@fleetagent/pi-ai 0.2.0 → 0.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -862,6 +862,23 @@ export const MODELS = {
862
862
  contextWindow: 1050000,
863
863
  maxTokens: 128000,
864
864
  },
865
+ "global.xai.grok-4.6": {
866
+ id: "global.xai.grok-4.6",
867
+ name: "Grok 4.6 (Global)",
868
+ api: "bedrock-converse-stream",
869
+ provider: "amazon-bedrock",
870
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
871
+ reasoning: true,
872
+ input: ["text", "image"],
873
+ cost: {
874
+ input: 2,
875
+ output: 6,
876
+ cacheRead: 0.5,
877
+ cacheWrite: 0,
878
+ },
879
+ contextWindow: 500000,
880
+ maxTokens: 500000,
881
+ },
865
882
  "google.gemma-3-27b-it": {
866
883
  id: "google.gemma-3-27b-it",
867
884
  name: "Google Gemma 3 27B Instruct",
@@ -1975,6 +1992,23 @@ export const MODELS = {
1975
1992
  contextWindow: 3500000,
1976
1993
  maxTokens: 16384,
1977
1994
  },
1995
+ "us.xai.grok-4.6": {
1996
+ id: "us.xai.grok-4.6",
1997
+ name: "Grok 4.6 (US)",
1998
+ api: "bedrock-converse-stream",
1999
+ provider: "amazon-bedrock",
2000
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2001
+ reasoning: true,
2002
+ input: ["text", "image"],
2003
+ cost: {
2004
+ input: 2.2,
2005
+ output: 6.6,
2006
+ cacheRead: 0.55,
2007
+ cacheWrite: 0,
2008
+ },
2009
+ contextWindow: 500000,
2010
+ maxTokens: 500000,
2011
+ },
1978
2012
  "writer.palmyra-x4-v1:0": {
1979
2013
  id: "writer.palmyra-x4-v1:0",
1980
2014
  name: "Palmyra X4",
@@ -2944,6 +2978,23 @@ export const MODELS = {
2944
2978
  contextWindow: 1050000,
2945
2979
  maxTokens: 128000,
2946
2980
  },
2981
+ "gpt-6-astra": {
2982
+ id: "gpt-6-astra",
2983
+ name: "GPT-6 Astra",
2984
+ api: "azure-openai-responses",
2985
+ provider: "azure-openai-responses",
2986
+ baseUrl: "",
2987
+ reasoning: true,
2988
+ input: ["text", "image"],
2989
+ cost: {
2990
+ input: 10,
2991
+ output: 50,
2992
+ cacheRead: 1,
2993
+ cacheWrite: 12.5,
2994
+ },
2995
+ contextWindow: 1050000,
2996
+ maxTokens: 128000,
2997
+ },
2947
2998
  "gpt-realtime-2.1": {
2948
2999
  id: "gpt-realtime-2.1",
2949
3000
  name: "GPT-Realtime-2.1",
@@ -3065,39 +3116,39 @@ export const MODELS = {
3065
3116
  },
3066
3117
  },
3067
3118
  "cerebras": {
3068
- "gemma-4-31b": {
3069
- id: "gemma-4-31b",
3070
- name: "Gemma 4 31B IT",
3119
+ "gpt-oss-120b": {
3120
+ id: "gpt-oss-120b",
3121
+ name: "GPT OSS 120B",
3071
3122
  api: "openai-completions",
3072
3123
  provider: "cerebras",
3073
3124
  baseUrl: "https://api.cerebras.ai/v1",
3074
3125
  reasoning: true,
3075
- input: ["text", "image"],
3126
+ input: ["text"],
3076
3127
  cost: {
3077
- input: 0.99,
3078
- output: 1.49,
3128
+ input: 0.35,
3129
+ output: 0.75,
3079
3130
  cacheRead: 0,
3080
3131
  cacheWrite: 0,
3081
3132
  },
3082
3133
  contextWindow: 131072,
3083
3134
  maxTokens: 40960,
3084
3135
  },
3085
- "gpt-oss-120b": {
3086
- id: "gpt-oss-120b",
3087
- name: "GPT OSS 120B",
3136
+ "qwen-3.8-27b": {
3137
+ id: "qwen-3.8-27b",
3138
+ name: "Qwen3.8 27B",
3088
3139
  api: "openai-completions",
3089
3140
  provider: "cerebras",
3090
3141
  baseUrl: "https://api.cerebras.ai/v1",
3091
3142
  reasoning: true,
3092
- input: ["text"],
3143
+ input: ["text", "image"],
3093
3144
  cost: {
3094
- input: 0.35,
3095
- output: 0.75,
3145
+ input: 0.99,
3146
+ output: 1.49,
3096
3147
  cacheRead: 0,
3097
3148
  cacheWrite: 0,
3098
3149
  },
3099
- contextWindow: 131072,
3100
- maxTokens: 40960,
3150
+ contextWindow: 65536,
3151
+ maxTokens: 32768,
3101
3152
  },
3102
3153
  },
3103
3154
  "cloudflare-ai-gateway": {
@@ -3118,6 +3169,23 @@ export const MODELS = {
3118
3169
  contextWindow: 1000000,
3119
3170
  maxTokens: 128000,
3120
3171
  },
3172
+ "claude-fable-5.1": {
3173
+ id: "claude-fable-5.1",
3174
+ name: "Claude Fable 5.1",
3175
+ api: "anthropic-messages",
3176
+ provider: "cloudflare-ai-gateway",
3177
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3178
+ reasoning: true,
3179
+ input: ["text", "image"],
3180
+ cost: {
3181
+ input: 10,
3182
+ output: 50,
3183
+ cacheRead: 0.25,
3184
+ cacheWrite: 12.5,
3185
+ },
3186
+ contextWindow: 1000000,
3187
+ maxTokens: 128000,
3188
+ },
3121
3189
  "claude-haiku-4.5": {
3122
3190
  id: "claude-haiku-4.5",
3123
3191
  name: "Claude Haiku 4.5 (latest)",
@@ -4053,6 +4121,24 @@ export const MODELS = {
4053
4121
  contextWindow: 1000000,
4054
4122
  maxTokens: 384000,
4055
4123
  },
4124
+ "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4125
+ id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4126
+ name: "DeepSeek V4 Flash Vision Exp",
4127
+ api: "anthropic-messages",
4128
+ provider: "fireworks",
4129
+ baseUrl: "https://api.fireworks.ai/inference",
4130
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
4131
+ reasoning: true,
4132
+ input: ["text", "image"],
4133
+ cost: {
4134
+ input: 0.22,
4135
+ output: 0.66,
4136
+ cacheRead: 0.007,
4137
+ cacheWrite: 0,
4138
+ },
4139
+ contextWindow: 1000000,
4140
+ maxTokens: 384000,
4141
+ },
4056
4142
  "accounts/fireworks/models/deepseek-v4-pro-0813": {
4057
4143
  id: "accounts/fireworks/models/deepseek-v4-pro-0813",
4058
4144
  name: "DeepSeek V4 Pro 0813",
@@ -4104,8 +4190,8 @@ export const MODELS = {
4104
4190
  cacheRead: 0.26,
4105
4191
  cacheWrite: 0,
4106
4192
  },
4107
- contextWindow: 1000000,
4108
- maxTokens: 131072,
4193
+ contextWindow: 1048573,
4194
+ maxTokens: 262144,
4109
4195
  },
4110
4196
  "accounts/fireworks/models/glm-5p3-flash": {
4111
4197
  id: "accounts/fireworks/models/glm-5p3-flash",
@@ -4119,10 +4205,10 @@ export const MODELS = {
4119
4205
  cost: {
4120
4206
  input: 0.15,
4121
4207
  output: 0.5,
4122
- cacheRead: 0.029,
4208
+ cacheRead: 0.03,
4123
4209
  cacheWrite: 0,
4124
4210
  },
4125
- contextWindow: 1000000,
4211
+ contextWindow: 1048573,
4126
4212
  maxTokens: 131072,
4127
4213
  },
4128
4214
  "accounts/fireworks/models/gpt-oss-120b": {
@@ -4305,6 +4391,24 @@ export const MODELS = {
4305
4391
  contextWindow: 262144,
4306
4392
  maxTokens: 65536,
4307
4393
  },
4394
+ "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
4395
+ id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
4396
+ name: "Qwen3.8 2.4T A95B",
4397
+ api: "anthropic-messages",
4398
+ provider: "fireworks",
4399
+ baseUrl: "https://api.fireworks.ai/inference",
4400
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
4401
+ reasoning: true,
4402
+ input: ["text"],
4403
+ cost: {
4404
+ input: 2,
4405
+ output: 6,
4406
+ cacheRead: 0.25,
4407
+ cacheWrite: 0,
4408
+ },
4409
+ contextWindow: 262144,
4410
+ maxTokens: 131072,
4411
+ },
4308
4412
  "accounts/fireworks/models/qwen3p8-max": {
4309
4413
  id: "accounts/fireworks/models/qwen3p8-max",
4310
4414
  name: "Qwen3.8 Max",
@@ -4341,6 +4445,24 @@ export const MODELS = {
4341
4445
  contextWindow: 1048575,
4342
4446
  maxTokens: 131072,
4343
4447
  },
4448
+ "accounts/fireworks/routers/glm-5p3-fast": {
4449
+ id: "accounts/fireworks/routers/glm-5p3-fast",
4450
+ name: "GLM 5.3 Fast",
4451
+ api: "anthropic-messages",
4452
+ provider: "fireworks",
4453
+ baseUrl: "https://api.fireworks.ai/inference",
4454
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
4455
+ reasoning: true,
4456
+ input: ["text"],
4457
+ cost: {
4458
+ input: 2.1,
4459
+ output: 6.6,
4460
+ cacheRead: 0.39,
4461
+ cacheWrite: 0,
4462
+ },
4463
+ contextWindow: 1048572,
4464
+ maxTokens: 262144,
4465
+ },
4344
4466
  "accounts/fireworks/routers/kimi-k2p6-turbo": {
4345
4467
  id: "accounts/fireworks/routers/kimi-k2p6-turbo",
4346
4468
  name: "Kimi K2.6 Turbo",
@@ -4398,6 +4520,25 @@ export const MODELS = {
4398
4520
  contextWindow: 1000000,
4399
4521
  maxTokens: 128000,
4400
4522
  },
4523
+ "claude-fable-5.1": {
4524
+ id: "claude-fable-5.1",
4525
+ name: "Claude Fable 5.1",
4526
+ api: "openai-completions",
4527
+ provider: "github-copilot",
4528
+ baseUrl: "https://api.individual.githubcopilot.com",
4529
+ 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" },
4530
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4531
+ reasoning: true,
4532
+ input: ["text", "image"],
4533
+ cost: {
4534
+ input: 10,
4535
+ output: 50,
4536
+ cacheRead: 0.25,
4537
+ cacheWrite: 12.5,
4538
+ },
4539
+ contextWindow: 1000000,
4540
+ maxTokens: 128000,
4541
+ },
4401
4542
  "claude-haiku-4.5": {
4402
4543
  id: "claude-haiku-4.5",
4403
4544
  name: "Claude Haiku 4.5 (latest)",
@@ -4417,44 +4558,6 @@ export const MODELS = {
4417
4558
  contextWindow: 200000,
4418
4559
  maxTokens: 64000,
4419
4560
  },
4420
- "claude-opus-4.5": {
4421
- id: "claude-opus-4.5",
4422
- name: "Claude Opus 4.5 (latest)",
4423
- api: "anthropic-messages",
4424
- provider: "github-copilot",
4425
- baseUrl: "https://api.individual.githubcopilot.com",
4426
- 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" },
4427
- reasoning: true,
4428
- input: ["text", "image"],
4429
- cost: {
4430
- input: 5,
4431
- output: 25,
4432
- cacheRead: 0.5,
4433
- cacheWrite: 6.25,
4434
- },
4435
- contextWindow: 200000,
4436
- maxTokens: 32000,
4437
- },
4438
- "claude-opus-4.6": {
4439
- id: "claude-opus-4.6",
4440
- name: "Claude Opus 4.6",
4441
- api: "anthropic-messages",
4442
- provider: "github-copilot",
4443
- baseUrl: "https://api.individual.githubcopilot.com",
4444
- 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" },
4445
- compat: { "forceAdaptiveThinking": true },
4446
- reasoning: true,
4447
- thinkingLevelMap: { "xhigh": "max" },
4448
- input: ["text", "image"],
4449
- cost: {
4450
- input: 5,
4451
- output: 25,
4452
- cacheRead: 0.5,
4453
- cacheWrite: 6.25,
4454
- },
4455
- contextWindow: 1000000,
4456
- maxTokens: 32000,
4457
- },
4458
4561
  "claude-opus-4.7": {
4459
4562
  id: "claude-opus-4.7",
4460
4563
  name: "Claude Opus 4.7",
@@ -4513,44 +4616,6 @@ export const MODELS = {
4513
4616
  contextWindow: 1000000,
4514
4617
  maxTokens: 64000,
4515
4618
  },
4516
- "claude-sonnet-4": {
4517
- id: "claude-sonnet-4",
4518
- name: "Claude Sonnet 4 (latest)",
4519
- api: "anthropic-messages",
4520
- provider: "github-copilot",
4521
- baseUrl: "https://api.individual.githubcopilot.com",
4522
- 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" },
4523
- compat: { "supportsEagerToolInputStreaming": false },
4524
- reasoning: true,
4525
- input: ["text", "image"],
4526
- cost: {
4527
- input: 3,
4528
- output: 15,
4529
- cacheRead: 0.3,
4530
- cacheWrite: 3.75,
4531
- },
4532
- contextWindow: 216000,
4533
- maxTokens: 16000,
4534
- },
4535
- "claude-sonnet-4.5": {
4536
- id: "claude-sonnet-4.5",
4537
- name: "Claude Sonnet 4.5 (latest)",
4538
- api: "anthropic-messages",
4539
- provider: "github-copilot",
4540
- baseUrl: "https://api.individual.githubcopilot.com",
4541
- 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" },
4542
- compat: { "supportsEagerToolInputStreaming": false },
4543
- reasoning: true,
4544
- input: ["text", "image"],
4545
- cost: {
4546
- input: 3,
4547
- output: 15,
4548
- cacheRead: 0.3,
4549
- cacheWrite: 3.75,
4550
- },
4551
- contextWindow: 200000,
4552
- maxTokens: 32000,
4553
- },
4554
4619
  "claude-sonnet-4.6": {
4555
4620
  id: "claude-sonnet-4.6",
4556
4621
  name: "Claude Sonnet 4.6",
@@ -4589,25 +4654,6 @@ export const MODELS = {
4589
4654
  contextWindow: 1000000,
4590
4655
  maxTokens: 128000,
4591
4656
  },
4592
- "gemini-3.1-pro-preview": {
4593
- id: "gemini-3.1-pro-preview",
4594
- name: "Gemini 3.1 Pro Preview",
4595
- api: "openai-completions",
4596
- provider: "github-copilot",
4597
- baseUrl: "https://api.individual.githubcopilot.com",
4598
- 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" },
4599
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4600
- reasoning: true,
4601
- input: ["text", "image"],
4602
- cost: {
4603
- input: 2,
4604
- output: 12,
4605
- cacheRead: 0.2,
4606
- cacheWrite: 0,
4607
- },
4608
- contextWindow: 1000000,
4609
- maxTokens: 64000,
4610
- },
4611
4657
  "gemini-3.5-flash": {
4612
4658
  id: "gemini-3.5-flash",
4613
4659
  name: "Gemini 3.5 Flash",
@@ -4665,24 +4711,24 @@ export const MODELS = {
4665
4711
  contextWindow: 1000000,
4666
4712
  maxTokens: 64000,
4667
4713
  },
4668
- "gpt-4.1": {
4669
- id: "gpt-4.1",
4670
- name: "GPT-4.1",
4714
+ "gemini-3.8-flash": {
4715
+ id: "gemini-3.8-flash",
4716
+ name: "Gemini 3.8 Flash",
4671
4717
  api: "openai-completions",
4672
4718
  provider: "github-copilot",
4673
4719
  baseUrl: "https://api.individual.githubcopilot.com",
4674
4720
  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" },
4675
4721
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4676
- reasoning: false,
4722
+ reasoning: true,
4677
4723
  input: ["text", "image"],
4678
4724
  cost: {
4679
- input: 2,
4680
- output: 8,
4681
- cacheRead: 0.5,
4725
+ input: 0.75,
4726
+ output: 3.75,
4727
+ cacheRead: 0.075,
4682
4728
  cacheWrite: 0,
4683
4729
  },
4684
- contextWindow: 128000,
4685
- maxTokens: 16384,
4730
+ contextWindow: 1000000,
4731
+ maxTokens: 64000,
4686
4732
  },
4687
4733
  "gpt-5-mini": {
4688
4734
  id: "gpt-5-mini",
@@ -4703,44 +4749,6 @@ export const MODELS = {
4703
4749
  contextWindow: 264000,
4704
4750
  maxTokens: 64000,
4705
4751
  },
4706
- "gpt-5.2": {
4707
- id: "gpt-5.2",
4708
- name: "GPT-5.2",
4709
- api: "openai-responses",
4710
- provider: "github-copilot",
4711
- baseUrl: "https://api.individual.githubcopilot.com",
4712
- 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" },
4713
- reasoning: true,
4714
- thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
4715
- input: ["text", "image"],
4716
- cost: {
4717
- input: 1.75,
4718
- output: 14,
4719
- cacheRead: 0.175,
4720
- cacheWrite: 0,
4721
- },
4722
- contextWindow: 400000,
4723
- maxTokens: 128000,
4724
- },
4725
- "gpt-5.2-codex": {
4726
- id: "gpt-5.2-codex",
4727
- name: "GPT-5.2 Codex",
4728
- api: "openai-responses",
4729
- provider: "github-copilot",
4730
- baseUrl: "https://api.individual.githubcopilot.com",
4731
- 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" },
4732
- reasoning: true,
4733
- thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
4734
- input: ["text", "image"],
4735
- cost: {
4736
- input: 1.75,
4737
- output: 14,
4738
- cacheRead: 0.175,
4739
- cacheWrite: 0,
4740
- },
4741
- contextWindow: 400000,
4742
- maxTokens: 128000,
4743
- },
4744
4752
  "gpt-5.3-codex": {
4745
4753
  id: "gpt-5.3-codex",
4746
4754
  name: "GPT-5.3 Codex",
@@ -4866,10 +4874,10 @@ export const MODELS = {
4866
4874
  thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
4867
4875
  input: ["text", "image"],
4868
4876
  cost: {
4869
- input: 2,
4870
- output: 10,
4871
- cacheRead: 0.2,
4872
- cacheWrite: 2.5,
4877
+ input: 4,
4878
+ output: 20,
4879
+ cacheRead: 0.4,
4880
+ cacheWrite: 5,
4873
4881
  },
4874
4882
  contextWindow: 1050000,
4875
4883
  maxTokens: 128000,
@@ -4893,6 +4901,25 @@ export const MODELS = {
4893
4901
  contextWindow: 1050000,
4894
4902
  maxTokens: 128000,
4895
4903
  },
4904
+ "gpt-6-astra": {
4905
+ id: "gpt-6-astra",
4906
+ name: "GPT-6 Astra",
4907
+ api: "openai-completions",
4908
+ provider: "github-copilot",
4909
+ baseUrl: "https://api.individual.githubcopilot.com",
4910
+ 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" },
4911
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4912
+ reasoning: true,
4913
+ input: ["text", "image"],
4914
+ cost: {
4915
+ input: 10,
4916
+ output: 50,
4917
+ cacheRead: 1,
4918
+ cacheWrite: 12.5,
4919
+ },
4920
+ contextWindow: 1050000,
4921
+ maxTokens: 128000,
4922
+ },
4896
4923
  "grok-4.5": {
4897
4924
  id: "grok-4.5",
4898
4925
  name: "Grok 4.5",
@@ -5309,6 +5336,24 @@ export const MODELS = {
5309
5336
  contextWindow: 1048576,
5310
5337
  maxTokens: 65536,
5311
5338
  },
5339
+ "gemini-3.8-flash": {
5340
+ id: "gemini-3.8-flash",
5341
+ name: "Gemini 3.8 Flash",
5342
+ api: "google-generative-ai",
5343
+ provider: "google",
5344
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5345
+ reasoning: true,
5346
+ thinkingLevelMap: { "off": null },
5347
+ input: ["text", "image"],
5348
+ cost: {
5349
+ input: 0.75,
5350
+ output: 3.75,
5351
+ cacheRead: 0.075,
5352
+ cacheWrite: 0,
5353
+ },
5354
+ contextWindow: 1048576,
5355
+ maxTokens: 65536,
5356
+ },
5312
5357
  "gemini-flash-latest": {
5313
5358
  id: "gemini-flash-latest",
5314
5359
  name: "Gemini Flash Latest",
@@ -6414,6 +6459,24 @@ export const MODELS = {
6414
6459
  contextWindow: 1048576,
6415
6460
  maxTokens: 384000,
6416
6461
  },
6462
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
6463
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
6464
+ name: "DeepSeek V4 Flash Vision Exp",
6465
+ api: "openai-completions",
6466
+ provider: "huggingface",
6467
+ baseUrl: "https://router.huggingface.co/v1",
6468
+ compat: { "supportsDeveloperRole": false },
6469
+ reasoning: true,
6470
+ input: ["text", "image"],
6471
+ cost: {
6472
+ input: 0.44,
6473
+ output: 1.32,
6474
+ cacheRead: 0,
6475
+ cacheWrite: 0,
6476
+ },
6477
+ contextWindow: 1048576,
6478
+ maxTokens: 384000,
6479
+ },
6417
6480
  "deepseek-ai/DeepSeek-V4-Pro": {
6418
6481
  id: "deepseek-ai/DeepSeek-V4-Pro",
6419
6482
  name: "DeepSeek V4 Pro",
@@ -6736,7 +6799,7 @@ export const MODELS = {
6736
6799
  cacheWrite: 0,
6737
6800
  },
6738
6801
  contextWindow: 262144,
6739
- maxTokens: 64000,
6802
+ maxTokens: 128000,
6740
6803
  },
6741
6804
  "thinkingmachines/Inkling": {
6742
6805
  id: "thinkingmachines/Inkling",
@@ -7684,114 +7747,6 @@ export const MODELS = {
7684
7747
  },
7685
7748
  },
7686
7749
  "moonshotai": {
7687
- "kimi-k2-0711-preview": {
7688
- id: "kimi-k2-0711-preview",
7689
- name: "Kimi K2 0711",
7690
- api: "openai-completions",
7691
- provider: "moonshotai",
7692
- baseUrl: "https://api.moonshot.ai/v1",
7693
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7694
- reasoning: false,
7695
- input: ["text"],
7696
- cost: {
7697
- input: 0.6,
7698
- output: 2.5,
7699
- cacheRead: 0.15,
7700
- cacheWrite: 0,
7701
- },
7702
- contextWindow: 131072,
7703
- maxTokens: 16384,
7704
- },
7705
- "kimi-k2-0905-preview": {
7706
- id: "kimi-k2-0905-preview",
7707
- name: "Kimi K2 0905",
7708
- api: "openai-completions",
7709
- provider: "moonshotai",
7710
- baseUrl: "https://api.moonshot.ai/v1",
7711
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7712
- reasoning: false,
7713
- input: ["text"],
7714
- cost: {
7715
- input: 0.6,
7716
- output: 2.5,
7717
- cacheRead: 0.15,
7718
- cacheWrite: 0,
7719
- },
7720
- contextWindow: 262144,
7721
- maxTokens: 262144,
7722
- },
7723
- "kimi-k2-thinking": {
7724
- id: "kimi-k2-thinking",
7725
- name: "Kimi K2 Thinking",
7726
- api: "openai-completions",
7727
- provider: "moonshotai",
7728
- baseUrl: "https://api.moonshot.ai/v1",
7729
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7730
- reasoning: true,
7731
- input: ["text"],
7732
- cost: {
7733
- input: 0.6,
7734
- output: 2.5,
7735
- cacheRead: 0.15,
7736
- cacheWrite: 0,
7737
- },
7738
- contextWindow: 262144,
7739
- maxTokens: 262144,
7740
- },
7741
- "kimi-k2-thinking-turbo": {
7742
- id: "kimi-k2-thinking-turbo",
7743
- name: "Kimi K2 Thinking Turbo",
7744
- api: "openai-completions",
7745
- provider: "moonshotai",
7746
- baseUrl: "https://api.moonshot.ai/v1",
7747
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7748
- reasoning: true,
7749
- input: ["text"],
7750
- cost: {
7751
- input: 1.15,
7752
- output: 8,
7753
- cacheRead: 0.15,
7754
- cacheWrite: 0,
7755
- },
7756
- contextWindow: 262144,
7757
- maxTokens: 262144,
7758
- },
7759
- "kimi-k2-turbo-preview": {
7760
- id: "kimi-k2-turbo-preview",
7761
- name: "Kimi K2 Turbo",
7762
- api: "openai-completions",
7763
- provider: "moonshotai",
7764
- baseUrl: "https://api.moonshot.ai/v1",
7765
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7766
- reasoning: false,
7767
- input: ["text"],
7768
- cost: {
7769
- input: 2.4,
7770
- output: 10,
7771
- cacheRead: 0.6,
7772
- cacheWrite: 0,
7773
- },
7774
- contextWindow: 262144,
7775
- maxTokens: 262144,
7776
- },
7777
- "kimi-k2.5": {
7778
- id: "kimi-k2.5",
7779
- name: "Kimi K2.5",
7780
- api: "openai-completions",
7781
- provider: "moonshotai",
7782
- baseUrl: "https://api.moonshot.ai/v1",
7783
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7784
- reasoning: true,
7785
- input: ["text", "image"],
7786
- cost: {
7787
- input: 0.6,
7788
- output: 3,
7789
- cacheRead: 0.1,
7790
- cacheWrite: 0,
7791
- },
7792
- contextWindow: 262144,
7793
- maxTokens: 262144,
7794
- },
7795
7750
  "kimi-k2.6": {
7796
7751
  id: "kimi-k2.6",
7797
7752
  name: "Kimi K2.6",
@@ -7866,114 +7821,6 @@ export const MODELS = {
7866
7821
  },
7867
7822
  },
7868
7823
  "moonshotai-cn": {
7869
- "kimi-k2-0711-preview": {
7870
- id: "kimi-k2-0711-preview",
7871
- name: "Kimi K2 0711",
7872
- api: "openai-completions",
7873
- provider: "moonshotai-cn",
7874
- baseUrl: "https://api.moonshot.cn/v1",
7875
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7876
- reasoning: false,
7877
- input: ["text"],
7878
- cost: {
7879
- input: 0.6,
7880
- output: 2.5,
7881
- cacheRead: 0.15,
7882
- cacheWrite: 0,
7883
- },
7884
- contextWindow: 131072,
7885
- maxTokens: 16384,
7886
- },
7887
- "kimi-k2-0905-preview": {
7888
- id: "kimi-k2-0905-preview",
7889
- name: "Kimi K2 0905",
7890
- api: "openai-completions",
7891
- provider: "moonshotai-cn",
7892
- baseUrl: "https://api.moonshot.cn/v1",
7893
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7894
- reasoning: false,
7895
- input: ["text"],
7896
- cost: {
7897
- input: 0.6,
7898
- output: 2.5,
7899
- cacheRead: 0.15,
7900
- cacheWrite: 0,
7901
- },
7902
- contextWindow: 262144,
7903
- maxTokens: 262144,
7904
- },
7905
- "kimi-k2-thinking": {
7906
- id: "kimi-k2-thinking",
7907
- name: "Kimi K2 Thinking",
7908
- api: "openai-completions",
7909
- provider: "moonshotai-cn",
7910
- baseUrl: "https://api.moonshot.cn/v1",
7911
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7912
- reasoning: true,
7913
- input: ["text"],
7914
- cost: {
7915
- input: 0.6,
7916
- output: 2.5,
7917
- cacheRead: 0.15,
7918
- cacheWrite: 0,
7919
- },
7920
- contextWindow: 262144,
7921
- maxTokens: 262144,
7922
- },
7923
- "kimi-k2-thinking-turbo": {
7924
- id: "kimi-k2-thinking-turbo",
7925
- name: "Kimi K2 Thinking Turbo",
7926
- api: "openai-completions",
7927
- provider: "moonshotai-cn",
7928
- baseUrl: "https://api.moonshot.cn/v1",
7929
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7930
- reasoning: true,
7931
- input: ["text"],
7932
- cost: {
7933
- input: 1.15,
7934
- output: 8,
7935
- cacheRead: 0.15,
7936
- cacheWrite: 0,
7937
- },
7938
- contextWindow: 262144,
7939
- maxTokens: 262144,
7940
- },
7941
- "kimi-k2-turbo-preview": {
7942
- id: "kimi-k2-turbo-preview",
7943
- name: "Kimi K2 Turbo",
7944
- api: "openai-completions",
7945
- provider: "moonshotai-cn",
7946
- baseUrl: "https://api.moonshot.cn/v1",
7947
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7948
- reasoning: false,
7949
- input: ["text"],
7950
- cost: {
7951
- input: 2.4,
7952
- output: 10,
7953
- cacheRead: 0.6,
7954
- cacheWrite: 0,
7955
- },
7956
- contextWindow: 262144,
7957
- maxTokens: 262144,
7958
- },
7959
- "kimi-k2.5": {
7960
- id: "kimi-k2.5",
7961
- name: "Kimi K2.5",
7962
- api: "openai-completions",
7963
- provider: "moonshotai-cn",
7964
- baseUrl: "https://api.moonshot.cn/v1",
7965
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7966
- reasoning: true,
7967
- input: ["text", "image"],
7968
- cost: {
7969
- input: 0.6,
7970
- output: 3,
7971
- cacheRead: 0.1,
7972
- cacheWrite: 0,
7973
- },
7974
- contextWindow: 262144,
7975
- maxTokens: 262144,
7976
- },
7977
7824
  "kimi-k2.6": {
7978
7825
  id: "kimi-k2.6",
7979
7826
  name: "Kimi K2.6",
@@ -8650,6 +8497,23 @@ export const MODELS = {
8650
8497
  contextWindow: 1050000,
8651
8498
  maxTokens: 128000,
8652
8499
  },
8500
+ "gpt-6-astra": {
8501
+ id: "gpt-6-astra",
8502
+ name: "GPT-6 Astra",
8503
+ api: "openai-responses",
8504
+ provider: "openai",
8505
+ baseUrl: "https://api.openai.com/v1",
8506
+ reasoning: true,
8507
+ input: ["text", "image"],
8508
+ cost: {
8509
+ input: 10,
8510
+ output: 50,
8511
+ cacheRead: 1,
8512
+ cacheWrite: 12.5,
8513
+ },
8514
+ contextWindow: 1050000,
8515
+ maxTokens: 128000,
8516
+ },
8653
8517
  "gpt-realtime-2.1": {
8654
8518
  id: "gpt-realtime-2.1",
8655
8519
  name: "GPT-Realtime-2.1",
@@ -9199,6 +9063,25 @@ export const MODELS = {
9199
9063
  contextWindow: 1000000,
9200
9064
  maxTokens: 384000,
9201
9065
  },
9066
+ "deepseek-v4-flash-vision-exp": {
9067
+ id: "deepseek-v4-flash-vision-exp",
9068
+ name: "DeepSeek V4 Flash Vision Exp",
9069
+ api: "openai-completions",
9070
+ provider: "opencode",
9071
+ baseUrl: "https://opencode.ai/zen/v1",
9072
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9073
+ reasoning: true,
9074
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9075
+ input: ["text", "image"],
9076
+ cost: {
9077
+ input: 0.14,
9078
+ output: 0.28,
9079
+ cacheRead: 0.028,
9080
+ cacheWrite: 0,
9081
+ },
9082
+ contextWindow: 1000000,
9083
+ maxTokens: 384000,
9084
+ },
9202
9085
  "deepseek-v4-pro": {
9203
9086
  id: "deepseek-v4-pro",
9204
9087
  name: "DeepSeek V4 Pro",
@@ -9326,6 +9209,24 @@ export const MODELS = {
9326
9209
  contextWindow: 1048576,
9327
9210
  maxTokens: 65536,
9328
9211
  },
9212
+ "gemini-3.8-flash": {
9213
+ id: "gemini-3.8-flash",
9214
+ name: "Gemini 3.8 Flash",
9215
+ api: "google-generative-ai",
9216
+ provider: "opencode",
9217
+ baseUrl: "https://opencode.ai/zen/v1",
9218
+ reasoning: true,
9219
+ thinkingLevelMap: { "off": null },
9220
+ input: ["text", "image"],
9221
+ cost: {
9222
+ input: 1.5,
9223
+ output: 7.5,
9224
+ cacheRead: 0.15,
9225
+ cacheWrite: 0,
9226
+ },
9227
+ contextWindow: 1048576,
9228
+ maxTokens: 65536,
9229
+ },
9329
9230
  "glm-5": {
9330
9231
  id: "glm-5",
9331
9232
  name: "GLM-5",
@@ -9377,6 +9278,40 @@ export const MODELS = {
9377
9278
  contextWindow: 1000000,
9378
9279
  maxTokens: 131072,
9379
9280
  },
9281
+ "glm-5.3": {
9282
+ id: "glm-5.3",
9283
+ name: "GLM-5.3",
9284
+ api: "openai-completions",
9285
+ provider: "opencode",
9286
+ baseUrl: "https://opencode.ai/zen/v1",
9287
+ reasoning: true,
9288
+ input: ["text"],
9289
+ cost: {
9290
+ input: 1.4,
9291
+ output: 4.4,
9292
+ cacheRead: 0.26,
9293
+ cacheWrite: 0,
9294
+ },
9295
+ contextWindow: 1000000,
9296
+ maxTokens: 131072,
9297
+ },
9298
+ "glm-5.3-flash": {
9299
+ id: "glm-5.3-flash",
9300
+ name: "GLM-5.3-Flash",
9301
+ api: "openai-completions",
9302
+ provider: "opencode",
9303
+ baseUrl: "https://opencode.ai/zen/v1",
9304
+ reasoning: true,
9305
+ input: ["text", "image"],
9306
+ cost: {
9307
+ input: 0.15,
9308
+ output: 0.5,
9309
+ cacheRead: 0.03,
9310
+ cacheWrite: 0,
9311
+ },
9312
+ contextWindow: 1000000,
9313
+ maxTokens: 131072,
9314
+ },
9380
9315
  "gpt-5": {
9381
9316
  id: "gpt-5",
9382
9317
  name: "GPT-5",
@@ -9719,6 +9654,23 @@ export const MODELS = {
9719
9654
  contextWindow: 1050000,
9720
9655
  maxTokens: 128000,
9721
9656
  },
9657
+ "gpt-6-astra": {
9658
+ id: "gpt-6-astra",
9659
+ name: "GPT-6 Astra",
9660
+ api: "openai-responses",
9661
+ provider: "opencode",
9662
+ baseUrl: "https://opencode.ai/zen/v1",
9663
+ reasoning: true,
9664
+ input: ["text", "image"],
9665
+ cost: {
9666
+ input: 10,
9667
+ output: 50,
9668
+ cacheRead: 1,
9669
+ cacheWrite: 12.5,
9670
+ },
9671
+ contextWindow: 1050000,
9672
+ maxTokens: 128000,
9673
+ },
9722
9674
  "grok-4.5": {
9723
9675
  id: "grok-4.5",
9724
9676
  name: "Grok 4.5",
@@ -9960,6 +9912,40 @@ export const MODELS = {
9960
9912
  contextWindow: 1048576,
9961
9913
  maxTokens: 131072,
9962
9914
  },
9915
+ "muse-spark-1.3": {
9916
+ id: "muse-spark-1.3",
9917
+ name: "Muse Spark 1.3",
9918
+ api: "openai-responses",
9919
+ provider: "opencode",
9920
+ baseUrl: "https://opencode.ai/zen/v1",
9921
+ reasoning: true,
9922
+ input: ["text", "image"],
9923
+ cost: {
9924
+ input: 1.25,
9925
+ output: 4.25,
9926
+ cacheRead: 0.15,
9927
+ cacheWrite: 0,
9928
+ },
9929
+ contextWindow: 1048576,
9930
+ maxTokens: 131072,
9931
+ },
9932
+ "muse-spark-1.3-contributor-free": {
9933
+ id: "muse-spark-1.3-contributor-free",
9934
+ name: "Muse Spark 1.3 Free",
9935
+ api: "openai-responses",
9936
+ provider: "opencode",
9937
+ baseUrl: "https://opencode.ai/zen/v1",
9938
+ reasoning: true,
9939
+ input: ["text", "image"],
9940
+ cost: {
9941
+ input: 0,
9942
+ output: 0,
9943
+ cacheRead: 0,
9944
+ cacheWrite: 0,
9945
+ },
9946
+ contextWindow: 1048576,
9947
+ maxTokens: 131072,
9948
+ },
9963
9949
  "nemotron-3-ultra-free": {
9964
9950
  id: "nemotron-3-ultra-free",
9965
9951
  name: "Nemotron 3 Ultra Free",
@@ -10205,7 +10191,7 @@ export const MODELS = {
10205
10191
  cacheWrite: 0,
10206
10192
  },
10207
10193
  contextWindow: 256000,
10208
- maxTokens: 64000,
10194
+ maxTokens: 128000,
10209
10195
  },
10210
10196
  "hy4-preview": {
10211
10197
  id: "hy4-preview",
@@ -10359,12 +10345,29 @@ export const MODELS = {
10359
10345
  cacheRead: 0.06,
10360
10346
  cacheWrite: 0,
10361
10347
  },
10362
- contextWindow: 1000000,
10348
+ contextWindow: 1000000,
10349
+ maxTokens: 131072,
10350
+ },
10351
+ "muse-spark-1.2-contributor": {
10352
+ id: "muse-spark-1.2-contributor",
10353
+ name: "Muse Spark 1.2 Contributor",
10354
+ api: "openai-responses",
10355
+ provider: "opencode-go",
10356
+ baseUrl: "https://opencode.ai/zen/go/v1",
10357
+ reasoning: true,
10358
+ input: ["text", "image"],
10359
+ cost: {
10360
+ input: 0.1,
10361
+ output: 0.2,
10362
+ cacheRead: 0.002,
10363
+ cacheWrite: 0,
10364
+ },
10365
+ contextWindow: 1048576,
10363
10366
  maxTokens: 131072,
10364
10367
  },
10365
- "muse-spark-1.2-contributor": {
10366
- id: "muse-spark-1.2-contributor",
10367
- name: "Muse Spark 1.2 Contributor",
10368
+ "muse-spark-1.3-contributor": {
10369
+ id: "muse-spark-1.3-contributor",
10370
+ name: "Muse Spark 1.3 Contributor",
10368
10371
  api: "openai-responses",
10369
10372
  provider: "opencode-go",
10370
10373
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -10379,6 +10382,23 @@ export const MODELS = {
10379
10382
  contextWindow: 1048576,
10380
10383
  maxTokens: 131072,
10381
10384
  },
10385
+ "omen-alpha": {
10386
+ id: "omen-alpha",
10387
+ name: "Omen Alpha",
10388
+ api: "openai-completions",
10389
+ provider: "opencode-go",
10390
+ baseUrl: "https://opencode.ai/zen/go/v1",
10391
+ reasoning: true,
10392
+ input: ["text", "image"],
10393
+ cost: {
10394
+ input: 0.2,
10395
+ output: 0.66,
10396
+ cacheRead: 0.04,
10397
+ cacheWrite: 0,
10398
+ },
10399
+ contextWindow: 500000,
10400
+ maxTokens: 128000,
10401
+ },
10382
10402
  "qwen3.6-plus": {
10383
10403
  id: "qwen3.6-plus",
10384
10404
  name: "Qwen3.6 Plus",
@@ -11262,13 +11282,13 @@ export const MODELS = {
11262
11282
  reasoning: false,
11263
11283
  input: ["text"],
11264
11284
  cost: {
11265
- input: 0.2574,
11266
- output: 1.0287,
11285
+ input: 0.32,
11286
+ output: 0.8899999999999999,
11267
11287
  cacheRead: 0,
11268
11288
  cacheWrite: 0,
11269
11289
  },
11270
11290
  contextWindow: 163840,
11271
- maxTokens: 16000,
11291
+ maxTokens: 16384,
11272
11292
  },
11273
11293
  "deepseek/deepseek-chat-v3-0324": {
11274
11294
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11279,9 +11299,9 @@ export const MODELS = {
11279
11299
  reasoning: false,
11280
11300
  input: ["text"],
11281
11301
  cost: {
11282
- input: 0.25,
11283
- output: 1,
11284
- cacheRead: 0,
11302
+ input: 0.29,
11303
+ output: 1.1400000000000001,
11304
+ cacheRead: 0.11,
11285
11305
  cacheWrite: 0,
11286
11306
  },
11287
11307
  contextWindow: 163840,
@@ -11476,9 +11496,9 @@ export const MODELS = {
11476
11496
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
11477
11497
  input: ["text"],
11478
11498
  cost: {
11479
- input: 1.04226,
11480
- output: 2.08452,
11481
- cacheRead: 0.086855,
11499
+ input: 0.9552599999999999,
11500
+ output: 1.9105199999999998,
11501
+ cacheRead: 0.07960500000000001,
11482
11502
  cacheWrite: 0,
11483
11503
  },
11484
11504
  contextWindow: 1048576,
@@ -11495,9 +11515,9 @@ export const MODELS = {
11495
11515
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
11496
11516
  input: ["text"],
11497
11517
  cost: {
11498
- input: 1.1154,
11499
- output: 3.3461999999999996,
11500
- cacheRead: 0.03718,
11518
+ input: 1.0494,
11519
+ output: 3.1482,
11520
+ cacheRead: 0.03498,
11501
11521
  cacheWrite: 0,
11502
11522
  },
11503
11523
  contextWindow: 1048576,
@@ -11956,10 +11976,44 @@ export const MODELS = {
11956
11976
  reasoning: true,
11957
11977
  input: ["text", "image"],
11958
11978
  cost: {
11959
- input: 0.1875,
11960
- output: 0.9375,
11961
- cacheRead: 0.01875,
11962
- cacheWrite: 0.0208333333333333,
11979
+ input: 0.375,
11980
+ output: 1.875,
11981
+ cacheRead: 0.0375,
11982
+ cacheWrite: 0.0416666666666667,
11983
+ },
11984
+ contextWindow: 1048576,
11985
+ maxTokens: 65536,
11986
+ },
11987
+ "google/gemini-3.8-flash": {
11988
+ id: "google/gemini-3.8-flash",
11989
+ name: "Google: Gemini 3.8 Flash",
11990
+ api: "openai-completions",
11991
+ provider: "openrouter",
11992
+ baseUrl: "https://openrouter.ai/api/v1",
11993
+ reasoning: true,
11994
+ input: ["text", "image"],
11995
+ cost: {
11996
+ input: 0.75,
11997
+ output: 3.75,
11998
+ cacheRead: 0.075,
11999
+ cacheWrite: 0.0416666666666667,
12000
+ },
12001
+ contextWindow: 1048576,
12002
+ maxTokens: 65536,
12003
+ },
12004
+ "google/gemini-3.8-flash:batch": {
12005
+ id: "google/gemini-3.8-flash:batch",
12006
+ name: "Google: Gemini 3.8 Flash (batch)",
12007
+ api: "openai-completions",
12008
+ provider: "openrouter",
12009
+ baseUrl: "https://openrouter.ai/api/v1",
12010
+ reasoning: true,
12011
+ input: ["text", "image"],
12012
+ cost: {
12013
+ input: 0.375,
12014
+ output: 1.875,
12015
+ cacheRead: 0.0375,
12016
+ cacheWrite: 0.0416666666666667,
11963
12017
  },
11964
12018
  contextWindow: 1048576,
11965
12019
  maxTokens: 65536,
@@ -12083,23 +12137,6 @@ export const MODELS = {
12083
12137
  contextWindow: 262144,
12084
12138
  maxTokens: 32768,
12085
12139
  },
12086
- "ibm-granite/granite-4.1-8b": {
12087
- id: "ibm-granite/granite-4.1-8b",
12088
- name: "IBM: Granite 4.1 8B",
12089
- api: "openai-completions",
12090
- provider: "openrouter",
12091
- baseUrl: "https://openrouter.ai/api/v1",
12092
- reasoning: false,
12093
- input: ["text"],
12094
- cost: {
12095
- input: 0.049999999999999996,
12096
- output: 0.09999999999999999,
12097
- cacheRead: 0.049999999999999996,
12098
- cacheWrite: 0,
12099
- },
12100
- contextWindow: 131072,
12101
- maxTokens: 117964,
12102
- },
12103
12140
  "ibm-granite/granite-4.2-8b": {
12104
12141
  id: "ibm-granite/granite-4.2-8b",
12105
12142
  name: "IBM: Granite 4.2 8B",
@@ -12155,7 +12192,7 @@ export const MODELS = {
12155
12192
  },
12156
12193
  "inclusionai/ling-3.0-flash": {
12157
12194
  id: "inclusionai/ling-3.0-flash",
12158
- name: "Ling-3.0-flash",
12195
+ name: "inclusionAI: Ling 3.0 Flash",
12159
12196
  api: "openai-completions",
12160
12197
  provider: "openrouter",
12161
12198
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12170,9 +12207,43 @@ export const MODELS = {
12170
12207
  contextWindow: 262144,
12171
12208
  maxTokens: 32768,
12172
12209
  },
12210
+ "inclusionai/ling-3.0-flash-fin": {
12211
+ id: "inclusionai/ling-3.0-flash-fin",
12212
+ name: "inclusionAI: Ling 3.0 Flash Fin",
12213
+ api: "openai-completions",
12214
+ provider: "openrouter",
12215
+ baseUrl: "https://openrouter.ai/api/v1",
12216
+ reasoning: true,
12217
+ input: ["text"],
12218
+ cost: {
12219
+ input: 0.06,
12220
+ output: 0.18,
12221
+ cacheRead: 0.012,
12222
+ cacheWrite: 0,
12223
+ },
12224
+ contextWindow: 262144,
12225
+ maxTokens: 235929,
12226
+ },
12173
12227
  "inclusionai/ling-3.0-flash-fin:free": {
12174
12228
  id: "inclusionai/ling-3.0-flash-fin:free",
12175
- name: "Ling 3.0 Flash Fin (free)",
12229
+ name: "inclusionAI: Ling 3.0 Flash Fin (free)",
12230
+ api: "openai-completions",
12231
+ provider: "openrouter",
12232
+ baseUrl: "https://openrouter.ai/api/v1",
12233
+ reasoning: true,
12234
+ input: ["text"],
12235
+ cost: {
12236
+ input: 0,
12237
+ output: 0,
12238
+ cacheRead: 0,
12239
+ cacheWrite: 0,
12240
+ },
12241
+ contextWindow: 262144,
12242
+ maxTokens: 32768,
12243
+ },
12244
+ "inclusionai/ling-3.0-flash-sante:free": {
12245
+ id: "inclusionai/ling-3.0-flash-sante:free",
12246
+ name: "inclusionAI: Ling 3.0 Flash Sante (free)",
12176
12247
  api: "openai-completions",
12177
12248
  provider: "openrouter",
12178
12249
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12298,13 +12369,13 @@ export const MODELS = {
12298
12369
  reasoning: false,
12299
12370
  input: ["text"],
12300
12371
  cost: {
12301
- input: 0.71,
12302
- output: 0.71,
12303
- cacheRead: 0.71,
12372
+ input: 0.09999999999999999,
12373
+ output: 0.32,
12374
+ cacheRead: 0,
12304
12375
  cacheWrite: 0,
12305
12376
  },
12306
12377
  contextWindow: 131072,
12307
- maxTokens: 115200,
12378
+ maxTokens: 16384,
12308
12379
  },
12309
12380
  "meta-llama/llama-4-maverick": {
12310
12381
  id: "meta-llama/llama-4-maverick",
@@ -12350,12 +12421,12 @@ export const MODELS = {
12350
12421
  input: ["text", "image"],
12351
12422
  cost: {
12352
12423
  input: 0.3,
12353
- output: 1.2,
12424
+ output: 1.1,
12354
12425
  cacheRead: 0.04,
12355
12426
  cacheWrite: 0,
12356
12427
  },
12357
12428
  contextWindow: 131072,
12358
- maxTokens: 16384,
12429
+ maxTokens: 117964,
12359
12430
  },
12360
12431
  "meta/muse-glimmer-30b:batch": {
12361
12432
  id: "meta/muse-glimmer-30b:batch",
@@ -12425,6 +12496,40 @@ export const MODELS = {
12425
12496
  contextWindow: 1048576,
12426
12497
  maxTokens: 943718,
12427
12498
  },
12499
+ "meta/muse-spark-1.3": {
12500
+ id: "meta/muse-spark-1.3",
12501
+ name: "Meta: Muse Spark 1.3",
12502
+ api: "openai-completions",
12503
+ provider: "openrouter",
12504
+ baseUrl: "https://openrouter.ai/api/v1",
12505
+ reasoning: true,
12506
+ input: ["text", "image"],
12507
+ cost: {
12508
+ input: 1.25,
12509
+ output: 4.25,
12510
+ cacheRead: 0.15,
12511
+ cacheWrite: 0,
12512
+ },
12513
+ contextWindow: 1048576,
12514
+ maxTokens: 943718,
12515
+ },
12516
+ "meta/muse-spark-1.3-contributor": {
12517
+ id: "meta/muse-spark-1.3-contributor",
12518
+ name: "Meta: Muse Spark 1.3 Contributor",
12519
+ api: "openai-completions",
12520
+ provider: "openrouter",
12521
+ baseUrl: "https://openrouter.ai/api/v1",
12522
+ reasoning: true,
12523
+ input: ["text", "image"],
12524
+ cost: {
12525
+ input: 0.09999999999999999,
12526
+ output: 0.19999999999999998,
12527
+ cacheRead: 0.002,
12528
+ cacheWrite: 0,
12529
+ },
12530
+ contextWindow: 1048576,
12531
+ maxTokens: 943718,
12532
+ },
12428
12533
  "minimax/minimax-m1": {
12429
12534
  id: "minimax/minimax-m1",
12430
12535
  name: "MiniMax: MiniMax M1",
@@ -12434,7 +12539,7 @@ export const MODELS = {
12434
12539
  reasoning: true,
12435
12540
  input: ["text"],
12436
12541
  cost: {
12437
- input: 0.55,
12542
+ input: 0.39999999999999997,
12438
12543
  output: 2.2,
12439
12544
  cacheRead: 0,
12440
12545
  cacheWrite: 0,
@@ -12510,23 +12615,6 @@ export const MODELS = {
12510
12615
  contextWindow: 204800,
12511
12616
  maxTokens: 131072,
12512
12617
  },
12513
- "minimax/minimax-m2.7:free": {
12514
- id: "minimax/minimax-m2.7:free",
12515
- name: "MiniMax: MiniMax M2.7 (free)",
12516
- api: "openai-completions",
12517
- provider: "openrouter",
12518
- baseUrl: "https://openrouter.ai/api/v1",
12519
- reasoning: true,
12520
- input: ["text"],
12521
- cost: {
12522
- input: 0,
12523
- output: 0,
12524
- cacheRead: 0,
12525
- cacheWrite: 0,
12526
- },
12527
- contextWindow: 196608,
12528
- maxTokens: 176947,
12529
- },
12530
12618
  "minimax/minimax-m3": {
12531
12619
  id: "minimax/minimax-m3",
12532
12620
  name: "MiniMax: MiniMax M3",
@@ -12561,23 +12649,6 @@ export const MODELS = {
12561
12649
  contextWindow: 524288,
12562
12650
  maxTokens: 471859,
12563
12651
  },
12564
- "minimax/minimax-m3:free": {
12565
- id: "minimax/minimax-m3:free",
12566
- name: "MiniMax: MiniMax M3 (free)",
12567
- api: "openai-completions",
12568
- provider: "openrouter",
12569
- baseUrl: "https://openrouter.ai/api/v1",
12570
- reasoning: true,
12571
- input: ["text", "image"],
12572
- cost: {
12573
- input: 0,
12574
- output: 0,
12575
- cacheRead: 0,
12576
- cacheWrite: 0,
12577
- },
12578
- contextWindow: 1048576,
12579
- maxTokens: 943718,
12580
- },
12581
12652
  "mistralai/codestral-2508": {
12582
12653
  id: "mistralai/codestral-2508",
12583
12654
  name: "Mistral: Codestral 2508",
@@ -12929,11 +13000,11 @@ export const MODELS = {
12929
13000
  cost: {
12930
13001
  input: 0.6,
12931
13002
  output: 2.5,
12932
- cacheRead: 0.15,
13003
+ cacheRead: 0,
12933
13004
  cacheWrite: 0,
12934
13005
  },
12935
13006
  contextWindow: 262144,
12936
- maxTokens: 100352,
13007
+ maxTokens: 235929,
12937
13008
  },
12938
13009
  "moonshotai/kimi-k2.5": {
12939
13010
  id: "moonshotai/kimi-k2.5",
@@ -12979,9 +13050,9 @@ export const MODELS = {
12979
13050
  reasoning: true,
12980
13051
  input: ["text", "image"],
12981
13052
  cost: {
12982
- input: 0.66,
12983
- output: 3.4,
12984
- cacheRead: 0.18,
13053
+ input: 0.71,
13054
+ output: 3.5,
13055
+ cacheRead: 0.15,
12985
13056
  cacheWrite: 0,
12986
13057
  },
12987
13058
  contextWindow: 262144,
@@ -13066,11 +13137,11 @@ export const MODELS = {
13066
13137
  cost: {
13067
13138
  input: 0.049999999999999996,
13068
13139
  output: 0.19999999999999998,
13069
- cacheRead: 0.024999999999999998,
13140
+ cacheRead: 0.03,
13070
13141
  cacheWrite: 0,
13071
13142
  },
13072
13143
  contextWindow: 262144,
13073
- maxTokens: 228000,
13144
+ maxTokens: 235929,
13074
13145
  },
13075
13146
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
13076
13147
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -13140,23 +13211,6 @@ export const MODELS = {
13140
13211
  contextWindow: 262144,
13141
13212
  maxTokens: 32768,
13142
13213
  },
13143
- "nvidia/nemotron-3-ultra-550b-a55b:batch": {
13144
- id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
13145
- name: "NVIDIA: Nemotron 3 Ultra (batch)",
13146
- api: "openai-completions",
13147
- provider: "openrouter",
13148
- baseUrl: "https://openrouter.ai/api/v1",
13149
- reasoning: true,
13150
- input: ["text"],
13151
- cost: {
13152
- input: 0.6,
13153
- output: 3.5999999999999996,
13154
- cacheRead: 0.19999999999999998,
13155
- cacheWrite: 0,
13156
- },
13157
- contextWindow: 512288,
13158
- maxTokens: 461059,
13159
- },
13160
13214
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13161
13215
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
13162
13216
  name: "NVIDIA: Nemotron 3 Ultra (free)",
@@ -14344,21 +14398,89 @@ export const MODELS = {
14344
14398
  contextWindow: 1050000,
14345
14399
  maxTokens: 128000,
14346
14400
  },
14347
- "openai/gpt-5:batch": {
14348
- id: "openai/gpt-5:batch",
14349
- name: "OpenAI: GPT-5 (batch)",
14401
+ "openai/gpt-5:batch": {
14402
+ id: "openai/gpt-5:batch",
14403
+ name: "OpenAI: GPT-5 (batch)",
14404
+ api: "openai-completions",
14405
+ provider: "openrouter",
14406
+ baseUrl: "https://openrouter.ai/api/v1",
14407
+ reasoning: true,
14408
+ input: ["text", "image"],
14409
+ cost: {
14410
+ input: 0.625,
14411
+ output: 5,
14412
+ cacheRead: 0.0625,
14413
+ cacheWrite: 0,
14414
+ },
14415
+ contextWindow: 400000,
14416
+ maxTokens: 128000,
14417
+ },
14418
+ "openai/gpt-6-astra": {
14419
+ id: "openai/gpt-6-astra",
14420
+ name: "OpenAI: GPT-6 Astra",
14421
+ api: "openai-completions",
14422
+ provider: "openrouter",
14423
+ baseUrl: "https://openrouter.ai/api/v1",
14424
+ reasoning: true,
14425
+ input: ["text", "image"],
14426
+ cost: {
14427
+ input: 10,
14428
+ output: 50,
14429
+ cacheRead: 1,
14430
+ cacheWrite: 12.5,
14431
+ },
14432
+ contextWindow: 1050000,
14433
+ maxTokens: 128000,
14434
+ },
14435
+ "openai/gpt-6-astra-pro": {
14436
+ id: "openai/gpt-6-astra-pro",
14437
+ name: "OpenAI: GPT-6 Astra Pro",
14438
+ api: "openai-completions",
14439
+ provider: "openrouter",
14440
+ baseUrl: "https://openrouter.ai/api/v1",
14441
+ reasoning: true,
14442
+ input: ["text", "image"],
14443
+ cost: {
14444
+ input: 10,
14445
+ output: 50,
14446
+ cacheRead: 1,
14447
+ cacheWrite: 12.5,
14448
+ },
14449
+ contextWindow: 1050000,
14450
+ maxTokens: 128000,
14451
+ },
14452
+ "openai/gpt-6-astra-pro:batch": {
14453
+ id: "openai/gpt-6-astra-pro:batch",
14454
+ name: "OpenAI: GPT-6 Astra Pro (batch)",
14455
+ api: "openai-completions",
14456
+ provider: "openrouter",
14457
+ baseUrl: "https://openrouter.ai/api/v1",
14458
+ reasoning: true,
14459
+ input: ["text", "image"],
14460
+ cost: {
14461
+ input: 5,
14462
+ output: 25,
14463
+ cacheRead: 0.5,
14464
+ cacheWrite: 6.25,
14465
+ },
14466
+ contextWindow: 1050000,
14467
+ maxTokens: 128000,
14468
+ },
14469
+ "openai/gpt-6-astra:batch": {
14470
+ id: "openai/gpt-6-astra:batch",
14471
+ name: "OpenAI: GPT-6 Astra (batch)",
14350
14472
  api: "openai-completions",
14351
14473
  provider: "openrouter",
14352
14474
  baseUrl: "https://openrouter.ai/api/v1",
14353
14475
  reasoning: true,
14354
14476
  input: ["text", "image"],
14355
14477
  cost: {
14356
- input: 0.625,
14357
- output: 5,
14358
- cacheRead: 0.0625,
14359
- cacheWrite: 0,
14478
+ input: 5,
14479
+ output: 25,
14480
+ cacheRead: 0.5,
14481
+ cacheWrite: 6.25,
14360
14482
  },
14361
- contextWindow: 400000,
14483
+ contextWindow: 1050000,
14362
14484
  maxTokens: 128000,
14363
14485
  },
14364
14486
  "openai/gpt-audio": {
@@ -14846,13 +14968,13 @@ export const MODELS = {
14846
14968
  reasoning: true,
14847
14969
  input: ["text"],
14848
14970
  cost: {
14849
- input: 0.12,
14850
- output: 0.24,
14971
+ input: 0.22749999999999998,
14972
+ output: 0.9099999999999999,
14851
14973
  cacheRead: 0,
14852
14974
  cacheWrite: 0,
14853
14975
  },
14854
14976
  contextWindow: 131072,
14855
- maxTokens: 16384,
14977
+ maxTokens: 8192,
14856
14978
  },
14857
14979
  "qwen/qwen3-235b-a22b": {
14858
14980
  id: "qwen/qwen3-235b-a22b",
@@ -14880,13 +15002,13 @@ export const MODELS = {
14880
15002
  reasoning: false,
14881
15003
  input: ["text"],
14882
15004
  cost: {
14883
- input: 0.0875,
14884
- output: 0.35,
14885
- cacheRead: 0.0175,
15005
+ input: 0.09,
15006
+ output: 0.55,
15007
+ cacheRead: 0,
14886
15008
  cacheWrite: 0,
14887
15009
  },
14888
15010
  contextWindow: 262144,
14889
- maxTokens: 235929,
15011
+ maxTokens: 16384,
14890
15012
  },
14891
15013
  "qwen/qwen3-235b-a22b-thinking-2507": {
14892
15014
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -15141,7 +15263,7 @@ export const MODELS = {
15141
15263
  cacheWrite: 0,
15142
15264
  },
15143
15265
  contextWindow: 262144,
15144
- maxTokens: 32768,
15266
+ maxTokens: 235929,
15145
15267
  },
15146
15268
  "qwen/qwen3-vl-235b-a22b-instruct": {
15147
15269
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -15305,13 +15427,13 @@ export const MODELS = {
15305
15427
  reasoning: true,
15306
15428
  input: ["text", "image"],
15307
15429
  cost: {
15308
- input: 0.25,
15430
+ input: 0.3125,
15309
15431
  output: 1.25,
15310
- cacheRead: 0.25,
15432
+ cacheRead: 0.15625,
15311
15433
  cacheWrite: 0,
15312
15434
  },
15313
15435
  contextWindow: 262144,
15314
- maxTokens: 235929,
15436
+ maxTokens: 16384,
15315
15437
  },
15316
15438
  "qwen/qwen3.5-397b-a17b": {
15317
15439
  id: "qwen/qwen3.5-397b-a17b",
@@ -15424,13 +15546,13 @@ export const MODELS = {
15424
15546
  reasoning: true,
15425
15547
  input: ["text", "image"],
15426
15548
  cost: {
15427
- input: 0.6,
15428
- output: 3.5999999999999996,
15429
- cacheRead: 0.12,
15549
+ input: 0.3,
15550
+ output: 2,
15551
+ cacheRead: 0.03,
15430
15552
  cacheWrite: 0,
15431
15553
  },
15432
15554
  contextWindow: 262144,
15433
- maxTokens: 235929,
15555
+ maxTokens: 65536,
15434
15556
  },
15435
15557
  "qwen/qwen3.6-35b-a3b": {
15436
15558
  id: "qwen/qwen3.6-35b-a3b",
@@ -15562,11 +15684,11 @@ export const MODELS = {
15562
15684
  cost: {
15563
15685
  input: 2,
15564
15686
  output: 6,
15565
- cacheRead: 0.19999999999999998,
15687
+ cacheRead: 0.25,
15566
15688
  cacheWrite: 0,
15567
15689
  },
15568
15690
  contextWindow: 1048576,
15569
- maxTokens: 131072,
15691
+ maxTokens: 262144,
15570
15692
  },
15571
15693
  "qwen/qwen3.8-2.4t-a95b:batch": {
15572
15694
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -15594,10 +15716,10 @@ export const MODELS = {
15594
15716
  reasoning: true,
15595
15717
  input: ["text", "image"],
15596
15718
  cost: {
15597
- input: 0.425,
15598
- output: 2.5500000000000003,
15719
+ input: 0.42,
15720
+ output: 3,
15599
15721
  cacheRead: 0.08499999999999999,
15600
- cacheWrite: 0.53125,
15722
+ cacheWrite: 0,
15601
15723
  },
15602
15724
  contextWindow: 1000000,
15603
15725
  maxTokens: 131072,
@@ -15619,9 +15741,9 @@ export const MODELS = {
15619
15741
  contextWindow: 1000000,
15620
15742
  maxTokens: 131072,
15621
15743
  },
15622
- "qwen/qwen3.8-max": {
15623
- id: "qwen/qwen3.8-max",
15624
- name: "Qwen: Qwen3.8 Max",
15744
+ "qwen/qwen3.8-max-0902": {
15745
+ id: "qwen/qwen3.8-max-0902",
15746
+ name: "Qwen: Qwen3.8 Max (0902)",
15625
15747
  api: "openai-completions",
15626
15748
  provider: "openrouter",
15627
15749
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15821,7 +15943,7 @@ export const MODELS = {
15821
15943
  cacheWrite: 0,
15822
15944
  },
15823
15945
  contextWindow: 1024000,
15824
- maxTokens: 26214,
15946
+ maxTokens: 819200,
15825
15947
  },
15826
15948
  "thinkingmachines/inkling": {
15827
15949
  id: "thinkingmachines/inkling",
@@ -15993,6 +16115,23 @@ export const MODELS = {
15993
16115
  contextWindow: 1000000,
15994
16116
  maxTokens: 900000,
15995
16117
  },
16118
+ "x-ai/grok-4.3:batch": {
16119
+ id: "x-ai/grok-4.3:batch",
16120
+ name: "SpaceXAI: Grok 4.3 (batch)",
16121
+ api: "openai-completions",
16122
+ provider: "openrouter",
16123
+ baseUrl: "https://openrouter.ai/api/v1",
16124
+ reasoning: true,
16125
+ input: ["text", "image"],
16126
+ cost: {
16127
+ input: 1,
16128
+ output: 2,
16129
+ cacheRead: 0.16,
16130
+ cacheWrite: 0,
16131
+ },
16132
+ contextWindow: 1000000,
16133
+ maxTokens: 900000,
16134
+ },
15996
16135
  "x-ai/grok-4.5": {
15997
16136
  id: "x-ai/grok-4.5",
15998
16137
  name: "SpaceXAI: Grok 4.5",
@@ -16138,13 +16277,13 @@ export const MODELS = {
16138
16277
  reasoning: true,
16139
16278
  input: ["text"],
16140
16279
  cost: {
16141
- input: 0.43,
16142
- output: 1.75,
16143
- cacheRead: 0.08,
16280
+ input: 0.55,
16281
+ output: 2.2,
16282
+ cacheRead: 0.11,
16144
16283
  cacheWrite: 0,
16145
16284
  },
16146
16285
  contextWindow: 204800,
16147
- maxTokens: 16384,
16286
+ maxTokens: 131072,
16148
16287
  },
16149
16288
  "z-ai/glm-4.6v": {
16150
16289
  id: "z-ai/glm-4.6v",
@@ -16189,13 +16328,13 @@ export const MODELS = {
16189
16328
  reasoning: true,
16190
16329
  input: ["text"],
16191
16330
  cost: {
16192
- input: 0.06,
16331
+ input: 0.060500000000000005,
16193
16332
  output: 0.39999999999999997,
16194
- cacheRead: 0.01,
16333
+ cacheRead: 0,
16195
16334
  cacheWrite: 0,
16196
16335
  },
16197
16336
  contextWindow: 202752,
16198
- maxTokens: 16384,
16337
+ maxTokens: 117964,
16199
16338
  },
16200
16339
  "z-ai/glm-5": {
16201
16340
  id: "z-ai/glm-5",
@@ -16265,23 +16404,6 @@ export const MODELS = {
16265
16404
  contextWindow: 1048576,
16266
16405
  maxTokens: 131072,
16267
16406
  },
16268
- "z-ai/glm-5.2:free": {
16269
- id: "z-ai/glm-5.2:free",
16270
- name: "Z.ai: GLM 5.2 (free)",
16271
- api: "openai-completions",
16272
- provider: "openrouter",
16273
- baseUrl: "https://openrouter.ai/api/v1",
16274
- reasoning: true,
16275
- input: ["text"],
16276
- cost: {
16277
- input: 0,
16278
- output: 0,
16279
- cacheRead: 0,
16280
- cacheWrite: 0,
16281
- },
16282
- contextWindow: 256000,
16283
- maxTokens: 230400,
16284
- },
16285
16407
  "z-ai/glm-5.3": {
16286
16408
  id: "z-ai/glm-5.3",
16287
16409
  name: "Z.ai: GLM 5.3",
@@ -16297,7 +16419,7 @@ export const MODELS = {
16297
16419
  cacheWrite: 0,
16298
16420
  },
16299
16421
  contextWindow: 1310720,
16300
- maxTokens: 131072,
16422
+ maxTokens: 943718,
16301
16423
  },
16302
16424
  "z-ai/glm-5.3-flash": {
16303
16425
  id: "z-ai/glm-5.3-flash",
@@ -16480,9 +16602,9 @@ export const MODELS = {
16480
16602
  reasoning: true,
16481
16603
  input: ["text", "image"],
16482
16604
  cost: {
16483
- input: 2.5500000000000003,
16484
- output: 12.75,
16485
- cacheRead: 0.25599998999999996,
16605
+ input: 2.5,
16606
+ output: 14,
16607
+ cacheRead: 0.29,
16486
16608
  cacheWrite: 0,
16487
16609
  },
16488
16610
  contextWindow: 1048576,
@@ -16548,9 +16670,9 @@ export const MODELS = {
16548
16670
  reasoning: true,
16549
16671
  input: ["text", "image"],
16550
16672
  cost: {
16551
- input: 0.075,
16552
- output: 0.25,
16553
- cacheRead: 0.015,
16673
+ input: 0.07125000000000001,
16674
+ output: 0.2375,
16675
+ cacheRead: 0.01425,
16554
16676
  cacheWrite: 0,
16555
16677
  },
16556
16678
  contextWindow: 1310720,
@@ -16565,9 +16687,9 @@ export const MODELS = {
16565
16687
  reasoning: true,
16566
16688
  input: ["text"],
16567
16689
  cost: {
16568
- input: 1.17,
16569
- output: 3.9600000000000004,
16570
- cacheRead: 0.234,
16690
+ input: 1.12,
16691
+ output: 3.52,
16692
+ cacheRead: 0.20800000000000002,
16571
16693
  cacheWrite: 0,
16572
16694
  },
16573
16695
  contextWindow: 1310720,
@@ -18255,6 +18377,23 @@ export const MODELS = {
18255
18377
  contextWindow: 1000000,
18256
18378
  maxTokens: 65536,
18257
18379
  },
18380
+ "google/gemini-3.8-flash": {
18381
+ id: "google/gemini-3.8-flash",
18382
+ name: "Gemini 3.8 Flash",
18383
+ api: "anthropic-messages",
18384
+ provider: "vercel-ai-gateway",
18385
+ baseUrl: "https://ai-gateway.vercel.sh",
18386
+ reasoning: true,
18387
+ input: ["text", "image"],
18388
+ cost: {
18389
+ input: 0.75,
18390
+ output: 3.75,
18391
+ cacheRead: 0.075,
18392
+ cacheWrite: 0,
18393
+ },
18394
+ contextWindow: 1000000,
18395
+ maxTokens: 65536,
18396
+ },
18258
18397
  "google/gemma-4-26b-a4b-it": {
18259
18398
  id: "google/gemma-4-26b-a4b-it",
18260
18399
  name: "Google Gemma 4 26B A4B",
@@ -18374,6 +18513,40 @@ export const MODELS = {
18374
18513
  contextWindow: 256000,
18375
18514
  maxTokens: 32000,
18376
18515
  },
18516
+ "inclusionai/ling-3.0-flash-sante": {
18517
+ id: "inclusionai/ling-3.0-flash-sante",
18518
+ name: "Ling 3.0 Flash Sante",
18519
+ api: "anthropic-messages",
18520
+ provider: "vercel-ai-gateway",
18521
+ baseUrl: "https://ai-gateway.vercel.sh",
18522
+ reasoning: true,
18523
+ input: ["text"],
18524
+ cost: {
18525
+ input: 0,
18526
+ output: 0,
18527
+ cacheRead: 0,
18528
+ cacheWrite: 0,
18529
+ },
18530
+ contextWindow: 256000,
18531
+ maxTokens: 32000,
18532
+ },
18533
+ "inclusionai/ling-3.0-flash-sante-free": {
18534
+ id: "inclusionai/ling-3.0-flash-sante-free",
18535
+ name: "Ling 3.0 Flash Sante (Free)",
18536
+ api: "anthropic-messages",
18537
+ provider: "vercel-ai-gateway",
18538
+ baseUrl: "https://ai-gateway.vercel.sh",
18539
+ reasoning: true,
18540
+ input: ["text"],
18541
+ cost: {
18542
+ input: 0,
18543
+ output: 0,
18544
+ cacheRead: 0,
18545
+ cacheWrite: 0,
18546
+ },
18547
+ contextWindow: 256000,
18548
+ maxTokens: 32000,
18549
+ },
18377
18550
  "interfaze/interfaze-beta": {
18378
18551
  id: "interfaze/interfaze-beta",
18379
18552
  name: "Interfaze Beta",
@@ -18612,6 +18785,40 @@ export const MODELS = {
18612
18785
  contextWindow: 1048576,
18613
18786
  maxTokens: 1048576,
18614
18787
  },
18788
+ "meta/muse-spark-1.3": {
18789
+ id: "meta/muse-spark-1.3",
18790
+ name: "Muse Spark 1.3",
18791
+ api: "anthropic-messages",
18792
+ provider: "vercel-ai-gateway",
18793
+ baseUrl: "https://ai-gateway.vercel.sh",
18794
+ reasoning: true,
18795
+ input: ["text", "image"],
18796
+ cost: {
18797
+ input: 1.25,
18798
+ output: 4.25,
18799
+ cacheRead: 0.15,
18800
+ cacheWrite: 0,
18801
+ },
18802
+ contextWindow: 1048576,
18803
+ maxTokens: 1048576,
18804
+ },
18805
+ "meta/muse-spark-1.3-contributor": {
18806
+ id: "meta/muse-spark-1.3-contributor",
18807
+ name: "Muse Spark 1.3 Contributor",
18808
+ api: "anthropic-messages",
18809
+ provider: "vercel-ai-gateway",
18810
+ baseUrl: "https://ai-gateway.vercel.sh",
18811
+ reasoning: true,
18812
+ input: ["text", "image"],
18813
+ cost: {
18814
+ input: 0.09999999999999999,
18815
+ output: 0.19999999999999998,
18816
+ cacheRead: 0.002,
18817
+ cacheWrite: 0,
18818
+ },
18819
+ contextWindow: 1048576,
18820
+ maxTokens: 1048576,
18821
+ },
18615
18822
  "minimax/minimax-m2": {
18616
18823
  id: "minimax/minimax-m2",
18617
18824
  name: "MiniMax M2",
@@ -18714,23 +18921,6 @@ export const MODELS = {
18714
18921
  contextWindow: 204800,
18715
18922
  maxTokens: 131000,
18716
18923
  },
18717
- "minimax/minimax-m2.7-free": {
18718
- id: "minimax/minimax-m2.7-free",
18719
- name: "MiniMax M2.7 (Free)",
18720
- api: "anthropic-messages",
18721
- provider: "vercel-ai-gateway",
18722
- baseUrl: "https://ai-gateway.vercel.sh",
18723
- reasoning: true,
18724
- input: ["text"],
18725
- cost: {
18726
- input: 0,
18727
- output: 0,
18728
- cacheRead: 0,
18729
- cacheWrite: 0,
18730
- },
18731
- contextWindow: 196608,
18732
- maxTokens: 196608,
18733
- },
18734
18924
  "minimax/minimax-m2.7-highspeed": {
18735
18925
  id: "minimax/minimax-m2.7-highspeed",
18736
18926
  name: "MiniMax M2.7 High Speed",
@@ -18765,23 +18955,6 @@ export const MODELS = {
18765
18955
  contextWindow: 512000,
18766
18956
  maxTokens: 512000,
18767
18957
  },
18768
- "minimax/minimax-m3-free": {
18769
- id: "minimax/minimax-m3-free",
18770
- name: "MiniMax M3 (Free)",
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: 0,
18778
- output: 0,
18779
- cacheRead: 0,
18780
- cacheWrite: 0,
18781
- },
18782
- contextWindow: 1048576,
18783
- maxTokens: 1048576,
18784
- },
18785
18958
  "mistral/codestral": {
18786
18959
  id: "mistral/codestral",
18787
18960
  name: "Mistral Codestral",
@@ -19933,7 +20106,7 @@ export const MODELS = {
19933
20106
  input: 0.39999999999999997,
19934
20107
  output: 2.4,
19935
20108
  cacheRead: 0.04,
19936
- cacheWrite: 0.25,
20109
+ cacheWrite: 0.5,
19937
20110
  },
19938
20111
  contextWindow: 1050000,
19939
20112
  maxTokens: 128000,
@@ -19969,7 +20142,7 @@ export const MODELS = {
19969
20142
  input: 4,
19970
20143
  output: 20,
19971
20144
  cacheRead: 0.39999999999999997,
19972
- cacheWrite: 2.5,
20145
+ cacheWrite: 5,
19973
20146
  },
19974
20147
  contextWindow: 1050000,
19975
20148
  maxTokens: 128000,
@@ -20005,7 +20178,41 @@ export const MODELS = {
20005
20178
  input: 4,
20006
20179
  output: 24,
20007
20180
  cacheRead: 0.39999999999999997,
20008
- cacheWrite: 2.5,
20181
+ cacheWrite: 5,
20182
+ },
20183
+ contextWindow: 1050000,
20184
+ maxTokens: 128000,
20185
+ },
20186
+ "openai/gpt-6-astra": {
20187
+ id: "openai/gpt-6-astra",
20188
+ name: "GPT-6 Astra",
20189
+ api: "anthropic-messages",
20190
+ provider: "vercel-ai-gateway",
20191
+ baseUrl: "https://ai-gateway.vercel.sh",
20192
+ reasoning: true,
20193
+ input: ["text", "image"],
20194
+ cost: {
20195
+ input: 10,
20196
+ output: 50,
20197
+ cacheRead: 1,
20198
+ cacheWrite: 12.5,
20199
+ },
20200
+ contextWindow: 1050000,
20201
+ maxTokens: 128000,
20202
+ },
20203
+ "openai/gpt-6-astra-fast": {
20204
+ id: "openai/gpt-6-astra-fast",
20205
+ name: "GPT-6 Astra (Fast)",
20206
+ api: "anthropic-messages",
20207
+ provider: "vercel-ai-gateway",
20208
+ baseUrl: "https://ai-gateway.vercel.sh",
20209
+ reasoning: true,
20210
+ input: ["text", "image"],
20211
+ cost: {
20212
+ input: 20,
20213
+ output: 100,
20214
+ cacheRead: 2,
20215
+ cacheWrite: 25,
20009
20216
  },
20010
20217
  contextWindow: 1050000,
20011
20218
  maxTokens: 128000,
@@ -20835,14 +21042,31 @@ export const MODELS = {
20835
21042
  reasoning: true,
20836
21043
  input: ["text"],
20837
21044
  cost: {
20838
- input: 1.4,
20839
- output: 4.4,
20840
- cacheRead: 0.14,
21045
+ input: 0.7,
21046
+ output: 2.2,
21047
+ cacheRead: 0.13,
20841
21048
  cacheWrite: 0,
20842
21049
  },
20843
21050
  contextWindow: 1000000,
20844
21051
  maxTokens: 1000000,
20845
21052
  },
21053
+ "zai/glm-5.3-fast": {
21054
+ id: "zai/glm-5.3-fast",
21055
+ name: "GLM 5.3 Fast",
21056
+ api: "anthropic-messages",
21057
+ provider: "vercel-ai-gateway",
21058
+ baseUrl: "https://ai-gateway.vercel.sh",
21059
+ reasoning: true,
21060
+ input: ["text"],
21061
+ cost: {
21062
+ input: 2.0999999999999996,
21063
+ output: 6.6000000000000005,
21064
+ cacheRead: 0.21,
21065
+ cacheWrite: 0,
21066
+ },
21067
+ contextWindow: 1048576,
21068
+ maxTokens: 262144,
21069
+ },
20846
21070
  "zai/glm-5.3-flash": {
20847
21071
  id: "zai/glm-5.3-flash",
20848
21072
  name: "GLM 5.3 Flash",
@@ -20860,6 +21084,23 @@ export const MODELS = {
20860
21084
  contextWindow: 1000000,
20861
21085
  maxTokens: 131000,
20862
21086
  },
21087
+ "zai/glm-5.3-promo-50": {
21088
+ id: "zai/glm-5.3-promo-50",
21089
+ name: "GLM 5.3 (50% off)",
21090
+ api: "anthropic-messages",
21091
+ provider: "vercel-ai-gateway",
21092
+ baseUrl: "https://ai-gateway.vercel.sh",
21093
+ reasoning: true,
21094
+ input: ["text"],
21095
+ cost: {
21096
+ input: 0.7,
21097
+ output: 2.2,
21098
+ cacheRead: 0.13,
21099
+ cacheWrite: 0,
21100
+ },
21101
+ contextWindow: 1048576,
21102
+ maxTokens: 1048576,
21103
+ },
20863
21104
  "zai/glm-5v-turbo": {
20864
21105
  id: "zai/glm-5v-turbo",
20865
21106
  name: "GLM 5V Turbo",