@elyracode/ai 0.9.14 → 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.
@@ -2742,6 +2742,23 @@ export const MODELS = {
2742
2742
  contextWindow: 1050000,
2743
2743
  maxTokens: 128000,
2744
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
+ },
2745
2762
  "o1": {
2746
2763
  id: "o1",
2747
2764
  name: "o1",
@@ -4338,7 +4355,7 @@ export const MODELS = {
4338
4355
  cacheRead: 0.2,
4339
4356
  cacheWrite: 0,
4340
4357
  },
4341
- contextWindow: 200000,
4358
+ contextWindow: 1000000,
4342
4359
  maxTokens: 64000,
4343
4360
  },
4344
4361
  "gemini-3.5-flash": {
@@ -4471,7 +4488,7 @@ export const MODELS = {
4471
4488
  cacheRead: 0.25,
4472
4489
  cacheWrite: 0,
4473
4490
  },
4474
- contextWindow: 400000,
4491
+ contextWindow: 1050000,
4475
4492
  maxTokens: 128000,
4476
4493
  },
4477
4494
  "gpt-5.4-mini": {
@@ -4528,7 +4545,64 @@ export const MODELS = {
4528
4545
  cacheRead: 0.5,
4529
4546
  cacheWrite: 0,
4530
4547
  },
4531
- 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,
4532
4606
  maxTokens: 128000,
4533
4607
  },
4534
4608
  "kimi-k2.7-code": {
@@ -7677,6 +7751,23 @@ export const MODELS = {
7677
7751
  contextWindow: 1050000,
7678
7752
  maxTokens: 128000,
7679
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
+ },
7680
7771
  "o1": {
7681
7772
  id: "o1",
7682
7773
  name: "o1",
@@ -8653,6 +8744,60 @@ export const MODELS = {
8653
8744
  contextWindow: 1050000,
8654
8745
  maxTokens: 128000,
8655
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
+ },
8656
8801
  "grok-4.5": {
8657
8802
  id: "grok-4.5",
8658
8803
  name: "Grok 4.5",
@@ -8701,7 +8846,7 @@ export const MODELS = {
8701
8846
  cacheRead: 0,
8702
8847
  cacheWrite: 0,
8703
8848
  },
8704
- contextWindow: 256000,
8849
+ contextWindow: 190000,
8705
8850
  maxTokens: 64000,
8706
8851
  },
8707
8852
  "kimi-k2.5": {
@@ -9552,23 +9697,6 @@ export const MODELS = {
9552
9697
  contextWindow: 262144,
9553
9698
  maxTokens: 80000,
9554
9699
  },
9555
- "arcee-ai/trinity-mini": {
9556
- id: "arcee-ai/trinity-mini",
9557
- name: "Arcee AI: Trinity Mini",
9558
- api: "openai-completions",
9559
- provider: "openrouter",
9560
- baseUrl: "https://openrouter.ai/api/v1",
9561
- reasoning: true,
9562
- input: ["text"],
9563
- cost: {
9564
- input: 0.045,
9565
- output: 0.15,
9566
- cacheRead: 0,
9567
- cacheWrite: 0,
9568
- },
9569
- contextWindow: 131072,
9570
- maxTokens: 131072,
9571
- },
9572
9700
  "arcee-ai/virtuoso-large": {
9573
9701
  id: "arcee-ai/virtuoso-large",
9574
9702
  name: "Arcee AI: Virtuoso Large",
@@ -9833,9 +9961,9 @@ export const MODELS = {
9833
9961
  reasoning: true,
9834
9962
  input: ["text"],
9835
9963
  cost: {
9836
- input: 0.2288,
9837
- output: 0.3432,
9838
- cacheRead: 0.02288,
9964
+ input: 0.2145,
9965
+ output: 0.32175,
9966
+ cacheRead: 0.02145,
9839
9967
  cacheWrite: 0,
9840
9968
  },
9841
9969
  contextWindow: 131072,
@@ -9869,13 +9997,13 @@ export const MODELS = {
9869
9997
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9870
9998
  input: ["text"],
9871
9999
  cost: {
9872
- input: 0.09,
9873
- output: 0.18,
9874
- cacheRead: 0.018,
10000
+ input: 0.077,
10001
+ output: 0.154,
10002
+ cacheRead: 0.015399999999999999,
9875
10003
  cacheWrite: 0,
9876
10004
  },
9877
10005
  contextWindow: 1048576,
9878
- maxTokens: 65536,
10006
+ maxTokens: 384000,
9879
10007
  },
9880
10008
  "deepseek/deepseek-v4-pro": {
9881
10009
  id: "deepseek/deepseek-v4-pro",
@@ -10398,8 +10526,8 @@ export const MODELS = {
10398
10526
  reasoning: false,
10399
10527
  input: ["text", "image"],
10400
10528
  cost: {
10401
- input: 0.15,
10402
- output: 0.6,
10529
+ input: 0.19999999999999998,
10530
+ output: 0.7999999999999999,
10403
10531
  cacheRead: 0,
10404
10532
  cacheWrite: 0,
10405
10533
  },
@@ -10523,7 +10651,7 @@ export const MODELS = {
10523
10651
  cacheWrite: 0,
10524
10652
  },
10525
10653
  contextWindow: 1048576,
10526
- maxTokens: 512000,
10654
+ maxTokens: 131072,
10527
10655
  },
10528
10656
  "mistralai/codestral-2508": {
10529
10657
  id: "mistralai/codestral-2508",
@@ -10891,9 +11019,9 @@ export const MODELS = {
10891
11019
  reasoning: true,
10892
11020
  input: ["text", "image"],
10893
11021
  cost: {
10894
- input: 0.65,
11022
+ input: 0.66,
10895
11023
  output: 3.41,
10896
- cacheRead: 0.14,
11024
+ cacheRead: 0.15,
10897
11025
  cacheWrite: 0,
10898
11026
  },
10899
11027
  contextWindow: 262144,
@@ -10909,8 +11037,8 @@ export const MODELS = {
10909
11037
  input: ["text", "image"],
10910
11038
  cost: {
10911
11039
  input: 0.72,
10912
- output: 3.49,
10913
- cacheRead: 0.159,
11040
+ output: 3.5,
11041
+ cacheRead: 0.15,
10914
11042
  cacheWrite: 0,
10915
11043
  },
10916
11044
  contextWindow: 262144,
@@ -12281,7 +12409,7 @@ export const MODELS = {
12281
12409
  input: ["text"],
12282
12410
  cost: {
12283
12411
  input: 0.09,
12284
- output: 0.09999999999999999,
12412
+ output: 0.55,
12285
12413
  cacheRead: 0,
12286
12414
  cacheWrite: 0,
12287
12415
  },
@@ -13284,12 +13412,12 @@ export const MODELS = {
13284
13412
  input: ["text"],
13285
13413
  cost: {
13286
13414
  input: 0.43,
13287
- output: 1.74,
13415
+ output: 1.75,
13288
13416
  cacheRead: 0.08,
13289
13417
  cacheWrite: 0,
13290
13418
  },
13291
- contextWindow: 202752,
13292
- maxTokens: 131072,
13419
+ contextWindow: 200000,
13420
+ maxTokens: 16384,
13293
13421
  },
13294
13422
  "z-ai/glm-4.6v": {
13295
13423
  id: "z-ai/glm-4.6v",
@@ -13402,13 +13530,13 @@ export const MODELS = {
13402
13530
  reasoning: true,
13403
13531
  input: ["text"],
13404
13532
  cost: {
13405
- input: 0.54,
13406
- output: 1.76,
13407
- cacheRead: 0.09999999999999999,
13533
+ input: 0.42,
13534
+ output: 1.32,
13535
+ cacheRead: 0.078,
13408
13536
  cacheWrite: 0,
13409
13537
  },
13410
13538
  contextWindow: 1048576,
13411
- maxTokens: 101376,
13539
+ maxTokens: 131072,
13412
13540
  },
13413
13541
  "z-ai/glm-5v-turbo": {
13414
13542
  id: "z-ai/glm-5v-turbo",
@@ -13539,9 +13667,9 @@ export const MODELS = {
13539
13667
  reasoning: true,
13540
13668
  input: ["text", "image"],
13541
13669
  cost: {
13542
- input: 0.65,
13670
+ input: 0.66,
13543
13671
  output: 3.41,
13544
- cacheRead: 0.14,
13672
+ cacheRead: 0.15,
13545
13673
  cacheWrite: 0,
13546
13674
  },
13547
13675
  contextWindow: 262144,
@@ -14893,7 +15021,7 @@ export const MODELS = {
14893
15021
  cost: {
14894
15022
  input: 0.14,
14895
15023
  output: 0.28,
14896
- cacheRead: 0.0028,
15024
+ cacheRead: 0.028,
14897
15025
  cacheWrite: 0,
14898
15026
  },
14899
15027
  contextWindow: 1000000,
@@ -15154,6 +15282,23 @@ export const MODELS = {
15154
15282
  contextWindow: 1000000,
15155
15283
  maxTokens: 32000,
15156
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
+ },
15157
15302
  "kwaipilot/kat-coder-pro-v1": {
15158
15303
  id: "kwaipilot/kat-coder-pro-v1",
15159
15304
  name: "KAT-Coder-Pro V1",
@@ -15188,6 +15333,23 @@ export const MODELS = {
15188
15333
  contextWindow: 256000,
15189
15334
  maxTokens: 256000,
15190
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
+ },
15191
15353
  "meituan/longcat-flash-chat": {
15192
15354
  id: "meituan/longcat-flash-chat",
15193
15355
  name: "LongCat Flash Chat",
@@ -15348,7 +15510,7 @@ export const MODELS = {
15348
15510
  provider: "vercel-ai-gateway",
15349
15511
  baseUrl: "https://ai-gateway.vercel.sh",
15350
15512
  reasoning: true,
15351
- input: ["text"],
15513
+ input: ["text", "image"],
15352
15514
  cost: {
15353
15515
  input: 1.25,
15354
15516
  output: 4.25,
@@ -17164,9 +17326,9 @@ export const MODELS = {
17164
17326
  reasoning: true,
17165
17327
  input: ["text"],
17166
17328
  cost: {
17167
- input: 3,
17168
- output: 10.25,
17169
- cacheRead: 0.5,
17329
+ input: 2.0999999999999996,
17330
+ output: 6.6000000000000005,
17331
+ cacheRead: 0.21,
17170
17332
  cacheWrite: 0,
17171
17333
  },
17172
17334
  contextWindow: 1000000,