8389,13 @@ export const MODELS = {
8268
8389
  reasoning: true,
8269
8390
  input: ["text", "image"],
8270
8391
  cost: {
8271
- input: 0.07,
8272
- output: 0.35,
8273
- cacheRead: 0.04,
8392
+ input: 0.06,
8393
+ output: 0.33,
8394
+ cacheRead: 0,
8274
8395
  cacheWrite: 0,
8275
8396
  },
8276
8397
  contextWindow: 262144,
8277
- maxTokens: 262144,
8398
+ maxTokens: 4096,
8278
8399
  },
8279
8400
  "google/gemma-4-26b-a4b-it:free": {
8280
8401
  id: "google/gemma-4-26b-a4b-it:free",
@@ -8304,7 +8425,7 @@ export const MODELS = {
8304
8425
  cost: {
8305
8426
  input: 0.13,
8306
8427
  output: 0.38,
8307
- cacheRead: 0.019999999499999997,
8428
+ cacheRead: 0,
8308
8429
  cacheWrite: 0,
8309
8430
  },
8310
8431
  contextWindow: 262144,
@@ -8344,6 +8465,23 @@ export const MODELS = {
8344
8465
  contextWindow: 128000,
8345
8466
  maxTokens: 50000,
8346
8467
  },
8468
+ "inclusionai/ling-2.6-1t:free": {
8469
+ id: "inclusionai/ling-2.6-1t:free",
8470
+ name: "inclusionAI: Ling-2.6-1T (free)",
8471
+ api: "openai-completions",
8472
+ provider: "openrouter",
8473
+ baseUrl: "https://openrouter.ai/api/v1",
8474
+ reasoning: false,
8475
+ input: ["text"],
8476
+ cost: {
8477
+ input: 0,
8478
+ output: 0,
8479
+ cacheRead: 0,
8480
+ cacheWrite: 0,
8481
+ },
8482
+ contextWindow: 262144,
8483
+ maxTokens: 32768,
8484
+ },
8347
8485
  "inclusionai/ling-2.6-flash:free": {
8348
8486
  id: "inclusionai/ling-2.6-flash:free",
8349
8487
  name: "inclusionAI: Ling-2.6-flash (free)",
@@ -8541,12 +8679,12 @@ export const MODELS = {
8541
8679
  input: ["text"],
8542
8680
  cost: {
8543
8681
  input: 0.15,
8544
- output: 1.2,
8545
- cacheRead: 0.075,
8682
+ output: 1.15,
8683
+ cacheRead: 0.03,
8546
8684
  cacheWrite: 0,
8547
8685
  },
8548
8686
  contextWindow: 196608,
8549
- maxTokens: 65536,
8687
+ maxTokens: 4096,
8550
8688
  },
8551
8689
  "minimax/minimax-m2.5:free": {
8552
8690
  id: "minimax/minimax-m2.5:free",
@@ -8812,13 +8950,13 @@ export const MODELS = {
8812
8950
  reasoning: false,
8813
8951
  input: ["text"],
8814
8952
  cost: {
8815
- input: 0.02,
8816
- output: 0.04,
8953
+ input: 0.01,
8954
+ output: 0.03,
8817
8955
  cacheRead: 0,
8818
8956
  cacheWrite: 0,
8819
8957
  },
8820
8958
  contextWindow: 131072,
8821
- maxTokens: 16384,
8959
+ maxTokens: 4096,
8822
8960
  },
8823
8961
  "mistralai/mistral-saba": {
8824
8962
  id: "mistralai/mistral-saba",
@@ -9033,13 +9171,13 @@ export const MODELS = {
9033
9171
  reasoning: true,
9034
9172
  input: ["text", "image"],
9035
9173
  cost: {
9036
- input: 0.7999999999999999,
9037
- output: 3.5,
9038
- cacheRead: 0.19999999999999998,
9174
+ input: 0.7448,
9175
+ output: 4.655,
9176
+ cacheRead: 0.1463,
9039
9177
  cacheWrite: 0,
9040
9178
  },
9041
- contextWindow: 262144,
9042
- maxTokens: 262144,
9179
+ contextWindow: 256000,
9180
+ maxTokens: 65536,
9043
9181
  },
9044
9182
  "nex-agi/deepseek-v3.1-nex-n1": {
9045
9183
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10376,13 +10514,13 @@ export const MODELS = {
10376
10514
  reasoning: true,
10377
10515
  input: ["text"],
10378
10516
  cost: {
10379
- input: 0.13,
10380
- output: 0.6,
10517
+ input: 0.14950000000000002,
10518
+ output: 1.495,
10381
10519
  cacheRead: 0,
10382
10520
  cacheWrite: 0,
10383
10521
  },
10384
- contextWindow: 262144,
10385
- maxTokens: 262144,
10522
+ contextWindow: 131072,
10523
+ maxTokens: 4096,
10386
10524
  },
10387
10525
  "qwen/qwen3-30b-a3b": {
10388
10526
  id: "qwen/qwen3-30b-a3b",
@@ -11013,6 +11151,23 @@ export const MODELS = {
11013
11151
  contextWindow: 262144,
11014
11152
  maxTokens: 65536,
11015
11153
  },
11154
+ "tencent/hy3-preview:free": {
11155
+ id: "tencent/hy3-preview:free",
11156
+ name: "Tencent: Hy3 preview (free)",
11157
+ api: "openai-completions",
11158
+ provider: "openrouter",
11159
+ baseUrl: "https://openrouter.ai/api/v1",
11160
+ reasoning: true,
11161
+ input: ["text"],
11162
+ cost: {
11163
+ input: 0,
11164
+ output: 0,
11165
+ cacheRead: 0,
11166
+ cacheWrite: 0,
11167
+ },
11168
+ contextWindow: 262144,
11169
+ maxTokens: 262144,
11170
+ },
11016
11171
  "thedrummer/rocinante-12b": {
11017
11172
  id: "thedrummer/rocinante-12b",
11018
11173
  name: "TheDrummer: Rocinante 12B",
@@ -11285,6 +11440,40 @@ export const MODELS = {
11285
11440
  contextWindow: 1048576,
11286
11441
  maxTokens: 131072,
11287
11442
  },
11443
+ "xiaomi/mimo-v2.5": {
11444
+ id: "xiaomi/mimo-v2.5",
11445
+ name: "Xiaomi: MiMo-V2.5",
11446
+ api: "openai-completions",
11447
+ provider: "openrouter",
11448
+ baseUrl: "https://openrouter.ai/api/v1",
11449
+ reasoning: true,
11450
+ input: ["text", "image"],
11451
+ cost: {
11452
+ input: 0.39999999999999997,
11453
+ output: 2,
11454
+ cacheRead: 0.08,
11455
+ cacheWrite: 0,
11456
+ },
11457
+ contextWindow: 1048576,
11458
+ maxTokens: 131072,
11459
+ },
11460
+ "xiaomi/mimo-v2.5-pro": {
11461
+ id: "xiaomi/mimo-v2.5-pro",
11462
+ name: "Xiaomi: MiMo-V2.5-Pro",
11463
+ api: "openai-completions",
11464
+ provider: "openrouter",
11465
+ baseUrl: "https://openrouter.ai/api/v1",
11466
+ reasoning: true,
11467
+ input: ["text"],
11468
+ cost: {
11469
+ input: 1,
11470
+ output: 3,
11471
+ cacheRead: 0.19999999999999998,
11472
+ cacheWrite: 0,
11473
+ },
11474
+ contextWindow: 1048576,
11475
+ maxTokens: 131072,
11476
+ },
11288
11477
  "z-ai/glm-4-32b": {
11289
11478
  id: "z-ai/glm-4-32b",
11290
11479
  name: "Z.ai: GLM 4 32B ",
@@ -11809,7 +11998,7 @@ export const MODELS = {
11809
11998
  input: 0.5,
11810
11999
  output: 3,
11811
12000
  cacheRead: 0.09999999999999999,
11812
- cacheWrite: 0,
12001
+ cacheWrite: 0.625,
11813
12002
  },
11814
12003
  contextWindow: 1000000,
11815
12004
  maxTokens: 64000,
@@ -13931,9 +14120,9 @@ export const MODELS = {
13931
14120
  reasoning: true,
13932
14121
  input: ["text"],
13933
14122
  cost: {
13934
- input: 0.09,
13935
- output: 0.29,
13936
- cacheRead: 0.045,
14123
+ input: 0.09999999999999999,
14124
+ output: 0.3,
14125
+ cacheRead: 0.01,
13937
14126
  cacheWrite: 0,
13938
14127
  },
13939
14128
  contextWindow: 262144,
@@ -14150,15 +14339,15 @@ export const MODELS = {
14150
14339
  provider: "vercel-ai-gateway",
14151
14340
  baseUrl: "https://ai-gateway.vercel.sh",
14152
14341
  reasoning: true,
14153
- input: ["text", "image"],
14342
+ input: ["text"],
14154
14343
  cost: {
14155
14344
  input: 1.4,
14156
14345
  output: 4.4,
14157
14346
  cacheRead: 0.26,
14158
14347
  cacheWrite: 0,
14159
14348
  },
14160
- contextWindow: 202752,
14161
- maxTokens: 202752,
14349
+ contextWindow: 202800,
14350
+ maxTokens: 64000,
14162
14351
  },
14163
14352
  "zai/glm-5v-turbo": {
14164
14353
  id: "zai/glm-5v-turbo",