@elyracode/ai 0.9.34 → 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)",
@@ -4035,9 +4070,26 @@ export const MODELS = {
4035
4070
  reasoning: true,
4036
4071
  input: ["text"],
4037
4072
  cost: {
4038
- input: 0.14,
4039
- output: 0.28,
4040
- cacheRead: 0.028,
4073
+ input: 0.22,
4074
+ output: 0.66,
4075
+ cacheRead: 0.007,
4076
+ cacheWrite: 0,
4077
+ },
4078
+ contextWindow: 1000000,
4079
+ maxTokens: 384000,
4080
+ },
4081
+ "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4082
+ id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4083
+ name: "DeepSeek V4 Flash Vision Exp",
4084
+ api: "anthropic-messages",
4085
+ provider: "fireworks",
4086
+ baseUrl: "https://api.fireworks.ai/inference",
4087
+ reasoning: true,
4088
+ input: ["text", "image"],
4089
+ cost: {
4090
+ input: 0.22,
4091
+ output: 0.66,
4092
+ cacheRead: 0.007,
4041
4093
  cacheWrite: 0,
4042
4094
  },
4043
4095
  contextWindow: 1000000,
@@ -4105,7 +4157,7 @@ export const MODELS = {
4105
4157
  cost: {
4106
4158
  input: 0.15,
4107
4159
  output: 0.5,
4108
- cacheRead: 0.029,
4160
+ cacheRead: 0.03,
4109
4161
  cacheWrite: 0,
4110
4162
  },
4111
4163
  contextWindow: 1000000,
@@ -4281,6 +4333,23 @@ export const MODELS = {
4281
4333
  contextWindow: 262144,
4282
4334
  maxTokens: 65536,
4283
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
+ },
4284
4353
  "accounts/fireworks/models/qwen3p8-max": {
4285
4354
  id: "accounts/fireworks/models/qwen3p8-max",
4286
4355
  name: "Qwen3.8 Max",
@@ -4354,6 +4423,26 @@ export const MODELS = {
4354
4423
  contextWindow: 1000000,
4355
4424
  maxTokens: 128000,
4356
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
+ },
4357
4446
  "claude-haiku-4.5": {
4358
4447
  id: "claude-haiku-4.5",
4359
4448
  name: "Claude Haiku 4.5 (latest)",
@@ -4373,43 +4462,6 @@ export const MODELS = {
4373
4462
  contextWindow: 200000,
4374
4463
  maxTokens: 64000,
4375
4464
  },
4376
- "claude-opus-4.5": {
4377
- id: "claude-opus-4.5",
4378
- name: "Claude Opus 4.5 (latest)",
4379
- api: "anthropic-messages",
4380
- provider: "github-copilot",
4381
- baseUrl: "https://api.individual.githubcopilot.com",
4382
- 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" },
4383
- reasoning: true,
4384
- input: ["text", "image"],
4385
- cost: {
4386
- input: 5,
4387
- output: 25,
4388
- cacheRead: 0.5,
4389
- cacheWrite: 6.25,
4390
- },
4391
- contextWindow: 200000,
4392
- maxTokens: 32000,
4393
- },
4394
- "claude-opus-4.6": {
4395
- id: "claude-opus-4.6",
4396
- name: "Claude Opus 4.6",
4397
- api: "anthropic-messages",
4398
- provider: "github-copilot",
4399
- baseUrl: "https://api.individual.githubcopilot.com",
4400
- 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" },
4401
- reasoning: true,
4402
- thinkingLevelMap: { "xhigh": "max" },
4403
- input: ["text", "image"],
4404
- cost: {
4405
- input: 5,
4406
- output: 25,
4407
- cacheRead: 0.5,
4408
- cacheWrite: 6.25,
4409
- },
4410
- contextWindow: 1000000,
4411
- maxTokens: 32000,
4412
- },
4413
4465
  "claude-opus-4.7": {
4414
4466
  id: "claude-opus-4.7",
4415
4467
  name: "Claude Opus 4.7",
@@ -4467,44 +4519,6 @@ export const MODELS = {
4467
4519
  contextWindow: 1000000,
4468
4520
  maxTokens: 64000,
4469
4521
  },
4470
- "claude-sonnet-4": {
4471
- id: "claude-sonnet-4",
4472
- name: "Claude Sonnet 4 (latest)",
4473
- api: "anthropic-messages",
4474
- provider: "github-copilot",
4475
- baseUrl: "https://api.individual.githubcopilot.com",
4476
- 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" },
4477
- compat: { "supportsEagerToolInputStreaming": false },
4478
- reasoning: true,
4479
- input: ["text", "image"],
4480
- cost: {
4481
- input: 3,
4482
- output: 15,
4483
- cacheRead: 0.3,
4484
- cacheWrite: 3.75,
4485
- },
4486
- contextWindow: 216000,
4487
- maxTokens: 16000,
4488
- },
4489
- "claude-sonnet-4.5": {
4490
- id: "claude-sonnet-4.5",
4491
- name: "Claude Sonnet 4.5 (latest)",
4492
- api: "anthropic-messages",
4493
- provider: "github-copilot",
4494
- baseUrl: "https://api.individual.githubcopilot.com",
4495
- 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" },
4496
- compat: { "supportsEagerToolInputStreaming": false },
4497
- reasoning: true,
4498
- input: ["text", "image"],
4499
- cost: {
4500
- input: 3,
4501
- output: 15,
4502
- cacheRead: 0.3,
4503
- cacheWrite: 3.75,
4504
- },
4505
- contextWindow: 200000,
4506
- maxTokens: 32000,
4507
- },
4508
4522
  "claude-sonnet-4.6": {
4509
4523
  id: "claude-sonnet-4.6",
4510
4524
  name: "Claude Sonnet 4.6",
@@ -4542,25 +4556,6 @@ export const MODELS = {
4542
4556
  contextWindow: 1000000,
4543
4557
  maxTokens: 128000,
4544
4558
  },
4545
- "gemini-3.1-pro-preview": {
4546
- id: "gemini-3.1-pro-preview",
4547
- name: "Gemini 3.1 Pro Preview",
4548
- api: "openai-completions",
4549
- provider: "github-copilot",
4550
- baseUrl: "https://api.individual.githubcopilot.com",
4551
- 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" },
4552
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4553
- reasoning: true,
4554
- input: ["text", "image"],
4555
- cost: {
4556
- input: 2,
4557
- output: 12,
4558
- cacheRead: 0.2,
4559
- cacheWrite: 0,
4560
- },
4561
- contextWindow: 1000000,
4562
- maxTokens: 64000,
4563
- },
4564
4559
  "gemini-3.5-flash": {
4565
4560
  id: "gemini-3.5-flash",
4566
4561
  name: "Gemini 3.5 Flash",
@@ -4618,24 +4613,24 @@ export const MODELS = {
4618
4613
  contextWindow: 1000000,
4619
4614
  maxTokens: 64000,
4620
4615
  },
4621
- "gpt-4.1": {
4622
- id: "gpt-4.1",
4623
- name: "GPT-4.1",
4616
+ "gemini-3.8-flash": {
4617
+ id: "gemini-3.8-flash",
4618
+ name: "Gemini 3.8 Flash",
4624
4619
  api: "openai-completions",
4625
4620
  provider: "github-copilot",
4626
4621
  baseUrl: "https://api.individual.githubcopilot.com",
4627
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" },
4628
4623
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4629
- reasoning: false,
4624
+ reasoning: true,
4630
4625
  input: ["text", "image"],
4631
4626
  cost: {
4632
- input: 2,
4633
- output: 8,
4634
- cacheRead: 0.5,
4627
+ input: 0.75,
4628
+ output: 3.75,
4629
+ cacheRead: 0.075,
4635
4630
  cacheWrite: 0,
4636
4631
  },
4637
- contextWindow: 128000,
4638
- maxTokens: 16384,
4632
+ contextWindow: 1000000,
4633
+ maxTokens: 64000,
4639
4634
  },
4640
4635
  "gpt-5-mini": {
4641
4636
  id: "gpt-5-mini",
@@ -4656,44 +4651,6 @@ export const MODELS = {
4656
4651
  contextWindow: 264000,
4657
4652
  maxTokens: 64000,
4658
4653
  },
4659
- "gpt-5.2": {
4660
- id: "gpt-5.2",
4661
- name: "GPT-5.2",
4662
- api: "openai-responses",
4663
- provider: "github-copilot",
4664
- baseUrl: "https://api.individual.githubcopilot.com",
4665
- 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" },
4666
- reasoning: true,
4667
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4668
- input: ["text", "image"],
4669
- cost: {
4670
- input: 1.75,
4671
- output: 14,
4672
- cacheRead: 0.175,
4673
- cacheWrite: 0,
4674
- },
4675
- contextWindow: 400000,
4676
- maxTokens: 128000,
4677
- },
4678
- "gpt-5.2-codex": {
4679
- id: "gpt-5.2-codex",
4680
- name: "GPT-5.2 Codex",
4681
- api: "openai-responses",
4682
- provider: "github-copilot",
4683
- baseUrl: "https://api.individual.githubcopilot.com",
4684
- 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" },
4685
- reasoning: true,
4686
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4687
- input: ["text", "image"],
4688
- cost: {
4689
- input: 1.75,
4690
- output: 14,
4691
- cacheRead: 0.175,
4692
- cacheWrite: 0,
4693
- },
4694
- contextWindow: 400000,
4695
- maxTokens: 128000,
4696
- },
4697
4654
  "gpt-5.3-codex": {
4698
4655
  id: "gpt-5.3-codex",
4699
4656
  name: "GPT-5.3 Codex",
@@ -4819,10 +4776,10 @@ export const MODELS = {
4819
4776
  thinkingLevelMap: { "off": null },
4820
4777
  input: ["text", "image"],
4821
4778
  cost: {
4822
- input: 2,
4823
- output: 10,
4824
- cacheRead: 0.2,
4825
- cacheWrite: 2.5,
4779
+ input: 4,
4780
+ output: 20,
4781
+ cacheRead: 0.4,
4782
+ cacheWrite: 5,
4826
4783
  },
4827
4784
  contextWindow: 1050000,
4828
4785
  maxTokens: 128000,
@@ -4846,6 +4803,25 @@ export const MODELS = {
4846
4803
  contextWindow: 1050000,
4847
4804
  maxTokens: 128000,
4848
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
+ },
4849
4825
  "grok-4.5": {
4850
4826
  id: "grok-4.5",
4851
4827
  name: "Grok 4.5",
@@ -5262,6 +5238,24 @@ export const MODELS = {
5262
5238
  contextWindow: 1048576,
5263
5239
  maxTokens: 65536,
5264
5240
  },
5241
+ "gemini-3.8-flash": {
5242
+ id: "gemini-3.8-flash",
5243
+ name: "Gemini 3.8 Flash",
5244
+ api: "google-generative-ai",
5245
+ provider: "google",
5246
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5247
+ reasoning: true,
5248
+ thinkingLevelMap: { "off": null },
5249
+ input: ["text", "image"],
5250
+ cost: {
5251
+ input: 0.75,
5252
+ output: 3.75,
5253
+ cacheRead: 0.075,
5254
+ cacheWrite: 0,
5255
+ },
5256
+ contextWindow: 1048576,
5257
+ maxTokens: 65536,
5258
+ },
5265
5259
  "gemini-flash-latest": {
5266
5260
  id: "gemini-flash-latest",
5267
5261
  name: "Gemini Flash Latest",
@@ -6348,6 +6342,24 @@ export const MODELS = {
6348
6342
  contextWindow: 1048576,
6349
6343
  maxTokens: 384000,
6350
6344
  },
6345
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
6346
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
6347
+ name: "DeepSeek V4 Flash Vision Exp",
6348
+ api: "openai-completions",
6349
+ provider: "huggingface",
6350
+ baseUrl: "https://router.huggingface.co/v1",
6351
+ compat: { "supportsDeveloperRole": false },
6352
+ reasoning: true,
6353
+ input: ["text", "image"],
6354
+ cost: {
6355
+ input: 0.44,
6356
+ output: 1.32,
6357
+ cacheRead: 0,
6358
+ cacheWrite: 0,
6359
+ },
6360
+ contextWindow: 1048576,
6361
+ maxTokens: 384000,
6362
+ },
6351
6363
  "deepseek-ai/DeepSeek-V4-Pro": {
6352
6364
  id: "deepseek-ai/DeepSeek-V4-Pro",
6353
6365
  name: "DeepSeek V4 Pro",
@@ -6670,7 +6682,7 @@ export const MODELS = {
6670
6682
  cacheWrite: 0,
6671
6683
  },
6672
6684
  contextWindow: 262144,
6673
- maxTokens: 64000,
6685
+ maxTokens: 128000,
6674
6686
  },
6675
6687
  "thinkingmachines/Inkling": {
6676
6688
  id: "thinkingmachines/Inkling",
@@ -8550,6 +8562,23 @@ export const MODELS = {
8550
8562
  contextWindow: 1050000,
8551
8563
  maxTokens: 128000,
8552
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
+ },
8553
8582
  "gpt-realtime-2.1": {
8554
8583
  id: "gpt-realtime-2.1",
8555
8584
  name: "GPT-Realtime-2.1",
@@ -9096,6 +9125,25 @@ export const MODELS = {
9096
9125
  contextWindow: 1000000,
9097
9126
  maxTokens: 384000,
9098
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
+ },
9099
9147
  "deepseek-v4-pro": {
9100
9148
  id: "deepseek-v4-pro",
9101
9149
  name: "DeepSeek V4 Pro",
@@ -9223,6 +9271,24 @@ export const MODELS = {
9223
9271
  contextWindow: 1048576,
9224
9272
  maxTokens: 65536,
9225
9273
  },
9274
+ "gemini-3.8-flash": {
9275
+ id: "gemini-3.8-flash",
9276
+ name: "Gemini 3.8 Flash",
9277
+ api: "google-generative-ai",
9278
+ provider: "opencode",
9279
+ baseUrl: "https://opencode.ai/zen/v1",
9280
+ reasoning: true,
9281
+ thinkingLevelMap: { "off": null },
9282
+ input: ["text", "image"],
9283
+ cost: {
9284
+ input: 1.5,
9285
+ output: 7.5,
9286
+ cacheRead: 0.15,
9287
+ cacheWrite: 0,
9288
+ },
9289
+ contextWindow: 1048576,
9290
+ maxTokens: 65536,
9291
+ },
9226
9292
  "glm-5": {
9227
9293
  id: "glm-5",
9228
9294
  name: "GLM-5",
@@ -9274,6 +9340,40 @@ export const MODELS = {
9274
9340
  contextWindow: 1000000,
9275
9341
  maxTokens: 131072,
9276
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"],
9368
+ cost: {
9369
+ input: 0.15,
9370
+ output: 0.5,
9371
+ cacheRead: 0.03,
9372
+ cacheWrite: 0,
9373
+ },
9374
+ contextWindow: 1000000,
9375
+ maxTokens: 131072,
9376
+ },
9277
9377
  "gpt-5": {
9278
9378
  id: "gpt-5",
9279
9379
  name: "GPT-5",
@@ -9616,6 +9716,23 @@ export const MODELS = {
9616
9716
  contextWindow: 1050000,
9617
9717
  maxTokens: 128000,
9618
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
+ },
9619
9736
  "grok-4.5": {
9620
9737
  id: "grok-4.5",
9621
9738
  name: "Grok 4.5",
@@ -9820,9 +9937,43 @@ export const MODELS = {
9820
9937
  contextWindow: 512000,
9821
9938
  maxTokens: 128000,
9822
9939
  },
9823
- "muse-spark-1.2": {
9824
- id: "muse-spark-1.2",
9825
- name: "Muse Spark 1.2",
9940
+ "muse-spark-1.2": {
9941
+ id: "muse-spark-1.2",
9942
+ name: "Muse Spark 1.2",
9943
+ api: "openai-responses",
9944
+ provider: "opencode",
9945
+ baseUrl: "https://opencode.ai/zen/v1",
9946
+ reasoning: true,
9947
+ input: ["text", "image"],
9948
+ cost: {
9949
+ input: 1.25,
9950
+ output: 4.25,
9951
+ cacheRead: 0.15,
9952
+ cacheWrite: 0,
9953
+ },
9954
+ contextWindow: 1048576,
9955
+ maxTokens: 131072,
9956
+ },
9957
+ "muse-spark-1.2-contributor-free": {
9958
+ id: "muse-spark-1.2-contributor-free",
9959
+ name: "Muse Spark 1.2 Free",
9960
+ api: "openai-responses",
9961
+ provider: "opencode",
9962
+ baseUrl: "https://opencode.ai/zen/v1",
9963
+ reasoning: true,
9964
+ input: ["text", "image"],
9965
+ cost: {
9966
+ input: 0,
9967
+ output: 0,
9968
+ cacheRead: 0,
9969
+ cacheWrite: 0,
9970
+ },
9971
+ contextWindow: 1048576,
9972
+ maxTokens: 131072,
9973
+ },
9974
+ "muse-spark-1.3": {
9975
+ id: "muse-spark-1.3",
9976
+ name: "Muse Spark 1.3",
9826
9977
  api: "openai-responses",
9827
9978
  provider: "opencode",
9828
9979
  baseUrl: "https://opencode.ai/zen/v1",
@@ -9837,9 +9988,9 @@ export const MODELS = {
9837
9988
  contextWindow: 1048576,
9838
9989
  maxTokens: 131072,
9839
9990
  },
9840
- "muse-spark-1.2-contributor-free": {
9841
- id: "muse-spark-1.2-contributor-free",
9842
- name: "Muse Spark 1.2 Free",
9991
+ "muse-spark-1.3-contributor-free": {
9992
+ id: "muse-spark-1.3-contributor-free",
9993
+ name: "Muse Spark 1.3 Free",
9843
9994
  api: "openai-responses",
9844
9995
  provider: "opencode",
9845
9996
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10099,7 +10250,7 @@ export const MODELS = {
10099
10250
  cacheWrite: 0,
10100
10251
  },
10101
10252
  contextWindow: 256000,
10102
- maxTokens: 64000,
10253
+ maxTokens: 128000,
10103
10254
  },
10104
10255
  "hy4-preview": {
10105
10256
  id: "hy4-preview",
@@ -10271,6 +10422,40 @@ export const MODELS = {
10271
10422
  contextWindow: 1048576,
10272
10423
  maxTokens: 131072,
10273
10424
  },
10425
+ "muse-spark-1.3-contributor": {
10426
+ id: "muse-spark-1.3-contributor",
10427
+ name: "Muse Spark 1.3 Contributor",
10428
+ api: "openai-responses",
10429
+ provider: "opencode-go",
10430
+ baseUrl: "https://opencode.ai/zen/go/v1",
10431
+ reasoning: true,
10432
+ input: ["text", "image"],
10433
+ cost: {
10434
+ input: 0.1,
10435
+ output: 0.2,
10436
+ cacheRead: 0.002,
10437
+ cacheWrite: 0,
10438
+ },
10439
+ contextWindow: 1048576,
10440
+ maxTokens: 131072,
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
+ },
10274
10459
  "qwen3.6-plus": {
10275
10460
  id: "qwen3.6-plus",
10276
10461
  name: "Qwen3.6 Plus",
@@ -10548,6 +10733,24 @@ export const MODELS = {
10548
10733
  contextWindow: 1000000,
10549
10734
  maxTokens: 128000,
10550
10735
  },
10736
+ "anthropic/claude-fable-5.1:batch": {
10737
+ id: "anthropic/claude-fable-5.1:batch",
10738
+ name: "Anthropic: Claude Fable 5.1 (batch)",
10739
+ api: "openai-completions",
10740
+ provider: "openrouter",
10741
+ baseUrl: "https://openrouter.ai/api/v1",
10742
+ reasoning: true,
10743
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10744
+ input: ["text", "image"],
10745
+ cost: {
10746
+ input: 5,
10747
+ output: 25,
10748
+ cacheRead: 0.125,
10749
+ cacheWrite: 6.25,
10750
+ },
10751
+ contextWindow: 1000000,
10752
+ maxTokens: 128000,
10753
+ },
10551
10754
  "anthropic/claude-fable-5:batch": {
10552
10755
  id: "anthropic/claude-fable-5:batch",
10553
10756
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -11142,13 +11345,13 @@ export const MODELS = {
11142
11345
  reasoning: false,
11143
11346
  input: ["text"],
11144
11347
  cost: {
11145
- input: 0.2574,
11146
- output: 1.0287,
11348
+ input: 0.32,
11349
+ output: 0.8899999999999999,
11147
11350
  cacheRead: 0,
11148
11351
  cacheWrite: 0,
11149
11352
  },
11150
11353
  contextWindow: 163840,
11151
- maxTokens: 16000,
11354
+ maxTokens: 16384,
11152
11355
  },
11153
11356
  "deepseek/deepseek-chat-v3-0324": {
11154
11357
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11280,9 +11483,9 @@ export const MODELS = {
11280
11483
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11281
11484
  input: ["text"],
11282
11485
  cost: {
11283
- input: 0.07322000000000001,
11284
- output: 0.14644000000000001,
11285
- cacheRead: 0.014644,
11486
+ input: 0.08358,
11487
+ output: 0.16716,
11488
+ cacheRead: 0.016715999999999998,
11286
11489
  cacheWrite: 0,
11287
11490
  },
11288
11491
  contextWindow: 1048576,
@@ -11356,13 +11559,13 @@ export const MODELS = {
11356
11559
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11357
11560
  input: ["text"],
11358
11561
  cost: {
11359
- input: 1.5999999999999999,
11360
- output: 3.1999999999999997,
11361
- cacheRead: 0.135,
11562
+ input: 0.8193659999999999,
11563
+ output: 1.6387319999999999,
11564
+ cacheRead: 0.0682805,
11362
11565
  cacheWrite: 0,
11363
11566
  },
11364
11567
  contextWindow: 1048576,
11365
- maxTokens: 393216,
11568
+ maxTokens: 384000,
11366
11569
  },
11367
11570
  "deepseek/deepseek-v4-pro-0813": {
11368
11571
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11375,9 +11578,9 @@ export const MODELS = {
11375
11578
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11376
11579
  input: ["text"],
11377
11580
  cost: {
11378
- input: 0.66,
11379
- output: 1.9800000000000002,
11380
- cacheRead: 0.022,
11581
+ input: 0.57948,
11582
+ output: 1.73844,
11583
+ cacheRead: 0.019316,
11381
11584
  cacheWrite: 0,
11382
11585
  },
11383
11586
  contextWindow: 1048576,
@@ -11836,10 +12039,44 @@ export const MODELS = {
11836
12039
  reasoning: true,
11837
12040
  input: ["text", "image"],
11838
12041
  cost: {
11839
- input: 0.1875,
11840
- output: 0.9375,
11841
- cacheRead: 0.01875,
11842
- cacheWrite: 0.0208333333333333,
12042
+ input: 0.375,
12043
+ output: 1.875,
12044
+ cacheRead: 0.0375,
12045
+ cacheWrite: 0.0416666666666667,
12046
+ },
12047
+ contextWindow: 1048576,
12048
+ maxTokens: 65536,
12049
+ },
12050
+ "google/gemini-3.8-flash": {
12051
+ id: "google/gemini-3.8-flash",
12052
+ name: "Google: Gemini 3.8 Flash",
12053
+ api: "openai-completions",
12054
+ provider: "openrouter",
12055
+ baseUrl: "https://openrouter.ai/api/v1",
12056
+ reasoning: true,
12057
+ input: ["text", "image"],
12058
+ cost: {
12059
+ input: 0.75,
12060
+ output: 3.75,
12061
+ cacheRead: 0.075,
12062
+ cacheWrite: 0.0416666666666667,
12063
+ },
12064
+ contextWindow: 1048576,
12065
+ maxTokens: 65536,
12066
+ },
12067
+ "google/gemini-3.8-flash:batch": {
12068
+ id: "google/gemini-3.8-flash:batch",
12069
+ name: "Google: Gemini 3.8 Flash (batch)",
12070
+ api: "openai-completions",
12071
+ provider: "openrouter",
12072
+ baseUrl: "https://openrouter.ai/api/v1",
12073
+ reasoning: true,
12074
+ input: ["text", "image"],
12075
+ cost: {
12076
+ input: 0.375,
12077
+ output: 1.875,
12078
+ cacheRead: 0.0375,
12079
+ cacheWrite: 0.0416666666666667,
11843
12080
  },
11844
12081
  contextWindow: 1048576,
11845
12082
  maxTokens: 65536,
@@ -11963,23 +12200,6 @@ export const MODELS = {
11963
12200
  contextWindow: 262144,
11964
12201
  maxTokens: 32768,
11965
12202
  },
11966
- "ibm-granite/granite-4.1-8b": {
11967
- id: "ibm-granite/granite-4.1-8b",
11968
- name: "IBM: Granite 4.1 8B",
11969
- api: "openai-completions",
11970
- provider: "openrouter",
11971
- baseUrl: "https://openrouter.ai/api/v1",
11972
- reasoning: false,
11973
- input: ["text"],
11974
- cost: {
11975
- input: 0.049999999999999996,
11976
- output: 0.09999999999999999,
11977
- cacheRead: 0.049999999999999996,
11978
- cacheWrite: 0,
11979
- },
11980
- contextWindow: 131072,
11981
- maxTokens: 117964,
11982
- },
11983
12203
  "ibm-granite/granite-4.2-8b": {
11984
12204
  id: "ibm-granite/granite-4.2-8b",
11985
12205
  name: "IBM: Granite 4.2 8B",
@@ -12033,7 +12253,7 @@ export const MODELS = {
12033
12253
  },
12034
12254
  "inclusionai/ling-3.0-flash": {
12035
12255
  id: "inclusionai/ling-3.0-flash",
12036
- name: "Ling-3.0-flash",
12256
+ name: "inclusionAI: Ling 3.0 Flash",
12037
12257
  api: "openai-completions",
12038
12258
  provider: "openrouter",
12039
12259
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12048,9 +12268,43 @@ export const MODELS = {
12048
12268
  contextWindow: 262144,
12049
12269
  maxTokens: 32768,
12050
12270
  },
12271
+ "inclusionai/ling-3.0-flash-fin": {
12272
+ id: "inclusionai/ling-3.0-flash-fin",
12273
+ name: "inclusionAI: Ling 3.0 Flash Fin",
12274
+ api: "openai-completions",
12275
+ provider: "openrouter",
12276
+ baseUrl: "https://openrouter.ai/api/v1",
12277
+ reasoning: true,
12278
+ input: ["text"],
12279
+ cost: {
12280
+ input: 0.06,
12281
+ output: 0.18,
12282
+ cacheRead: 0.012,
12283
+ cacheWrite: 0,
12284
+ },
12285
+ contextWindow: 262144,
12286
+ maxTokens: 235929,
12287
+ },
12051
12288
  "inclusionai/ling-3.0-flash-fin:free": {
12052
12289
  id: "inclusionai/ling-3.0-flash-fin:free",
12053
- 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)",
12054
12308
  api: "openai-completions",
12055
12309
  provider: "openrouter",
12056
12310
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12176,13 +12430,13 @@ export const MODELS = {
12176
12430
  reasoning: false,
12177
12431
  input: ["text"],
12178
12432
  cost: {
12179
- input: 0.71,
12180
- output: 0.71,
12181
- cacheRead: 0.71,
12433
+ input: 0.09999999999999999,
12434
+ output: 0.32,
12435
+ cacheRead: 0,
12182
12436
  cacheWrite: 0,
12183
12437
  },
12184
12438
  contextWindow: 131072,
12185
- maxTokens: 115200,
12439
+ maxTokens: 16384,
12186
12440
  },
12187
12441
  "meta-llama/llama-4-maverick": {
12188
12442
  id: "meta-llama/llama-4-maverick",
@@ -12228,12 +12482,12 @@ export const MODELS = {
12228
12482
  input: ["text", "image"],
12229
12483
  cost: {
12230
12484
  input: 0.3,
12231
- output: 1.2,
12485
+ output: 1.1,
12232
12486
  cacheRead: 0.04,
12233
12487
  cacheWrite: 0,
12234
12488
  },
12235
12489
  contextWindow: 131072,
12236
- maxTokens: 16384,
12490
+ maxTokens: 117964,
12237
12491
  },
12238
12492
  "meta/muse-glimmer-30b:batch": {
12239
12493
  id: "meta/muse-glimmer-30b:batch",
@@ -12303,6 +12557,40 @@ export const MODELS = {
12303
12557
  contextWindow: 1048576,
12304
12558
  maxTokens: 943718,
12305
12559
  },
12560
+ "meta/muse-spark-1.3": {
12561
+ id: "meta/muse-spark-1.3",
12562
+ name: "Meta: Muse Spark 1.3",
12563
+ api: "openai-completions",
12564
+ provider: "openrouter",
12565
+ baseUrl: "https://openrouter.ai/api/v1",
12566
+ reasoning: true,
12567
+ input: ["text", "image"],
12568
+ cost: {
12569
+ input: 1.25,
12570
+ output: 4.25,
12571
+ cacheRead: 0.15,
12572
+ cacheWrite: 0,
12573
+ },
12574
+ contextWindow: 1048576,
12575
+ maxTokens: 943718,
12576
+ },
12577
+ "meta/muse-spark-1.3-contributor": {
12578
+ id: "meta/muse-spark-1.3-contributor",
12579
+ name: "Meta: Muse Spark 1.3 Contributor",
12580
+ api: "openai-completions",
12581
+ provider: "openrouter",
12582
+ baseUrl: "https://openrouter.ai/api/v1",
12583
+ reasoning: true,
12584
+ input: ["text", "image"],
12585
+ cost: {
12586
+ input: 0.09999999999999999,
12587
+ output: 0.19999999999999998,
12588
+ cacheRead: 0.002,
12589
+ cacheWrite: 0,
12590
+ },
12591
+ contextWindow: 1048576,
12592
+ maxTokens: 943718,
12593
+ },
12306
12594
  "minimax/minimax-m1": {
12307
12595
  id: "minimax/minimax-m1",
12308
12596
  name: "MiniMax: MiniMax M1",
@@ -12640,8 +12928,8 @@ export const MODELS = {
12640
12928
  cacheRead: 0,
12641
12929
  cacheWrite: 0,
12642
12930
  },
12643
- contextWindow: 262144,
12644
- maxTokens: 209715,
12931
+ contextWindow: 32768,
12932
+ maxTokens: 26214,
12645
12933
  },
12646
12934
  "mistralai/mistral-medium-3.1": {
12647
12935
  id: "mistralai/mistral-medium-3.1",
@@ -12943,11 +13231,11 @@ export const MODELS = {
12943
13231
  cost: {
12944
13232
  input: 0.049999999999999996,
12945
13233
  output: 0.19999999999999998,
12946
- cacheRead: 0.024999999999999998,
13234
+ cacheRead: 0.03,
12947
13235
  cacheWrite: 0,
12948
13236
  },
12949
13237
  contextWindow: 262144,
12950
- maxTokens: 228000,
13238
+ maxTokens: 235929,
12951
13239
  },
12952
13240
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12953
13241
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -13009,30 +13297,13 @@ export const MODELS = {
13009
13297
  reasoning: true,
13010
13298
  input: ["text"],
13011
13299
  cost: {
13012
- input: 0.5,
13013
- output: 2.2,
13014
- cacheRead: 0.09999999999999999,
13300
+ input: 0.625,
13301
+ output: 3.125,
13302
+ cacheRead: 0.1875,
13015
13303
  cacheWrite: 0,
13016
13304
  },
13017
13305
  contextWindow: 262144,
13018
- maxTokens: 16384,
13019
- },
13020
- "nvidia/nemotron-3-ultra-550b-a55b:batch": {
13021
- id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
13022
- name: "NVIDIA: Nemotron 3 Ultra (batch)",
13023
- api: "openai-completions",
13024
- provider: "openrouter",
13025
- baseUrl: "https://openrouter.ai/api/v1",
13026
- reasoning: true,
13027
- input: ["text"],
13028
- cost: {
13029
- input: 0.6,
13030
- output: 3.5999999999999996,
13031
- cacheRead: 0.19999999999999998,
13032
- cacheWrite: 0,
13033
- },
13034
- contextWindow: 512288,
13035
- maxTokens: 461059,
13306
+ maxTokens: 32768,
13036
13307
  },
13037
13308
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13038
13309
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14116,12 +14387,80 @@ export const MODELS = {
14116
14387
  reasoning: true,
14117
14388
  input: ["text", "image"],
14118
14389
  cost: {
14119
- input: 0.625,
14120
- output: 5,
14121
- cacheRead: 0.0625,
14122
- cacheWrite: 0,
14390
+ input: 0.625,
14391
+ output: 5,
14392
+ cacheRead: 0.0625,
14393
+ cacheWrite: 0,
14394
+ },
14395
+ contextWindow: 400000,
14396
+ maxTokens: 128000,
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,
14123
14462
  },
14124
- contextWindow: 400000,
14463
+ contextWindow: 1050000,
14125
14464
  maxTokens: 128000,
14126
14465
  },
14127
14466
  "openai/gpt-audio": {
@@ -14643,13 +14982,13 @@ export const MODELS = {
14643
14982
  reasoning: false,
14644
14983
  input: ["text"],
14645
14984
  cost: {
14646
- input: 0.0875,
14647
- output: 0.35,
14648
- cacheRead: 0.0175,
14985
+ input: 0.09,
14986
+ output: 0.55,
14987
+ cacheRead: 0,
14649
14988
  cacheWrite: 0,
14650
14989
  },
14651
14990
  contextWindow: 262144,
14652
- maxTokens: 235929,
14991
+ maxTokens: 16384,
14653
14992
  },
14654
14993
  "qwen/qwen3-235b-a22b-thinking-2507": {
14655
14994
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -15068,13 +15407,13 @@ export const MODELS = {
15068
15407
  reasoning: true,
15069
15408
  input: ["text", "image"],
15070
15409
  cost: {
15071
- input: 0.25,
15410
+ input: 0.3125,
15072
15411
  output: 1.25,
15073
- cacheRead: 0.25,
15412
+ cacheRead: 0.15625,
15074
15413
  cacheWrite: 0,
15075
15414
  },
15076
15415
  contextWindow: 262144,
15077
- maxTokens: 235929,
15416
+ maxTokens: 16384,
15078
15417
  },
15079
15418
  "qwen/qwen3.5-397b-a17b": {
15080
15419
  id: "qwen/qwen3.5-397b-a17b",
@@ -15085,13 +15424,13 @@ export const MODELS = {
15085
15424
  reasoning: true,
15086
15425
  input: ["text", "image"],
15087
15426
  cost: {
15088
- input: 0.39,
15089
- output: 2.34,
15090
- cacheRead: 0,
15427
+ input: 0.55,
15428
+ output: 3.5,
15429
+ cacheRead: 0.22499999999999998,
15091
15430
  cacheWrite: 0,
15092
15431
  },
15093
15432
  contextWindow: 262144,
15094
- maxTokens: 65536,
15433
+ maxTokens: 235929,
15095
15434
  },
15096
15435
  "qwen/qwen3.5-9b": {
15097
15436
  id: "qwen/qwen3.5-9b",
@@ -15187,13 +15526,13 @@ export const MODELS = {
15187
15526
  reasoning: true,
15188
15527
  input: ["text", "image"],
15189
15528
  cost: {
15190
- input: 0.6,
15191
- output: 3.5999999999999996,
15192
- cacheRead: 0.12,
15529
+ input: 0.3,
15530
+ output: 2,
15531
+ cacheRead: 0.03,
15193
15532
  cacheWrite: 0,
15194
15533
  },
15195
15534
  contextWindow: 262144,
15196
- maxTokens: 235929,
15535
+ maxTokens: 65536,
15197
15536
  },
15198
15537
  "qwen/qwen3.6-35b-a3b": {
15199
15538
  id: "qwen/qwen3.6-35b-a3b",
@@ -15340,9 +15679,9 @@ export const MODELS = {
15340
15679
  reasoning: true,
15341
15680
  input: ["text"],
15342
15681
  cost: {
15343
- input: 2.5,
15344
- output: 6.25,
15345
- cacheRead: 0.5,
15682
+ input: 2,
15683
+ output: 6,
15684
+ cacheRead: 0.25,
15346
15685
  cacheWrite: 0,
15347
15686
  },
15348
15687
  contextWindow: 1010000,
@@ -15357,10 +15696,10 @@ export const MODELS = {
15357
15696
  reasoning: true,
15358
15697
  input: ["text", "image"],
15359
15698
  cost: {
15360
- input: 0.425,
15361
- output: 2.5500000000000003,
15699
+ input: 0.42,
15700
+ output: 3,
15362
15701
  cacheRead: 0.08499999999999999,
15363
- cacheWrite: 0.53125,
15702
+ cacheWrite: 0,
15364
15703
  },
15365
15704
  contextWindow: 1000000,
15366
15705
  maxTokens: 131072,
@@ -15382,9 +15721,9 @@ export const MODELS = {
15382
15721
  contextWindow: 1000000,
15383
15722
  maxTokens: 131072,
15384
15723
  },
15385
- "qwen/qwen3.8-max": {
15386
- id: "qwen/qwen3.8-max",
15387
- 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)",
15388
15727
  api: "openai-completions",
15389
15728
  provider: "openrouter",
15390
15729
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15739,6 +16078,23 @@ export const MODELS = {
15739
16078
  contextWindow: 1000000,
15740
16079
  maxTokens: 900000,
15741
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
+ },
15742
16098
  "x-ai/grok-4.5": {
15743
16099
  id: "x-ai/grok-4.5",
15744
16100
  name: "SpaceXAI: Grok 4.5",
@@ -15884,13 +16240,13 @@ export const MODELS = {
15884
16240
  reasoning: true,
15885
16241
  input: ["text"],
15886
16242
  cost: {
15887
- input: 0.43,
15888
- output: 1.75,
15889
- cacheRead: 0.08,
16243
+ input: 0.55,
16244
+ output: 2.2,
16245
+ cacheRead: 0.11,
15890
16246
  cacheWrite: 0,
15891
16247
  },
15892
16248
  contextWindow: 204800,
15893
- maxTokens: 16384,
16249
+ maxTokens: 131072,
15894
16250
  },
15895
16251
  "z-ai/glm-4.6v": {
15896
16252
  id: "z-ai/glm-4.6v",
@@ -16003,13 +16359,13 @@ export const MODELS = {
16003
16359
  reasoning: true,
16004
16360
  input: ["text"],
16005
16361
  cost: {
16006
- input: 1.19,
16007
- output: 3.74,
16008
- cacheRead: 0.221,
16362
+ input: 0.966,
16363
+ output: 3.036,
16364
+ cacheRead: 0.1932,
16009
16365
  cacheWrite: 0,
16010
16366
  },
16011
16367
  contextWindow: 1048576,
16012
- maxTokens: 262144,
16368
+ maxTokens: 131072,
16013
16369
  },
16014
16370
  "z-ai/glm-5.2:free": {
16015
16371
  id: "z-ai/glm-5.2:free",
@@ -16039,11 +16395,11 @@ export const MODELS = {
16039
16395
  cost: {
16040
16396
  input: 1.4,
16041
16397
  output: 4.4,
16042
- cacheRead: 0.26,
16398
+ cacheRead: 0.14,
16043
16399
  cacheWrite: 0,
16044
16400
  },
16045
16401
  contextWindow: 1310720,
16046
- maxTokens: 131072,
16402
+ maxTokens: 262144,
16047
16403
  },
16048
16404
  "z-ai/glm-5.3-flash": {
16049
16405
  id: "z-ai/glm-5.3-flash",
@@ -16286,6 +16642,23 @@ export const MODELS = {
16286
16642
  contextWindow: 500000,
16287
16643
  maxTokens: 450000,
16288
16644
  },
16645
+ "~z-ai/glm-flash-latest": {
16646
+ id: "~z-ai/glm-flash-latest",
16647
+ name: "Z.ai: GLM Flash Latest",
16648
+ api: "openai-completions",
16649
+ provider: "openrouter",
16650
+ baseUrl: "https://openrouter.ai/api/v1",
16651
+ reasoning: true,
16652
+ input: ["text", "image"],
16653
+ cost: {
16654
+ input: 0.075,
16655
+ output: 0.25,
16656
+ cacheRead: 0.015,
16657
+ cacheWrite: 0,
16658
+ },
16659
+ contextWindow: 1310720,
16660
+ maxTokens: 943718,
16661
+ },
16289
16662
  "~z-ai/glm-latest": {
16290
16663
  id: "~z-ai/glm-latest",
16291
16664
  name: "Z.ai: GLM Latest",
@@ -16295,13 +16668,13 @@ export const MODELS = {
16295
16668
  reasoning: true,
16296
16669
  input: ["text"],
16297
16670
  cost: {
16298
- input: 1.17,
16299
- output: 3.9600000000000004,
16300
- cacheRead: 0.234,
16671
+ input: 1.15,
16672
+ output: 3.5,
16673
+ cacheRead: 0.09999999999999999,
16301
16674
  cacheWrite: 0,
16302
16675
  },
16303
16676
  contextWindow: 1310720,
16304
- maxTokens: 943718,
16677
+ maxTokens: 235929,
16305
16678
  },
16306
16679
  },
16307
16680
  "together": {
@@ -17213,6 +17586,23 @@ export const MODELS = {
17213
17586
  contextWindow: 1000000,
17214
17587
  maxTokens: 128000,
17215
17588
  },
17589
+ "alibaba/qwen3.8-max-0902": {
17590
+ id: "alibaba/qwen3.8-max-0902",
17591
+ name: "Qwen3.8 Max 0902",
17592
+ api: "anthropic-messages",
17593
+ provider: "vercel-ai-gateway",
17594
+ baseUrl: "https://ai-gateway.vercel.sh",
17595
+ reasoning: true,
17596
+ input: ["text", "image"],
17597
+ cost: {
17598
+ input: 2,
17599
+ output: 6,
17600
+ cacheRead: 0.25,
17601
+ cacheWrite: 2.5,
17602
+ },
17603
+ contextWindow: 991000,
17604
+ maxTokens: 128000,
17605
+ },
17216
17606
  "amazon/nova-2-lite": {
17217
17607
  id: "amazon/nova-2-lite",
17218
17608
  name: "Nova 2 Lite",
@@ -17644,23 +18034,6 @@ export const MODELS = {
17644
18034
  contextWindow: 128000,
17645
18035
  maxTokens: 8192,
17646
18036
  },
17647
- "deepseek/deepseek-v3": {
17648
- id: "deepseek/deepseek-v3",
17649
- name: "DeepSeek V3 0324",
17650
- api: "anthropic-messages",
17651
- provider: "vercel-ai-gateway",
17652
- baseUrl: "https://ai-gateway.vercel.sh",
17653
- reasoning: false,
17654
- input: ["text"],
17655
- cost: {
17656
- input: 0.27,
17657
- output: 1.12,
17658
- cacheRead: 0.135,
17659
- cacheWrite: 0,
17660
- },
17661
- contextWindow: 163840,
17662
- maxTokens: 163840,
17663
- },
17664
18037
  "deepseek/deepseek-v3.1": {
17665
18038
  id: "deepseek/deepseek-v3.1",
17666
18039
  name: "DeepSeek V3.1",
@@ -17984,6 +18357,23 @@ export const MODELS = {
17984
18357
  contextWindow: 1000000,
17985
18358
  maxTokens: 65536,
17986
18359
  },
18360
+ "google/gemini-3.8-flash": {
18361
+ id: "google/gemini-3.8-flash",
18362
+ name: "Gemini 3.8 Flash",
18363
+ api: "anthropic-messages",
18364
+ provider: "vercel-ai-gateway",
18365
+ baseUrl: "https://ai-gateway.vercel.sh",
18366
+ reasoning: true,
18367
+ input: ["text", "image"],
18368
+ cost: {
18369
+ input: 0.75,
18370
+ output: 3.75,
18371
+ cacheRead: 0.075,
18372
+ cacheWrite: 0,
18373
+ },
18374
+ contextWindow: 1000000,
18375
+ maxTokens: 65536,
18376
+ },
17987
18377
  "google/gemma-4-26b-a4b-it": {
17988
18378
  id: "google/gemma-4-26b-a4b-it",
17989
18379
  name: "Google Gemma 4 26B A4B",
@@ -18103,6 +18493,40 @@ export const MODELS = {
18103
18493
  contextWindow: 256000,
18104
18494
  maxTokens: 32000,
18105
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
+ },
18106
18530
  "interfaze/interfaze-beta": {
18107
18531
  id: "interfaze/interfaze-beta",
18108
18532
  name: "Interfaze Beta",
@@ -18341,6 +18765,40 @@ export const MODELS = {
18341
18765
  contextWindow: 1048576,
18342
18766
  maxTokens: 1048576,
18343
18767
  },
18768
+ "meta/muse-spark-1.3": {
18769
+ id: "meta/muse-spark-1.3",
18770
+ name: "Muse Spark 1.3",
18771
+ api: "anthropic-messages",
18772
+ provider: "vercel-ai-gateway",
18773
+ baseUrl: "https://ai-gateway.vercel.sh",
18774
+ reasoning: true,
18775
+ input: ["text", "image"],
18776
+ cost: {
18777
+ input: 1.25,
18778
+ output: 4.25,
18779
+ cacheRead: 0.15,
18780
+ cacheWrite: 0,
18781
+ },
18782
+ contextWindow: 1048576,
18783
+ maxTokens: 1048576,
18784
+ },
18785
+ "meta/muse-spark-1.3-contributor": {
18786
+ id: "meta/muse-spark-1.3-contributor",
18787
+ name: "Muse Spark 1.3 Contributor",
18788
+ api: "anthropic-messages",
18789
+ provider: "vercel-ai-gateway",
18790
+ baseUrl: "https://ai-gateway.vercel.sh",
18791
+ reasoning: true,
18792
+ input: ["text", "image"],
18793
+ cost: {
18794
+ input: 0.09999999999999999,
18795
+ output: 0.19999999999999998,
18796
+ cacheRead: 0.002,
18797
+ cacheWrite: 0,
18798
+ },
18799
+ contextWindow: 1048576,
18800
+ maxTokens: 1048576,
18801
+ },
18344
18802
  "minimax/minimax-m2": {
18345
18803
  id: "minimax/minimax-m2",
18346
18804
  name: "MiniMax M2",
@@ -19643,7 +20101,7 @@ export const MODELS = {
19643
20101
  input: 0.39999999999999997,
19644
20102
  output: 2.4,
19645
20103
  cacheRead: 0.04,
19646
- cacheWrite: 0.25,
20104
+ cacheWrite: 0.5,
19647
20105
  },
19648
20106
  contextWindow: 1050000,
19649
20107
  maxTokens: 128000,
@@ -19677,7 +20135,7 @@ export const MODELS = {
19677
20135
  input: 4,
19678
20136
  output: 20,
19679
20137
  cacheRead: 0.39999999999999997,
19680
- cacheWrite: 2.5,
20138
+ cacheWrite: 5,
19681
20139
  },
19682
20140
  contextWindow: 1050000,
19683
20141
  maxTokens: 128000,
@@ -19711,7 +20169,41 @@ export const MODELS = {
19711
20169
  input: 4,
19712
20170
  output: 24,
19713
20171
  cacheRead: 0.39999999999999997,
19714
- 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,
19715
20207
  },
19716
20208
  contextWindow: 1050000,
19717
20209
  maxTokens: 128000,
@@ -20541,14 +21033,31 @@ export const MODELS = {
20541
21033
  reasoning: true,
20542
21034
  input: ["text"],
20543
21035
  cost: {
20544
- input: 1.4,
20545
- output: 4.4,
20546
- cacheRead: 0.14,
21036
+ input: 0.7,
21037
+ output: 2.2,
21038
+ cacheRead: 0.13,
20547
21039
  cacheWrite: 0,
20548
21040
  },
20549
21041
  contextWindow: 1000000,
20550
21042
  maxTokens: 1000000,
20551
21043
  },
21044
+ "zai/glm-5.3-fast": {
21045
+ id: "zai/glm-5.3-fast",
21046
+ name: "GLM 5.3 Fast",
21047
+ api: "anthropic-messages",
21048
+ provider: "vercel-ai-gateway",
21049
+ baseUrl: "https://ai-gateway.vercel.sh",
21050
+ reasoning: true,
21051
+ input: ["text"],
21052
+ cost: {
21053
+ input: 2.0999999999999996,
21054
+ output: 6.6000000000000005,
21055
+ cacheRead: 0.21,
21056
+ cacheWrite: 0,
21057
+ },
21058
+ contextWindow: 1048576,
21059
+ maxTokens: 262144,
21060
+ },
20552
21061
  "zai/glm-5.3-flash": {
20553
21062
  id: "zai/glm-5.3-flash",
20554
21063
  name: "GLM 5.3 Flash",
@@ -20566,6 +21075,23 @@ export const MODELS = {
20566
21075
  contextWindow: 1000000,
20567
21076
  maxTokens: 131000,
20568
21077
  },
21078
+ "zai/glm-5.3-promo-50": {
21079
+ id: "zai/glm-5.3-promo-50",
21080
+ name: "GLM 5.3 (50% off)",
21081
+ api: "anthropic-messages",
21082
+ provider: "vercel-ai-gateway",
21083
+ baseUrl: "https://ai-gateway.vercel.sh",
21084
+ reasoning: true,
21085
+ input: ["text"],
21086
+ cost: {
21087
+ input: 0.7,
21088
+ output: 2.2,
21089
+ cacheRead: 0.13,
21090
+ cacheWrite: 0,
21091
+ },
21092
+ contextWindow: 1048576,
21093
+ maxTokens: 1048576,
21094
+ },
20569
21095
  "zai/glm-5v-turbo": {
20570
21096
  id: "zai/glm-5v-turbo",
20571
21097
  name: "GLM 5V Turbo",