@elyracode/ai 0.9.35 → 0.9.36

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.
@@ -2955,6 +2955,23 @@ export const MODELS = {
2955
2955
  contextWindow: 1050000,
2956
2956
  maxTokens: 128000,
2957
2957
  },
2958
+ "gpt-6-astra": {
2959
+ id: "gpt-6-astra",
2960
+ name: "GPT-6 Astra",
2961
+ api: "azure-openai-responses",
2962
+ provider: "azure-openai-responses",
2963
+ baseUrl: "",
2964
+ reasoning: true,
2965
+ input: ["text", "image"],
2966
+ cost: {
2967
+ input: 10,
2968
+ output: 50,
2969
+ cacheRead: 1,
2970
+ cacheWrite: 12.5,
2971
+ },
2972
+ contextWindow: 1050000,
2973
+ maxTokens: 128000,
2974
+ },
2958
2975
  "gpt-realtime-2.1": {
2959
2976
  id: "gpt-realtime-2.1",
2960
2977
  name: "GPT-Realtime-2.1",
@@ -3130,6 +3147,24 @@ export const MODELS = {
3130
3147
  contextWindow: 1000000,
3131
3148
  maxTokens: 128000,
3132
3149
  },
3150
+ "claude-fable-5.1": {
3151
+ id: "claude-fable-5.1",
3152
+ name: "Claude Fable 5.1",
3153
+ api: "anthropic-messages",
3154
+ provider: "cloudflare-ai-gateway",
3155
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3156
+ reasoning: true,
3157
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3158
+ input: ["text", "image"],
3159
+ cost: {
3160
+ input: 10,
3161
+ output: 50,
3162
+ cacheRead: 0.25,
3163
+ cacheWrite: 12.5,
3164
+ },
3165
+ contextWindow: 1000000,
3166
+ maxTokens: 128000,
3167
+ },
3133
3168
  "claude-haiku-4.5": {
3134
3169
  id: "claude-haiku-4.5",
3135
3170
  name: "Claude Haiku 4.5 (latest)",
@@ -4298,6 +4333,23 @@ export const MODELS = {
4298
4333
  contextWindow: 262144,
4299
4334
  maxTokens: 65536,
4300
4335
  },
4336
+ "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
4337
+ id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
4338
+ name: "Qwen3.8 2.4T A95B",
4339
+ api: "anthropic-messages",
4340
+ provider: "fireworks",
4341
+ baseUrl: "https://api.fireworks.ai/inference",
4342
+ reasoning: true,
4343
+ input: ["text"],
4344
+ cost: {
4345
+ input: 2,
4346
+ output: 6,
4347
+ cacheRead: 0.25,
4348
+ cacheWrite: 0,
4349
+ },
4350
+ contextWindow: 262144,
4351
+ maxTokens: 131072,
4352
+ },
4301
4353
  "accounts/fireworks/models/qwen3p8-max": {
4302
4354
  id: "accounts/fireworks/models/qwen3p8-max",
4303
4355
  name: "Qwen3.8 Max",
@@ -4371,6 +4423,26 @@ export const MODELS = {
4371
4423
  contextWindow: 1000000,
4372
4424
  maxTokens: 128000,
4373
4425
  },
4426
+ "claude-fable-5.1": {
4427
+ id: "claude-fable-5.1",
4428
+ name: "Claude Fable 5.1",
4429
+ api: "openai-completions",
4430
+ provider: "github-copilot",
4431
+ baseUrl: "https://api.individual.githubcopilot.com",
4432
+ 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" },
4433
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4434
+ reasoning: true,
4435
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4436
+ input: ["text", "image"],
4437
+ cost: {
4438
+ input: 10,
4439
+ output: 50,
4440
+ cacheRead: 0.25,
4441
+ cacheWrite: 12.5,
4442
+ },
4443
+ contextWindow: 1000000,
4444
+ maxTokens: 128000,
4445
+ },
4374
4446
  "claude-haiku-4.5": {
4375
4447
  id: "claude-haiku-4.5",
4376
4448
  name: "Claude Haiku 4.5 (latest)",
@@ -4390,43 +4462,6 @@ export const MODELS = {
4390
4462
  contextWindow: 200000,
4391
4463
  maxTokens: 64000,
4392
4464
  },
4393
- "claude-opus-4.5": {
4394
- id: "claude-opus-4.5",
4395
- name: "Claude Opus 4.5 (latest)",
4396
- api: "anthropic-messages",
4397
- provider: "github-copilot",
4398
- baseUrl: "https://api.individual.githubcopilot.com",
4399
- 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" },
4400
- reasoning: true,
4401
- input: ["text", "image"],
4402
- cost: {
4403
- input: 5,
4404
- output: 25,
4405
- cacheRead: 0.5,
4406
- cacheWrite: 6.25,
4407
- },
4408
- contextWindow: 200000,
4409
- maxTokens: 32000,
4410
- },
4411
- "claude-opus-4.6": {
4412
- id: "claude-opus-4.6",
4413
- name: "Claude Opus 4.6",
4414
- api: "anthropic-messages",
4415
- provider: "github-copilot",
4416
- baseUrl: "https://api.individual.githubcopilot.com",
4417
- 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" },
4418
- reasoning: true,
4419
- thinkingLevelMap: { "xhigh": "max" },
4420
- input: ["text", "image"],
4421
- cost: {
4422
- input: 5,
4423
- output: 25,
4424
- cacheRead: 0.5,
4425
- cacheWrite: 6.25,
4426
- },
4427
- contextWindow: 1000000,
4428
- maxTokens: 32000,
4429
- },
4430
4465
  "claude-opus-4.7": {
4431
4466
  id: "claude-opus-4.7",
4432
4467
  name: "Claude Opus 4.7",
@@ -4484,44 +4519,6 @@ export const MODELS = {
4484
4519
  contextWindow: 1000000,
4485
4520
  maxTokens: 64000,
4486
4521
  },
4487
- "claude-sonnet-4": {
4488
- id: "claude-sonnet-4",
4489
- name: "Claude Sonnet 4 (latest)",
4490
- api: "anthropic-messages",
4491
- provider: "github-copilot",
4492
- baseUrl: "https://api.individual.githubcopilot.com",
4493
- 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" },
4494
- compat: { "supportsEagerToolInputStreaming": false },
4495
- reasoning: true,
4496
- input: ["text", "image"],
4497
- cost: {
4498
- input: 3,
4499
- output: 15,
4500
- cacheRead: 0.3,
4501
- cacheWrite: 3.75,
4502
- },
4503
- contextWindow: 216000,
4504
- maxTokens: 16000,
4505
- },
4506
- "claude-sonnet-4.5": {
4507
- id: "claude-sonnet-4.5",
4508
- name: "Claude Sonnet 4.5 (latest)",
4509
- api: "anthropic-messages",
4510
- provider: "github-copilot",
4511
- baseUrl: "https://api.individual.githubcopilot.com",
4512
- 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" },
4513
- compat: { "supportsEagerToolInputStreaming": false },
4514
- reasoning: true,
4515
- input: ["text", "image"],
4516
- cost: {
4517
- input: 3,
4518
- output: 15,
4519
- cacheRead: 0.3,
4520
- cacheWrite: 3.75,
4521
- },
4522
- contextWindow: 200000,
4523
- maxTokens: 32000,
4524
- },
4525
4522
  "claude-sonnet-4.6": {
4526
4523
  id: "claude-sonnet-4.6",
4527
4524
  name: "Claude Sonnet 4.6",
@@ -4559,25 +4556,6 @@ export const MODELS = {
4559
4556
  contextWindow: 1000000,
4560
4557
  maxTokens: 128000,
4561
4558
  },
4562
- "gemini-3.1-pro-preview": {
4563
- id: "gemini-3.1-pro-preview",
4564
- name: "Gemini 3.1 Pro Preview",
4565
- api: "openai-completions",
4566
- provider: "github-copilot",
4567
- baseUrl: "https://api.individual.githubcopilot.com",
4568
- 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" },
4569
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4570
- reasoning: true,
4571
- input: ["text", "image"],
4572
- cost: {
4573
- input: 2,
4574
- output: 12,
4575
- cacheRead: 0.2,
4576
- cacheWrite: 0,
4577
- },
4578
- contextWindow: 1000000,
4579
- maxTokens: 64000,
4580
- },
4581
4559
  "gemini-3.5-flash": {
4582
4560
  id: "gemini-3.5-flash",
4583
4561
  name: "Gemini 3.5 Flash",
@@ -4635,24 +4613,24 @@ export const MODELS = {
4635
4613
  contextWindow: 1000000,
4636
4614
  maxTokens: 64000,
4637
4615
  },
4638
- "gpt-4.1": {
4639
- id: "gpt-4.1",
4640
- name: "GPT-4.1",
4616
+ "gemini-3.8-flash": {
4617
+ id: "gemini-3.8-flash",
4618
+ name: "Gemini 3.8 Flash",
4641
4619
  api: "openai-completions",
4642
4620
  provider: "github-copilot",
4643
4621
  baseUrl: "https://api.individual.githubcopilot.com",
4644
4622
  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" },
4645
4623
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4646
- reasoning: false,
4624
+ reasoning: true,
4647
4625
  input: ["text", "image"],
4648
4626
  cost: {
4649
- input: 2,
4650
- output: 8,
4651
- cacheRead: 0.5,
4627
+ input: 0.75,
4628
+ output: 3.75,
4629
+ cacheRead: 0.075,
4652
4630
  cacheWrite: 0,
4653
4631
  },
4654
- contextWindow: 128000,
4655
- maxTokens: 16384,
4632
+ contextWindow: 1000000,
4633
+ maxTokens: 64000,
4656
4634
  },
4657
4635
  "gpt-5-mini": {
4658
4636
  id: "gpt-5-mini",
@@ -4673,44 +4651,6 @@ export const MODELS = {
4673
4651
  contextWindow: 264000,
4674
4652
  maxTokens: 64000,
4675
4653
  },
4676
- "gpt-5.2": {
4677
- id: "gpt-5.2",
4678
- name: "GPT-5.2",
4679
- api: "openai-responses",
4680
- provider: "github-copilot",
4681
- baseUrl: "https://api.individual.githubcopilot.com",
4682
- 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" },
4683
- reasoning: true,
4684
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4685
- input: ["text", "image"],
4686
- cost: {
4687
- input: 1.75,
4688
- output: 14,
4689
- cacheRead: 0.175,
4690
- cacheWrite: 0,
4691
- },
4692
- contextWindow: 400000,
4693
- maxTokens: 128000,
4694
- },
4695
- "gpt-5.2-codex": {
4696
- id: "gpt-5.2-codex",
4697
- name: "GPT-5.2 Codex",
4698
- api: "openai-responses",
4699
- provider: "github-copilot",
4700
- baseUrl: "https://api.individual.githubcopilot.com",
4701
- 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" },
4702
- reasoning: true,
4703
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4704
- input: ["text", "image"],
4705
- cost: {
4706
- input: 1.75,
4707
- output: 14,
4708
- cacheRead: 0.175,
4709
- cacheWrite: 0,
4710
- },
4711
- contextWindow: 400000,
4712
- maxTokens: 128000,
4713
- },
4714
4654
  "gpt-5.3-codex": {
4715
4655
  id: "gpt-5.3-codex",
4716
4656
  name: "GPT-5.3 Codex",
@@ -4836,10 +4776,10 @@ export const MODELS = {
4836
4776
  thinkingLevelMap: { "off": null },
4837
4777
  input: ["text", "image"],
4838
4778
  cost: {
4839
- input: 2,
4840
- output: 10,
4841
- cacheRead: 0.2,
4842
- cacheWrite: 2.5,
4779
+ input: 4,
4780
+ output: 20,
4781
+ cacheRead: 0.4,
4782
+ cacheWrite: 5,
4843
4783
  },
4844
4784
  contextWindow: 1050000,
4845
4785
  maxTokens: 128000,
@@ -4863,6 +4803,25 @@ export const MODELS = {
4863
4803
  contextWindow: 1050000,
4864
4804
  maxTokens: 128000,
4865
4805
  },
4806
+ "gpt-6-astra": {
4807
+ id: "gpt-6-astra",
4808
+ name: "GPT-6 Astra",
4809
+ api: "openai-completions",
4810
+ provider: "github-copilot",
4811
+ baseUrl: "https://api.individual.githubcopilot.com",
4812
+ 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" },
4813
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4814
+ reasoning: true,
4815
+ input: ["text", "image"],
4816
+ cost: {
4817
+ input: 10,
4818
+ output: 50,
4819
+ cacheRead: 1,
4820
+ cacheWrite: 12.5,
4821
+ },
4822
+ contextWindow: 1050000,
4823
+ maxTokens: 128000,
4824
+ },
4866
4825
  "grok-4.5": {
4867
4826
  id: "grok-4.5",
4868
4827
  name: "Grok 4.5",
@@ -8603,6 +8562,23 @@ export const MODELS = {
8603
8562
  contextWindow: 1050000,
8604
8563
  maxTokens: 128000,
8605
8564
  },
8565
+ "gpt-6-astra": {
8566
+ id: "gpt-6-astra",
8567
+ name: "GPT-6 Astra",
8568
+ api: "openai-responses",
8569
+ provider: "openai",
8570
+ baseUrl: "https://api.openai.com/v1",
8571
+ reasoning: true,
8572
+ input: ["text", "image"],
8573
+ cost: {
8574
+ input: 10,
8575
+ output: 50,
8576
+ cacheRead: 1,
8577
+ cacheWrite: 12.5,
8578
+ },
8579
+ contextWindow: 1050000,
8580
+ maxTokens: 128000,
8581
+ },
8606
8582
  "gpt-realtime-2.1": {
8607
8583
  id: "gpt-realtime-2.1",
8608
8584
  name: "GPT-Realtime-2.1",
@@ -9149,6 +9125,25 @@ export const MODELS = {
9149
9125
  contextWindow: 1000000,
9150
9126
  maxTokens: 384000,
9151
9127
  },
9128
+ "deepseek-v4-flash-vision-exp": {
9129
+ id: "deepseek-v4-flash-vision-exp",
9130
+ name: "DeepSeek V4 Flash Vision Exp",
9131
+ api: "openai-completions",
9132
+ provider: "opencode",
9133
+ baseUrl: "https://opencode.ai/zen/v1",
9134
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9135
+ reasoning: true,
9136
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9137
+ input: ["text", "image"],
9138
+ cost: {
9139
+ input: 0.14,
9140
+ output: 0.28,
9141
+ cacheRead: 0.028,
9142
+ cacheWrite: 0,
9143
+ },
9144
+ contextWindow: 1000000,
9145
+ maxTokens: 384000,
9146
+ },
9152
9147
  "deepseek-v4-pro": {
9153
9148
  id: "deepseek-v4-pro",
9154
9149
  name: "DeepSeek V4 Pro",
@@ -9335,11 +9330,45 @@ export const MODELS = {
9335
9330
  provider: "opencode",
9336
9331
  baseUrl: "https://opencode.ai/zen/v1",
9337
9332
  reasoning: true,
9338
- input: ["text"],
9333
+ input: ["text"],
9334
+ cost: {
9335
+ input: 1.4,
9336
+ output: 4.4,
9337
+ cacheRead: 0.26,
9338
+ cacheWrite: 0,
9339
+ },
9340
+ contextWindow: 1000000,
9341
+ maxTokens: 131072,
9342
+ },
9343
+ "glm-5.3": {
9344
+ id: "glm-5.3",
9345
+ name: "GLM-5.3",
9346
+ api: "openai-completions",
9347
+ provider: "opencode",
9348
+ baseUrl: "https://opencode.ai/zen/v1",
9349
+ reasoning: true,
9350
+ input: ["text"],
9351
+ cost: {
9352
+ input: 1.4,
9353
+ output: 4.4,
9354
+ cacheRead: 0.26,
9355
+ cacheWrite: 0,
9356
+ },
9357
+ contextWindow: 1000000,
9358
+ maxTokens: 131072,
9359
+ },
9360
+ "glm-5.3-flash": {
9361
+ id: "glm-5.3-flash",
9362
+ name: "GLM-5.3-Flash",
9363
+ api: "openai-completions",
9364
+ provider: "opencode",
9365
+ baseUrl: "https://opencode.ai/zen/v1",
9366
+ reasoning: true,
9367
+ input: ["text", "image"],
9339
9368
  cost: {
9340
- input: 1.4,
9341
- output: 4.4,
9342
- cacheRead: 0.26,
9369
+ input: 0.15,
9370
+ output: 0.5,
9371
+ cacheRead: 0.03,
9343
9372
  cacheWrite: 0,
9344
9373
  },
9345
9374
  contextWindow: 1000000,
@@ -9687,6 +9716,23 @@ export const MODELS = {
9687
9716
  contextWindow: 1050000,
9688
9717
  maxTokens: 128000,
9689
9718
  },
9719
+ "gpt-6-astra": {
9720
+ id: "gpt-6-astra",
9721
+ name: "GPT-6 Astra",
9722
+ api: "openai-responses",
9723
+ provider: "opencode",
9724
+ baseUrl: "https://opencode.ai/zen/v1",
9725
+ reasoning: true,
9726
+ input: ["text", "image"],
9727
+ cost: {
9728
+ input: 10,
9729
+ output: 50,
9730
+ cacheRead: 1,
9731
+ cacheWrite: 12.5,
9732
+ },
9733
+ contextWindow: 1050000,
9734
+ maxTokens: 128000,
9735
+ },
9690
9736
  "grok-4.5": {
9691
9737
  id: "grok-4.5",
9692
9738
  name: "Grok 4.5",
@@ -9925,6 +9971,23 @@ export const MODELS = {
9925
9971
  contextWindow: 1048576,
9926
9972
  maxTokens: 131072,
9927
9973
  },
9974
+ "muse-spark-1.3": {
9975
+ id: "muse-spark-1.3",
9976
+ name: "Muse Spark 1.3",
9977
+ api: "openai-responses",
9978
+ provider: "opencode",
9979
+ baseUrl: "https://opencode.ai/zen/v1",
9980
+ reasoning: true,
9981
+ input: ["text", "image"],
9982
+ cost: {
9983
+ input: 1.25,
9984
+ output: 4.25,
9985
+ cacheRead: 0.15,
9986
+ cacheWrite: 0,
9987
+ },
9988
+ contextWindow: 1048576,
9989
+ maxTokens: 131072,
9990
+ },
9928
9991
  "muse-spark-1.3-contributor-free": {
9929
9992
  id: "muse-spark-1.3-contributor-free",
9930
9993
  name: "Muse Spark 1.3 Free",
@@ -10376,6 +10439,23 @@ export const MODELS = {
10376
10439
  contextWindow: 1048576,
10377
10440
  maxTokens: 131072,
10378
10441
  },
10442
+ "omen-alpha": {
10443
+ id: "omen-alpha",
10444
+ name: "Omen Alpha",
10445
+ api: "openai-completions",
10446
+ provider: "opencode-go",
10447
+ baseUrl: "https://opencode.ai/zen/go/v1",
10448
+ reasoning: true,
10449
+ input: ["text", "image"],
10450
+ cost: {
10451
+ input: 0.2,
10452
+ output: 0.66,
10453
+ cacheRead: 0.04,
10454
+ cacheWrite: 0,
10455
+ },
10456
+ contextWindow: 500000,
10457
+ maxTokens: 128000,
10458
+ },
10379
10459
  "qwen3.6-plus": {
10380
10460
  id: "qwen3.6-plus",
10381
10461
  name: "Qwen3.6 Plus",
@@ -11403,9 +11483,9 @@ export const MODELS = {
11403
11483
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11404
11484
  input: ["text"],
11405
11485
  cost: {
11406
- input: 0.07784,
11407
- output: 0.15568,
11408
- cacheRead: 0.015568,
11486
+ input: 0.08358,
11487
+ output: 0.16716,
11488
+ cacheRead: 0.016715999999999998,
11409
11489
  cacheWrite: 0,
11410
11490
  },
11411
11491
  contextWindow: 1048576,
@@ -11479,9 +11559,9 @@ export const MODELS = {
11479
11559
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11480
11560
  input: ["text"],
11481
11561
  cost: {
11482
- input: 1.030776,
11483
- output: 2.061552,
11484
- cacheRead: 0.085898,
11562
+ input: 0.8193659999999999,
11563
+ output: 1.6387319999999999,
11564
+ cacheRead: 0.0682805,
11485
11565
  cacheWrite: 0,
11486
11566
  },
11487
11567
  contextWindow: 1048576,
@@ -11498,9 +11578,9 @@ export const MODELS = {
11498
11578
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11499
11579
  input: ["text"],
11500
11580
  cost: {
11501
- input: 0.66,
11502
- output: 1.9800000000000002,
11503
- cacheRead: 0.022,
11581
+ input: 0.57948,
11582
+ output: 1.73844,
11583
+ cacheRead: 0.019316,
11504
11584
  cacheWrite: 0,
11505
11585
  },
11506
11586
  contextWindow: 1048576,
@@ -12120,23 +12200,6 @@ export const MODELS = {
12120
12200
  contextWindow: 262144,
12121
12201
  maxTokens: 32768,
12122
12202
  },
12123
- "ibm-granite/granite-4.1-8b": {
12124
- id: "ibm-granite/granite-4.1-8b",
12125
- name: "IBM: Granite 4.1 8B",
12126
- api: "openai-completions",
12127
- provider: "openrouter",
12128
- baseUrl: "https://openrouter.ai/api/v1",
12129
- reasoning: false,
12130
- input: ["text"],
12131
- cost: {
12132
- input: 0.049999999999999996,
12133
- output: 0.09999999999999999,
12134
- cacheRead: 0.049999999999999996,
12135
- cacheWrite: 0,
12136
- },
12137
- contextWindow: 131072,
12138
- maxTokens: 117964,
12139
- },
12140
12203
  "ibm-granite/granite-4.2-8b": {
12141
12204
  id: "ibm-granite/granite-4.2-8b",
12142
12205
  name: "IBM: Granite 4.2 8B",
@@ -12190,7 +12253,7 @@ export const MODELS = {
12190
12253
  },
12191
12254
  "inclusionai/ling-3.0-flash": {
12192
12255
  id: "inclusionai/ling-3.0-flash",
12193
- name: "Ling-3.0-flash",
12256
+ name: "inclusionAI: Ling 3.0 Flash",
12194
12257
  api: "openai-completions",
12195
12258
  provider: "openrouter",
12196
12259
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12207,7 +12270,7 @@ export const MODELS = {
12207
12270
  },
12208
12271
  "inclusionai/ling-3.0-flash-fin": {
12209
12272
  id: "inclusionai/ling-3.0-flash-fin",
12210
- name: "Ling 3.0 Flash Fin",
12273
+ name: "inclusionAI: Ling 3.0 Flash Fin",
12211
12274
  api: "openai-completions",
12212
12275
  provider: "openrouter",
12213
12276
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12224,7 +12287,24 @@ export const MODELS = {
12224
12287
  },
12225
12288
  "inclusionai/ling-3.0-flash-fin:free": {
12226
12289
  id: "inclusionai/ling-3.0-flash-fin:free",
12227
- name: "Ling 3.0 Flash Fin (free)",
12290
+ name: "inclusionAI: Ling 3.0 Flash Fin (free)",
12291
+ api: "openai-completions",
12292
+ provider: "openrouter",
12293
+ baseUrl: "https://openrouter.ai/api/v1",
12294
+ reasoning: true,
12295
+ input: ["text"],
12296
+ cost: {
12297
+ input: 0,
12298
+ output: 0,
12299
+ cacheRead: 0,
12300
+ cacheWrite: 0,
12301
+ },
12302
+ contextWindow: 262144,
12303
+ maxTokens: 32768,
12304
+ },
12305
+ "inclusionai/ling-3.0-flash-sante:free": {
12306
+ id: "inclusionai/ling-3.0-flash-sante:free",
12307
+ name: "inclusionAI: Ling 3.0 Flash Sante (free)",
12228
12308
  api: "openai-completions",
12229
12309
  provider: "openrouter",
12230
12310
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12848,8 +12928,8 @@ export const MODELS = {
12848
12928
  cacheRead: 0,
12849
12929
  cacheWrite: 0,
12850
12930
  },
12851
- contextWindow: 262144,
12852
- maxTokens: 209715,
12931
+ contextWindow: 32768,
12932
+ maxTokens: 26214,
12853
12933
  },
12854
12934
  "mistralai/mistral-medium-3.1": {
12855
12935
  id: "mistralai/mistral-medium-3.1",
@@ -13217,13 +13297,13 @@ export const MODELS = {
13217
13297
  reasoning: true,
13218
13298
  input: ["text"],
13219
13299
  cost: {
13220
- input: 0.6,
13221
- output: 2.4,
13222
- cacheRead: 0.12,
13300
+ input: 0.625,
13301
+ output: 3.125,
13302
+ cacheRead: 0.1875,
13223
13303
  cacheWrite: 0,
13224
13304
  },
13225
13305
  contextWindow: 262144,
13226
- maxTokens: 182520,
13306
+ maxTokens: 32768,
13227
13307
  },
13228
13308
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13229
13309
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14315,6 +14395,74 @@ export const MODELS = {
14315
14395
  contextWindow: 400000,
14316
14396
  maxTokens: 128000,
14317
14397
  },
14398
+ "openai/gpt-6-astra": {
14399
+ id: "openai/gpt-6-astra",
14400
+ name: "OpenAI: GPT-6 Astra",
14401
+ api: "openai-completions",
14402
+ provider: "openrouter",
14403
+ baseUrl: "https://openrouter.ai/api/v1",
14404
+ reasoning: true,
14405
+ input: ["text", "image"],
14406
+ cost: {
14407
+ input: 10,
14408
+ output: 50,
14409
+ cacheRead: 1,
14410
+ cacheWrite: 12.5,
14411
+ },
14412
+ contextWindow: 1050000,
14413
+ maxTokens: 128000,
14414
+ },
14415
+ "openai/gpt-6-astra-pro": {
14416
+ id: "openai/gpt-6-astra-pro",
14417
+ name: "OpenAI: GPT-6 Astra Pro",
14418
+ api: "openai-completions",
14419
+ provider: "openrouter",
14420
+ baseUrl: "https://openrouter.ai/api/v1",
14421
+ reasoning: true,
14422
+ input: ["text", "image"],
14423
+ cost: {
14424
+ input: 10,
14425
+ output: 50,
14426
+ cacheRead: 1,
14427
+ cacheWrite: 12.5,
14428
+ },
14429
+ contextWindow: 1050000,
14430
+ maxTokens: 128000,
14431
+ },
14432
+ "openai/gpt-6-astra-pro:batch": {
14433
+ id: "openai/gpt-6-astra-pro:batch",
14434
+ name: "OpenAI: GPT-6 Astra Pro (batch)",
14435
+ api: "openai-completions",
14436
+ provider: "openrouter",
14437
+ baseUrl: "https://openrouter.ai/api/v1",
14438
+ reasoning: true,
14439
+ input: ["text", "image"],
14440
+ cost: {
14441
+ input: 5,
14442
+ output: 25,
14443
+ cacheRead: 0.5,
14444
+ cacheWrite: 6.25,
14445
+ },
14446
+ contextWindow: 1050000,
14447
+ maxTokens: 128000,
14448
+ },
14449
+ "openai/gpt-6-astra:batch": {
14450
+ id: "openai/gpt-6-astra:batch",
14451
+ name: "OpenAI: GPT-6 Astra (batch)",
14452
+ api: "openai-completions",
14453
+ provider: "openrouter",
14454
+ baseUrl: "https://openrouter.ai/api/v1",
14455
+ reasoning: true,
14456
+ input: ["text", "image"],
14457
+ cost: {
14458
+ input: 5,
14459
+ output: 25,
14460
+ cacheRead: 0.5,
14461
+ cacheWrite: 6.25,
14462
+ },
14463
+ contextWindow: 1050000,
14464
+ maxTokens: 128000,
14465
+ },
14318
14466
  "openai/gpt-audio": {
14319
14467
  id: "openai/gpt-audio",
14320
14468
  name: "OpenAI: GPT Audio",
@@ -14834,13 +14982,13 @@ export const MODELS = {
14834
14982
  reasoning: false,
14835
14983
  input: ["text"],
14836
14984
  cost: {
14837
- input: 0.0875,
14838
- output: 0.35,
14839
- cacheRead: 0.0175,
14985
+ input: 0.09,
14986
+ output: 0.55,
14987
+ cacheRead: 0,
14840
14988
  cacheWrite: 0,
14841
14989
  },
14842
14990
  contextWindow: 262144,
14843
- maxTokens: 235929,
14991
+ maxTokens: 16384,
14844
14992
  },
14845
14993
  "qwen/qwen3-235b-a22b-thinking-2507": {
14846
14994
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -15259,13 +15407,13 @@ export const MODELS = {
15259
15407
  reasoning: true,
15260
15408
  input: ["text", "image"],
15261
15409
  cost: {
15262
- input: 0.25,
15410
+ input: 0.3125,
15263
15411
  output: 1.25,
15264
- cacheRead: 0.25,
15412
+ cacheRead: 0.15625,
15265
15413
  cacheWrite: 0,
15266
15414
  },
15267
15415
  contextWindow: 262144,
15268
- maxTokens: 235929,
15416
+ maxTokens: 16384,
15269
15417
  },
15270
15418
  "qwen/qwen3.5-397b-a17b": {
15271
15419
  id: "qwen/qwen3.5-397b-a17b",
@@ -15378,13 +15526,13 @@ export const MODELS = {
15378
15526
  reasoning: true,
15379
15527
  input: ["text", "image"],
15380
15528
  cost: {
15381
- input: 0.6,
15382
- output: 3.5999999999999996,
15383
- cacheRead: 0.12,
15529
+ input: 0.3,
15530
+ output: 2,
15531
+ cacheRead: 0.03,
15384
15532
  cacheWrite: 0,
15385
15533
  },
15386
15534
  contextWindow: 262144,
15387
- maxTokens: 235929,
15535
+ maxTokens: 65536,
15388
15536
  },
15389
15537
  "qwen/qwen3.6-35b-a3b": {
15390
15538
  id: "qwen/qwen3.6-35b-a3b",
@@ -15573,9 +15721,9 @@ export const MODELS = {
15573
15721
  contextWindow: 1000000,
15574
15722
  maxTokens: 131072,
15575
15723
  },
15576
- "qwen/qwen3.8-max": {
15577
- id: "qwen/qwen3.8-max",
15578
- name: "Qwen: Qwen3.8 Max",
15724
+ "qwen/qwen3.8-max-0902": {
15725
+ id: "qwen/qwen3.8-max-0902",
15726
+ name: "Qwen: Qwen3.8 Max (0902)",
15579
15727
  api: "openai-completions",
15580
15728
  provider: "openrouter",
15581
15729
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15930,6 +16078,23 @@ export const MODELS = {
15930
16078
  contextWindow: 1000000,
15931
16079
  maxTokens: 900000,
15932
16080
  },
16081
+ "x-ai/grok-4.3:batch": {
16082
+ id: "x-ai/grok-4.3:batch",
16083
+ name: "SpaceXAI: Grok 4.3 (batch)",
16084
+ api: "openai-completions",
16085
+ provider: "openrouter",
16086
+ baseUrl: "https://openrouter.ai/api/v1",
16087
+ reasoning: true,
16088
+ input: ["text", "image"],
16089
+ cost: {
16090
+ input: 1,
16091
+ output: 2,
16092
+ cacheRead: 0.16,
16093
+ cacheWrite: 0,
16094
+ },
16095
+ contextWindow: 1000000,
16096
+ maxTokens: 900000,
16097
+ },
15933
16098
  "x-ai/grok-4.5": {
15934
16099
  id: "x-ai/grok-4.5",
15935
16100
  name: "SpaceXAI: Grok 4.5",
@@ -16367,13 +16532,13 @@ export const MODELS = {
16367
16532
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
16368
16533
  input: ["text"],
16369
16534
  cost: {
16370
- input: 0.049999999999999996,
16371
- output: 0.16,
16372
- cacheRead: 0.013000000000000001,
16535
+ input: 0.049980000000000004,
16536
+ output: 0.09996000000000001,
16537
+ cacheRead: 0.009996000000000001,
16373
16538
  cacheWrite: 0,
16374
16539
  },
16375
16540
  contextWindow: 1310720,
16376
- maxTokens: 393216,
16541
+ maxTokens: 131072,
16377
16542
  },
16378
16543
  "~google/gemini-flash-latest": {
16379
16544
  id: "~google/gemini-flash-latest",
@@ -16418,9 +16583,9 @@ export const MODELS = {
16418
16583
  reasoning: true,
16419
16584
  input: ["text", "image"],
16420
16585
  cost: {
16421
- input: 2.5,
16422
- output: 14,
16423
- cacheRead: 0.29,
16586
+ input: 2.5500000000000003,
16587
+ output: 12.75,
16588
+ cacheRead: 0.25599998999999996,
16424
16589
  cacheWrite: 0,
16425
16590
  },
16426
16591
  contextWindow: 1048576,
@@ -16486,13 +16651,13 @@ export const MODELS = {
16486
16651
  reasoning: true,
16487
16652
  input: ["text", "image"],
16488
16653
  cost: {
16489
- input: 0.07125000000000001,
16490
- output: 0.2375,
16491
- cacheRead: 0.01425,
16654
+ input: 0.075,
16655
+ output: 0.25,
16656
+ cacheRead: 0.015,
16492
16657
  cacheWrite: 0,
16493
16658
  },
16494
16659
  contextWindow: 1310720,
16495
- maxTokens: 131072,
16660
+ maxTokens: 943718,
16496
16661
  },
16497
16662
  "~z-ai/glm-latest": {
16498
16663
  id: "~z-ai/glm-latest",
@@ -16503,13 +16668,13 @@ export const MODELS = {
16503
16668
  reasoning: true,
16504
16669
  input: ["text"],
16505
16670
  cost: {
16506
- input: 1.1480000000000001,
16507
- output: 3.608,
16508
- cacheRead: 0.18860000000000002,
16671
+ input: 1.15,
16672
+ output: 3.5,
16673
+ cacheRead: 0.09999999999999999,
16509
16674
  cacheWrite: 0,
16510
16675
  },
16511
16676
  contextWindow: 1310720,
16512
- maxTokens: 943718,
16677
+ maxTokens: 235929,
16513
16678
  },
16514
16679
  },
16515
16680
  "together": {
@@ -18328,6 +18493,40 @@ export const MODELS = {
18328
18493
  contextWindow: 256000,
18329
18494
  maxTokens: 32000,
18330
18495
  },
18496
+ "inclusionai/ling-3.0-flash-sante": {
18497
+ id: "inclusionai/ling-3.0-flash-sante",
18498
+ name: "Ling 3.0 Flash Sante",
18499
+ api: "anthropic-messages",
18500
+ provider: "vercel-ai-gateway",
18501
+ baseUrl: "https://ai-gateway.vercel.sh",
18502
+ reasoning: true,
18503
+ input: ["text"],
18504
+ cost: {
18505
+ input: 0,
18506
+ output: 0,
18507
+ cacheRead: 0,
18508
+ cacheWrite: 0,
18509
+ },
18510
+ contextWindow: 256000,
18511
+ maxTokens: 32000,
18512
+ },
18513
+ "inclusionai/ling-3.0-flash-sante-free": {
18514
+ id: "inclusionai/ling-3.0-flash-sante-free",
18515
+ name: "Ling 3.0 Flash Sante (Free)",
18516
+ api: "anthropic-messages",
18517
+ provider: "vercel-ai-gateway",
18518
+ baseUrl: "https://ai-gateway.vercel.sh",
18519
+ reasoning: true,
18520
+ input: ["text"],
18521
+ cost: {
18522
+ input: 0,
18523
+ output: 0,
18524
+ cacheRead: 0,
18525
+ cacheWrite: 0,
18526
+ },
18527
+ contextWindow: 256000,
18528
+ maxTokens: 32000,
18529
+ },
18331
18530
  "interfaze/interfaze-beta": {
18332
18531
  id: "interfaze/interfaze-beta",
18333
18532
  name: "Interfaze Beta",
@@ -19902,7 +20101,7 @@ export const MODELS = {
19902
20101
  input: 0.39999999999999997,
19903
20102
  output: 2.4,
19904
20103
  cacheRead: 0.04,
19905
- cacheWrite: 0.25,
20104
+ cacheWrite: 0.5,
19906
20105
  },
19907
20106
  contextWindow: 1050000,
19908
20107
  maxTokens: 128000,
@@ -19936,7 +20135,7 @@ export const MODELS = {
19936
20135
  input: 4,
19937
20136
  output: 20,
19938
20137
  cacheRead: 0.39999999999999997,
19939
- cacheWrite: 2.5,
20138
+ cacheWrite: 5,
19940
20139
  },
19941
20140
  contextWindow: 1050000,
19942
20141
  maxTokens: 128000,
@@ -19970,7 +20169,41 @@ export const MODELS = {
19970
20169
  input: 4,
19971
20170
  output: 24,
19972
20171
  cacheRead: 0.39999999999999997,
19973
- cacheWrite: 2.5,
20172
+ cacheWrite: 5,
20173
+ },
20174
+ contextWindow: 1050000,
20175
+ maxTokens: 128000,
20176
+ },
20177
+ "openai/gpt-6-astra": {
20178
+ id: "openai/gpt-6-astra",
20179
+ name: "GPT-6 Astra",
20180
+ api: "anthropic-messages",
20181
+ provider: "vercel-ai-gateway",
20182
+ baseUrl: "https://ai-gateway.vercel.sh",
20183
+ reasoning: true,
20184
+ input: ["text", "image"],
20185
+ cost: {
20186
+ input: 10,
20187
+ output: 50,
20188
+ cacheRead: 1,
20189
+ cacheWrite: 12.5,
20190
+ },
20191
+ contextWindow: 1050000,
20192
+ maxTokens: 128000,
20193
+ },
20194
+ "openai/gpt-6-astra-fast": {
20195
+ id: "openai/gpt-6-astra-fast",
20196
+ name: "GPT-6 Astra (Fast)",
20197
+ api: "anthropic-messages",
20198
+ provider: "vercel-ai-gateway",
20199
+ baseUrl: "https://ai-gateway.vercel.sh",
20200
+ reasoning: true,
20201
+ input: ["text", "image"],
20202
+ cost: {
20203
+ input: 20,
20204
+ output: 100,
20205
+ cacheRead: 2,
20206
+ cacheWrite: 25,
19974
20207
  },
19975
20208
  contextWindow: 1050000,
19976
20209
  maxTokens: 128000,