@mariozechner/pi-ai 0.52.9 → 0.52.11

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 (30) hide show
  1. package/dist/models.generated.d.ts +373 -170
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +469 -251
  4. package/dist/models.generated.js.map +1 -1
  5. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  6. package/dist/providers/amazon-bedrock.js +2 -2
  7. package/dist/providers/amazon-bedrock.js.map +1 -1
  8. package/dist/providers/anthropic.d.ts.map +1 -1
  9. package/dist/providers/anthropic.js +51 -19
  10. package/dist/providers/anthropic.js.map +1 -1
  11. package/dist/providers/github-copilot-headers.d.ts +8 -0
  12. package/dist/providers/github-copilot-headers.d.ts.map +1 -0
  13. package/dist/providers/github-copilot-headers.js +29 -0
  14. package/dist/providers/github-copilot-headers.js.map +1 -0
  15. package/dist/providers/openai-completions.d.ts.map +1 -1
  16. package/dist/providers/openai-completions.js +7 -25
  17. package/dist/providers/openai-completions.js.map +1 -1
  18. package/dist/providers/openai-responses-shared.d.ts.map +1 -1
  19. package/dist/providers/openai-responses-shared.js +2 -2
  20. package/dist/providers/openai-responses-shared.js.map +1 -1
  21. package/dist/providers/openai-responses.d.ts.map +1 -1
  22. package/dist/providers/openai-responses.js +6 -20
  23. package/dist/providers/openai-responses.js.map +1 -1
  24. package/dist/providers/simple-options.d.ts.map +1 -1
  25. package/dist/providers/simple-options.js +1 -0
  26. package/dist/providers/simple-options.js.map +1 -1
  27. package/dist/types.d.ts +6 -0
  28. package/dist/types.d.ts.map +1 -1
  29. package/dist/types.js.map +1 -1
  30. package/package.json +1 -1
@@ -801,6 +801,23 @@ export const MODELS = {
801
801
  contextWindow: 204608,
802
802
  maxTokens: 128000,
803
803
  },
804
+ "minimax.minimax-m2.1": {
805
+ id: "minimax.minimax-m2.1",
806
+ name: "MiniMax M2.1",
807
+ api: "bedrock-converse-stream",
808
+ provider: "amazon-bedrock",
809
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
810
+ reasoning: true,
811
+ input: ["text"],
812
+ cost: {
813
+ input: 0.3,
814
+ output: 1.2,
815
+ cacheRead: 0,
816
+ cacheWrite: 0,
817
+ },
818
+ contextWindow: 204800,
819
+ maxTokens: 131072,
820
+ },
804
821
  "mistral.ministral-3-14b-instruct": {
805
822
  id: "mistral.ministral-3-14b-instruct",
806
823
  name: "Ministral 14B 3.0",
@@ -903,6 +920,23 @@ export const MODELS = {
903
920
  contextWindow: 256000,
904
921
  maxTokens: 256000,
905
922
  },
923
+ "moonshotai.kimi-k2.5": {
924
+ id: "moonshotai.kimi-k2.5",
925
+ name: "Kimi K2.5",
926
+ api: "bedrock-converse-stream",
927
+ provider: "amazon-bedrock",
928
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
929
+ reasoning: true,
930
+ input: ["text", "image"],
931
+ cost: {
932
+ input: 0.6,
933
+ output: 3,
934
+ cacheRead: 0,
935
+ cacheWrite: 0,
936
+ },
937
+ contextWindow: 256000,
938
+ maxTokens: 256000,
939
+ },
906
940
  "nvidia.nemotron-nano-12b-v2": {
907
941
  id: "nvidia.nemotron-nano-12b-v2",
908
942
  name: "NVIDIA Nemotron Nano 12B v2 VL BF16",
@@ -1226,6 +1260,74 @@ export const MODELS = {
1226
1260
  contextWindow: 200000,
1227
1261
  maxTokens: 64000,
1228
1262
  },
1263
+ "writer.palmyra-x4-v1:0": {
1264
+ id: "writer.palmyra-x4-v1:0",
1265
+ name: "Palmyra X4",
1266
+ api: "bedrock-converse-stream",
1267
+ provider: "amazon-bedrock",
1268
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1269
+ reasoning: true,
1270
+ input: ["text"],
1271
+ cost: {
1272
+ input: 2.5,
1273
+ output: 10,
1274
+ cacheRead: 0,
1275
+ cacheWrite: 0,
1276
+ },
1277
+ contextWindow: 122880,
1278
+ maxTokens: 8192,
1279
+ },
1280
+ "writer.palmyra-x5-v1:0": {
1281
+ id: "writer.palmyra-x5-v1:0",
1282
+ name: "Palmyra X5",
1283
+ api: "bedrock-converse-stream",
1284
+ provider: "amazon-bedrock",
1285
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1286
+ reasoning: true,
1287
+ input: ["text"],
1288
+ cost: {
1289
+ input: 0.6,
1290
+ output: 6,
1291
+ cacheRead: 0,
1292
+ cacheWrite: 0,
1293
+ },
1294
+ contextWindow: 1040000,
1295
+ maxTokens: 8192,
1296
+ },
1297
+ "zai.glm-4.7": {
1298
+ id: "zai.glm-4.7",
1299
+ name: "GLM-4.7",
1300
+ api: "bedrock-converse-stream",
1301
+ provider: "amazon-bedrock",
1302
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1303
+ reasoning: true,
1304
+ input: ["text"],
1305
+ cost: {
1306
+ input: 0.6,
1307
+ output: 2.2,
1308
+ cacheRead: 0,
1309
+ cacheWrite: 0,
1310
+ },
1311
+ contextWindow: 204800,
1312
+ maxTokens: 131072,
1313
+ },
1314
+ "zai.glm-4.7-flash": {
1315
+ id: "zai.glm-4.7-flash",
1316
+ name: "GLM-4.7-Flash",
1317
+ api: "bedrock-converse-stream",
1318
+ provider: "amazon-bedrock",
1319
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1320
+ reasoning: true,
1321
+ input: ["text"],
1322
+ cost: {
1323
+ input: 0.07,
1324
+ output: 0.4,
1325
+ cacheRead: 0,
1326
+ cacheWrite: 0,
1327
+ },
1328
+ contextWindow: 200000,
1329
+ maxTokens: 131072,
1330
+ },
1229
1331
  },
1230
1332
  "anthropic": {
1231
1333
  "claude-3-5-haiku-20241022": {
@@ -2063,6 +2165,23 @@ export const MODELS = {
2063
2165
  contextWindow: 400000,
2064
2166
  maxTokens: 128000,
2065
2167
  },
2168
+ "gpt-5.3-codex-spark": {
2169
+ id: "gpt-5.3-codex-spark",
2170
+ name: "GPT-5.3 Codex Spark",
2171
+ api: "azure-openai-responses",
2172
+ provider: "azure-openai-responses",
2173
+ baseUrl: "",
2174
+ reasoning: true,
2175
+ input: ["text", "image"],
2176
+ cost: {
2177
+ input: 1.75,
2178
+ output: 14,
2179
+ cacheRead: 0.175,
2180
+ cacheWrite: 0,
2181
+ },
2182
+ contextWindow: 128000,
2183
+ maxTokens: 32000,
2184
+ },
2066
2185
  "o1": {
2067
2186
  id: "o1",
2068
2187
  name: "o1",
@@ -2218,6 +2337,23 @@ export const MODELS = {
2218
2337
  contextWindow: 131072,
2219
2338
  maxTokens: 32768,
2220
2339
  },
2340
+ "llama3.1-8b": {
2341
+ id: "llama3.1-8b",
2342
+ name: "Llama 3.1 8B",
2343
+ api: "openai-completions",
2344
+ provider: "cerebras",
2345
+ baseUrl: "https://api.cerebras.ai/v1",
2346
+ reasoning: false,
2347
+ input: ["text"],
2348
+ cost: {
2349
+ input: 0.1,
2350
+ output: 0.1,
2351
+ cacheRead: 0,
2352
+ cacheWrite: 0,
2353
+ },
2354
+ contextWindow: 32000,
2355
+ maxTokens: 8000,
2356
+ },
2221
2357
  "qwen-3-235b-a22b-instruct-2507": {
2222
2358
  id: "qwen-3-235b-a22b-instruct-2507",
2223
2359
  name: "Qwen 3 235B Instruct",
@@ -2257,11 +2393,10 @@ export const MODELS = {
2257
2393
  "claude-haiku-4.5": {
2258
2394
  id: "claude-haiku-4.5",
2259
2395
  name: "Claude Haiku 4.5",
2260
- api: "openai-completions",
2396
+ api: "anthropic-messages",
2261
2397
  provider: "github-copilot",
2262
2398
  baseUrl: "https://api.individual.githubcopilot.com",
2263
2399
  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" },
2264
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2265
2400
  reasoning: true,
2266
2401
  input: ["text", "image"],
2267
2402
  cost: {
@@ -2271,16 +2406,15 @@ export const MODELS = {
2271
2406
  cacheWrite: 0,
2272
2407
  },
2273
2408
  contextWindow: 128000,
2274
- maxTokens: 16000,
2409
+ maxTokens: 32000,
2275
2410
  },
2276
2411
  "claude-opus-4.5": {
2277
2412
  id: "claude-opus-4.5",
2278
2413
  name: "Claude Opus 4.5",
2279
- api: "openai-completions",
2414
+ api: "anthropic-messages",
2280
2415
  provider: "github-copilot",
2281
2416
  baseUrl: "https://api.individual.githubcopilot.com",
2282
2417
  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" },
2283
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2284
2418
  reasoning: true,
2285
2419
  input: ["text", "image"],
2286
2420
  cost: {
@@ -2290,16 +2424,15 @@ export const MODELS = {
2290
2424
  cacheWrite: 0,
2291
2425
  },
2292
2426
  contextWindow: 128000,
2293
- maxTokens: 16000,
2427
+ maxTokens: 32000,
2294
2428
  },
2295
2429
  "claude-opus-4.6": {
2296
2430
  id: "claude-opus-4.6",
2297
2431
  name: "Claude Opus 4.6",
2298
- api: "openai-completions",
2432
+ api: "anthropic-messages",
2299
2433
  provider: "github-copilot",
2300
2434
  baseUrl: "https://api.individual.githubcopilot.com",
2301
2435
  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" },
2302
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2303
2436
  reasoning: true,
2304
2437
  input: ["text", "image"],
2305
2438
  cost: {
@@ -2314,11 +2447,10 @@ export const MODELS = {
2314
2447
  "claude-sonnet-4": {
2315
2448
  id: "claude-sonnet-4",
2316
2449
  name: "Claude Sonnet 4",
2317
- api: "openai-completions",
2450
+ api: "anthropic-messages",
2318
2451
  provider: "github-copilot",
2319
2452
  baseUrl: "https://api.individual.githubcopilot.com",
2320
2453
  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" },
2321
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2322
2454
  reasoning: true,
2323
2455
  input: ["text", "image"],
2324
2456
  cost: {
@@ -2333,11 +2465,10 @@ export const MODELS = {
2333
2465
  "claude-sonnet-4.5": {
2334
2466
  id: "claude-sonnet-4.5",
2335
2467
  name: "Claude Sonnet 4.5",
2336
- api: "openai-completions",
2468
+ api: "anthropic-messages",
2337
2469
  provider: "github-copilot",
2338
2470
  baseUrl: "https://api.individual.githubcopilot.com",
2339
2471
  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" },
2340
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2341
2472
  reasoning: true,
2342
2473
  input: ["text", "image"],
2343
2474
  cost: {
@@ -2347,7 +2478,7 @@ export const MODELS = {
2347
2478
  cacheWrite: 0,
2348
2479
  },
2349
2480
  contextWindow: 128000,
2350
- maxTokens: 16000,
2481
+ maxTokens: 32000,
2351
2482
  },
2352
2483
  "gemini-2.5-pro": {
2353
2484
  id: "gemini-2.5-pro",
@@ -2422,7 +2553,7 @@ export const MODELS = {
2422
2553
  cacheRead: 0,
2423
2554
  cacheWrite: 0,
2424
2555
  },
2425
- contextWindow: 128000,
2556
+ contextWindow: 64000,
2426
2557
  maxTokens: 16384,
2427
2558
  },
2428
2559
  "gpt-4o": {
@@ -2496,7 +2627,7 @@ export const MODELS = {
2496
2627
  cacheWrite: 0,
2497
2628
  },
2498
2629
  contextWindow: 128000,
2499
- maxTokens: 128000,
2630
+ maxTokens: 64000,
2500
2631
  },
2501
2632
  "gpt-5.1-codex": {
2502
2633
  id: "gpt-5.1-codex",
@@ -2550,7 +2681,7 @@ export const MODELS = {
2550
2681
  cacheWrite: 0,
2551
2682
  },
2552
2683
  contextWindow: 128000,
2553
- maxTokens: 100000,
2684
+ maxTokens: 128000,
2554
2685
  },
2555
2686
  "gpt-5.2": {
2556
2687
  id: "gpt-5.2",
@@ -3874,6 +4005,24 @@ export const MODELS = {
3874
4005
  contextWindow: 200000,
3875
4006
  maxTokens: 128000,
3876
4007
  },
4008
+ "zai-org/GLM-5": {
4009
+ id: "zai-org/GLM-5",
4010
+ name: "GLM-5",
4011
+ api: "openai-completions",
4012
+ provider: "huggingface",
4013
+ baseUrl: "https://router.huggingface.co/v1",
4014
+ compat: { "supportsDeveloperRole": false },
4015
+ reasoning: true,
4016
+ input: ["text"],
4017
+ cost: {
4018
+ input: 1,
4019
+ output: 3.2,
4020
+ cacheRead: 0.2,
4021
+ cacheWrite: 0,
4022
+ },
4023
+ contextWindow: 202752,
4024
+ maxTokens: 131072,
4025
+ },
3877
4026
  },
3878
4027
  "kimi-coding": {
3879
4028
  "k2p5": {
@@ -3946,6 +4095,23 @@ export const MODELS = {
3946
4095
  contextWindow: 204800,
3947
4096
  maxTokens: 131072,
3948
4097
  },
4098
+ "MiniMax-M2.5": {
4099
+ id: "MiniMax-M2.5",
4100
+ name: "MiniMax-M2.5",
4101
+ api: "anthropic-messages",
4102
+ provider: "minimax",
4103
+ baseUrl: "https://api.minimax.io/anthropic",
4104
+ reasoning: true,
4105
+ input: ["text"],
4106
+ cost: {
4107
+ input: 0.3,
4108
+ output: 1.2,
4109
+ cacheRead: 0.03,
4110
+ cacheWrite: 0.375,
4111
+ },
4112
+ contextWindow: 204800,
4113
+ maxTokens: 131072,
4114
+ },
3949
4115
  },
3950
4116
  "minimax-cn": {
3951
4117
  "MiniMax-M2": {
@@ -3982,6 +4148,23 @@ export const MODELS = {
3982
4148
  contextWindow: 204800,
3983
4149
  maxTokens: 131072,
3984
4150
  },
4151
+ "MiniMax-M2.5": {
4152
+ id: "MiniMax-M2.5",
4153
+ name: "MiniMax-M2.5",
4154
+ api: "anthropic-messages",
4155
+ provider: "minimax-cn",
4156
+ baseUrl: "https://api.minimaxi.com/anthropic",
4157
+ reasoning: true,
4158
+ input: ["text"],
4159
+ cost: {
4160
+ input: 0.3,
4161
+ output: 1.2,
4162
+ cacheRead: 0.03,
4163
+ cacheWrite: 0.375,
4164
+ },
4165
+ contextWindow: 204800,
4166
+ maxTokens: 131072,
4167
+ },
3985
4168
  },
3986
4169
  "mistral": {
3987
4170
  "codestral-latest": {
@@ -4870,6 +5053,23 @@ export const MODELS = {
4870
5053
  contextWindow: 400000,
4871
5054
  maxTokens: 128000,
4872
5055
  },
5056
+ "gpt-5.3-codex-spark": {
5057
+ id: "gpt-5.3-codex-spark",
5058
+ name: "GPT-5.3 Codex Spark",
5059
+ api: "openai-responses",
5060
+ provider: "openai",
5061
+ baseUrl: "https://api.openai.com/v1",
5062
+ reasoning: true,
5063
+ input: ["text", "image"],
5064
+ cost: {
5065
+ input: 1.75,
5066
+ output: 14,
5067
+ cacheRead: 0.175,
5068
+ cacheWrite: 0,
5069
+ },
5070
+ contextWindow: 128000,
5071
+ maxTokens: 32000,
5072
+ },
4873
5073
  "o1": {
4874
5074
  id: "o1",
4875
5075
  name: "o1",
@@ -5110,6 +5310,23 @@ export const MODELS = {
5110
5310
  contextWindow: 272000,
5111
5311
  maxTokens: 128000,
5112
5312
  },
5313
+ "gpt-5.3-codex-spark": {
5314
+ id: "gpt-5.3-codex-spark",
5315
+ name: "GPT-5.3 Codex Spark",
5316
+ api: "openai-codex-responses",
5317
+ provider: "openai-codex",
5318
+ baseUrl: "https://chatgpt.com/backend-api",
5319
+ reasoning: true,
5320
+ input: ["text"],
5321
+ cost: {
5322
+ input: 0,
5323
+ output: 0,
5324
+ cacheRead: 0,
5325
+ cacheWrite: 0,
5326
+ },
5327
+ contextWindow: 128000,
5328
+ maxTokens: 128000,
5329
+ },
5113
5330
  },
5114
5331
  "opencode": {
5115
5332
  "big-pickle": {
@@ -5316,23 +5533,6 @@ export const MODELS = {
5316
5533
  contextWindow: 204800,
5317
5534
  maxTokens: 131072,
5318
5535
  },
5319
- "glm-4.7-free": {
5320
- id: "glm-4.7-free",
5321
- name: "GLM-4.7 Free",
5322
- api: "openai-completions",
5323
- provider: "opencode",
5324
- baseUrl: "https://opencode.ai/zen/v1",
5325
- reasoning: true,
5326
- input: ["text"],
5327
- cost: {
5328
- input: 0,
5329
- output: 0,
5330
- cacheRead: 0,
5331
- cacheWrite: 0,
5332
- },
5333
- contextWindow: 204800,
5334
- maxTokens: 131072,
5335
- },
5336
5536
  "gpt-5": {
5337
5537
  id: "gpt-5",
5338
5538
  name: "GPT-5",
@@ -5571,47 +5771,13 @@ export const MODELS = {
5571
5771
  contextWindow: 204800,
5572
5772
  maxTokens: 131072,
5573
5773
  },
5574
- "minimax-m2.1-free": {
5575
- id: "minimax-m2.1-free",
5576
- name: "MiniMax M2.1 Free",
5577
- api: "anthropic-messages",
5578
- provider: "opencode",
5579
- baseUrl: "https://opencode.ai/zen",
5580
- reasoning: true,
5581
- input: ["text"],
5582
- cost: {
5583
- input: 0,
5584
- output: 0,
5585
- cacheRead: 0,
5586
- cacheWrite: 0,
5587
- },
5588
- contextWindow: 204800,
5589
- maxTokens: 131072,
5590
- },
5591
- "qwen3-coder": {
5592
- id: "qwen3-coder",
5593
- name: "Qwen3 Coder",
5594
- api: "openai-completions",
5595
- provider: "opencode",
5596
- baseUrl: "https://opencode.ai/zen/v1",
5597
- reasoning: false,
5598
- input: ["text"],
5599
- cost: {
5600
- input: 0.45,
5601
- output: 1.8,
5602
- cacheRead: 0,
5603
- cacheWrite: 0,
5604
- },
5605
- contextWindow: 262144,
5606
- maxTokens: 65536,
5607
- },
5608
- "trinity-large-preview-free": {
5609
- id: "trinity-large-preview-free",
5610
- name: "Trinity Large Preview",
5774
+ "minimax-m2.5-free": {
5775
+ id: "minimax-m2.5-free",
5776
+ name: "MiniMax M2.5 Free",
5611
5777
  api: "openai-completions",
5612
5778
  provider: "opencode",
5613
5779
  baseUrl: "https://opencode.ai/zen/v1",
5614
- reasoning: false,
5780
+ reasoning: true,
5615
5781
  input: ["text"],
5616
5782
  cost: {
5617
5783
  input: 0,
@@ -5619,7 +5785,7 @@ export const MODELS = {
5619
5785
  cacheRead: 0,
5620
5786
  cacheWrite: 0,
5621
5787
  },
5622
- contextWindow: 131072,
5788
+ contextWindow: 204800,
5623
5789
  maxTokens: 131072,
5624
5790
  },
5625
5791
  },
@@ -5641,23 +5807,6 @@ export const MODELS = {
5641
5807
  contextWindow: 256000,
5642
5808
  maxTokens: 4096,
5643
5809
  },
5644
- "ai21/jamba-mini-1.7": {
5645
- id: "ai21/jamba-mini-1.7",
5646
- name: "AI21: Jamba Mini 1.7",
5647
- api: "openai-completions",
5648
- provider: "openrouter",
5649
- baseUrl: "https://openrouter.ai/api/v1",
5650
- reasoning: false,
5651
- input: ["text"],
5652
- cost: {
5653
- input: 0.19999999999999998,
5654
- output: 0.39999999999999997,
5655
- cacheRead: 0,
5656
- cacheWrite: 0,
5657
- },
5658
- contextWindow: 256000,
5659
- maxTokens: 4096,
5660
- },
5661
5810
  "alibaba/tongyi-deepresearch-30b-a3b": {
5662
5811
  id: "alibaba/tongyi-deepresearch-30b-a3b",
5663
5812
  name: "Tongyi DeepResearch 30B A3B",
@@ -6780,6 +6929,23 @@ export const MODELS = {
6780
6929
  contextWindow: 196608,
6781
6930
  maxTokens: 4096,
6782
6931
  },
6932
+ "minimax/minimax-m2.5": {
6933
+ id: "minimax/minimax-m2.5",
6934
+ name: "MiniMax: MiniMax M2.5",
6935
+ api: "openai-completions",
6936
+ provider: "openrouter",
6937
+ baseUrl: "https://openrouter.ai/api/v1",
6938
+ reasoning: true,
6939
+ input: ["text"],
6940
+ cost: {
6941
+ input: 0.3,
6942
+ output: 1.2,
6943
+ cacheRead: 0.03,
6944
+ cacheWrite: 0,
6945
+ },
6946
+ contextWindow: 204800,
6947
+ maxTokens: 131072,
6948
+ },
6783
6949
  "mistralai/codestral-2508": {
6784
6950
  id: "mistralai/codestral-2508",
6785
6951
  name: "Mistral: Codestral 2508",
@@ -6862,51 +7028,17 @@ export const MODELS = {
6862
7028
  cacheRead: 0,
6863
7029
  cacheWrite: 0,
6864
7030
  },
6865
- contextWindow: 262144,
6866
- maxTokens: 4096,
6867
- },
6868
- "mistralai/ministral-3b": {
6869
- id: "mistralai/ministral-3b",
6870
- name: "Mistral: Ministral 3B",
6871
- api: "openai-completions",
6872
- provider: "openrouter",
6873
- baseUrl: "https://openrouter.ai/api/v1",
6874
- reasoning: false,
6875
- input: ["text"],
6876
- cost: {
6877
- input: 0.04,
6878
- output: 0.04,
6879
- cacheRead: 0,
6880
- cacheWrite: 0,
6881
- },
6882
- contextWindow: 131072,
6883
- maxTokens: 4096,
6884
- },
6885
- "mistralai/ministral-3b-2512": {
6886
- id: "mistralai/ministral-3b-2512",
6887
- name: "Mistral: Ministral 3 3B 2512",
6888
- api: "openai-completions",
6889
- provider: "openrouter",
6890
- baseUrl: "https://openrouter.ai/api/v1",
6891
- reasoning: false,
6892
- input: ["text", "image"],
6893
- cost: {
6894
- input: 0.09999999999999999,
6895
- output: 0.09999999999999999,
6896
- cacheRead: 0,
6897
- cacheWrite: 0,
6898
- },
6899
- contextWindow: 131072,
7031
+ contextWindow: 262144,
6900
7032
  maxTokens: 4096,
6901
7033
  },
6902
- "mistralai/ministral-8b": {
6903
- id: "mistralai/ministral-8b",
6904
- name: "Mistral: Ministral 8B",
7034
+ "mistralai/ministral-3b-2512": {
7035
+ id: "mistralai/ministral-3b-2512",
7036
+ name: "Mistral: Ministral 3 3B 2512",
6905
7037
  api: "openai-completions",
6906
7038
  provider: "openrouter",
6907
7039
  baseUrl: "https://openrouter.ai/api/v1",
6908
7040
  reasoning: false,
6909
- input: ["text"],
7041
+ input: ["text", "image"],
6910
7042
  cost: {
6911
7043
  input: 0.09999999999999999,
6912
7044
  output: 0.09999999999999999,
@@ -7154,23 +7286,6 @@ export const MODELS = {
7154
7286
  contextWindow: 32768,
7155
7287
  maxTokens: 4096,
7156
7288
  },
7157
- "mistralai/mistral-tiny": {
7158
- id: "mistralai/mistral-tiny",
7159
- name: "Mistral Tiny",
7160
- api: "openai-completions",
7161
- provider: "openrouter",
7162
- baseUrl: "https://openrouter.ai/api/v1",
7163
- reasoning: false,
7164
- input: ["text"],
7165
- cost: {
7166
- input: 0.25,
7167
- output: 0.25,
7168
- cacheRead: 0,
7169
- cacheWrite: 0,
7170
- },
7171
- contextWindow: 32768,
7172
- maxTokens: 4096,
7173
- },
7174
7289
  "mistralai/mixtral-8x22b-instruct": {
7175
7290
  id: "mistralai/mixtral-8x22b-instruct",
7176
7291
  name: "Mistral: Mixtral 8x22B Instruct",
@@ -7205,23 +7320,6 @@ export const MODELS = {
7205
7320
  contextWindow: 32768,
7206
7321
  maxTokens: 16384,
7207
7322
  },
7208
- "mistralai/pixtral-12b": {
7209
- id: "mistralai/pixtral-12b",
7210
- name: "Mistral: Pixtral 12B",
7211
- api: "openai-completions",
7212
- provider: "openrouter",
7213
- baseUrl: "https://openrouter.ai/api/v1",
7214
- reasoning: false,
7215
- input: ["text", "image"],
7216
- cost: {
7217
- input: 0.09999999999999999,
7218
- output: 0.09999999999999999,
7219
- cacheRead: 0,
7220
- cacheWrite: 0,
7221
- },
7222
- contextWindow: 32768,
7223
- maxTokens: 4096,
7224
- },
7225
7323
  "mistralai/pixtral-large-2411": {
7226
7324
  id: "mistralai/pixtral-large-2411",
7227
7325
  name: "Mistral: Pixtral Large 2411",
@@ -7333,9 +7431,9 @@ export const MODELS = {
7333
7431
  reasoning: true,
7334
7432
  input: ["text", "image"],
7335
7433
  cost: {
7336
- input: 0.3,
7337
- output: 1.5,
7338
- cacheRead: 0.049999999999999996,
7434
+ input: 0.44999999999999996,
7435
+ output: 2.25,
7436
+ cacheRead: 0.070000002,
7339
7437
  cacheWrite: 0,
7340
7438
  },
7341
7439
  contextWindow: 262144,
@@ -8361,6 +8459,23 @@ export const MODELS = {
8361
8459
  contextWindow: 200000,
8362
8460
  maxTokens: 100000,
8363
8461
  },
8462
+ "openrouter/aurora-alpha": {
8463
+ id: "openrouter/aurora-alpha",
8464
+ name: "Aurora Alpha",
8465
+ api: "openai-completions",
8466
+ provider: "openrouter",
8467
+ baseUrl: "https://openrouter.ai/api/v1",
8468
+ reasoning: true,
8469
+ input: ["text"],
8470
+ cost: {
8471
+ input: 0,
8472
+ output: 0,
8473
+ cacheRead: 0,
8474
+ cacheWrite: 0,
8475
+ },
8476
+ contextWindow: 128000,
8477
+ maxTokens: 50000,
8478
+ },
8364
8479
  "openrouter/auto": {
8365
8480
  id: "openrouter/auto",
8366
8481
  name: "Auto Router",
@@ -8395,23 +8510,6 @@ export const MODELS = {
8395
8510
  contextWindow: 200000,
8396
8511
  maxTokens: 4096,
8397
8512
  },
8398
- "openrouter/pony-alpha": {
8399
- id: "openrouter/pony-alpha",
8400
- name: "Pony Alpha",
8401
- api: "openai-completions",
8402
- provider: "openrouter",
8403
- baseUrl: "https://openrouter.ai/api/v1",
8404
- reasoning: true,
8405
- input: ["text"],
8406
- cost: {
8407
- input: 0,
8408
- output: 0,
8409
- cacheRead: 0,
8410
- cacheWrite: 0,
8411
- },
8412
- contextWindow: 200000,
8413
- maxTokens: 131000,
8414
- },
8415
8513
  "prime-intellect/intellect-3": {
8416
8514
  id: "prime-intellect/intellect-3",
8417
8515
  name: "Prime Intellect: INTELLECT-3",
@@ -8474,7 +8572,7 @@ export const MODELS = {
8474
8572
  cost: {
8475
8573
  input: 1.5999999999999999,
8476
8574
  output: 6.3999999999999995,
8477
- cacheRead: 0.64,
8575
+ cacheRead: 0.32,
8478
8576
  cacheWrite: 0,
8479
8577
  },
8480
8578
  contextWindow: 32768,
@@ -8491,11 +8589,11 @@ export const MODELS = {
8491
8589
  cost: {
8492
8590
  input: 0.39999999999999997,
8493
8591
  output: 1.2,
8494
- cacheRead: 0.16,
8592
+ cacheRead: 0.08,
8495
8593
  cacheWrite: 0,
8496
8594
  },
8497
- contextWindow: 131072,
8498
- maxTokens: 8192,
8595
+ contextWindow: 1000000,
8596
+ maxTokens: 32768,
8499
8597
  },
8500
8598
  "qwen/qwen-plus-2025-07-28": {
8501
8599
  id: "qwen/qwen-plus-2025-07-28",
@@ -8524,7 +8622,7 @@ export const MODELS = {
8524
8622
  input: ["text"],
8525
8623
  cost: {
8526
8624
  input: 0.39999999999999997,
8527
- output: 4,
8625
+ output: 1.2,
8528
8626
  cacheRead: 0,
8529
8627
  cacheWrite: 0,
8530
8628
  },
@@ -8542,10 +8640,10 @@ export const MODELS = {
8542
8640
  cost: {
8543
8641
  input: 0.049999999999999996,
8544
8642
  output: 0.19999999999999998,
8545
- cacheRead: 0.02,
8643
+ cacheRead: 0.01,
8546
8644
  cacheWrite: 0,
8547
8645
  },
8548
- contextWindow: 1000000,
8646
+ contextWindow: 131072,
8549
8647
  maxTokens: 8192,
8550
8648
  },
8551
8649
  "qwen/qwen-vl-max": {
@@ -8563,7 +8661,7 @@ export const MODELS = {
8563
8661
  cacheWrite: 0,
8564
8662
  },
8565
8663
  contextWindow: 131072,
8566
- maxTokens: 8192,
8664
+ maxTokens: 32768,
8567
8665
  },
8568
8666
  "qwen/qwen3-14b": {
8569
8667
  id: "qwen/qwen3-14b",
@@ -8591,13 +8689,13 @@ export const MODELS = {
8591
8689
  reasoning: true,
8592
8690
  input: ["text"],
8593
8691
  cost: {
8594
- input: 0.19999999999999998,
8595
- output: 0.6,
8596
- cacheRead: 0,
8692
+ input: 0.3,
8693
+ output: 1.2,
8694
+ cacheRead: 0.15,
8597
8695
  cacheWrite: 0,
8598
8696
  },
8599
8697
  contextWindow: 40960,
8600
- maxTokens: 4096,
8698
+ maxTokens: 40960,
8601
8699
  },
8602
8700
  "qwen/qwen3-235b-a22b-2507": {
8603
8701
  id: "qwen/qwen3-235b-a22b-2507",
@@ -8625,13 +8723,13 @@ export const MODELS = {
8625
8723
  reasoning: true,
8626
8724
  input: ["text"],
8627
8725
  cost: {
8628
- input: 0.11,
8629
- output: 0.6,
8630
- cacheRead: 0.055,
8726
+ input: 0,
8727
+ output: 0,
8728
+ cacheRead: 0,
8631
8729
  cacheWrite: 0,
8632
8730
  },
8633
- contextWindow: 262144,
8634
- maxTokens: 262144,
8731
+ contextWindow: 131072,
8732
+ maxTokens: 4096,
8635
8733
  },
8636
8734
  "qwen/qwen3-30b-a3b": {
8637
8735
  id: "qwen/qwen3-30b-a3b",
@@ -8701,6 +8799,23 @@ export const MODELS = {
8701
8799
  contextWindow: 40960,
8702
8800
  maxTokens: 40960,
8703
8801
  },
8802
+ "qwen/qwen3-4b": {
8803
+ id: "qwen/qwen3-4b",
8804
+ name: "Qwen: Qwen3 4B",
8805
+ api: "openai-completions",
8806
+ provider: "openrouter",
8807
+ baseUrl: "https://openrouter.ai/api/v1",
8808
+ reasoning: true,
8809
+ input: ["text"],
8810
+ cost: {
8811
+ input: 0.0715,
8812
+ output: 0.273,
8813
+ cacheRead: 0,
8814
+ cacheWrite: 0,
8815
+ },
8816
+ contextWindow: 131072,
8817
+ maxTokens: 8192,
8818
+ },
8704
8819
  "qwen/qwen3-4b:free": {
8705
8820
  id: "qwen/qwen3-4b:free",
8706
8821
  name: "Qwen: Qwen3 4B (free)",
@@ -8741,7 +8856,7 @@ export const MODELS = {
8741
8856
  api: "openai-completions",
8742
8857
  provider: "openrouter",
8743
8858
  baseUrl: "https://openrouter.ai/api/v1",
8744
- reasoning: true,
8859
+ reasoning: false,
8745
8860
  input: ["text"],
8746
8861
  cost: {
8747
8862
  input: 0.22,
@@ -8780,10 +8895,10 @@ export const MODELS = {
8780
8895
  cost: {
8781
8896
  input: 0.3,
8782
8897
  output: 1.5,
8783
- cacheRead: 0.08,
8898
+ cacheRead: 0.06,
8784
8899
  cacheWrite: 0,
8785
8900
  },
8786
- contextWindow: 128000,
8901
+ contextWindow: 1000000,
8787
8902
  maxTokens: 65536,
8788
8903
  },
8789
8904
  "qwen/qwen3-coder-next": {
@@ -8814,10 +8929,10 @@ export const MODELS = {
8814
8929
  cost: {
8815
8930
  input: 1,
8816
8931
  output: 5,
8817
- cacheRead: 0.09999999999999999,
8932
+ cacheRead: 0.19999999999999998,
8818
8933
  cacheWrite: 0,
8819
8934
  },
8820
- contextWindow: 128000,
8935
+ contextWindow: 1000000,
8821
8936
  maxTokens: 65536,
8822
8937
  },
8823
8938
  "qwen/qwen3-coder:exacto": {
@@ -8868,8 +8983,25 @@ export const MODELS = {
8868
8983
  cacheRead: 0.24,
8869
8984
  cacheWrite: 0,
8870
8985
  },
8871
- contextWindow: 256000,
8872
- maxTokens: 32768,
8986
+ contextWindow: 262144,
8987
+ maxTokens: 65536,
8988
+ },
8989
+ "qwen/qwen3-max-thinking": {
8990
+ id: "qwen/qwen3-max-thinking",
8991
+ name: "Qwen: Qwen3 Max Thinking",
8992
+ api: "openai-completions",
8993
+ provider: "openrouter",
8994
+ baseUrl: "https://openrouter.ai/api/v1",
8995
+ reasoning: true,
8996
+ input: ["text"],
8997
+ cost: {
8998
+ input: 1.2,
8999
+ output: 6,
9000
+ cacheRead: 0,
9001
+ cacheWrite: 0,
9002
+ },
9003
+ contextWindow: 262144,
9004
+ maxTokens: 65536,
8873
9005
  },
8874
9006
  "qwen/qwen3-next-80b-a3b-instruct": {
8875
9007
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -8948,13 +9080,13 @@ export const MODELS = {
8948
9080
  reasoning: true,
8949
9081
  input: ["text", "image"],
8950
9082
  cost: {
8951
- input: 0.44999999999999996,
8952
- output: 3.5,
9083
+ input: 0,
9084
+ output: 0,
8953
9085
  cacheRead: 0,
8954
9086
  cacheWrite: 0,
8955
9087
  },
8956
- contextWindow: 262144,
8957
- maxTokens: 262144,
9088
+ contextWindow: 131072,
9089
+ maxTokens: 32768,
8958
9090
  },
8959
9091
  "qwen/qwen3-vl-30b-a3b-instruct": {
8960
9092
  id: "qwen/qwen3-vl-30b-a3b-instruct",
@@ -8965,13 +9097,13 @@ export const MODELS = {
8965
9097
  reasoning: false,
8966
9098
  input: ["text", "image"],
8967
9099
  cost: {
8968
- input: 0.15,
8969
- output: 0.6,
8970
- cacheRead: 0.075,
9100
+ input: 0.13,
9101
+ output: 0.52,
9102
+ cacheRead: 0,
8971
9103
  cacheWrite: 0,
8972
9104
  },
8973
- contextWindow: 262144,
8974
- maxTokens: 4096,
9105
+ contextWindow: 131072,
9106
+ maxTokens: 32768,
8975
9107
  },
8976
9108
  "qwen/qwen3-vl-30b-a3b-thinking": {
8977
9109
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -8982,8 +9114,25 @@ export const MODELS = {
8982
9114
  reasoning: true,
8983
9115
  input: ["text", "image"],
8984
9116
  cost: {
8985
- input: 0.19999999999999998,
8986
- output: 1,
9117
+ input: 0,
9118
+ output: 0,
9119
+ cacheRead: 0,
9120
+ cacheWrite: 0,
9121
+ },
9122
+ contextWindow: 131072,
9123
+ maxTokens: 32768,
9124
+ },
9125
+ "qwen/qwen3-vl-32b-instruct": {
9126
+ id: "qwen/qwen3-vl-32b-instruct",
9127
+ name: "Qwen: Qwen3 VL 32B Instruct",
9128
+ api: "openai-completions",
9129
+ provider: "openrouter",
9130
+ baseUrl: "https://openrouter.ai/api/v1",
9131
+ reasoning: false,
9132
+ input: ["text", "image"],
9133
+ cost: {
9134
+ input: 0.10400000000000001,
9135
+ output: 0.41600000000000004,
8987
9136
  cacheRead: 0,
8988
9137
  cacheWrite: 0,
8989
9138
  },
@@ -9016,12 +9165,12 @@ export const MODELS = {
9016
9165
  reasoning: true,
9017
9166
  input: ["text", "image"],
9018
9167
  cost: {
9019
- input: 0.18,
9020
- output: 2.0999999999999996,
9168
+ input: 0.117,
9169
+ output: 1.365,
9021
9170
  cacheRead: 0,
9022
9171
  cacheWrite: 0,
9023
9172
  },
9024
- contextWindow: 256000,
9173
+ contextWindow: 131072,
9025
9174
  maxTokens: 32768,
9026
9175
  },
9027
9176
  "qwen/qwq-32b": {
@@ -9092,22 +9241,22 @@ export const MODELS = {
9092
9241
  contextWindow: 32768,
9093
9242
  maxTokens: 32768,
9094
9243
  },
9095
- "stepfun-ai/step3": {
9096
- id: "stepfun-ai/step3",
9097
- name: "StepFun: Step3",
9244
+ "stepfun/step-3.5-flash": {
9245
+ id: "stepfun/step-3.5-flash",
9246
+ name: "StepFun: Step 3.5 Flash",
9098
9247
  api: "openai-completions",
9099
9248
  provider: "openrouter",
9100
9249
  baseUrl: "https://openrouter.ai/api/v1",
9101
9250
  reasoning: true,
9102
- input: ["text", "image"],
9251
+ input: ["text"],
9103
9252
  cost: {
9104
- input: 0.5700000000000001,
9105
- output: 1.42,
9106
- cacheRead: 0,
9253
+ input: 0.09999999999999999,
9254
+ output: 0.3,
9255
+ cacheRead: 0.02,
9107
9256
  cacheWrite: 0,
9108
9257
  },
9109
- contextWindow: 65536,
9110
- maxTokens: 65536,
9258
+ contextWindow: 256000,
9259
+ maxTokens: 256000,
9111
9260
  },
9112
9261
  "stepfun/step-3.5-flash:free": {
9113
9262
  id: "stepfun/step-3.5-flash:free",
@@ -9383,7 +9532,7 @@ export const MODELS = {
9383
9532
  },
9384
9533
  "z-ai/glm-4-32b": {
9385
9534
  id: "z-ai/glm-4-32b",
9386
- name: "Z.AI: GLM 4 32B ",
9535
+ name: "Z.ai: GLM 4 32B ",
9387
9536
  api: "openai-completions",
9388
9537
  provider: "openrouter",
9389
9538
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9400,7 +9549,7 @@ export const MODELS = {
9400
9549
  },
9401
9550
  "z-ai/glm-4.5": {
9402
9551
  id: "z-ai/glm-4.5",
9403
- name: "Z.AI: GLM 4.5",
9552
+ name: "Z.ai: GLM 4.5",
9404
9553
  api: "openai-completions",
9405
9554
  provider: "openrouter",
9406
9555
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9417,7 +9566,7 @@ export const MODELS = {
9417
9566
  },
9418
9567
  "z-ai/glm-4.5-air": {
9419
9568
  id: "z-ai/glm-4.5-air",
9420
- name: "Z.AI: GLM 4.5 Air",
9569
+ name: "Z.ai: GLM 4.5 Air",
9421
9570
  api: "openai-completions",
9422
9571
  provider: "openrouter",
9423
9572
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9434,7 +9583,7 @@ export const MODELS = {
9434
9583
  },
9435
9584
  "z-ai/glm-4.5-air:free": {
9436
9585
  id: "z-ai/glm-4.5-air:free",
9437
- name: "Z.AI: GLM 4.5 Air (free)",
9586
+ name: "Z.ai: GLM 4.5 Air (free)",
9438
9587
  api: "openai-completions",
9439
9588
  provider: "openrouter",
9440
9589
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9451,7 +9600,7 @@ export const MODELS = {
9451
9600
  },
9452
9601
  "z-ai/glm-4.5v": {
9453
9602
  id: "z-ai/glm-4.5v",
9454
- name: "Z.AI: GLM 4.5V",
9603
+ name: "Z.ai: GLM 4.5V",
9455
9604
  api: "openai-completions",
9456
9605
  provider: "openrouter",
9457
9606
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9468,7 +9617,7 @@ export const MODELS = {
9468
9617
  },
9469
9618
  "z-ai/glm-4.6": {
9470
9619
  id: "z-ai/glm-4.6",
9471
- name: "Z.AI: GLM 4.6",
9620
+ name: "Z.ai: GLM 4.6",
9472
9621
  api: "openai-completions",
9473
9622
  provider: "openrouter",
9474
9623
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9485,7 +9634,7 @@ export const MODELS = {
9485
9634
  },
9486
9635
  "z-ai/glm-4.6:exacto": {
9487
9636
  id: "z-ai/glm-4.6:exacto",
9488
- name: "Z.AI: GLM 4.6 (exacto)",
9637
+ name: "Z.ai: GLM 4.6 (exacto)",
9489
9638
  api: "openai-completions",
9490
9639
  provider: "openrouter",
9491
9640
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9502,7 +9651,7 @@ export const MODELS = {
9502
9651
  },
9503
9652
  "z-ai/glm-4.6v": {
9504
9653
  id: "z-ai/glm-4.6v",
9505
- name: "Z.AI: GLM 4.6V",
9654
+ name: "Z.ai: GLM 4.6V",
9506
9655
  api: "openai-completions",
9507
9656
  provider: "openrouter",
9508
9657
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9519,7 +9668,7 @@ export const MODELS = {
9519
9668
  },
9520
9669
  "z-ai/glm-4.7": {
9521
9670
  id: "z-ai/glm-4.7",
9522
- name: "Z.AI: GLM 4.7",
9671
+ name: "Z.ai: GLM 4.7",
9523
9672
  api: "openai-completions",
9524
9673
  provider: "openrouter",
9525
9674
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9536,7 +9685,7 @@ export const MODELS = {
9536
9685
  },
9537
9686
  "z-ai/glm-4.7-flash": {
9538
9687
  id: "z-ai/glm-4.7-flash",
9539
- name: "Z.AI: GLM 4.7 Flash",
9688
+ name: "Z.ai: GLM 4.7 Flash",
9540
9689
  api: "openai-completions",
9541
9690
  provider: "openrouter",
9542
9691
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9551,6 +9700,23 @@ export const MODELS = {
9551
9700
  contextWindow: 202752,
9552
9701
  maxTokens: 4096,
9553
9702
  },
9703
+ "z-ai/glm-5": {
9704
+ id: "z-ai/glm-5",
9705
+ name: "Z.ai: GLM 5",
9706
+ api: "openai-completions",
9707
+ provider: "openrouter",
9708
+ baseUrl: "https://openrouter.ai/api/v1",
9709
+ reasoning: true,
9710
+ input: ["text"],
9711
+ cost: {
9712
+ input: 0.7999999999999999,
9713
+ output: 2.56,
9714
+ cacheRead: 0.16,
9715
+ cacheWrite: 0,
9716
+ },
9717
+ contextWindow: 202752,
9718
+ maxTokens: 131072,
9719
+ },
9554
9720
  },
9555
9721
  "vercel-ai-gateway": {
9556
9722
  "alibaba/qwen-3-14b": {
@@ -10038,8 +10204,8 @@ export const MODELS = {
10038
10204
  reasoning: true,
10039
10205
  input: ["text"],
10040
10206
  cost: {
10041
- input: 0.3,
10042
- output: 1,
10207
+ input: 0.21,
10208
+ output: 0.7899999999999999,
10043
10209
  cacheRead: 0,
10044
10210
  cacheWrite: 0,
10045
10211
  },
@@ -10063,22 +10229,22 @@ export const MODELS = {
10063
10229
  contextWindow: 131072,
10064
10230
  maxTokens: 65536,
10065
10231
  },
10066
- "deepseek/deepseek-v3.2-exp": {
10067
- id: "deepseek/deepseek-v3.2-exp",
10068
- name: "DeepSeek V3.2 Exp",
10232
+ "deepseek/deepseek-v3.2": {
10233
+ id: "deepseek/deepseek-v3.2",
10234
+ name: "DeepSeek V3.2",
10069
10235
  api: "anthropic-messages",
10070
10236
  provider: "vercel-ai-gateway",
10071
10237
  baseUrl: "https://ai-gateway.vercel.sh",
10072
- reasoning: true,
10238
+ reasoning: false,
10073
10239
  input: ["text"],
10074
10240
  cost: {
10075
- input: 0.27,
10076
- output: 0.39999999999999997,
10077
- cacheRead: 0,
10241
+ input: 0.26,
10242
+ output: 0.38,
10243
+ cacheRead: 0.13,
10078
10244
  cacheWrite: 0,
10079
10245
  },
10080
- contextWindow: 163840,
10081
- maxTokens: 163840,
10246
+ contextWindow: 128000,
10247
+ maxTokens: 8000,
10082
10248
  },
10083
10249
  "deepseek/deepseek-v3.2-thinking": {
10084
10250
  id: "deepseek/deepseek-v3.2-thinking",
@@ -10437,6 +10603,23 @@ export const MODELS = {
10437
10603
  contextWindow: 204800,
10438
10604
  maxTokens: 131072,
10439
10605
  },
10606
+ "minimax/minimax-m2.5": {
10607
+ id: "minimax/minimax-m2.5",
10608
+ name: "MiniMax M2.5",
10609
+ api: "anthropic-messages",
10610
+ provider: "vercel-ai-gateway",
10611
+ baseUrl: "https://ai-gateway.vercel.sh",
10612
+ reasoning: true,
10613
+ input: ["text"],
10614
+ cost: {
10615
+ input: 0.3,
10616
+ output: 1.2,
10617
+ cacheRead: 0.03,
10618
+ cacheWrite: 0.375,
10619
+ },
10620
+ contextWindow: 204800,
10621
+ maxTokens: 131000,
10622
+ },
10440
10623
  "mistral/codestral": {
10441
10624
  id: "mistral/codestral",
10442
10625
  name: "Mistral Codestral",
@@ -10958,7 +11141,7 @@ export const MODELS = {
10958
11141
  cost: {
10959
11142
  input: 1.25,
10960
11143
  output: 10,
10961
- cacheRead: 0.125,
11144
+ cacheRead: 0.13,
10962
11145
  cacheWrite: 0,
10963
11146
  },
10964
11147
  contextWindow: 400000,
@@ -11678,6 +11861,23 @@ export const MODELS = {
11678
11861
  contextWindow: 200000,
11679
11862
  maxTokens: 128000,
11680
11863
  },
11864
+ "zai/glm-5": {
11865
+ id: "zai/glm-5",
11866
+ name: "GLM-5",
11867
+ api: "anthropic-messages",
11868
+ provider: "vercel-ai-gateway",
11869
+ baseUrl: "https://ai-gateway.vercel.sh",
11870
+ reasoning: true,
11871
+ input: ["text"],
11872
+ cost: {
11873
+ input: 1,
11874
+ output: 3.1999999999999997,
11875
+ cacheRead: 0.19999999999999998,
11876
+ cacheWrite: 0,
11877
+ },
11878
+ contextWindow: 202800,
11879
+ maxTokens: 131072,
11880
+ },
11681
11881
  },
11682
11882
  "xai": {
11683
11883
  "grok-2": {
@@ -12200,6 +12400,24 @@ export const MODELS = {
12200
12400
  contextWindow: 200000,
12201
12401
  maxTokens: 131072,
12202
12402
  },
12403
+ "glm-5": {
12404
+ id: "glm-5",
12405
+ name: "GLM-5",
12406
+ api: "openai-completions",
12407
+ provider: "zai",
12408
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
12409
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
12410
+ reasoning: true,
12411
+ input: ["text"],
12412
+ cost: {
12413
+ input: 1,
12414
+ output: 3.2,
12415
+ cacheRead: 0.2,
12416
+ cacheWrite: 0,
12417
+ },
12418
+ contextWindow: 204800,
12419
+ maxTokens: 131072,
12420
+ },
12203
12421
  },
12204
12422
  };
12205
12423
  //# sourceMappingURL=models.generated.js.map