omk-ai 0.94.1 → 0.95.1

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 (33) hide show
  1. package/dist/models.generated.d.ts +720 -283
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +729 -440
  4. package/dist/models.generated.js.map +1 -1
  5. package/dist/providers/anthropic-image-guard.d.ts +42 -0
  6. package/dist/providers/anthropic-image-guard.d.ts.map +1 -0
  7. package/dist/providers/anthropic-image-guard.js +151 -0
  8. package/dist/providers/anthropic-image-guard.js.map +1 -0
  9. package/dist/providers/anthropic.d.ts.map +1 -1
  10. package/dist/providers/anthropic.js +40 -1
  11. package/dist/providers/anthropic.js.map +1 -1
  12. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  13. package/dist/providers/openai-codex-responses.js +99 -8
  14. package/dist/providers/openai-codex-responses.js.map +1 -1
  15. package/dist/providers/simple-options.d.ts.map +1 -1
  16. package/dist/providers/simple-options.js +1 -0
  17. package/dist/providers/simple-options.js.map +1 -1
  18. package/dist/types.d.ts +15 -0
  19. package/dist/types.d.ts.map +1 -1
  20. package/dist/types.js.map +1 -1
  21. package/dist/utils/oauth/anthropic.d.ts.map +1 -1
  22. package/dist/utils/oauth/anthropic.js +47 -4
  23. package/dist/utils/oauth/anthropic.js.map +1 -1
  24. package/dist/utils/oauth/openai-codex.d.ts.map +1 -1
  25. package/dist/utils/oauth/openai-codex.js +22 -2
  26. package/dist/utils/oauth/openai-codex.js.map +1 -1
  27. package/dist/utils/oauth/types.d.ts +2 -0
  28. package/dist/utils/oauth/types.d.ts.map +1 -1
  29. package/dist/utils/oauth/types.js.map +1 -1
  30. package/dist/utils/retry.d.ts.map +1 -1
  31. package/dist/utils/retry.js +1 -0
  32. package/dist/utils/retry.js.map +1 -1
  33. package/package.json +2 -1
@@ -4469,7 +4469,7 @@ export declare const MODELS: {
4469
4469
  contextWindow: number;
4470
4470
  maxTokens: number;
4471
4471
  };
4472
- readonly "accounts/fireworks/models/glm-5p1": {
4472
+ readonly "accounts/fireworks/models/glm-5p2": {
4473
4473
  id: string;
4474
4474
  name: string;
4475
4475
  api: "anthropic-messages";
@@ -4492,7 +4492,7 @@ export declare const MODELS: {
4492
4492
  contextWindow: number;
4493
4493
  maxTokens: number;
4494
4494
  };
4495
- readonly "accounts/fireworks/models/glm-5p2": {
4495
+ readonly "accounts/fireworks/models/gpt-oss-120b": {
4496
4496
  id: string;
4497
4497
  name: string;
4498
4498
  api: "anthropic-messages";
@@ -4515,7 +4515,7 @@ export declare const MODELS: {
4515
4515
  contextWindow: number;
4516
4516
  maxTokens: number;
4517
4517
  };
4518
- readonly "accounts/fireworks/models/gpt-oss-120b": {
4518
+ readonly "accounts/fireworks/models/gpt-oss-20b": {
4519
4519
  id: string;
4520
4520
  name: string;
4521
4521
  api: "anthropic-messages";
@@ -4538,7 +4538,7 @@ export declare const MODELS: {
4538
4538
  contextWindow: number;
4539
4539
  maxTokens: number;
4540
4540
  };
4541
- readonly "accounts/fireworks/models/gpt-oss-20b": {
4541
+ readonly "accounts/fireworks/models/kimi-k2p6": {
4542
4542
  id: string;
4543
4543
  name: string;
4544
4544
  api: "anthropic-messages";
@@ -4551,7 +4551,7 @@ export declare const MODELS: {
4551
4551
  supportsLongCacheRetention: false;
4552
4552
  };
4553
4553
  reasoning: true;
4554
- input: "text"[];
4554
+ input: ("image" | "text")[];
4555
4555
  cost: {
4556
4556
  input: number;
4557
4557
  output: number;
@@ -4561,7 +4561,7 @@ export declare const MODELS: {
4561
4561
  contextWindow: number;
4562
4562
  maxTokens: number;
4563
4563
  };
4564
- readonly "accounts/fireworks/models/kimi-k2p6": {
4564
+ readonly "accounts/fireworks/models/kimi-k2p7-code": {
4565
4565
  id: string;
4566
4566
  name: string;
4567
4567
  api: "anthropic-messages";
@@ -4584,7 +4584,7 @@ export declare const MODELS: {
4584
4584
  contextWindow: number;
4585
4585
  maxTokens: number;
4586
4586
  };
4587
- readonly "accounts/fireworks/models/kimi-k2p7-code": {
4587
+ readonly "accounts/fireworks/models/kimi-k3": {
4588
4588
  id: string;
4589
4589
  name: string;
4590
4590
  api: "anthropic-messages";
@@ -4680,7 +4680,7 @@ export declare const MODELS: {
4680
4680
  contextWindow: number;
4681
4681
  maxTokens: number;
4682
4682
  };
4683
- readonly "accounts/fireworks/routers/glm-5p1-fast": {
4683
+ readonly "accounts/fireworks/routers/glm-5p2-fast": {
4684
4684
  id: string;
4685
4685
  name: string;
4686
4686
  api: "anthropic-messages";
@@ -4703,7 +4703,7 @@ export declare const MODELS: {
4703
4703
  contextWindow: number;
4704
4704
  maxTokens: number;
4705
4705
  };
4706
- readonly "accounts/fireworks/routers/glm-5p2-fast": {
4706
+ readonly "accounts/fireworks/routers/kimi-k2p6-fast": {
4707
4707
  id: string;
4708
4708
  name: string;
4709
4709
  api: "anthropic-messages";
@@ -4716,7 +4716,7 @@ export declare const MODELS: {
4716
4716
  supportsLongCacheRetention: false;
4717
4717
  };
4718
4718
  reasoning: true;
4719
- input: "text"[];
4719
+ input: ("image" | "text")[];
4720
4720
  cost: {
4721
4721
  input: number;
4722
4722
  output: number;
@@ -4726,7 +4726,7 @@ export declare const MODELS: {
4726
4726
  contextWindow: number;
4727
4727
  maxTokens: number;
4728
4728
  };
4729
- readonly "accounts/fireworks/routers/kimi-k2p6-fast": {
4729
+ readonly "accounts/fireworks/routers/kimi-k2p6-turbo": {
4730
4730
  id: string;
4731
4731
  name: string;
4732
4732
  api: "anthropic-messages";
@@ -4749,7 +4749,7 @@ export declare const MODELS: {
4749
4749
  contextWindow: number;
4750
4750
  maxTokens: number;
4751
4751
  };
4752
- readonly "accounts/fireworks/routers/kimi-k2p6-turbo": {
4752
+ readonly "accounts/fireworks/routers/kimi-k2p7-code-fast": {
4753
4753
  id: string;
4754
4754
  name: string;
4755
4755
  api: "anthropic-messages";
@@ -4772,7 +4772,7 @@ export declare const MODELS: {
4772
4772
  contextWindow: number;
4773
4773
  maxTokens: number;
4774
4774
  };
4775
- readonly "accounts/fireworks/routers/kimi-k2p7-code-fast": {
4775
+ readonly "accounts/fireworks/routers/kimi-k3-fast": {
4776
4776
  id: string;
4777
4777
  name: string;
4778
4778
  api: "anthropic-messages";
@@ -7235,6 +7235,26 @@ export declare const MODELS: {
7235
7235
  contextWindow: number;
7236
7236
  maxTokens: number;
7237
7237
  };
7238
+ readonly "moonshotai/Kimi-K3": {
7239
+ id: string;
7240
+ name: string;
7241
+ api: "openai-completions";
7242
+ provider: string;
7243
+ baseUrl: string;
7244
+ compat: {
7245
+ supportsDeveloperRole: false;
7246
+ };
7247
+ reasoning: true;
7248
+ input: ("image" | "text")[];
7249
+ cost: {
7250
+ input: number;
7251
+ output: number;
7252
+ cacheRead: number;
7253
+ cacheWrite: number;
7254
+ };
7255
+ contextWindow: number;
7256
+ maxTokens: number;
7257
+ };
7238
7258
  readonly "openai/gpt-oss-120b": {
7239
7259
  id: string;
7240
7260
  name: string;
@@ -7315,6 +7335,46 @@ export declare const MODELS: {
7315
7335
  contextWindow: number;
7316
7336
  maxTokens: number;
7317
7337
  };
7338
+ readonly "tencent/Hy3": {
7339
+ id: string;
7340
+ name: string;
7341
+ api: "openai-completions";
7342
+ provider: string;
7343
+ baseUrl: string;
7344
+ compat: {
7345
+ supportsDeveloperRole: false;
7346
+ };
7347
+ reasoning: true;
7348
+ input: "text"[];
7349
+ cost: {
7350
+ input: number;
7351
+ output: number;
7352
+ cacheRead: number;
7353
+ cacheWrite: number;
7354
+ };
7355
+ contextWindow: number;
7356
+ maxTokens: number;
7357
+ };
7358
+ readonly "thinkingmachines/Inkling": {
7359
+ id: string;
7360
+ name: string;
7361
+ api: "openai-completions";
7362
+ provider: string;
7363
+ baseUrl: string;
7364
+ compat: {
7365
+ supportsDeveloperRole: false;
7366
+ };
7367
+ reasoning: true;
7368
+ input: ("image" | "text")[];
7369
+ cost: {
7370
+ input: number;
7371
+ output: number;
7372
+ cacheRead: number;
7373
+ cacheWrite: number;
7374
+ };
7375
+ contextWindow: number;
7376
+ maxTokens: number;
7377
+ };
7318
7378
  readonly "zai-org/GLM-4.5": {
7319
7379
  id: string;
7320
7380
  name: string;
@@ -8639,18 +8699,404 @@ export declare const MODELS: {
8639
8699
  contextWindow: number;
8640
8700
  maxTokens: number;
8641
8701
  };
8642
- readonly "kimi-k2.7-code": {
8702
+ readonly "kimi-k2.7-code": {
8703
+ id: string;
8704
+ name: string;
8705
+ api: "openai-completions";
8706
+ provider: string;
8707
+ baseUrl: string;
8708
+ compat: {
8709
+ supportsStore: false;
8710
+ supportsDeveloperRole: false;
8711
+ supportsReasoningEffort: false;
8712
+ maxTokensField: "max_tokens";
8713
+ supportsStrictMode: false;
8714
+ };
8715
+ reasoning: true;
8716
+ input: ("image" | "text")[];
8717
+ cost: {
8718
+ input: number;
8719
+ output: number;
8720
+ cacheRead: number;
8721
+ cacheWrite: number;
8722
+ };
8723
+ contextWindow: number;
8724
+ maxTokens: number;
8725
+ };
8726
+ readonly "kimi-k2.7-code-highspeed": {
8727
+ id: string;
8728
+ name: string;
8729
+ api: "openai-completions";
8730
+ provider: string;
8731
+ baseUrl: string;
8732
+ compat: {
8733
+ supportsStore: false;
8734
+ supportsDeveloperRole: false;
8735
+ supportsReasoningEffort: false;
8736
+ maxTokensField: "max_tokens";
8737
+ supportsStrictMode: false;
8738
+ };
8739
+ reasoning: true;
8740
+ input: ("image" | "text")[];
8741
+ cost: {
8742
+ input: number;
8743
+ output: number;
8744
+ cacheRead: number;
8745
+ cacheWrite: number;
8746
+ };
8747
+ contextWindow: number;
8748
+ maxTokens: number;
8749
+ };
8750
+ readonly "kimi-k3": {
8751
+ id: string;
8752
+ name: string;
8753
+ api: "openai-completions";
8754
+ provider: string;
8755
+ baseUrl: string;
8756
+ compat: {
8757
+ supportsStore: false;
8758
+ supportsDeveloperRole: false;
8759
+ supportsReasoningEffort: false;
8760
+ maxTokensField: "max_tokens";
8761
+ supportsStrictMode: false;
8762
+ };
8763
+ reasoning: true;
8764
+ input: ("image" | "text")[];
8765
+ cost: {
8766
+ input: number;
8767
+ output: number;
8768
+ cacheRead: number;
8769
+ cacheWrite: number;
8770
+ };
8771
+ contextWindow: number;
8772
+ maxTokens: number;
8773
+ };
8774
+ };
8775
+ readonly nvidia: {
8776
+ readonly "google/gemma-3-12b-it": {
8777
+ id: string;
8778
+ name: string;
8779
+ api: "openai-completions";
8780
+ provider: string;
8781
+ baseUrl: string;
8782
+ headers: {
8783
+ "NVCF-POLL-SECONDS": string;
8784
+ };
8785
+ compat: {
8786
+ supportsStore: false;
8787
+ supportsDeveloperRole: false;
8788
+ supportsReasoningEffort: false;
8789
+ maxTokensField: "max_tokens";
8790
+ supportsStrictMode: false;
8791
+ supportsLongCacheRetention: false;
8792
+ };
8793
+ reasoning: false;
8794
+ input: ("image" | "text")[];
8795
+ cost: {
8796
+ input: number;
8797
+ output: number;
8798
+ cacheRead: number;
8799
+ cacheWrite: number;
8800
+ };
8801
+ contextWindow: number;
8802
+ maxTokens: number;
8803
+ };
8804
+ readonly "google/gemma-3-4b-it": {
8805
+ id: string;
8806
+ name: string;
8807
+ api: "openai-completions";
8808
+ provider: string;
8809
+ baseUrl: string;
8810
+ headers: {
8811
+ "NVCF-POLL-SECONDS": string;
8812
+ };
8813
+ compat: {
8814
+ supportsStore: false;
8815
+ supportsDeveloperRole: false;
8816
+ supportsReasoningEffort: false;
8817
+ maxTokensField: "max_tokens";
8818
+ supportsStrictMode: false;
8819
+ supportsLongCacheRetention: false;
8820
+ };
8821
+ reasoning: false;
8822
+ input: ("image" | "text")[];
8823
+ cost: {
8824
+ input: number;
8825
+ output: number;
8826
+ cacheRead: number;
8827
+ cacheWrite: number;
8828
+ };
8829
+ contextWindow: number;
8830
+ maxTokens: number;
8831
+ };
8832
+ readonly "meta/llama-3.1-70b-instruct": {
8833
+ id: string;
8834
+ name: string;
8835
+ api: "openai-completions";
8836
+ provider: string;
8837
+ baseUrl: string;
8838
+ headers: {
8839
+ "NVCF-POLL-SECONDS": string;
8840
+ };
8841
+ compat: {
8842
+ supportsStore: false;
8843
+ supportsDeveloperRole: false;
8844
+ supportsReasoningEffort: false;
8845
+ maxTokensField: "max_tokens";
8846
+ supportsStrictMode: false;
8847
+ supportsLongCacheRetention: false;
8848
+ };
8849
+ reasoning: false;
8850
+ input: "text"[];
8851
+ cost: {
8852
+ input: number;
8853
+ output: number;
8854
+ cacheRead: number;
8855
+ cacheWrite: number;
8856
+ };
8857
+ contextWindow: number;
8858
+ maxTokens: number;
8859
+ };
8860
+ readonly "meta/llama-3.1-8b-instruct": {
8861
+ id: string;
8862
+ name: string;
8863
+ api: "openai-completions";
8864
+ provider: string;
8865
+ baseUrl: string;
8866
+ headers: {
8867
+ "NVCF-POLL-SECONDS": string;
8868
+ };
8869
+ compat: {
8870
+ supportsStore: false;
8871
+ supportsDeveloperRole: false;
8872
+ supportsReasoningEffort: false;
8873
+ maxTokensField: "max_tokens";
8874
+ supportsStrictMode: false;
8875
+ supportsLongCacheRetention: false;
8876
+ };
8877
+ reasoning: false;
8878
+ input: "text"[];
8879
+ cost: {
8880
+ input: number;
8881
+ output: number;
8882
+ cacheRead: number;
8883
+ cacheWrite: number;
8884
+ };
8885
+ contextWindow: number;
8886
+ maxTokens: number;
8887
+ };
8888
+ readonly "meta/llama-3.2-11b-vision-instruct": {
8889
+ id: string;
8890
+ name: string;
8891
+ api: "openai-completions";
8892
+ provider: string;
8893
+ baseUrl: string;
8894
+ headers: {
8895
+ "NVCF-POLL-SECONDS": string;
8896
+ };
8897
+ compat: {
8898
+ supportsStore: false;
8899
+ supportsDeveloperRole: false;
8900
+ supportsReasoningEffort: false;
8901
+ maxTokensField: "max_tokens";
8902
+ supportsStrictMode: false;
8903
+ supportsLongCacheRetention: false;
8904
+ };
8905
+ reasoning: false;
8906
+ input: ("image" | "text")[];
8907
+ cost: {
8908
+ input: number;
8909
+ output: number;
8910
+ cacheRead: number;
8911
+ cacheWrite: number;
8912
+ };
8913
+ contextWindow: number;
8914
+ maxTokens: number;
8915
+ };
8916
+ readonly "meta/llama-3.2-90b-vision-instruct": {
8917
+ id: string;
8918
+ name: string;
8919
+ api: "openai-completions";
8920
+ provider: string;
8921
+ baseUrl: string;
8922
+ headers: {
8923
+ "NVCF-POLL-SECONDS": string;
8924
+ };
8925
+ compat: {
8926
+ supportsStore: false;
8927
+ supportsDeveloperRole: false;
8928
+ supportsReasoningEffort: false;
8929
+ maxTokensField: "max_tokens";
8930
+ supportsStrictMode: false;
8931
+ supportsLongCacheRetention: false;
8932
+ };
8933
+ reasoning: false;
8934
+ input: ("image" | "text")[];
8935
+ cost: {
8936
+ input: number;
8937
+ output: number;
8938
+ cacheRead: number;
8939
+ cacheWrite: number;
8940
+ };
8941
+ contextWindow: number;
8942
+ maxTokens: number;
8943
+ };
8944
+ readonly "meta/llama-3.3-70b-instruct": {
8945
+ id: string;
8946
+ name: string;
8947
+ api: "openai-completions";
8948
+ provider: string;
8949
+ baseUrl: string;
8950
+ headers: {
8951
+ "NVCF-POLL-SECONDS": string;
8952
+ };
8953
+ compat: {
8954
+ supportsStore: false;
8955
+ supportsDeveloperRole: false;
8956
+ supportsReasoningEffort: false;
8957
+ maxTokensField: "max_tokens";
8958
+ supportsStrictMode: false;
8959
+ supportsLongCacheRetention: false;
8960
+ };
8961
+ reasoning: false;
8962
+ input: "text"[];
8963
+ cost: {
8964
+ input: number;
8965
+ output: number;
8966
+ cacheRead: number;
8967
+ cacheWrite: number;
8968
+ };
8969
+ contextWindow: number;
8970
+ maxTokens: number;
8971
+ };
8972
+ readonly "minimaxai/minimax-m3": {
8973
+ id: string;
8974
+ name: string;
8975
+ api: "openai-completions";
8976
+ provider: string;
8977
+ baseUrl: string;
8978
+ headers: {
8979
+ "NVCF-POLL-SECONDS": string;
8980
+ };
8981
+ compat: {
8982
+ supportsStore: false;
8983
+ supportsDeveloperRole: false;
8984
+ supportsReasoningEffort: false;
8985
+ maxTokensField: "max_tokens";
8986
+ supportsStrictMode: false;
8987
+ supportsLongCacheRetention: false;
8988
+ };
8989
+ reasoning: true;
8990
+ input: ("image" | "text")[];
8991
+ cost: {
8992
+ input: number;
8993
+ output: number;
8994
+ cacheRead: number;
8995
+ cacheWrite: number;
8996
+ };
8997
+ contextWindow: number;
8998
+ maxTokens: number;
8999
+ };
9000
+ readonly "mistralai/mistral-7b-instruct-v0.3": {
9001
+ id: string;
9002
+ name: string;
9003
+ api: "openai-completions";
9004
+ provider: string;
9005
+ baseUrl: string;
9006
+ headers: {
9007
+ "NVCF-POLL-SECONDS": string;
9008
+ };
9009
+ compat: {
9010
+ supportsStore: false;
9011
+ supportsDeveloperRole: false;
9012
+ supportsReasoningEffort: false;
9013
+ maxTokensField: "max_tokens";
9014
+ supportsStrictMode: false;
9015
+ supportsLongCacheRetention: false;
9016
+ };
9017
+ reasoning: false;
9018
+ input: "text"[];
9019
+ cost: {
9020
+ input: number;
9021
+ output: number;
9022
+ cacheRead: number;
9023
+ cacheWrite: number;
9024
+ };
9025
+ contextWindow: number;
9026
+ maxTokens: number;
9027
+ };
9028
+ readonly "mistralai/mistral-medium-3.5-128b": {
9029
+ id: string;
9030
+ name: string;
9031
+ api: "openai-completions";
9032
+ provider: string;
9033
+ baseUrl: string;
9034
+ headers: {
9035
+ "NVCF-POLL-SECONDS": string;
9036
+ };
9037
+ compat: {
9038
+ supportsStore: false;
9039
+ supportsDeveloperRole: false;
9040
+ supportsReasoningEffort: false;
9041
+ maxTokensField: "max_tokens";
9042
+ supportsStrictMode: false;
9043
+ supportsLongCacheRetention: false;
9044
+ };
9045
+ reasoning: true;
9046
+ input: ("image" | "text")[];
9047
+ cost: {
9048
+ input: number;
9049
+ output: number;
9050
+ cacheRead: number;
9051
+ cacheWrite: number;
9052
+ };
9053
+ contextWindow: number;
9054
+ maxTokens: number;
9055
+ };
9056
+ readonly "moonshotai/kimi-k2.6": {
9057
+ id: string;
9058
+ name: string;
9059
+ api: "openai-completions";
9060
+ provider: string;
9061
+ baseUrl: string;
9062
+ headers: {
9063
+ "NVCF-POLL-SECONDS": string;
9064
+ };
9065
+ compat: {
9066
+ supportsStore: false;
9067
+ supportsDeveloperRole: false;
9068
+ supportsReasoningEffort: false;
9069
+ maxTokensField: "max_tokens";
9070
+ supportsStrictMode: false;
9071
+ supportsLongCacheRetention: false;
9072
+ };
9073
+ reasoning: true;
9074
+ input: ("image" | "text")[];
9075
+ cost: {
9076
+ input: number;
9077
+ output: number;
9078
+ cacheRead: number;
9079
+ cacheWrite: number;
9080
+ };
9081
+ contextWindow: number;
9082
+ maxTokens: number;
9083
+ };
9084
+ readonly "nvidia/cosmos-reason2-8b": {
8643
9085
  id: string;
8644
9086
  name: string;
8645
9087
  api: "openai-completions";
8646
9088
  provider: string;
8647
9089
  baseUrl: string;
9090
+ headers: {
9091
+ "NVCF-POLL-SECONDS": string;
9092
+ };
8648
9093
  compat: {
8649
9094
  supportsStore: false;
8650
9095
  supportsDeveloperRole: false;
8651
9096
  supportsReasoningEffort: false;
8652
9097
  maxTokensField: "max_tokens";
8653
9098
  supportsStrictMode: false;
9099
+ supportsLongCacheRetention: false;
8654
9100
  };
8655
9101
  reasoning: true;
8656
9102
  input: ("image" | "text")[];
@@ -8663,21 +9109,25 @@ export declare const MODELS: {
8663
9109
  contextWindow: number;
8664
9110
  maxTokens: number;
8665
9111
  };
8666
- readonly "kimi-k2.7-code-highspeed": {
9112
+ readonly "nvidia/llama-3.1-nemotron-70b-instruct": {
8667
9113
  id: string;
8668
9114
  name: string;
8669
9115
  api: "openai-completions";
8670
9116
  provider: string;
8671
9117
  baseUrl: string;
9118
+ headers: {
9119
+ "NVCF-POLL-SECONDS": string;
9120
+ };
8672
9121
  compat: {
8673
9122
  supportsStore: false;
8674
9123
  supportsDeveloperRole: false;
8675
9124
  supportsReasoningEffort: false;
8676
9125
  maxTokensField: "max_tokens";
8677
9126
  supportsStrictMode: false;
9127
+ supportsLongCacheRetention: false;
8678
9128
  };
8679
- reasoning: true;
8680
- input: ("image" | "text")[];
9129
+ reasoning: false;
9130
+ input: "text"[];
8681
9131
  cost: {
8682
9132
  input: number;
8683
9133
  output: number;
@@ -8687,21 +9137,25 @@ export declare const MODELS: {
8687
9137
  contextWindow: number;
8688
9138
  maxTokens: number;
8689
9139
  };
8690
- readonly "kimi-k3": {
9140
+ readonly "nvidia/llama-3.1-nemotron-nano-8b-v1": {
8691
9141
  id: string;
8692
9142
  name: string;
8693
9143
  api: "openai-completions";
8694
9144
  provider: string;
8695
9145
  baseUrl: string;
9146
+ headers: {
9147
+ "NVCF-POLL-SECONDS": string;
9148
+ };
8696
9149
  compat: {
8697
9150
  supportsStore: false;
8698
9151
  supportsDeveloperRole: false;
8699
9152
  supportsReasoningEffort: false;
8700
9153
  maxTokensField: "max_tokens";
8701
9154
  supportsStrictMode: false;
9155
+ supportsLongCacheRetention: false;
8702
9156
  };
8703
9157
  reasoning: true;
8704
- input: ("image" | "text")[];
9158
+ input: "text"[];
8705
9159
  cost: {
8706
9160
  input: number;
8707
9161
  output: number;
@@ -8711,9 +9165,7 @@ export declare const MODELS: {
8711
9165
  contextWindow: number;
8712
9166
  maxTokens: number;
8713
9167
  };
8714
- };
8715
- readonly nvidia: {
8716
- readonly "meta/llama-3.1-70b-instruct": {
9168
+ readonly "nvidia/llama-3.1-nemotron-nano-vl-8b-v1": {
8717
9169
  id: string;
8718
9170
  name: string;
8719
9171
  api: "openai-completions";
@@ -8730,8 +9182,8 @@ export declare const MODELS: {
8730
9182
  supportsStrictMode: false;
8731
9183
  supportsLongCacheRetention: false;
8732
9184
  };
8733
- reasoning: false;
8734
- input: "text"[];
9185
+ reasoning: true;
9186
+ input: ("image" | "text")[];
8735
9187
  cost: {
8736
9188
  input: number;
8737
9189
  output: number;
@@ -8741,7 +9193,7 @@ export declare const MODELS: {
8741
9193
  contextWindow: number;
8742
9194
  maxTokens: number;
8743
9195
  };
8744
- readonly "meta/llama-3.1-8b-instruct": {
9196
+ readonly "nvidia/llama-3.1-nemotron-ultra-253b-v1": {
8745
9197
  id: string;
8746
9198
  name: string;
8747
9199
  api: "openai-completions";
@@ -8758,7 +9210,7 @@ export declare const MODELS: {
8758
9210
  supportsStrictMode: false;
8759
9211
  supportsLongCacheRetention: false;
8760
9212
  };
8761
- reasoning: false;
9213
+ reasoning: true;
8762
9214
  input: "text"[];
8763
9215
  cost: {
8764
9216
  input: number;
@@ -8769,7 +9221,7 @@ export declare const MODELS: {
8769
9221
  contextWindow: number;
8770
9222
  maxTokens: number;
8771
9223
  };
8772
- readonly "meta/llama-3.2-11b-vision-instruct": {
9224
+ readonly "nvidia/llama-3.3-nemotron-super-49b-v1": {
8773
9225
  id: string;
8774
9226
  name: string;
8775
9227
  api: "openai-completions";
@@ -8786,8 +9238,8 @@ export declare const MODELS: {
8786
9238
  supportsStrictMode: false;
8787
9239
  supportsLongCacheRetention: false;
8788
9240
  };
8789
- reasoning: false;
8790
- input: ("image" | "text")[];
9241
+ reasoning: true;
9242
+ input: "text"[];
8791
9243
  cost: {
8792
9244
  input: number;
8793
9245
  output: number;
@@ -8797,7 +9249,7 @@ export declare const MODELS: {
8797
9249
  contextWindow: number;
8798
9250
  maxTokens: number;
8799
9251
  };
8800
- readonly "meta/llama-3.2-90b-vision-instruct": {
9252
+ readonly "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
8801
9253
  id: string;
8802
9254
  name: string;
8803
9255
  api: "openai-completions";
@@ -8814,8 +9266,8 @@ export declare const MODELS: {
8814
9266
  supportsStrictMode: false;
8815
9267
  supportsLongCacheRetention: false;
8816
9268
  };
8817
- reasoning: false;
8818
- input: ("image" | "text")[];
9269
+ reasoning: true;
9270
+ input: "text"[];
8819
9271
  cost: {
8820
9272
  input: number;
8821
9273
  output: number;
@@ -8825,7 +9277,7 @@ export declare const MODELS: {
8825
9277
  contextWindow: number;
8826
9278
  maxTokens: number;
8827
9279
  };
8828
- readonly "meta/llama-3.3-70b-instruct": {
9280
+ readonly "nvidia/nemotron-3-nano-30b-a3b": {
8829
9281
  id: string;
8830
9282
  name: string;
8831
9283
  api: "openai-completions";
@@ -8842,7 +9294,7 @@ export declare const MODELS: {
8842
9294
  supportsStrictMode: false;
8843
9295
  supportsLongCacheRetention: false;
8844
9296
  };
8845
- reasoning: false;
9297
+ reasoning: true;
8846
9298
  input: "text"[];
8847
9299
  cost: {
8848
9300
  input: number;
@@ -8853,7 +9305,7 @@ export declare const MODELS: {
8853
9305
  contextWindow: number;
8854
9306
  maxTokens: number;
8855
9307
  };
8856
- readonly "minimaxai/minimax-m3": {
9308
+ readonly "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
8857
9309
  id: string;
8858
9310
  name: string;
8859
9311
  api: "openai-completions";
@@ -8881,7 +9333,7 @@ export declare const MODELS: {
8881
9333
  contextWindow: number;
8882
9334
  maxTokens: number;
8883
9335
  };
8884
- readonly "moonshotai/kimi-k2.6": {
9336
+ readonly "nvidia/nemotron-3-super-120b-a12b": {
8885
9337
  id: string;
8886
9338
  name: string;
8887
9339
  api: "openai-completions";
@@ -8899,7 +9351,7 @@ export declare const MODELS: {
8899
9351
  supportsLongCacheRetention: false;
8900
9352
  };
8901
9353
  reasoning: true;
8902
- input: ("image" | "text")[];
9354
+ input: "text"[];
8903
9355
  cost: {
8904
9356
  input: number;
8905
9357
  output: number;
@@ -8909,7 +9361,7 @@ export declare const MODELS: {
8909
9361
  contextWindow: number;
8910
9362
  maxTokens: number;
8911
9363
  };
8912
- readonly "nvidia/nemotron-3-nano-30b-a3b": {
9364
+ readonly "nvidia/nemotron-3-ultra-550b-a55b": {
8913
9365
  id: string;
8914
9366
  name: string;
8915
9367
  api: "openai-completions";
@@ -8937,7 +9389,7 @@ export declare const MODELS: {
8937
9389
  contextWindow: number;
8938
9390
  maxTokens: number;
8939
9391
  };
8940
- readonly "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
9392
+ readonly "nvidia/nemotron-nano-12b-v2-vl": {
8941
9393
  id: string;
8942
9394
  name: string;
8943
9395
  api: "openai-completions";
@@ -8965,7 +9417,7 @@ export declare const MODELS: {
8965
9417
  contextWindow: number;
8966
9418
  maxTokens: number;
8967
9419
  };
8968
- readonly "nvidia/nemotron-3-super-120b-a12b": {
9420
+ readonly "nvidia/nvidia-nemotron-nano-9b-v2": {
8969
9421
  id: string;
8970
9422
  name: string;
8971
9423
  api: "openai-completions";
@@ -8993,7 +9445,7 @@ export declare const MODELS: {
8993
9445
  contextWindow: number;
8994
9446
  maxTokens: number;
8995
9447
  };
8996
- readonly "nvidia/nemotron-3-ultra-550b-a55b": {
9448
+ readonly "openai/gpt-oss-120b": {
8997
9449
  id: string;
8998
9450
  name: string;
8999
9451
  api: "openai-completions";
@@ -9021,7 +9473,7 @@ export declare const MODELS: {
9021
9473
  contextWindow: number;
9022
9474
  maxTokens: number;
9023
9475
  };
9024
- readonly "nvidia/nvidia-nemotron-nano-9b-v2": {
9476
+ readonly "openai/gpt-oss-20b": {
9025
9477
  id: string;
9026
9478
  name: string;
9027
9479
  api: "openai-completions";
@@ -9049,7 +9501,7 @@ export declare const MODELS: {
9049
9501
  contextWindow: number;
9050
9502
  maxTokens: number;
9051
9503
  };
9052
- readonly "openai/gpt-oss-120b": {
9504
+ readonly "poolside/laguna-xs-2.1": {
9053
9505
  id: string;
9054
9506
  name: string;
9055
9507
  api: "openai-completions";
@@ -9077,7 +9529,7 @@ export declare const MODELS: {
9077
9529
  contextWindow: number;
9078
9530
  maxTokens: number;
9079
9531
  };
9080
- readonly "openai/gpt-oss-20b": {
9532
+ readonly "stepfun-ai/step-3.7-flash": {
9081
9533
  id: string;
9082
9534
  name: string;
9083
9535
  api: "openai-completions";
@@ -9095,7 +9547,7 @@ export declare const MODELS: {
9095
9547
  supportsLongCacheRetention: false;
9096
9548
  };
9097
9549
  reasoning: true;
9098
- input: "text"[];
9550
+ input: ("image" | "text")[];
9099
9551
  cost: {
9100
9552
  input: number;
9101
9553
  output: number;
@@ -9105,7 +9557,7 @@ export declare const MODELS: {
9105
9557
  contextWindow: number;
9106
9558
  maxTokens: number;
9107
9559
  };
9108
- readonly "stepfun-ai/step-3.7-flash": {
9560
+ readonly "thinkingmachines/inkling": {
9109
9561
  id: string;
9110
9562
  name: string;
9111
9563
  api: "openai-completions";
@@ -11125,6 +11577,23 @@ export declare const MODELS: {
11125
11577
  contextWindow: number;
11126
11578
  maxTokens: number;
11127
11579
  };
11580
+ readonly "kimi-k3": {
11581
+ id: string;
11582
+ name: string;
11583
+ api: "openai-completions";
11584
+ provider: string;
11585
+ baseUrl: string;
11586
+ reasoning: true;
11587
+ input: ("image" | "text")[];
11588
+ cost: {
11589
+ input: number;
11590
+ output: number;
11591
+ cacheRead: number;
11592
+ cacheWrite: number;
11593
+ };
11594
+ contextWindow: number;
11595
+ maxTokens: number;
11596
+ };
11128
11597
  readonly "laguna-s-2.1-free": {
11129
11598
  id: string;
11130
11599
  name: string;
@@ -11395,6 +11864,28 @@ export declare const MODELS: {
11395
11864
  contextWindow: number;
11396
11865
  maxTokens: number;
11397
11866
  };
11867
+ readonly "gpt-5.6-luna": {
11868
+ id: string;
11869
+ name: string;
11870
+ api: "openai-responses";
11871
+ provider: string;
11872
+ baseUrl: string;
11873
+ reasoning: true;
11874
+ thinkingLevelMap: {
11875
+ off: null;
11876
+ xhigh: string;
11877
+ max: string;
11878
+ };
11879
+ input: ("image" | "text")[];
11880
+ cost: {
11881
+ input: number;
11882
+ output: number;
11883
+ cacheRead: number;
11884
+ cacheWrite: number;
11885
+ };
11886
+ contextWindow: number;
11887
+ maxTokens: number;
11888
+ };
11398
11889
  readonly "grok-4.5": {
11399
11890
  id: string;
11400
11891
  name: string;
@@ -12422,6 +12913,33 @@ export declare const MODELS: {
12422
12913
  contextWindow: number;
12423
12914
  maxTokens: number;
12424
12915
  };
12916
+ readonly "deepseek/deepseek-v4-flash-0731": {
12917
+ id: string;
12918
+ name: string;
12919
+ api: "openai-completions";
12920
+ provider: string;
12921
+ baseUrl: string;
12922
+ compat: {
12923
+ requiresReasoningContentOnAssistantMessages: true;
12924
+ };
12925
+ reasoning: true;
12926
+ thinkingLevelMap: {
12927
+ minimal: null;
12928
+ low: null;
12929
+ medium: null;
12930
+ high: string;
12931
+ xhigh: string;
12932
+ };
12933
+ input: "text"[];
12934
+ cost: {
12935
+ input: number;
12936
+ output: number;
12937
+ cacheRead: number;
12938
+ cacheWrite: number;
12939
+ };
12940
+ contextWindow: number;
12941
+ maxTokens: number;
12942
+ };
12425
12943
  readonly "deepseek/deepseek-v4-pro": {
12426
12944
  id: string;
12427
12945
  name: string;
@@ -13183,23 +13701,6 @@ export declare const MODELS: {
13183
13701
  contextWindow: number;
13184
13702
  maxTokens: number;
13185
13703
  };
13186
- readonly "mistralai/devstral-2512": {
13187
- id: string;
13188
- name: string;
13189
- api: "openai-completions";
13190
- provider: string;
13191
- baseUrl: string;
13192
- reasoning: false;
13193
- input: "text"[];
13194
- cost: {
13195
- input: number;
13196
- output: number;
13197
- cacheRead: number;
13198
- cacheWrite: number;
13199
- };
13200
- contextWindow: number;
13201
- maxTokens: number;
13202
- };
13203
13704
  readonly "mistralai/ministral-14b-2512": {
13204
13705
  id: string;
13205
13706
  name: string;
@@ -14037,23 +14538,6 @@ export declare const MODELS: {
14037
14538
  contextWindow: number;
14038
14539
  maxTokens: number;
14039
14540
  };
14040
- readonly "openai/gpt-5-codex": {
14041
- id: string;
14042
- name: string;
14043
- api: "openai-completions";
14044
- provider: string;
14045
- baseUrl: string;
14046
- reasoning: true;
14047
- input: ("image" | "text")[];
14048
- cost: {
14049
- input: number;
14050
- output: number;
14051
- cacheRead: number;
14052
- cacheWrite: number;
14053
- };
14054
- contextWindow: number;
14055
- maxTokens: number;
14056
- };
14057
14541
  readonly "openai/gpt-5-mini": {
14058
14542
  id: string;
14059
14543
  name: string;
@@ -14122,23 +14606,6 @@ export declare const MODELS: {
14122
14606
  contextWindow: number;
14123
14607
  maxTokens: number;
14124
14608
  };
14125
- readonly "openai/gpt-5.1-chat": {
14126
- id: string;
14127
- name: string;
14128
- api: "openai-completions";
14129
- provider: string;
14130
- baseUrl: string;
14131
- reasoning: false;
14132
- input: ("image" | "text")[];
14133
- cost: {
14134
- input: number;
14135
- output: number;
14136
- cacheRead: number;
14137
- cacheWrite: number;
14138
- };
14139
- contextWindow: number;
14140
- maxTokens: number;
14141
- };
14142
14609
  readonly "openai/gpt-5.1-codex": {
14143
14610
  id: string;
14144
14611
  name: string;
@@ -14627,82 +15094,14 @@ export declare const MODELS: {
14627
15094
  contextWindow: number;
14628
15095
  maxTokens: number;
14629
15096
  };
14630
- readonly "openai/gpt-oss-20b": {
14631
- id: string;
14632
- name: string;
14633
- api: "openai-completions";
14634
- provider: string;
14635
- baseUrl: string;
14636
- reasoning: true;
14637
- input: "text"[];
14638
- cost: {
14639
- input: number;
14640
- output: number;
14641
- cacheRead: number;
14642
- cacheWrite: number;
14643
- };
14644
- contextWindow: number;
14645
- maxTokens: number;
14646
- };
14647
- readonly "openai/gpt-oss-20b:free": {
14648
- id: string;
14649
- name: string;
14650
- api: "openai-completions";
14651
- provider: string;
14652
- baseUrl: string;
14653
- reasoning: true;
14654
- input: "text"[];
14655
- cost: {
14656
- input: number;
14657
- output: number;
14658
- cacheRead: number;
14659
- cacheWrite: number;
14660
- };
14661
- contextWindow: number;
14662
- maxTokens: number;
14663
- };
14664
- readonly "openai/gpt-oss-safeguard-20b": {
14665
- id: string;
14666
- name: string;
14667
- api: "openai-completions";
14668
- provider: string;
14669
- baseUrl: string;
14670
- reasoning: true;
14671
- input: "text"[];
14672
- cost: {
14673
- input: number;
14674
- output: number;
14675
- cacheRead: number;
14676
- cacheWrite: number;
14677
- };
14678
- contextWindow: number;
14679
- maxTokens: number;
14680
- };
14681
- readonly "openai/o1": {
14682
- id: string;
14683
- name: string;
14684
- api: "openai-completions";
14685
- provider: string;
14686
- baseUrl: string;
14687
- reasoning: true;
14688
- input: ("image" | "text")[];
14689
- cost: {
14690
- input: number;
14691
- output: number;
14692
- cacheRead: number;
14693
- cacheWrite: number;
14694
- };
14695
- contextWindow: number;
14696
- maxTokens: number;
14697
- };
14698
- readonly "openai/o3": {
15097
+ readonly "openai/gpt-oss-20b": {
14699
15098
  id: string;
14700
15099
  name: string;
14701
15100
  api: "openai-completions";
14702
15101
  provider: string;
14703
15102
  baseUrl: string;
14704
15103
  reasoning: true;
14705
- input: ("image" | "text")[];
15104
+ input: "text"[];
14706
15105
  cost: {
14707
15106
  input: number;
14708
15107
  output: number;
@@ -14712,14 +15111,14 @@ export declare const MODELS: {
14712
15111
  contextWindow: number;
14713
15112
  maxTokens: number;
14714
15113
  };
14715
- readonly "openai/o3-deep-research": {
15114
+ readonly "openai/gpt-oss-20b:free": {
14716
15115
  id: string;
14717
15116
  name: string;
14718
15117
  api: "openai-completions";
14719
15118
  provider: string;
14720
15119
  baseUrl: string;
14721
15120
  reasoning: true;
14722
- input: ("image" | "text")[];
15121
+ input: "text"[];
14723
15122
  cost: {
14724
15123
  input: number;
14725
15124
  output: number;
@@ -14729,7 +15128,7 @@ export declare const MODELS: {
14729
15128
  contextWindow: number;
14730
15129
  maxTokens: number;
14731
15130
  };
14732
- readonly "openai/o3-mini": {
15131
+ readonly "openai/gpt-oss-safeguard-20b": {
14733
15132
  id: string;
14734
15133
  name: string;
14735
15134
  api: "openai-completions";
@@ -14746,14 +15145,14 @@ export declare const MODELS: {
14746
15145
  contextWindow: number;
14747
15146
  maxTokens: number;
14748
15147
  };
14749
- readonly "openai/o3-mini-high": {
15148
+ readonly "openai/o1": {
14750
15149
  id: string;
14751
15150
  name: string;
14752
15151
  api: "openai-completions";
14753
15152
  provider: string;
14754
15153
  baseUrl: string;
14755
15154
  reasoning: true;
14756
- input: "text"[];
15155
+ input: ("image" | "text")[];
14757
15156
  cost: {
14758
15157
  input: number;
14759
15158
  output: number;
@@ -14763,7 +15162,7 @@ export declare const MODELS: {
14763
15162
  contextWindow: number;
14764
15163
  maxTokens: number;
14765
15164
  };
14766
- readonly "openai/o3-pro": {
15165
+ readonly "openai/o3": {
14767
15166
  id: string;
14768
15167
  name: string;
14769
15168
  api: "openai-completions";
@@ -14780,14 +15179,14 @@ export declare const MODELS: {
14780
15179
  contextWindow: number;
14781
15180
  maxTokens: number;
14782
15181
  };
14783
- readonly "openai/o4-mini": {
15182
+ readonly "openai/o3-mini": {
14784
15183
  id: string;
14785
15184
  name: string;
14786
15185
  api: "openai-completions";
14787
15186
  provider: string;
14788
15187
  baseUrl: string;
14789
15188
  reasoning: true;
14790
- input: ("image" | "text")[];
15189
+ input: "text"[];
14791
15190
  cost: {
14792
15191
  input: number;
14793
15192
  output: number;
@@ -14797,14 +15196,14 @@ export declare const MODELS: {
14797
15196
  contextWindow: number;
14798
15197
  maxTokens: number;
14799
15198
  };
14800
- readonly "openai/o4-mini-deep-research": {
15199
+ readonly "openai/o3-mini-high": {
14801
15200
  id: string;
14802
15201
  name: string;
14803
15202
  api: "openai-completions";
14804
15203
  provider: string;
14805
15204
  baseUrl: string;
14806
15205
  reasoning: true;
14807
- input: ("image" | "text")[];
15206
+ input: "text"[];
14808
15207
  cost: {
14809
15208
  input: number;
14810
15209
  output: number;
@@ -14814,7 +15213,7 @@ export declare const MODELS: {
14814
15213
  contextWindow: number;
14815
15214
  maxTokens: number;
14816
15215
  };
14817
- readonly "openai/o4-mini-high": {
15216
+ readonly "openai/o3-pro": {
14818
15217
  id: string;
14819
15218
  name: string;
14820
15219
  api: "openai-completions";
@@ -14831,7 +15230,7 @@ export declare const MODELS: {
14831
15230
  contextWindow: number;
14832
15231
  maxTokens: number;
14833
15232
  };
14834
- readonly "openrouter/auto": {
15233
+ readonly "openai/o4-mini": {
14835
15234
  id: string;
14836
15235
  name: string;
14837
15236
  api: "openai-completions";
@@ -14848,7 +15247,7 @@ export declare const MODELS: {
14848
15247
  contextWindow: number;
14849
15248
  maxTokens: number;
14850
15249
  };
14851
- readonly "openrouter/auto-beta": {
15250
+ readonly "openai/o4-mini-high": {
14852
15251
  id: string;
14853
15252
  name: string;
14854
15253
  api: "openai-completions";
@@ -14865,7 +15264,7 @@ export declare const MODELS: {
14865
15264
  contextWindow: number;
14866
15265
  maxTokens: number;
14867
15266
  };
14868
- readonly "openrouter/free": {
15267
+ readonly "openrouter/auto": {
14869
15268
  id: string;
14870
15269
  name: string;
14871
15270
  api: "openai-completions";
@@ -14882,14 +15281,14 @@ export declare const MODELS: {
14882
15281
  contextWindow: number;
14883
15282
  maxTokens: number;
14884
15283
  };
14885
- readonly "poolside/laguna-m.1": {
15284
+ readonly "openrouter/auto-beta": {
14886
15285
  id: string;
14887
15286
  name: string;
14888
15287
  api: "openai-completions";
14889
15288
  provider: string;
14890
15289
  baseUrl: string;
14891
15290
  reasoning: true;
14892
- input: "text"[];
15291
+ input: ("image" | "text")[];
14893
15292
  cost: {
14894
15293
  input: number;
14895
15294
  output: number;
@@ -14899,14 +15298,14 @@ export declare const MODELS: {
14899
15298
  contextWindow: number;
14900
15299
  maxTokens: number;
14901
15300
  };
14902
- readonly "poolside/laguna-m.1:free": {
15301
+ readonly "openrouter/free": {
14903
15302
  id: string;
14904
15303
  name: string;
14905
15304
  api: "openai-completions";
14906
15305
  provider: string;
14907
15306
  baseUrl: string;
14908
15307
  reasoning: true;
14909
- input: "text"[];
15308
+ input: ("image" | "text")[];
14910
15309
  cost: {
14911
15310
  input: number;
14912
15311
  output: number;
@@ -15819,6 +16218,27 @@ export declare const MODELS: {
15819
16218
  contextWindow: number;
15820
16219
  maxTokens: number;
15821
16220
  };
16221
+ readonly "qwen/qwen3.7-flash": {
16222
+ id: string;
16223
+ name: string;
16224
+ api: "openai-completions";
16225
+ provider: string;
16226
+ baseUrl: string;
16227
+ reasoning: true;
16228
+ thinkingLevelMap: {
16229
+ xhigh: string;
16230
+ max: string;
16231
+ };
16232
+ input: ("image" | "text")[];
16233
+ cost: {
16234
+ input: number;
16235
+ output: number;
16236
+ cacheRead: number;
16237
+ cacheWrite: number;
16238
+ };
16239
+ contextWindow: number;
16240
+ maxTokens: number;
16241
+ };
15822
16242
  readonly "qwen/qwen3.7-max": {
15823
16243
  id: string;
15824
16244
  name: string;
@@ -16031,6 +16451,23 @@ export declare const MODELS: {
16031
16451
  contextWindow: number;
16032
16452
  maxTokens: number;
16033
16453
  };
16454
+ readonly "thinkingmachines/inkling-small": {
16455
+ id: string;
16456
+ name: string;
16457
+ api: "openai-completions";
16458
+ provider: string;
16459
+ baseUrl: string;
16460
+ reasoning: true;
16461
+ input: ("image" | "text")[];
16462
+ cost: {
16463
+ input: number;
16464
+ output: number;
16465
+ cacheRead: number;
16466
+ cacheWrite: number;
16467
+ };
16468
+ contextWindow: number;
16469
+ maxTokens: number;
16470
+ };
16034
16471
  readonly "upstage/solar-pro-3": {
16035
16472
  id: string;
16036
16473
  name: string;
@@ -16855,6 +17292,37 @@ export declare const MODELS: {
16855
17292
  contextWindow: number;
16856
17293
  maxTokens: number;
16857
17294
  };
17295
+ readonly "moonshotai/Kimi-K3": {
17296
+ id: string;
17297
+ name: string;
17298
+ api: "openai-completions";
17299
+ provider: string;
17300
+ baseUrl: string;
17301
+ compat: {
17302
+ supportsStore: false;
17303
+ supportsDeveloperRole: false;
17304
+ supportsReasoningEffort: false;
17305
+ maxTokensField: "max_tokens";
17306
+ supportsStrictMode: false;
17307
+ supportsLongCacheRetention: false;
17308
+ thinkingFormat: "together";
17309
+ };
17310
+ reasoning: true;
17311
+ thinkingLevelMap: {
17312
+ minimal: null;
17313
+ low: null;
17314
+ medium: null;
17315
+ };
17316
+ input: ("image" | "text")[];
17317
+ cost: {
17318
+ input: number;
17319
+ output: number;
17320
+ cacheRead: number;
17321
+ cacheWrite: number;
17322
+ };
17323
+ contextWindow: number;
17324
+ maxTokens: number;
17325
+ };
16858
17326
  readonly "nvidia/nemotron-3-ultra-550b-a55b": {
16859
17327
  id: string;
16860
17328
  name: string;
@@ -17436,6 +17904,27 @@ export declare const MODELS: {
17436
17904
  contextWindow: number;
17437
17905
  maxTokens: number;
17438
17906
  };
17907
+ readonly "alibaba/qwen3.7-flash": {
17908
+ id: string;
17909
+ name: string;
17910
+ api: "anthropic-messages";
17911
+ provider: string;
17912
+ baseUrl: string;
17913
+ reasoning: true;
17914
+ thinkingLevelMap: {
17915
+ xhigh: string;
17916
+ max: string;
17917
+ };
17918
+ input: ("image" | "text")[];
17919
+ cost: {
17920
+ input: number;
17921
+ output: number;
17922
+ cacheRead: number;
17923
+ cacheWrite: number;
17924
+ };
17925
+ contextWindow: number;
17926
+ maxTokens: number;
17927
+ };
17439
17928
  readonly "alibaba/qwen3.7-max": {
17440
17929
  id: string;
17441
17930
  name: string;
@@ -18034,7 +18523,7 @@ export declare const MODELS: {
18034
18523
  api: "anthropic-messages";
18035
18524
  provider: string;
18036
18525
  baseUrl: string;
18037
- reasoning: true;
18526
+ reasoning: false;
18038
18527
  input: "text"[];
18039
18528
  cost: {
18040
18529
  input: number;
@@ -18062,7 +18551,7 @@ export declare const MODELS: {
18062
18551
  contextWindow: number;
18063
18552
  maxTokens: number;
18064
18553
  };
18065
- readonly "deepseek/deepseek-v4-pro": {
18554
+ readonly "deepseek/deepseek-v4-flash-0731": {
18066
18555
  id: string;
18067
18556
  name: string;
18068
18557
  api: "anthropic-messages";
@@ -18079,14 +18568,14 @@ export declare const MODELS: {
18079
18568
  contextWindow: number;
18080
18569
  maxTokens: number;
18081
18570
  };
18082
- readonly "google/gemini-2.5-flash": {
18571
+ readonly "deepseek/deepseek-v4-pro": {
18083
18572
  id: string;
18084
18573
  name: string;
18085
18574
  api: "anthropic-messages";
18086
18575
  provider: string;
18087
18576
  baseUrl: string;
18088
18577
  reasoning: true;
18089
- input: ("image" | "text")[];
18578
+ input: "text"[];
18090
18579
  cost: {
18091
18580
  input: number;
18092
18581
  output: number;
@@ -18096,7 +18585,7 @@ export declare const MODELS: {
18096
18585
  contextWindow: number;
18097
18586
  maxTokens: number;
18098
18587
  };
18099
- readonly "google/gemini-2.5-flash-lite": {
18588
+ readonly "google/gemini-2.5-flash": {
18100
18589
  id: string;
18101
18590
  name: string;
18102
18591
  api: "anthropic-messages";
@@ -18113,7 +18602,7 @@ export declare const MODELS: {
18113
18602
  contextWindow: number;
18114
18603
  maxTokens: number;
18115
18604
  };
18116
- readonly "google/gemini-2.5-pro": {
18605
+ readonly "google/gemini-2.5-flash-lite": {
18117
18606
  id: string;
18118
18607
  name: string;
18119
18608
  api: "anthropic-messages";
@@ -18130,7 +18619,7 @@ export declare const MODELS: {
18130
18619
  contextWindow: number;
18131
18620
  maxTokens: number;
18132
18621
  };
18133
- readonly "google/gemini-3-flash": {
18622
+ readonly "google/gemini-2.5-pro": {
18134
18623
  id: string;
18135
18624
  name: string;
18136
18625
  api: "anthropic-messages";
@@ -18147,7 +18636,7 @@ export declare const MODELS: {
18147
18636
  contextWindow: number;
18148
18637
  maxTokens: number;
18149
18638
  };
18150
- readonly "google/gemini-3-pro-preview": {
18639
+ readonly "google/gemini-3-flash": {
18151
18640
  id: string;
18152
18641
  name: string;
18153
18642
  api: "anthropic-messages";
@@ -19014,6 +19503,23 @@ export declare const MODELS: {
19014
19503
  contextWindow: number;
19015
19504
  maxTokens: number;
19016
19505
  };
19506
+ readonly "moonshotai/kimi-k3-fast": {
19507
+ id: string;
19508
+ name: string;
19509
+ api: "anthropic-messages";
19510
+ provider: string;
19511
+ baseUrl: string;
19512
+ reasoning: true;
19513
+ input: ("image" | "text")[];
19514
+ cost: {
19515
+ input: number;
19516
+ output: number;
19517
+ cacheRead: number;
19518
+ cacheWrite: number;
19519
+ };
19520
+ contextWindow: number;
19521
+ maxTokens: number;
19522
+ };
19017
19523
  readonly "nvidia/nemotron-3-nano-30b-a3b": {
19018
19524
  id: string;
19019
19525
  name: string;
@@ -19946,6 +20452,23 @@ export declare const MODELS: {
19946
20452
  contextWindow: number;
19947
20453
  maxTokens: number;
19948
20454
  };
20455
+ readonly "thinkingmachines/inkling-small": {
20456
+ id: string;
20457
+ name: string;
20458
+ api: "anthropic-messages";
20459
+ provider: string;
20460
+ baseUrl: string;
20461
+ reasoning: true;
20462
+ input: ("image" | "text")[];
20463
+ cost: {
20464
+ input: number;
20465
+ output: number;
20466
+ cacheRead: number;
20467
+ cacheWrite: number;
20468
+ };
20469
+ contextWindow: number;
20470
+ maxTokens: number;
20471
+ };
19949
20472
  readonly "xai/grok-4.1-fast-non-reasoning": {
19950
20473
  id: string;
19951
20474
  name: string;
@@ -21011,27 +21534,6 @@ export declare const MODELS: {
21011
21534
  };
21012
21535
  };
21013
21536
  readonly zai: {
21014
- readonly "glm-4.5-air": {
21015
- id: string;
21016
- name: string;
21017
- api: "openai-completions";
21018
- provider: string;
21019
- baseUrl: string;
21020
- compat: {
21021
- supportsDeveloperRole: false;
21022
- thinkingFormat: "zai";
21023
- };
21024
- reasoning: true;
21025
- input: "text"[];
21026
- cost: {
21027
- input: number;
21028
- output: number;
21029
- cacheRead: number;
21030
- cacheWrite: number;
21031
- };
21032
- contextWindow: number;
21033
- maxTokens: number;
21034
- };
21035
21537
  readonly "glm-4.7": {
21036
21538
  id: string;
21037
21539
  name: string;
@@ -21076,28 +21578,6 @@ export declare const MODELS: {
21076
21578
  contextWindow: number;
21077
21579
  maxTokens: number;
21078
21580
  };
21079
- readonly "glm-5.1": {
21080
- id: string;
21081
- name: string;
21082
- api: "openai-completions";
21083
- provider: string;
21084
- baseUrl: string;
21085
- compat: {
21086
- supportsDeveloperRole: false;
21087
- thinkingFormat: "zai";
21088
- zaiToolStream: true;
21089
- };
21090
- reasoning: true;
21091
- input: "text"[];
21092
- cost: {
21093
- input: number;
21094
- output: number;
21095
- cacheRead: number;
21096
- cacheWrite: number;
21097
- };
21098
- contextWindow: number;
21099
- maxTokens: number;
21100
- };
21101
21581
  readonly "glm-5.2": {
21102
21582
  id: string;
21103
21583
  name: string;
@@ -21120,7 +21600,7 @@ export declare const MODELS: {
21120
21600
  contextWindow: number;
21121
21601
  maxTokens: number;
21122
21602
  };
21123
- readonly "glm-5v-turbo": {
21603
+ readonly "glm-5.2-highspeed[1m]": {
21124
21604
  id: string;
21125
21605
  name: string;
21126
21606
  api: "openai-completions";
@@ -21132,7 +21612,7 @@ export declare const MODELS: {
21132
21612
  zaiToolStream: true;
21133
21613
  };
21134
21614
  reasoning: true;
21135
- input: ("image" | "text")[];
21615
+ input: "text"[];
21136
21616
  cost: {
21137
21617
  input: number;
21138
21618
  output: number;
@@ -21144,27 +21624,6 @@ export declare const MODELS: {
21144
21624
  };
21145
21625
  };
21146
21626
  readonly "zai-coding-cn": {
21147
- readonly "glm-4.5-air": {
21148
- id: string;
21149
- name: string;
21150
- api: "openai-completions";
21151
- provider: string;
21152
- baseUrl: string;
21153
- compat: {
21154
- supportsDeveloperRole: false;
21155
- thinkingFormat: "zai";
21156
- };
21157
- reasoning: true;
21158
- input: "text"[];
21159
- cost: {
21160
- input: number;
21161
- output: number;
21162
- cacheRead: number;
21163
- cacheWrite: number;
21164
- };
21165
- contextWindow: number;
21166
- maxTokens: number;
21167
- };
21168
21627
  readonly "glm-4.7": {
21169
21628
  id: string;
21170
21629
  name: string;
@@ -21209,28 +21668,6 @@ export declare const MODELS: {
21209
21668
  contextWindow: number;
21210
21669
  maxTokens: number;
21211
21670
  };
21212
- readonly "glm-5.1": {
21213
- id: string;
21214
- name: string;
21215
- api: "openai-completions";
21216
- provider: string;
21217
- baseUrl: string;
21218
- compat: {
21219
- supportsDeveloperRole: false;
21220
- thinkingFormat: "zai";
21221
- zaiToolStream: true;
21222
- };
21223
- reasoning: true;
21224
- input: "text"[];
21225
- cost: {
21226
- input: number;
21227
- output: number;
21228
- cacheRead: number;
21229
- cacheWrite: number;
21230
- };
21231
- contextWindow: number;
21232
- maxTokens: number;
21233
- };
21234
21671
  readonly "glm-5.2": {
21235
21672
  id: string;
21236
21673
  name: string;
@@ -21253,7 +21690,7 @@ export declare const MODELS: {
21253
21690
  contextWindow: number;
21254
21691
  maxTokens: number;
21255
21692
  };
21256
- readonly "glm-5v-turbo": {
21693
+ readonly "glm-5.2-highspeed[1m]": {
21257
21694
  id: string;
21258
21695
  name: string;
21259
21696
  api: "openai-completions";
@@ -21265,7 +21702,7 @@ export declare const MODELS: {
21265
21702
  zaiToolStream: true;
21266
21703
  };
21267
21704
  reasoning: true;
21268
- input: ("image" | "text")[];
21705
+ input: "text"[];
21269
21706
  cost: {
21270
21707
  input: number;
21271
21708
  output: number;