@elyracode/ai 0.9.13 → 0.9.15

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.
@@ -2670,6 +2670,95 @@ export const MODELS = {
2670
2670
  contextWindow: 1050000,
2671
2671
  maxTokens: 128000,
2672
2672
  },
2673
+ "gpt-5.6": {
2674
+ id: "gpt-5.6",
2675
+ name: "GPT-5.6",
2676
+ api: "azure-openai-responses",
2677
+ provider: "azure-openai-responses",
2678
+ baseUrl: "",
2679
+ reasoning: true,
2680
+ thinkingLevelMap: { "off": null },
2681
+ input: ["text", "image"],
2682
+ cost: {
2683
+ input: 5,
2684
+ output: 30,
2685
+ cacheRead: 0.5,
2686
+ cacheWrite: 6.25,
2687
+ },
2688
+ contextWindow: 1050000,
2689
+ maxTokens: 128000,
2690
+ },
2691
+ "gpt-5.6-luna": {
2692
+ id: "gpt-5.6-luna",
2693
+ name: "GPT-5.6 Luna",
2694
+ api: "azure-openai-responses",
2695
+ provider: "azure-openai-responses",
2696
+ baseUrl: "",
2697
+ reasoning: true,
2698
+ thinkingLevelMap: { "off": null },
2699
+ input: ["text", "image"],
2700
+ cost: {
2701
+ input: 1,
2702
+ output: 6,
2703
+ cacheRead: 0.1,
2704
+ cacheWrite: 1.25,
2705
+ },
2706
+ contextWindow: 1050000,
2707
+ maxTokens: 128000,
2708
+ },
2709
+ "gpt-5.6-sol": {
2710
+ id: "gpt-5.6-sol",
2711
+ name: "GPT-5.6 Sol",
2712
+ api: "azure-openai-responses",
2713
+ provider: "azure-openai-responses",
2714
+ baseUrl: "",
2715
+ reasoning: true,
2716
+ thinkingLevelMap: { "off": null },
2717
+ input: ["text", "image"],
2718
+ cost: {
2719
+ input: 5,
2720
+ output: 30,
2721
+ cacheRead: 0.5,
2722
+ cacheWrite: 6.25,
2723
+ },
2724
+ contextWindow: 1050000,
2725
+ maxTokens: 128000,
2726
+ },
2727
+ "gpt-5.6-terra": {
2728
+ id: "gpt-5.6-terra",
2729
+ name: "GPT-5.6 Terra",
2730
+ api: "azure-openai-responses",
2731
+ provider: "azure-openai-responses",
2732
+ baseUrl: "",
2733
+ reasoning: true,
2734
+ thinkingLevelMap: { "off": null },
2735
+ input: ["text", "image"],
2736
+ cost: {
2737
+ input: 2.5,
2738
+ output: 15,
2739
+ cacheRead: 0.25,
2740
+ cacheWrite: 3.125,
2741
+ },
2742
+ contextWindow: 1050000,
2743
+ maxTokens: 128000,
2744
+ },
2745
+ "gpt-realtime-2.1": {
2746
+ id: "gpt-realtime-2.1",
2747
+ name: "GPT-Realtime-2.1",
2748
+ api: "azure-openai-responses",
2749
+ provider: "azure-openai-responses",
2750
+ baseUrl: "",
2751
+ reasoning: true,
2752
+ input: ["text", "image"],
2753
+ cost: {
2754
+ input: 4,
2755
+ output: 24,
2756
+ cacheRead: 0.4,
2757
+ cacheWrite: 0,
2758
+ },
2759
+ contextWindow: 128000,
2760
+ maxTokens: 32000,
2761
+ },
2673
2762
  "o1": {
2674
2763
  id: "o1",
2675
2764
  name: "o1",
@@ -4266,7 +4355,7 @@ export const MODELS = {
4266
4355
  cacheRead: 0.2,
4267
4356
  cacheWrite: 0,
4268
4357
  },
4269
- contextWindow: 200000,
4358
+ contextWindow: 1000000,
4270
4359
  maxTokens: 64000,
4271
4360
  },
4272
4361
  "gemini-3.5-flash": {
@@ -4399,7 +4488,7 @@ export const MODELS = {
4399
4488
  cacheRead: 0.25,
4400
4489
  cacheWrite: 0,
4401
4490
  },
4402
- contextWindow: 400000,
4491
+ contextWindow: 1050000,
4403
4492
  maxTokens: 128000,
4404
4493
  },
4405
4494
  "gpt-5.4-mini": {
@@ -4456,7 +4545,64 @@ export const MODELS = {
4456
4545
  cacheRead: 0.5,
4457
4546
  cacheWrite: 0,
4458
4547
  },
4459
- contextWindow: 400000,
4548
+ contextWindow: 1050000,
4549
+ maxTokens: 128000,
4550
+ },
4551
+ "gpt-5.6-luna": {
4552
+ id: "gpt-5.6-luna",
4553
+ name: "GPT-5.6 Luna",
4554
+ api: "openai-responses",
4555
+ provider: "github-copilot",
4556
+ baseUrl: "https://api.individual.githubcopilot.com",
4557
+ 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" },
4558
+ reasoning: true,
4559
+ thinkingLevelMap: { "off": null },
4560
+ input: ["text", "image"],
4561
+ cost: {
4562
+ input: 1,
4563
+ output: 6,
4564
+ cacheRead: 0.1,
4565
+ cacheWrite: 0,
4566
+ },
4567
+ contextWindow: 1050000,
4568
+ maxTokens: 128000,
4569
+ },
4570
+ "gpt-5.6-sol": {
4571
+ id: "gpt-5.6-sol",
4572
+ name: "GPT-5.6 Sol",
4573
+ api: "openai-responses",
4574
+ provider: "github-copilot",
4575
+ baseUrl: "https://api.individual.githubcopilot.com",
4576
+ 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" },
4577
+ reasoning: true,
4578
+ thinkingLevelMap: { "off": null },
4579
+ input: ["text", "image"],
4580
+ cost: {
4581
+ input: 5,
4582
+ output: 30,
4583
+ cacheRead: 0.5,
4584
+ cacheWrite: 0,
4585
+ },
4586
+ contextWindow: 1050000,
4587
+ maxTokens: 128000,
4588
+ },
4589
+ "gpt-5.6-terra": {
4590
+ id: "gpt-5.6-terra",
4591
+ name: "GPT-5.6 Terra",
4592
+ api: "openai-responses",
4593
+ provider: "github-copilot",
4594
+ baseUrl: "https://api.individual.githubcopilot.com",
4595
+ 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" },
4596
+ reasoning: true,
4597
+ thinkingLevelMap: { "off": null },
4598
+ input: ["text", "image"],
4599
+ cost: {
4600
+ input: 2.5,
4601
+ output: 15,
4602
+ cacheRead: 0.25,
4603
+ cacheWrite: 0,
4604
+ },
4605
+ contextWindow: 1050000,
4460
4606
  maxTokens: 128000,
4461
4607
  },
4462
4608
  "kimi-k2.7-code": {
@@ -7533,6 +7679,95 @@ export const MODELS = {
7533
7679
  contextWindow: 1050000,
7534
7680
  maxTokens: 128000,
7535
7681
  },
7682
+ "gpt-5.6": {
7683
+ id: "gpt-5.6",
7684
+ name: "GPT-5.6",
7685
+ api: "openai-responses",
7686
+ provider: "openai",
7687
+ baseUrl: "https://api.openai.com/v1",
7688
+ reasoning: true,
7689
+ thinkingLevelMap: { "off": null },
7690
+ input: ["text", "image"],
7691
+ cost: {
7692
+ input: 5,
7693
+ output: 30,
7694
+ cacheRead: 0.5,
7695
+ cacheWrite: 6.25,
7696
+ },
7697
+ contextWindow: 1050000,
7698
+ maxTokens: 128000,
7699
+ },
7700
+ "gpt-5.6-luna": {
7701
+ id: "gpt-5.6-luna",
7702
+ name: "GPT-5.6 Luna",
7703
+ api: "openai-responses",
7704
+ provider: "openai",
7705
+ baseUrl: "https://api.openai.com/v1",
7706
+ reasoning: true,
7707
+ thinkingLevelMap: { "off": null },
7708
+ input: ["text", "image"],
7709
+ cost: {
7710
+ input: 1,
7711
+ output: 6,
7712
+ cacheRead: 0.1,
7713
+ cacheWrite: 1.25,
7714
+ },
7715
+ contextWindow: 1050000,
7716
+ maxTokens: 128000,
7717
+ },
7718
+ "gpt-5.6-sol": {
7719
+ id: "gpt-5.6-sol",
7720
+ name: "GPT-5.6 Sol",
7721
+ api: "openai-responses",
7722
+ provider: "openai",
7723
+ baseUrl: "https://api.openai.com/v1",
7724
+ reasoning: true,
7725
+ thinkingLevelMap: { "off": null },
7726
+ input: ["text", "image"],
7727
+ cost: {
7728
+ input: 5,
7729
+ output: 30,
7730
+ cacheRead: 0.5,
7731
+ cacheWrite: 6.25,
7732
+ },
7733
+ contextWindow: 1050000,
7734
+ maxTokens: 128000,
7735
+ },
7736
+ "gpt-5.6-terra": {
7737
+ id: "gpt-5.6-terra",
7738
+ name: "GPT-5.6 Terra",
7739
+ api: "openai-responses",
7740
+ provider: "openai",
7741
+ baseUrl: "https://api.openai.com/v1",
7742
+ reasoning: true,
7743
+ thinkingLevelMap: { "off": null },
7744
+ input: ["text", "image"],
7745
+ cost: {
7746
+ input: 2.5,
7747
+ output: 15,
7748
+ cacheRead: 0.25,
7749
+ cacheWrite: 3.125,
7750
+ },
7751
+ contextWindow: 1050000,
7752
+ maxTokens: 128000,
7753
+ },
7754
+ "gpt-realtime-2.1": {
7755
+ id: "gpt-realtime-2.1",
7756
+ name: "GPT-Realtime-2.1",
7757
+ api: "openai-responses",
7758
+ provider: "openai",
7759
+ baseUrl: "https://api.openai.com/v1",
7760
+ reasoning: true,
7761
+ input: ["text", "image"],
7762
+ cost: {
7763
+ input: 4,
7764
+ output: 24,
7765
+ cacheRead: 0.4,
7766
+ cacheWrite: 0,
7767
+ },
7768
+ contextWindow: 128000,
7769
+ maxTokens: 32000,
7770
+ },
7536
7771
  "o1": {
7537
7772
  id: "o1",
7538
7773
  name: "o1",
@@ -8509,6 +8744,77 @@ export const MODELS = {
8509
8744
  contextWindow: 1050000,
8510
8745
  maxTokens: 128000,
8511
8746
  },
8747
+ "gpt-5.6-luna": {
8748
+ id: "gpt-5.6-luna",
8749
+ name: "GPT-5.6 Luna",
8750
+ api: "openai-responses",
8751
+ provider: "opencode",
8752
+ baseUrl: "https://opencode.ai/zen/v1",
8753
+ reasoning: true,
8754
+ thinkingLevelMap: { "off": null },
8755
+ input: ["text", "image"],
8756
+ cost: {
8757
+ input: 1,
8758
+ output: 6,
8759
+ cacheRead: 0.1,
8760
+ cacheWrite: 1.25,
8761
+ },
8762
+ contextWindow: 1050000,
8763
+ maxTokens: 128000,
8764
+ },
8765
+ "gpt-5.6-sol": {
8766
+ id: "gpt-5.6-sol",
8767
+ name: "GPT-5.6 Sol",
8768
+ api: "openai-responses",
8769
+ provider: "opencode",
8770
+ baseUrl: "https://opencode.ai/zen/v1",
8771
+ reasoning: true,
8772
+ thinkingLevelMap: { "off": null },
8773
+ input: ["text", "image"],
8774
+ cost: {
8775
+ input: 5,
8776
+ output: 30,
8777
+ cacheRead: 0.5,
8778
+ cacheWrite: 6.25,
8779
+ },
8780
+ contextWindow: 1050000,
8781
+ maxTokens: 128000,
8782
+ },
8783
+ "gpt-5.6-terra": {
8784
+ id: "gpt-5.6-terra",
8785
+ name: "GPT-5.6 Terra",
8786
+ api: "openai-responses",
8787
+ provider: "opencode",
8788
+ baseUrl: "https://opencode.ai/zen/v1",
8789
+ reasoning: true,
8790
+ thinkingLevelMap: { "off": null },
8791
+ input: ["text", "image"],
8792
+ cost: {
8793
+ input: 2.5,
8794
+ output: 15,
8795
+ cacheRead: 0.25,
8796
+ cacheWrite: 3.125,
8797
+ },
8798
+ contextWindow: 1050000,
8799
+ maxTokens: 128000,
8800
+ },
8801
+ "grok-4.5": {
8802
+ id: "grok-4.5",
8803
+ name: "Grok 4.5",
8804
+ api: "openai-completions",
8805
+ provider: "opencode",
8806
+ baseUrl: "https://opencode.ai/zen/v1",
8807
+ reasoning: true,
8808
+ input: ["text", "image"],
8809
+ cost: {
8810
+ input: 2,
8811
+ output: 6,
8812
+ cacheRead: 0.5,
8813
+ cacheWrite: 0,
8814
+ },
8815
+ contextWindow: 500000,
8816
+ maxTokens: 500000,
8817
+ },
8512
8818
  "grok-build-0.1": {
8513
8819
  id: "grok-build-0.1",
8514
8820
  name: "Grok Build 0.1",
@@ -8540,7 +8846,7 @@ export const MODELS = {
8540
8846
  cacheRead: 0,
8541
8847
  cacheWrite: 0,
8542
8848
  },
8543
- contextWindow: 256000,
8849
+ contextWindow: 190000,
8544
8850
  maxTokens: 64000,
8545
8851
  },
8546
8852
  "kimi-k2.5": {
@@ -9391,23 +9697,6 @@ export const MODELS = {
9391
9697
  contextWindow: 262144,
9392
9698
  maxTokens: 80000,
9393
9699
  },
9394
- "arcee-ai/trinity-mini": {
9395
- id: "arcee-ai/trinity-mini",
9396
- name: "Arcee AI: Trinity Mini",
9397
- api: "openai-completions",
9398
- provider: "openrouter",
9399
- baseUrl: "https://openrouter.ai/api/v1",
9400
- reasoning: true,
9401
- input: ["text"],
9402
- cost: {
9403
- input: 0.045,
9404
- output: 0.15,
9405
- cacheRead: 0,
9406
- cacheWrite: 0,
9407
- },
9408
- contextWindow: 131072,
9409
- maxTokens: 131072,
9410
- },
9411
9700
  "arcee-ai/virtuoso-large": {
9412
9701
  id: "arcee-ai/virtuoso-large",
9413
9702
  name: "Arcee AI: Virtuoso Large",
@@ -9672,9 +9961,9 @@ export const MODELS = {
9672
9961
  reasoning: true,
9673
9962
  input: ["text"],
9674
9963
  cost: {
9675
- input: 0.2288,
9676
- output: 0.3432,
9677
- cacheRead: 0.02288,
9964
+ input: 0.2145,
9965
+ output: 0.32175,
9966
+ cacheRead: 0.02145,
9678
9967
  cacheWrite: 0,
9679
9968
  },
9680
9969
  contextWindow: 131072,
@@ -9708,13 +9997,13 @@ export const MODELS = {
9708
9997
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9709
9998
  input: ["text"],
9710
9999
  cost: {
9711
- input: 0.09,
9712
- output: 0.18,
9713
- cacheRead: 0.018,
10000
+ input: 0.077,
10001
+ output: 0.154,
10002
+ cacheRead: 0.015399999999999999,
9714
10003
  cacheWrite: 0,
9715
10004
  },
9716
10005
  contextWindow: 1048576,
9717
- maxTokens: 65536,
10006
+ maxTokens: 384000,
9718
10007
  },
9719
10008
  "deepseek/deepseek-v4-pro": {
9720
10009
  id: "deepseek/deepseek-v4-pro",
@@ -9769,23 +10058,6 @@ export const MODELS = {
9769
10058
  contextWindow: 1048576,
9770
10059
  maxTokens: 65535,
9771
10060
  },
9772
- "google/gemini-2.5-flash-lite-preview-09-2025": {
9773
- id: "google/gemini-2.5-flash-lite-preview-09-2025",
9774
- name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
9775
- api: "openai-completions",
9776
- provider: "openrouter",
9777
- baseUrl: "https://openrouter.ai/api/v1",
9778
- reasoning: true,
9779
- input: ["text", "image"],
9780
- cost: {
9781
- input: 0.09999999999999999,
9782
- output: 0.39999999999999997,
9783
- cacheRead: 0.01,
9784
- cacheWrite: 0.08333333333333334,
9785
- },
9786
- contextWindow: 1048576,
9787
- maxTokens: 65535,
9788
- },
9789
10061
  "google/gemini-2.5-pro": {
9790
10062
  id: "google/gemini-2.5-pro",
9791
10063
  name: "Google: Gemini 2.5 Pro",
@@ -10254,8 +10526,8 @@ export const MODELS = {
10254
10526
  reasoning: false,
10255
10527
  input: ["text", "image"],
10256
10528
  cost: {
10257
- input: 0.15,
10258
- output: 0.6,
10529
+ input: 0.19999999999999998,
10530
+ output: 0.7999999999999999,
10259
10531
  cacheRead: 0,
10260
10532
  cacheWrite: 0,
10261
10533
  },
@@ -10339,9 +10611,9 @@ export const MODELS = {
10339
10611
  reasoning: true,
10340
10612
  input: ["text"],
10341
10613
  cost: {
10342
- input: 0.12,
10343
- output: 0.48,
10344
- cacheRead: 0,
10614
+ input: 0.15,
10615
+ output: 0.8999999999999999,
10616
+ cacheRead: 0.049999999999999996,
10345
10617
  cacheWrite: 0,
10346
10618
  },
10347
10619
  contextWindow: 204800,
@@ -10356,8 +10628,8 @@ export const MODELS = {
10356
10628
  reasoning: true,
10357
10629
  input: ["text"],
10358
10630
  cost: {
10359
- input: 0.18,
10360
- output: 0.72,
10631
+ input: 0.24,
10632
+ output: 0.96,
10361
10633
  cacheRead: 0,
10362
10634
  cacheWrite: 0,
10363
10635
  },
@@ -10379,7 +10651,7 @@ export const MODELS = {
10379
10651
  cacheWrite: 0,
10380
10652
  },
10381
10653
  contextWindow: 1048576,
10382
- maxTokens: 512000,
10654
+ maxTokens: 131072,
10383
10655
  },
10384
10656
  "mistralai/codestral-2508": {
10385
10657
  id: "mistralai/codestral-2508",
@@ -10747,9 +11019,9 @@ export const MODELS = {
10747
11019
  reasoning: true,
10748
11020
  input: ["text", "image"],
10749
11021
  cost: {
10750
- input: 0.65,
11022
+ input: 0.66,
10751
11023
  output: 3.41,
10752
- cacheRead: 0.3,
11024
+ cacheRead: 0.15,
10753
11025
  cacheWrite: 0,
10754
11026
  },
10755
11027
  contextWindow: 262144,
@@ -10764,13 +11036,13 @@ export const MODELS = {
10764
11036
  reasoning: true,
10765
11037
  input: ["text", "image"],
10766
11038
  cost: {
10767
- input: 0.74,
11039
+ input: 0.72,
10768
11040
  output: 3.5,
10769
11041
  cacheRead: 0.15,
10770
11042
  cacheWrite: 0,
10771
11043
  },
10772
11044
  contextWindow: 262144,
10773
- maxTokens: 16384,
11045
+ maxTokens: 262144,
10774
11046
  },
10775
11047
  "nex-agi/nex-n2-mini": {
10776
11048
  id: "nex-agi/nex-n2-mini",
@@ -11515,6 +11787,108 @@ export const MODELS = {
11515
11787
  contextWindow: 1050000,
11516
11788
  maxTokens: 128000,
11517
11789
  },
11790
+ "openai/gpt-5.6-luna": {
11791
+ id: "openai/gpt-5.6-luna",
11792
+ name: "OpenAI: GPT-5.6 Luna",
11793
+ api: "openai-completions",
11794
+ provider: "openrouter",
11795
+ baseUrl: "https://openrouter.ai/api/v1",
11796
+ reasoning: true,
11797
+ input: ["text", "image"],
11798
+ cost: {
11799
+ input: 1,
11800
+ output: 6,
11801
+ cacheRead: 0.09999999999999999,
11802
+ cacheWrite: 1.25,
11803
+ },
11804
+ contextWindow: 1050000,
11805
+ maxTokens: 128000,
11806
+ },
11807
+ "openai/gpt-5.6-luna-pro": {
11808
+ id: "openai/gpt-5.6-luna-pro",
11809
+ name: "OpenAI: GPT-5.6 Luna Pro",
11810
+ api: "openai-completions",
11811
+ provider: "openrouter",
11812
+ baseUrl: "https://openrouter.ai/api/v1",
11813
+ reasoning: true,
11814
+ input: ["text", "image"],
11815
+ cost: {
11816
+ input: 1,
11817
+ output: 6,
11818
+ cacheRead: 0.09999999999999999,
11819
+ cacheWrite: 1.25,
11820
+ },
11821
+ contextWindow: 1050000,
11822
+ maxTokens: 128000,
11823
+ },
11824
+ "openai/gpt-5.6-sol": {
11825
+ id: "openai/gpt-5.6-sol",
11826
+ name: "OpenAI: GPT-5.6 Sol",
11827
+ api: "openai-completions",
11828
+ provider: "openrouter",
11829
+ baseUrl: "https://openrouter.ai/api/v1",
11830
+ reasoning: true,
11831
+ input: ["text", "image"],
11832
+ cost: {
11833
+ input: 5,
11834
+ output: 30,
11835
+ cacheRead: 0.5,
11836
+ cacheWrite: 6.25,
11837
+ },
11838
+ contextWindow: 1050000,
11839
+ maxTokens: 128000,
11840
+ },
11841
+ "openai/gpt-5.6-sol-pro": {
11842
+ id: "openai/gpt-5.6-sol-pro",
11843
+ name: "OpenAI: GPT-5.6 Sol Pro",
11844
+ api: "openai-completions",
11845
+ provider: "openrouter",
11846
+ baseUrl: "https://openrouter.ai/api/v1",
11847
+ reasoning: true,
11848
+ input: ["text", "image"],
11849
+ cost: {
11850
+ input: 5,
11851
+ output: 30,
11852
+ cacheRead: 0.5,
11853
+ cacheWrite: 6.25,
11854
+ },
11855
+ contextWindow: 1050000,
11856
+ maxTokens: 128000,
11857
+ },
11858
+ "openai/gpt-5.6-terra": {
11859
+ id: "openai/gpt-5.6-terra",
11860
+ name: "OpenAI: GPT-5.6 Terra",
11861
+ api: "openai-completions",
11862
+ provider: "openrouter",
11863
+ baseUrl: "https://openrouter.ai/api/v1",
11864
+ reasoning: true,
11865
+ input: ["text", "image"],
11866
+ cost: {
11867
+ input: 2.5,
11868
+ output: 15,
11869
+ cacheRead: 0.25,
11870
+ cacheWrite: 3.125,
11871
+ },
11872
+ contextWindow: 1050000,
11873
+ maxTokens: 128000,
11874
+ },
11875
+ "openai/gpt-5.6-terra-pro": {
11876
+ id: "openai/gpt-5.6-terra-pro",
11877
+ name: "OpenAI: GPT-5.6 Terra Pro",
11878
+ api: "openai-completions",
11879
+ provider: "openrouter",
11880
+ baseUrl: "https://openrouter.ai/api/v1",
11881
+ reasoning: true,
11882
+ input: ["text", "image"],
11883
+ cost: {
11884
+ input: 2.5,
11885
+ output: 15,
11886
+ cacheRead: 0.25,
11887
+ cacheWrite: 3.125,
11888
+ },
11889
+ contextWindow: 1050000,
11890
+ maxTokens: 128000,
11891
+ },
11518
11892
  "openai/gpt-audio": {
11519
11893
  id: "openai/gpt-audio",
11520
11894
  name: "OpenAI: GPT Audio",
@@ -11575,13 +11949,13 @@ export const MODELS = {
11575
11949
  reasoning: true,
11576
11950
  input: ["text"],
11577
11951
  cost: {
11578
- input: 0.03,
11579
- output: 0.15,
11952
+ input: 0.036,
11953
+ output: 0.18,
11580
11954
  cacheRead: 0,
11581
11955
  cacheWrite: 0,
11582
11956
  },
11583
11957
  contextWindow: 131072,
11584
- maxTokens: 131072,
11958
+ maxTokens: 4096,
11585
11959
  },
11586
11960
  "openai/gpt-oss-120b:free": {
11587
11961
  id: "openai/gpt-oss-120b:free",
@@ -11906,40 +12280,6 @@ export const MODELS = {
11906
12280
  contextWindow: 262144,
11907
12281
  maxTokens: 32768,
11908
12282
  },
11909
- "poolside/laguna-xs.2": {
11910
- id: "poolside/laguna-xs.2",
11911
- name: "Poolside: Laguna XS.2",
11912
- api: "openai-completions",
11913
- provider: "openrouter",
11914
- baseUrl: "https://openrouter.ai/api/v1",
11915
- reasoning: true,
11916
- input: ["text"],
11917
- cost: {
11918
- input: 0.09999999999999999,
11919
- output: 0.19999999999999998,
11920
- cacheRead: 0.049999999999999996,
11921
- cacheWrite: 0,
11922
- },
11923
- contextWindow: 262144,
11924
- maxTokens: 32768,
11925
- },
11926
- "poolside/laguna-xs.2:free": {
11927
- id: "poolside/laguna-xs.2:free",
11928
- name: "Poolside: Laguna XS.2 (free)",
11929
- api: "openai-completions",
11930
- provider: "openrouter",
11931
- baseUrl: "https://openrouter.ai/api/v1",
11932
- reasoning: true,
11933
- input: ["text"],
11934
- cost: {
11935
- input: 0,
11936
- output: 0,
11937
- cacheRead: 0,
11938
- cacheWrite: 0,
11939
- },
11940
- contextWindow: 262144,
11941
- maxTokens: 32768,
11942
- },
11943
12283
  "qwen/qwen-2.5-72b-instruct": {
11944
12284
  id: "qwen/qwen-2.5-72b-instruct",
11945
12285
  name: "Qwen2.5 72B Instruct",
@@ -12069,7 +12409,7 @@ export const MODELS = {
12069
12409
  input: ["text"],
12070
12410
  cost: {
12071
12411
  input: 0.09,
12072
- output: 0.09999999999999999,
12412
+ output: 0.55,
12073
12413
  cacheRead: 0,
12074
12414
  cacheWrite: 0,
12075
12415
  },
@@ -12850,13 +13190,13 @@ export const MODELS = {
12850
13190
  reasoning: true,
12851
13191
  input: ["text"],
12852
13192
  cost: {
12853
- input: 0.19999999999999998,
12854
- output: 0.7999999999999999,
12855
- cacheRead: 0.5,
13193
+ input: 0.14,
13194
+ output: 0.58,
13195
+ cacheRead: 0.035,
12856
13196
  cacheWrite: 0,
12857
13197
  },
12858
13198
  contextWindow: 262144,
12859
- maxTokens: 131072,
13199
+ maxTokens: 4096,
12860
13200
  },
12861
13201
  "tencent/hy3:free": {
12862
13202
  id: "tencent/hy3:free",
@@ -12943,6 +13283,23 @@ export const MODELS = {
12943
13283
  contextWindow: 1000000,
12944
13284
  maxTokens: 4096,
12945
13285
  },
13286
+ "x-ai/grok-4.5": {
13287
+ id: "x-ai/grok-4.5",
13288
+ name: "xAI: Grok 4.5",
13289
+ api: "openai-completions",
13290
+ provider: "openrouter",
13291
+ baseUrl: "https://openrouter.ai/api/v1",
13292
+ reasoning: true,
13293
+ input: ["text", "image"],
13294
+ cost: {
13295
+ input: 2,
13296
+ output: 6,
13297
+ cacheRead: 0.5,
13298
+ cacheWrite: 0,
13299
+ },
13300
+ contextWindow: 500000,
13301
+ maxTokens: 4096,
13302
+ },
12946
13303
  "x-ai/grok-build-0.1": {
12947
13304
  id: "x-ai/grok-build-0.1",
12948
13305
  name: "xAI: Grok Build 0.1",
@@ -13055,12 +13412,12 @@ export const MODELS = {
13055
13412
  input: ["text"],
13056
13413
  cost: {
13057
13414
  input: 0.43,
13058
- output: 1.74,
13415
+ output: 1.75,
13059
13416
  cacheRead: 0.08,
13060
13417
  cacheWrite: 0,
13061
13418
  },
13062
- contextWindow: 202752,
13063
- maxTokens: 131072,
13419
+ contextWindow: 200000,
13420
+ maxTokens: 16384,
13064
13421
  },
13065
13422
  "z-ai/glm-4.6v": {
13066
13423
  id: "z-ai/glm-4.6v",
@@ -13173,13 +13530,13 @@ export const MODELS = {
13173
13530
  reasoning: true,
13174
13531
  input: ["text"],
13175
13532
  cost: {
13176
- input: 0.56,
13177
- output: 1.76,
13178
- cacheRead: 0.10400000000000001,
13533
+ input: 0.42,
13534
+ output: 1.32,
13535
+ cacheRead: 0.078,
13179
13536
  cacheWrite: 0,
13180
13537
  },
13181
13538
  contextWindow: 1048576,
13182
- maxTokens: 128000,
13539
+ maxTokens: 131072,
13183
13540
  },
13184
13541
  "z-ai/glm-5v-turbo": {
13185
13542
  id: "z-ai/glm-5v-turbo",
@@ -13310,9 +13667,9 @@ export const MODELS = {
13310
13667
  reasoning: true,
13311
13668
  input: ["text", "image"],
13312
13669
  cost: {
13313
- input: 0.65,
13670
+ input: 0.66,
13314
13671
  output: 3.41,
13315
- cacheRead: 0.3,
13672
+ cacheRead: 0.15,
13316
13673
  cacheWrite: 0,
13317
13674
  },
13318
13675
  contextWindow: 262144,
@@ -13330,7 +13687,7 @@ export const MODELS = {
13330
13687
  input: 5,
13331
13688
  output: 30,
13332
13689
  cacheRead: 0.5,
13333
- cacheWrite: 0,
13690
+ cacheWrite: 6.25,
13334
13691
  },
13335
13692
  contextWindow: 1050000,
13336
13693
  maxTokens: 128000,
@@ -13361,12 +13718,12 @@ export const MODELS = {
13361
13718
  reasoning: true,
13362
13719
  input: ["text", "image"],
13363
13720
  cost: {
13364
- input: 1.25,
13365
- output: 2.5,
13366
- cacheRead: 0.19999999999999998,
13721
+ input: 2,
13722
+ output: 6,
13723
+ cacheRead: 0.5,
13367
13724
  cacheWrite: 0,
13368
13725
  },
13369
- contextWindow: 1000000,
13726
+ contextWindow: 500000,
13370
13727
  maxTokens: 4096,
13371
13728
  },
13372
13729
  },
@@ -14664,7 +15021,7 @@ export const MODELS = {
14664
15021
  cost: {
14665
15022
  input: 0.14,
14666
15023
  output: 0.28,
14667
- cacheRead: 0.0028,
15024
+ cacheRead: 0.028,
14668
15025
  cacheWrite: 0,
14669
15026
  },
14670
15027
  contextWindow: 1000000,
@@ -14925,6 +15282,23 @@ export const MODELS = {
14925
15282
  contextWindow: 1000000,
14926
15283
  maxTokens: 32000,
14927
15284
  },
15285
+ "kwaipilot/kat-coder-air-v2.5": {
15286
+ id: "kwaipilot/kat-coder-air-v2.5",
15287
+ name: "Kat Coder Air V2.5",
15288
+ api: "anthropic-messages",
15289
+ provider: "vercel-ai-gateway",
15290
+ baseUrl: "https://ai-gateway.vercel.sh",
15291
+ reasoning: true,
15292
+ input: ["text"],
15293
+ cost: {
15294
+ input: 0.15,
15295
+ output: 0.6,
15296
+ cacheRead: 0.03,
15297
+ cacheWrite: 0,
15298
+ },
15299
+ contextWindow: 256000,
15300
+ maxTokens: 80000,
15301
+ },
14928
15302
  "kwaipilot/kat-coder-pro-v1": {
14929
15303
  id: "kwaipilot/kat-coder-pro-v1",
14930
15304
  name: "KAT-Coder-Pro V1",
@@ -14959,6 +15333,23 @@ export const MODELS = {
14959
15333
  contextWindow: 256000,
14960
15334
  maxTokens: 256000,
14961
15335
  },
15336
+ "kwaipilot/kat-coder-pro-v2.5": {
15337
+ id: "kwaipilot/kat-coder-pro-v2.5",
15338
+ name: "Kat Coder Pro V2.5",
15339
+ api: "anthropic-messages",
15340
+ provider: "vercel-ai-gateway",
15341
+ baseUrl: "https://ai-gateway.vercel.sh",
15342
+ reasoning: true,
15343
+ input: ["text"],
15344
+ cost: {
15345
+ input: 0.74,
15346
+ output: 2.96,
15347
+ cacheRead: 0.15,
15348
+ cacheWrite: 0,
15349
+ },
15350
+ contextWindow: 256000,
15351
+ maxTokens: 80000,
15352
+ },
14962
15353
  "meituan/longcat-flash-chat": {
14963
15354
  id: "meituan/longcat-flash-chat",
14964
15355
  name: "LongCat Flash Chat",
@@ -15112,6 +15503,23 @@ export const MODELS = {
15112
15503
  contextWindow: 128000,
15113
15504
  maxTokens: 8192,
15114
15505
  },
15506
+ "meta/muse-spark-1.1": {
15507
+ id: "meta/muse-spark-1.1",
15508
+ name: "Muse Spark 1.1",
15509
+ api: "anthropic-messages",
15510
+ provider: "vercel-ai-gateway",
15511
+ baseUrl: "https://ai-gateway.vercel.sh",
15512
+ reasoning: true,
15513
+ input: ["text", "image"],
15514
+ cost: {
15515
+ input: 1.25,
15516
+ output: 4.25,
15517
+ cacheRead: 0.15,
15518
+ cacheWrite: 0,
15519
+ },
15520
+ contextWindow: 1048576,
15521
+ maxTokens: 1048576,
15522
+ },
15115
15523
  "minimax/minimax-m2": {
15116
15524
  id: "minimax/minimax-m2",
15117
15525
  name: "MiniMax M2",
@@ -16212,6 +16620,57 @@ export const MODELS = {
16212
16620
  contextWindow: 1000000,
16213
16621
  maxTokens: 128000,
16214
16622
  },
16623
+ "openai/gpt-5.6-luna": {
16624
+ id: "openai/gpt-5.6-luna",
16625
+ name: "GPT 5.6 Luna",
16626
+ api: "anthropic-messages",
16627
+ provider: "vercel-ai-gateway",
16628
+ baseUrl: "https://ai-gateway.vercel.sh",
16629
+ reasoning: true,
16630
+ input: ["text", "image"],
16631
+ cost: {
16632
+ input: 1,
16633
+ output: 6,
16634
+ cacheRead: 0.09999999999999999,
16635
+ cacheWrite: 1.25,
16636
+ },
16637
+ contextWindow: 1050000,
16638
+ maxTokens: 128000,
16639
+ },
16640
+ "openai/gpt-5.6-sol": {
16641
+ id: "openai/gpt-5.6-sol",
16642
+ name: "GPT 5.6 Sol",
16643
+ api: "anthropic-messages",
16644
+ provider: "vercel-ai-gateway",
16645
+ baseUrl: "https://ai-gateway.vercel.sh",
16646
+ reasoning: true,
16647
+ input: ["text", "image"],
16648
+ cost: {
16649
+ input: 5,
16650
+ output: 30,
16651
+ cacheRead: 0.5,
16652
+ cacheWrite: 6.25,
16653
+ },
16654
+ contextWindow: 1050000,
16655
+ maxTokens: 128000,
16656
+ },
16657
+ "openai/gpt-5.6-terra": {
16658
+ id: "openai/gpt-5.6-terra",
16659
+ name: "GPT 5.6 Terra",
16660
+ api: "anthropic-messages",
16661
+ provider: "vercel-ai-gateway",
16662
+ baseUrl: "https://ai-gateway.vercel.sh",
16663
+ reasoning: true,
16664
+ input: ["text", "image"],
16665
+ cost: {
16666
+ input: 2.5,
16667
+ output: 15,
16668
+ cacheRead: 0.25,
16669
+ cacheWrite: 3.125,
16670
+ },
16671
+ contextWindow: 1050000,
16672
+ maxTokens: 128000,
16673
+ },
16215
16674
  "openai/gpt-oss-120b": {
16216
16675
  id: "openai/gpt-oss-120b",
16217
16676
  name: "GPT OSS 120B",
@@ -16569,6 +17028,23 @@ export const MODELS = {
16569
17028
  contextWindow: 1000000,
16570
17029
  maxTokens: 1000000,
16571
17030
  },
17031
+ "xai/grok-4.5": {
17032
+ id: "xai/grok-4.5",
17033
+ name: "Grok 4.5",
17034
+ api: "anthropic-messages",
17035
+ provider: "vercel-ai-gateway",
17036
+ baseUrl: "https://ai-gateway.vercel.sh",
17037
+ reasoning: true,
17038
+ input: ["text", "image"],
17039
+ cost: {
17040
+ input: 2,
17041
+ output: 6,
17042
+ cacheRead: 0.5,
17043
+ cacheWrite: 0,
17044
+ },
17045
+ contextWindow: 500000,
17046
+ maxTokens: 500000,
17047
+ },
16572
17048
  "xai/grok-build-0.1": {
16573
17049
  id: "xai/grok-build-0.1",
16574
17050
  name: "Grok Build 0.1",
@@ -16850,9 +17326,9 @@ export const MODELS = {
16850
17326
  reasoning: true,
16851
17327
  input: ["text"],
16852
17328
  cost: {
16853
- input: 3,
16854
- output: 10.25,
16855
- cacheRead: 0.5,
17329
+ input: 2.0999999999999996,
17330
+ output: 6.6000000000000005,
17331
+ cacheRead: 0.21,
16856
17332
  cacheWrite: 0,
16857
17333
  },
16858
17334
  contextWindow: 1000000,
@@ -16928,6 +17404,23 @@ export const MODELS = {
16928
17404
  contextWindow: 1000000,
16929
17405
  maxTokens: 30000,
16930
17406
  },
17407
+ "grok-4.5": {
17408
+ id: "grok-4.5",
17409
+ name: "Grok 4.5",
17410
+ api: "openai-completions",
17411
+ provider: "xai",
17412
+ baseUrl: "https://api.x.ai/v1",
17413
+ reasoning: true,
17414
+ input: ["text", "image"],
17415
+ cost: {
17416
+ input: 2,
17417
+ output: 6,
17418
+ cacheRead: 0.5,
17419
+ cacheWrite: 0,
17420
+ },
17421
+ contextWindow: 500000,
17422
+ maxTokens: 500000,
17423
+ },
16931
17424
  "grok-build-0.1": {
16932
17425
  id: "grok-build-0.1",
16933
17426
  name: "Grok Build 0.1",