@draht/ai 2026.4.23 → 2026.4.25

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 (50) hide show
  1. package/README.md +4 -4
  2. package/dist/cli.js +0 -0
  3. package/dist/models.d.ts +7 -1
  4. package/dist/models.d.ts.map +1 -1
  5. package/dist/models.generated.d.ts +360 -209
  6. package/dist/models.generated.d.ts.map +1 -1
  7. package/dist/models.generated.js +374 -195
  8. package/dist/models.generated.js.map +1 -1
  9. package/dist/models.js +20 -2
  10. package/dist/models.js.map +1 -1
  11. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  12. package/dist/providers/amazon-bedrock.js +9 -5
  13. package/dist/providers/amazon-bedrock.js.map +1 -1
  14. package/dist/providers/anthropic.d.ts.map +1 -1
  15. package/dist/providers/anthropic.js +6 -3
  16. package/dist/providers/anthropic.js.map +1 -1
  17. package/dist/providers/azure-openai-responses.d.ts.map +1 -1
  18. package/dist/providers/azure-openai-responses.js +2 -2
  19. package/dist/providers/azure-openai-responses.js.map +1 -1
  20. package/dist/providers/google-gemini-cli.d.ts.map +1 -1
  21. package/dist/providers/google-gemini-cli.js.map +1 -1
  22. package/dist/providers/google-vertex.d.ts.map +1 -1
  23. package/dist/providers/google-vertex.js.map +1 -1
  24. package/dist/providers/google.d.ts.map +1 -1
  25. package/dist/providers/google.js.map +1 -1
  26. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  27. package/dist/providers/openai-codex-responses.js +2 -2
  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 +16 -10
  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 +2 -2
  34. package/dist/providers/openai-responses.js.map +1 -1
  35. package/dist/providers/simple-options.d.ts +6 -1
  36. package/dist/providers/simple-options.d.ts.map +1 -1
  37. package/dist/providers/simple-options.js +10 -1
  38. package/dist/providers/simple-options.js.map +1 -1
  39. package/dist/types.d.ts +1 -1
  40. package/dist/types.d.ts.map +1 -1
  41. package/dist/types.js.map +1 -1
  42. package/dist/utils/oauth/index.d.ts +1 -0
  43. package/dist/utils/oauth/index.d.ts.map +1 -1
  44. package/dist/utils/oauth/index.js +4 -0
  45. package/dist/utils/oauth/index.js.map +1 -1
  46. package/dist/utils/oauth/opencode-go.d.ts +23 -0
  47. package/dist/utils/oauth/opencode-go.d.ts.map +1 -0
  48. package/dist/utils/oauth/opencode-go.js +46 -0
  49. package/dist/utils/oauth/opencode-go.js.map +1 -0
  50. package/package.json +1 -1
@@ -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",
@@ -3134,6 +3185,24 @@ export const MODELS = {
3134
3185
  contextWindow: 400000,
3135
3186
  maxTokens: 128000,
3136
3187
  },
3188
+ "gpt-5.5": {
3189
+ id: "gpt-5.5",
3190
+ name: "GPT-5.5",
3191
+ api: "openai-responses",
3192
+ provider: "github-copilot",
3193
+ baseUrl: "https://api.individual.githubcopilot.com",
3194
+ 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" },
3195
+ reasoning: true,
3196
+ input: ["text", "image"],
3197
+ cost: {
3198
+ input: 0,
3199
+ output: 0,
3200
+ cacheRead: 0,
3201
+ cacheWrite: 0,
3202
+ },
3203
+ contextWindow: 400000,
3204
+ maxTokens: 128000,
3205
+ },
3137
3206
  "grok-code-fast-1": {
3138
3207
  id: "grok-code-fast-1",
3139
3208
  name: "Grok Code Fast 1",
@@ -5899,6 +5968,23 @@ export const MODELS = {
5899
5968
  contextWindow: 1050000,
5900
5969
  maxTokens: 128000,
5901
5970
  },
5971
+ "gpt-5.5": {
5972
+ id: "gpt-5.5",
5973
+ name: "GPT-5.5",
5974
+ api: "openai-responses",
5975
+ provider: "openai",
5976
+ baseUrl: "https://api.openai.com/v1",
5977
+ reasoning: true,
5978
+ input: ["text", "image"],
5979
+ cost: {
5980
+ input: 5,
5981
+ output: 30,
5982
+ cacheRead: 0.5,
5983
+ cacheWrite: 0,
5984
+ },
5985
+ contextWindow: 1050000,
5986
+ maxTokens: 130000,
5987
+ },
5902
5988
  "o1": {
5903
5989
  id: "o1",
5904
5990
  name: "o1",
@@ -6668,9 +6754,43 @@ export const MODELS = {
6668
6754
  contextWindow: 1050000,
6669
6755
  maxTokens: 128000,
6670
6756
  },
6757
+ "gpt-5.5": {
6758
+ id: "gpt-5.5",
6759
+ name: "GPT-5.5",
6760
+ api: "openai-responses",
6761
+ provider: "opencode",
6762
+ baseUrl: "https://opencode.ai/zen/v1",
6763
+ reasoning: true,
6764
+ input: ["text", "image"],
6765
+ cost: {
6766
+ input: 5,
6767
+ output: 30,
6768
+ cacheRead: 0.5,
6769
+ cacheWrite: 0,
6770
+ },
6771
+ contextWindow: 1050000,
6772
+ maxTokens: 130000,
6773
+ },
6774
+ "gpt-5.5-pro": {
6775
+ id: "gpt-5.5-pro",
6776
+ name: "GPT-5.5 Pro",
6777
+ api: "openai-responses",
6778
+ provider: "opencode",
6779
+ baseUrl: "https://opencode.ai/zen/v1",
6780
+ reasoning: true,
6781
+ input: ["text", "image"],
6782
+ cost: {
6783
+ input: 30,
6784
+ output: 180,
6785
+ cacheRead: 30,
6786
+ cacheWrite: 0,
6787
+ },
6788
+ contextWindow: 1050000,
6789
+ maxTokens: 128000,
6790
+ },
6671
6791
  "hy3-preview-free": {
6672
6792
  id: "hy3-preview-free",
6673
- name: "Hy3 Preview Free",
6793
+ name: "Hy3 preview Free",
6674
6794
  api: "openai-completions",
6675
6795
  provider: "opencode",
6676
6796
  baseUrl: "https://opencode.ai/zen/v1",
@@ -6840,6 +6960,40 @@ export const MODELS = {
6840
6960
  },
6841
6961
  },
6842
6962
  "opencode-go": {
6963
+ "deepseek-v4-flash": {
6964
+ id: "deepseek-v4-flash",
6965
+ name: "DeepSeek V4 Flash",
6966
+ api: "openai-completions",
6967
+ provider: "opencode-go",
6968
+ baseUrl: "https://opencode.ai/zen/go/v1",
6969
+ reasoning: true,
6970
+ input: ["text"],
6971
+ cost: {
6972
+ input: 0.14,
6973
+ output: 0.28,
6974
+ cacheRead: 0.028,
6975
+ cacheWrite: 0,
6976
+ },
6977
+ contextWindow: 1000000,
6978
+ maxTokens: 384000,
6979
+ },
6980
+ "deepseek-v4-pro": {
6981
+ id: "deepseek-v4-pro",
6982
+ name: "DeepSeek V4 Pro",
6983
+ api: "openai-completions",
6984
+ provider: "opencode-go",
6985
+ baseUrl: "https://opencode.ai/zen/go/v1",
6986
+ reasoning: true,
6987
+ input: ["text"],
6988
+ cost: {
6989
+ input: 1.74,
6990
+ output: 3.48,
6991
+ cacheRead: 0.145,
6992
+ cacheWrite: 0,
6993
+ },
6994
+ contextWindow: 1000000,
6995
+ maxTokens: 384000,
6996
+ },
6843
6997
  "glm-5": {
6844
6998
  id: "glm-5",
6845
6999
  name: "GLM-5",
@@ -7095,7 +7249,7 @@ export const MODELS = {
7095
7249
  cacheWrite: 0,
7096
7250
  },
7097
7251
  contextWindow: 65536,
7098
- maxTokens: 4096,
7252
+ maxTokens: 16384,
7099
7253
  },
7100
7254
  "amazon/nova-2-lite-v1": {
7101
7255
  id: "amazon/nova-2-lite-v1",
@@ -7656,7 +7810,7 @@ export const MODELS = {
7656
7810
  cacheWrite: 0,
7657
7811
  },
7658
7812
  contextWindow: 163840,
7659
- maxTokens: 163840,
7813
+ maxTokens: 16384,
7660
7814
  },
7661
7815
  "deepseek/deepseek-chat-v3-0324": {
7662
7816
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7673,7 +7827,7 @@ export const MODELS = {
7673
7827
  cacheWrite: 0,
7674
7828
  },
7675
7829
  contextWindow: 163840,
7676
- maxTokens: 4096,
7830
+ maxTokens: 16384,
7677
7831
  },
7678
7832
  "deepseek/deepseek-chat-v3.1": {
7679
7833
  id: "deepseek/deepseek-chat-v3.1",
@@ -7724,7 +7878,7 @@ export const MODELS = {
7724
7878
  cacheWrite: 0,
7725
7879
  },
7726
7880
  contextWindow: 163840,
7727
- maxTokens: 4096,
7881
+ maxTokens: 32768,
7728
7882
  },
7729
7883
  "deepseek/deepseek-v3.1-terminus": {
7730
7884
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7737,11 +7891,11 @@ export const MODELS = {
7737
7891
  cost: {
7738
7892
  input: 0.21,
7739
7893
  output: 0.7899999999999999,
7740
- cacheRead: 0.1300000002,
7894
+ cacheRead: 0.13,
7741
7895
  cacheWrite: 0,
7742
7896
  },
7743
7897
  contextWindow: 163840,
7744
- maxTokens: 4096,
7898
+ maxTokens: 32768,
7745
7899
  },
7746
7900
  "deepseek/deepseek-v3.2": {
7747
7901
  id: "deepseek/deepseek-v3.2",
@@ -7777,6 +7931,40 @@ export const MODELS = {
7777
7931
  contextWindow: 163840,
7778
7932
  maxTokens: 65536,
7779
7933
  },
7934
+ "deepseek/deepseek-v4-flash": {
7935
+ id: "deepseek/deepseek-v4-flash",
7936
+ name: "DeepSeek: DeepSeek V4 Flash",
7937
+ api: "openai-completions",
7938
+ provider: "openrouter",
7939
+ baseUrl: "https://openrouter.ai/api/v1",
7940
+ reasoning: true,
7941
+ input: ["text"],
7942
+ cost: {
7943
+ input: 0.14,
7944
+ output: 0.28,
7945
+ cacheRead: 0.028,
7946
+ cacheWrite: 0,
7947
+ },
7948
+ contextWindow: 1048576,
7949
+ maxTokens: 384000,
7950
+ },
7951
+ "deepseek/deepseek-v4-pro": {
7952
+ id: "deepseek/deepseek-v4-pro",
7953
+ name: "DeepSeek: DeepSeek V4 Pro",
7954
+ api: "openai-completions",
7955
+ provider: "openrouter",
7956
+ baseUrl: "https://openrouter.ai/api/v1",
7957
+ reasoning: true,
7958
+ input: ["text"],
7959
+ cost: {
7960
+ input: 0.435,
7961
+ output: 0.87,
7962
+ cacheRead: 0.03625,
7963
+ cacheWrite: 0,
7964
+ },
7965
+ contextWindow: 1048576,
7966
+ maxTokens: 384000,
7967
+ },
7780
7968
  "essentialai/rnj-1-instruct": {
7781
7969
  id: "essentialai/rnj-1-instruct",
7782
7970
  name: "EssentialAI: Rnj 1 Instruct",
@@ -7998,6 +8186,40 @@ export const MODELS = {
7998
8186
  contextWindow: 1048576,
7999
8187
  maxTokens: 65536,
8000
8188
  },
8189
+ "google/gemma-3-12b-it": {
8190
+ id: "google/gemma-3-12b-it",
8191
+ name: "Google: Gemma 3 12B",
8192
+ api: "openai-completions",
8193
+ provider: "openrouter",
8194
+ baseUrl: "https://openrouter.ai/api/v1",
8195
+ reasoning: false,
8196
+ input: ["text", "image"],
8197
+ cost: {
8198
+ input: 0.04,
8199
+ output: 0.13,
8200
+ cacheRead: 0,
8201
+ cacheWrite: 0,
8202
+ },
8203
+ contextWindow: 131072,
8204
+ maxTokens: 16384,
8205
+ },
8206
+ "google/gemma-3-27b-it": {
8207
+ id: "google/gemma-3-27b-it",
8208
+ name: "Google: Gemma 3 27B",
8209
+ api: "openai-completions",
8210
+ provider: "openrouter",
8211
+ baseUrl: "https://openrouter.ai/api/v1",
8212
+ reasoning: false,
8213
+ input: ["text", "image"],
8214
+ cost: {
8215
+ input: 0.08,
8216
+ output: 0.16,
8217
+ cacheRead: 0,
8218
+ cacheWrite: 0,
8219
+ },
8220
+ contextWindow: 131072,
8221
+ maxTokens: 16384,
8222
+ },
8001
8223
  "google/gemma-4-26b-a4b-it": {
8002
8224
  id: "google/gemma-4-26b-a4b-it",
8003
8225
  name: "Google: Gemma 4 26B A4B ",
@@ -8047,7 +8269,7 @@ export const MODELS = {
8047
8269
  cacheWrite: 0,
8048
8270
  },
8049
8271
  contextWindow: 262144,
8050
- maxTokens: 4096,
8272
+ maxTokens: 16384,
8051
8273
  },
8052
8274
  "google/gemma-4-31b-it:free": {
8053
8275
  id: "google/gemma-4-31b-it:free",
@@ -8083,6 +8305,23 @@ export const MODELS = {
8083
8305
  contextWindow: 128000,
8084
8306
  maxTokens: 50000,
8085
8307
  },
8308
+ "inclusionai/ling-2.6-1t:free": {
8309
+ id: "inclusionai/ling-2.6-1t:free",
8310
+ name: "inclusionAI: Ling-2.6-1T (free)",
8311
+ api: "openai-completions",
8312
+ provider: "openrouter",
8313
+ baseUrl: "https://openrouter.ai/api/v1",
8314
+ reasoning: false,
8315
+ input: ["text"],
8316
+ cost: {
8317
+ input: 0,
8318
+ output: 0,
8319
+ cacheRead: 0,
8320
+ cacheWrite: 0,
8321
+ },
8322
+ contextWindow: 262144,
8323
+ maxTokens: 32768,
8324
+ },
8086
8325
  "inclusionai/ling-2.6-flash:free": {
8087
8326
  id: "inclusionai/ling-2.6-flash:free",
8088
8327
  name: "inclusionAI: Ling-2.6-flash (free)",
@@ -8149,7 +8388,7 @@ export const MODELS = {
8149
8388
  cacheWrite: 0,
8150
8389
  },
8151
8390
  contextWindow: 131072,
8152
- maxTokens: 4096,
8391
+ maxTokens: 16384,
8153
8392
  },
8154
8393
  "meta-llama/llama-3.1-8b-instruct": {
8155
8394
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8280,12 +8519,12 @@ export const MODELS = {
8280
8519
  input: ["text"],
8281
8520
  cost: {
8282
8521
  input: 0.15,
8283
- output: 1.2,
8284
- cacheRead: 0.075,
8522
+ output: 1.15,
8523
+ cacheRead: 0.03,
8285
8524
  cacheWrite: 0,
8286
8525
  },
8287
8526
  contextWindow: 196608,
8288
- maxTokens: 65536,
8527
+ maxTokens: 131072,
8289
8528
  },
8290
8529
  "minimax/minimax-m2.5:free": {
8291
8530
  id: "minimax/minimax-m2.5:free",
@@ -8608,7 +8847,7 @@ export const MODELS = {
8608
8847
  cacheWrite: 0,
8609
8848
  },
8610
8849
  contextWindow: 128000,
8611
- maxTokens: 4096,
8850
+ maxTokens: 16384,
8612
8851
  },
8613
8852
  "mistralai/mistral-small-creative": {
8614
8853
  id: "mistralai/mistral-small-creative",
@@ -8772,9 +9011,9 @@ export const MODELS = {
8772
9011
  reasoning: true,
8773
9012
  input: ["text", "image"],
8774
9013
  cost: {
8775
- input: 0.56,
8776
- output: 3.5,
8777
- cacheRead: 0.11,
9014
+ input: 0.7448,
9015
+ output: 4.655,
9016
+ cacheRead: 0.1463,
8778
9017
  cacheWrite: 0,
8779
9018
  },
8780
9019
  contextWindow: 256000,
@@ -8829,7 +9068,7 @@ export const MODELS = {
8829
9068
  cacheWrite: 0,
8830
9069
  },
8831
9070
  contextWindow: 131072,
8832
- maxTokens: 4096,
9071
+ maxTokens: 16384,
8833
9072
  },
8834
9073
  "nvidia/nemotron-3-nano-30b-a3b": {
8835
9074
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8846,7 +9085,7 @@ export const MODELS = {
8846
9085
  cacheWrite: 0,
8847
9086
  },
8848
9087
  contextWindow: 262144,
8849
- maxTokens: 4096,
9088
+ maxTokens: 228000,
8850
9089
  },
8851
9090
  "nvidia/nemotron-3-nano-30b-a3b:free": {
8852
9091
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8931,7 +9170,7 @@ export const MODELS = {
8931
9170
  cacheWrite: 0,
8932
9171
  },
8933
9172
  contextWindow: 131072,
8934
- maxTokens: 4096,
9173
+ maxTokens: 16384,
8935
9174
  },
8936
9175
  "nvidia/nemotron-nano-9b-v2:free": {
8937
9176
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9596,6 +9835,40 @@ export const MODELS = {
9596
9835
  contextWindow: 1050000,
9597
9836
  maxTokens: 128000,
9598
9837
  },
9838
+ "openai/gpt-5.5": {
9839
+ id: "openai/gpt-5.5",
9840
+ name: "OpenAI: GPT-5.5",
9841
+ api: "openai-completions",
9842
+ provider: "openrouter",
9843
+ baseUrl: "https://openrouter.ai/api/v1",
9844
+ reasoning: true,
9845
+ input: ["text", "image"],
9846
+ cost: {
9847
+ input: 5,
9848
+ output: 30,
9849
+ cacheRead: 0.5,
9850
+ cacheWrite: 0,
9851
+ },
9852
+ contextWindow: 1050000,
9853
+ maxTokens: 128000,
9854
+ },
9855
+ "openai/gpt-5.5-pro": {
9856
+ id: "openai/gpt-5.5-pro",
9857
+ name: "OpenAI: GPT-5.5 Pro",
9858
+ api: "openai-completions",
9859
+ provider: "openrouter",
9860
+ baseUrl: "https://openrouter.ai/api/v1",
9861
+ reasoning: true,
9862
+ input: ["text", "image"],
9863
+ cost: {
9864
+ input: 30,
9865
+ output: 180,
9866
+ cacheRead: 0,
9867
+ cacheWrite: 0,
9868
+ },
9869
+ contextWindow: 1050000,
9870
+ maxTokens: 128000,
9871
+ },
9599
9872
  "openai/gpt-audio": {
9600
9873
  id: "openai/gpt-audio",
9601
9874
  name: "OpenAI: GPT Audio",
@@ -9645,7 +9918,7 @@ export const MODELS = {
9645
9918
  cacheWrite: 0,
9646
9919
  },
9647
9920
  contextWindow: 131072,
9648
- maxTokens: 4096,
9921
+ maxTokens: 131072,
9649
9922
  },
9650
9923
  "openai/gpt-oss-120b:free": {
9651
9924
  id: "openai/gpt-oss-120b:free",
@@ -9679,7 +9952,7 @@ export const MODELS = {
9679
9952
  cacheWrite: 0,
9680
9953
  },
9681
9954
  contextWindow: 131072,
9682
- maxTokens: 4096,
9955
+ maxTokens: 131072,
9683
9956
  },
9684
9957
  "openai/gpt-oss-20b:free": {
9685
9958
  id: "openai/gpt-oss-20b:free",
@@ -10104,7 +10377,7 @@ export const MODELS = {
10104
10377
  cacheWrite: 0,
10105
10378
  },
10106
10379
  contextWindow: 262144,
10107
- maxTokens: 4096,
10380
+ maxTokens: 16384,
10108
10381
  },
10109
10382
  "qwen/qwen3-235b-a22b-thinking-2507": {
10110
10383
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10138,7 +10411,7 @@ export const MODELS = {
10138
10411
  cacheWrite: 0,
10139
10412
  },
10140
10413
  contextWindow: 40960,
10141
- maxTokens: 40960,
10414
+ maxTokens: 16384,
10142
10415
  },
10143
10416
  "qwen/qwen3-30b-a3b-instruct-2507": {
10144
10417
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10223,7 +10496,7 @@ export const MODELS = {
10223
10496
  cacheWrite: 0,
10224
10497
  },
10225
10498
  contextWindow: 262144,
10226
- maxTokens: 4096,
10499
+ maxTokens: 65536,
10227
10500
  },
10228
10501
  "qwen/qwen3-coder-30b-a3b-instruct": {
10229
10502
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10268,9 +10541,9 @@ export const MODELS = {
10268
10541
  reasoning: false,
10269
10542
  input: ["text"],
10270
10543
  cost: {
10271
- input: 0.15,
10544
+ input: 0.14,
10272
10545
  output: 0.7999999999999999,
10273
- cacheRead: 0.11,
10546
+ cacheRead: 0.09,
10274
10547
  cacheWrite: 0,
10275
10548
  },
10276
10549
  contextWindow: 262144,
@@ -10359,7 +10632,7 @@ export const MODELS = {
10359
10632
  cacheWrite: 0,
10360
10633
  },
10361
10634
  contextWindow: 262144,
10362
- maxTokens: 4096,
10635
+ maxTokens: 16384,
10363
10636
  },
10364
10637
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10365
10638
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10410,7 +10683,7 @@ export const MODELS = {
10410
10683
  cacheWrite: 0,
10411
10684
  },
10412
10685
  contextWindow: 262144,
10413
- maxTokens: 4096,
10686
+ maxTokens: 16384,
10414
10687
  },
10415
10688
  "qwen/qwen3-vl-235b-a22b-thinking": {
10416
10689
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -11188,11 +11461,11 @@ export const MODELS = {
11188
11461
  cost: {
11189
11462
  input: 0.3,
11190
11463
  output: 0.8999999999999999,
11191
- cacheRead: 0,
11464
+ cacheRead: 0.049999999999999996,
11192
11465
  cacheWrite: 0,
11193
11466
  },
11194
11467
  contextWindow: 131072,
11195
- maxTokens: 131072,
11468
+ maxTokens: 24000,
11196
11469
  },
11197
11470
  "z-ai/glm-4.7": {
11198
11471
  id: "z-ai/glm-4.7",
@@ -11222,11 +11495,11 @@ export const MODELS = {
11222
11495
  cost: {
11223
11496
  input: 0.06,
11224
11497
  output: 0.39999999999999997,
11225
- cacheRead: 0.0100000002,
11498
+ cacheRead: 0.01,
11226
11499
  cacheWrite: 0,
11227
11500
  },
11228
11501
  contextWindow: 202752,
11229
- maxTokens: 4096,
11502
+ maxTokens: 16384,
11230
11503
  },
11231
11504
  "z-ai/glm-5": {
11232
11505
  id: "z-ai/glm-5",
@@ -11243,7 +11516,7 @@ export const MODELS = {
11243
11516
  cacheWrite: 0,
11244
11517
  },
11245
11518
  contextWindow: 202752,
11246
- maxTokens: 4096,
11519
+ maxTokens: 16384,
11247
11520
  },
11248
11521
  "z-ai/glm-5-turbo": {
11249
11522
  id: "z-ai/glm-5-turbo",
@@ -11978,6 +12251,40 @@ export const MODELS = {
11978
12251
  contextWindow: 128000,
11979
12252
  maxTokens: 64000,
11980
12253
  },
12254
+ "deepseek/deepseek-v4-flash": {
12255
+ id: "deepseek/deepseek-v4-flash",
12256
+ name: "DeepSeek V4 Flash",
12257
+ api: "anthropic-messages",
12258
+ provider: "vercel-ai-gateway",
12259
+ baseUrl: "https://ai-gateway.vercel.sh",
12260
+ reasoning: true,
12261
+ input: ["text"],
12262
+ cost: {
12263
+ input: 0.14,
12264
+ output: 0.28,
12265
+ cacheRead: 0.028,
12266
+ cacheWrite: 0,
12267
+ },
12268
+ contextWindow: 1000000,
12269
+ maxTokens: 384000,
12270
+ },
12271
+ "deepseek/deepseek-v4-pro": {
12272
+ id: "deepseek/deepseek-v4-pro",
12273
+ name: "DeepSeek V4 Pro",
12274
+ api: "anthropic-messages",
12275
+ provider: "vercel-ai-gateway",
12276
+ baseUrl: "https://ai-gateway.vercel.sh",
12277
+ reasoning: true,
12278
+ input: ["text"],
12279
+ cost: {
12280
+ input: 1.74,
12281
+ output: 3.48,
12282
+ cacheRead: 0.145,
12283
+ cacheWrite: 0,
12284
+ },
12285
+ contextWindow: 1000000,
12286
+ maxTokens: 384000,
12287
+ },
11981
12288
  "google/gemini-2.0-flash": {
11982
12289
  id: "google/gemini-2.0-flash",
11983
12290
  name: "Gemini 2.0 Flash",
@@ -13253,6 +13560,40 @@ export const MODELS = {
13253
13560
  contextWindow: 1050000,
13254
13561
  maxTokens: 128000,
13255
13562
  },
13563
+ "openai/gpt-5.5": {
13564
+ id: "openai/gpt-5.5",
13565
+ name: "GPT 5.5",
13566
+ api: "anthropic-messages",
13567
+ provider: "vercel-ai-gateway",
13568
+ baseUrl: "https://ai-gateway.vercel.sh",
13569
+ reasoning: true,
13570
+ input: ["text", "image"],
13571
+ cost: {
13572
+ input: 5,
13573
+ output: 30,
13574
+ cacheRead: 0.5,
13575
+ cacheWrite: 0,
13576
+ },
13577
+ contextWindow: 1000000,
13578
+ maxTokens: 128000,
13579
+ },
13580
+ "openai/gpt-5.5-pro": {
13581
+ id: "openai/gpt-5.5-pro",
13582
+ name: "GPT 5.5 Pro",
13583
+ api: "anthropic-messages",
13584
+ provider: "vercel-ai-gateway",
13585
+ baseUrl: "https://ai-gateway.vercel.sh",
13586
+ reasoning: true,
13587
+ input: ["text", "image"],
13588
+ cost: {
13589
+ input: 30,
13590
+ output: 180,
13591
+ cacheRead: 0,
13592
+ cacheWrite: 0,
13593
+ },
13594
+ contextWindow: 1000000,
13595
+ maxTokens: 128000,
13596
+ },
13256
13597
  "openai/gpt-oss-20b": {
13257
13598
  id: "openai/gpt-oss-20b",
13258
13599
  name: "GPT OSS 120B",
@@ -14379,24 +14720,6 @@ export const MODELS = {
14379
14720
  },
14380
14721
  },
14381
14722
  "zai": {
14382
- "glm-4.5": {
14383
- id: "glm-4.5",
14384
- name: "GLM-4.5",
14385
- api: "openai-completions",
14386
- provider: "zai",
14387
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14388
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14389
- reasoning: true,
14390
- input: ["text"],
14391
- cost: {
14392
- input: 0,
14393
- output: 0,
14394
- cacheRead: 0,
14395
- cacheWrite: 0,
14396
- },
14397
- contextWindow: 131072,
14398
- maxTokens: 98304,
14399
- },
14400
14723
  "glm-4.5-air": {
14401
14724
  id: "glm-4.5-air",
14402
14725
  name: "GLM-4.5-Air",
@@ -14415,78 +14738,6 @@ export const MODELS = {
14415
14738
  contextWindow: 131072,
14416
14739
  maxTokens: 98304,
14417
14740
  },
14418
- "glm-4.5-flash": {
14419
- id: "glm-4.5-flash",
14420
- name: "GLM-4.5-Flash",
14421
- api: "openai-completions",
14422
- provider: "zai",
14423
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14424
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14425
- reasoning: true,
14426
- input: ["text"],
14427
- cost: {
14428
- input: 0,
14429
- output: 0,
14430
- cacheRead: 0,
14431
- cacheWrite: 0,
14432
- },
14433
- contextWindow: 131072,
14434
- maxTokens: 98304,
14435
- },
14436
- "glm-4.5v": {
14437
- id: "glm-4.5v",
14438
- name: "GLM-4.5V",
14439
- api: "openai-completions",
14440
- provider: "zai",
14441
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14442
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14443
- reasoning: true,
14444
- input: ["text", "image"],
14445
- cost: {
14446
- input: 0,
14447
- output: 0,
14448
- cacheRead: 0,
14449
- cacheWrite: 0,
14450
- },
14451
- contextWindow: 64000,
14452
- maxTokens: 16384,
14453
- },
14454
- "glm-4.6": {
14455
- id: "glm-4.6",
14456
- name: "GLM-4.6",
14457
- api: "openai-completions",
14458
- provider: "zai",
14459
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14460
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14461
- reasoning: true,
14462
- input: ["text"],
14463
- cost: {
14464
- input: 0,
14465
- output: 0,
14466
- cacheRead: 0,
14467
- cacheWrite: 0,
14468
- },
14469
- contextWindow: 204800,
14470
- maxTokens: 131072,
14471
- },
14472
- "glm-4.6v": {
14473
- id: "glm-4.6v",
14474
- name: "GLM-4.6V",
14475
- api: "openai-completions",
14476
- provider: "zai",
14477
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14478
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14479
- reasoning: true,
14480
- input: ["text", "image"],
14481
- cost: {
14482
- input: 0,
14483
- output: 0,
14484
- cacheRead: 0,
14485
- cacheWrite: 0,
14486
- },
14487
- contextWindow: 128000,
14488
- maxTokens: 32768,
14489
- },
14490
14741
  "glm-4.7": {
14491
14742
  id: "glm-4.7",
14492
14743
  name: "GLM-4.7",
@@ -14505,60 +14756,6 @@ export const MODELS = {
14505
14756
  contextWindow: 204800,
14506
14757
  maxTokens: 131072,
14507
14758
  },
14508
- "glm-4.7-flash": {
14509
- id: "glm-4.7-flash",
14510
- name: "GLM-4.7-Flash",
14511
- api: "openai-completions",
14512
- provider: "zai",
14513
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14514
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14515
- reasoning: true,
14516
- input: ["text"],
14517
- cost: {
14518
- input: 0,
14519
- output: 0,
14520
- cacheRead: 0,
14521
- cacheWrite: 0,
14522
- },
14523
- contextWindow: 200000,
14524
- maxTokens: 131072,
14525
- },
14526
- "glm-4.7-flashx": {
14527
- id: "glm-4.7-flashx",
14528
- name: "GLM-4.7-FlashX",
14529
- api: "openai-completions",
14530
- provider: "zai",
14531
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14532
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14533
- reasoning: true,
14534
- input: ["text"],
14535
- cost: {
14536
- input: 0.07,
14537
- output: 0.4,
14538
- cacheRead: 0.01,
14539
- cacheWrite: 0,
14540
- },
14541
- contextWindow: 200000,
14542
- maxTokens: 131072,
14543
- },
14544
- "glm-5": {
14545
- id: "glm-5",
14546
- name: "GLM-5",
14547
- api: "openai-completions",
14548
- provider: "zai",
14549
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14550
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14551
- reasoning: true,
14552
- input: ["text"],
14553
- cost: {
14554
- input: 0,
14555
- output: 0,
14556
- cacheRead: 0,
14557
- cacheWrite: 0,
14558
- },
14559
- contextWindow: 204800,
14560
- maxTokens: 131072,
14561
- },
14562
14759
  "glm-5-turbo": {
14563
14760
  id: "glm-5-turbo",
14564
14761
  name: "GLM-5-Turbo",
@@ -14595,24 +14792,6 @@ export const MODELS = {
14595
14792
  contextWindow: 200000,
14596
14793
  maxTokens: 131072,
14597
14794
  },
14598
- "glm-5v-turbo": {
14599
- id: "glm-5v-turbo",
14600
- name: "glm-5v-turbo",
14601
- api: "openai-completions",
14602
- provider: "zai",
14603
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14604
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14605
- reasoning: true,
14606
- input: ["text", "image"],
14607
- cost: {
14608
- input: 0,
14609
- output: 0,
14610
- cacheRead: 0,
14611
- cacheWrite: 0,
14612
- },
14613
- contextWindow: 200000,
14614
- maxTokens: 131072,
14615
- },
14616
14795
  },
14617
14796
  };
14618
14797
  //# sourceMappingURL=models.generated.js.map