@elyracode/ai 0.9.57 → 0.9.58

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.
@@ -4499,6 +4499,40 @@ export const MODELS = {
4499
4499
  contextWindow: 1050000,
4500
4500
  maxTokens: 128000,
4501
4501
  },
4502
+ "gpt-6.2-astra": {
4503
+ id: "gpt-6.2-astra",
4504
+ name: "GPT-6.2 Astra",
4505
+ api: "azure-openai-responses",
4506
+ provider: "azure-openai-responses",
4507
+ baseUrl: "",
4508
+ reasoning: true,
4509
+ input: ["text", "image"],
4510
+ cost: {
4511
+ input: 8,
4512
+ output: 40,
4513
+ cacheRead: 0.4,
4514
+ cacheWrite: 10,
4515
+ },
4516
+ contextWindow: 1050000,
4517
+ maxTokens: 128000,
4518
+ },
4519
+ "gpt-6.2-sol": {
4520
+ id: "gpt-6.2-sol",
4521
+ name: "GPT-6.2 Sol",
4522
+ api: "azure-openai-responses",
4523
+ provider: "azure-openai-responses",
4524
+ baseUrl: "",
4525
+ reasoning: true,
4526
+ input: ["text", "image"],
4527
+ cost: {
4528
+ input: 2,
4529
+ output: 10,
4530
+ cacheRead: 0.1,
4531
+ cacheWrite: 2.5,
4532
+ },
4533
+ contextWindow: 1050000,
4534
+ maxTokens: 128000,
4535
+ },
4502
4536
  "gpt-daybreak-blue-latest": {
4503
4537
  id: "gpt-daybreak-blue-latest",
4504
4538
  name: "Daybreak Blue",
@@ -4726,6 +4760,24 @@ export const MODELS = {
4726
4760
  contextWindow: 1000000,
4727
4761
  maxTokens: 128000,
4728
4762
  },
4763
+ "claude-fable-5.2": {
4764
+ id: "claude-fable-5.2",
4765
+ name: "Claude Fable 5.2",
4766
+ api: "anthropic-messages",
4767
+ provider: "cloudflare-ai-gateway",
4768
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4769
+ reasoning: true,
4770
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
4771
+ input: ["text", "image"],
4772
+ cost: {
4773
+ input: 8,
4774
+ output: 40,
4775
+ cacheRead: 0.2,
4776
+ cacheWrite: 10,
4777
+ },
4778
+ contextWindow: 1000000,
4779
+ maxTokens: 128000,
4780
+ },
4729
4781
  "claude-haiku-4.5": {
4730
4782
  id: "claude-haiku-4.5",
4731
4783
  name: "Claude Haiku 4.5 (latest)",
@@ -4980,7 +5032,7 @@ export const MODELS = {
4980
5032
  cost: {
4981
5033
  input: 0.1,
4982
5034
  output: 0.4,
4983
- cacheRead: 0.025,
5035
+ cacheRead: 0.03,
4984
5036
  cacheWrite: 0,
4985
5037
  },
4986
5038
  contextWindow: 1000000,
@@ -5665,6 +5717,24 @@ export const MODELS = {
5665
5717
  contextWindow: 262144,
5666
5718
  maxTokens: 262144,
5667
5719
  },
5720
+ "@cf/thinkingmachines/inkling-2-small": {
5721
+ id: "@cf/thinkingmachines/inkling-2-small",
5722
+ name: "Inkling 2 Small",
5723
+ api: "openai-completions",
5724
+ provider: "cloudflare-workers-ai",
5725
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
5726
+ compat: { "sendSessionAffinityHeaders": true },
5727
+ reasoning: true,
5728
+ input: ["text", "image"],
5729
+ cost: {
5730
+ input: 0.3,
5731
+ output: 1,
5732
+ cacheRead: 0.1,
5733
+ cacheWrite: 0,
5734
+ },
5735
+ contextWindow: 1048576,
5736
+ maxTokens: 1048576,
5737
+ },
5668
5738
  "@cf/zai-org/glm-4.7-flash": {
5669
5739
  id: "@cf/zai-org/glm-4.7-flash",
5670
5740
  name: "GLM-4.7-Flash",
@@ -5879,7 +5949,7 @@ export const MODELS = {
5879
5949
  cacheWrite: 0,
5880
5950
  },
5881
5951
  contextWindow: 1048576,
5882
- maxTokens: 131072,
5952
+ maxTokens: 1048576,
5883
5953
  },
5884
5954
  "accounts/fireworks/models/kimi-k3p1-pro": {
5885
5955
  id: "accounts/fireworks/models/kimi-k3p1-pro",
@@ -5896,7 +5966,7 @@ export const MODELS = {
5896
5966
  cacheWrite: 0,
5897
5967
  },
5898
5968
  contextWindow: 1048576,
5899
- maxTokens: 131072,
5969
+ maxTokens: 1048576,
5900
5970
  },
5901
5971
  "accounts/fireworks/models/minimax-m3": {
5902
5972
  id: "accounts/fireworks/models/minimax-m3",
@@ -6151,7 +6221,7 @@ export const MODELS = {
6151
6221
  cacheWrite: 0,
6152
6222
  },
6153
6223
  contextWindow: 1048576,
6154
- maxTokens: 131072,
6224
+ maxTokens: 1048576,
6155
6225
  },
6156
6226
  "accounts/fireworks/routers/kimi-k3-fast": {
6157
6227
  id: "accounts/fireworks/routers/kimi-k3-fast",
@@ -6168,7 +6238,7 @@ export const MODELS = {
6168
6238
  cacheWrite: 0,
6169
6239
  },
6170
6240
  contextWindow: 1048576,
6171
- maxTokens: 131072,
6241
+ maxTokens: 1048576,
6172
6242
  },
6173
6243
  "accounts/fireworks/routers/kimi-k3-spot": {
6174
6244
  id: "accounts/fireworks/routers/kimi-k3-spot",
@@ -6185,7 +6255,7 @@ export const MODELS = {
6185
6255
  cacheWrite: 0,
6186
6256
  },
6187
6257
  contextWindow: 1048576,
6188
- maxTokens: 131072,
6258
+ maxTokens: 1048576,
6189
6259
  },
6190
6260
  "accounts/fireworks/routers/kimi-latest": {
6191
6261
  id: "accounts/fireworks/routers/kimi-latest",
@@ -6196,13 +6266,13 @@ export const MODELS = {
6196
6266
  reasoning: true,
6197
6267
  input: ["text", "image"],
6198
6268
  cost: {
6199
- input: 3,
6200
- output: 15,
6201
- cacheRead: 0.3,
6269
+ input: 2,
6270
+ output: 10,
6271
+ cacheRead: 0.2,
6202
6272
  cacheWrite: 0,
6203
6273
  },
6204
6274
  contextWindow: 1048576,
6205
- maxTokens: 131072,
6275
+ maxTokens: 1048576,
6206
6276
  },
6207
6277
  "accounts/fireworks/routers/minimax-latest": {
6208
6278
  id: "accounts/fireworks/routers/minimax-latest",
@@ -6280,6 +6350,26 @@ export const MODELS = {
6280
6350
  contextWindow: 1000000,
6281
6351
  maxTokens: 128000,
6282
6352
  },
6353
+ "claude-fable-5.2": {
6354
+ id: "claude-fable-5.2",
6355
+ name: "Claude Fable 5.2",
6356
+ api: "openai-completions",
6357
+ provider: "github-copilot",
6358
+ baseUrl: "https://api.individual.githubcopilot.com",
6359
+ 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" },
6360
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6361
+ reasoning: true,
6362
+ thinkingLevelMap: { "off": null, "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
6363
+ input: ["text", "image"],
6364
+ cost: {
6365
+ input: 8,
6366
+ output: 40,
6367
+ cacheRead: 0.2,
6368
+ cacheWrite: 10,
6369
+ },
6370
+ contextWindow: 1000000,
6371
+ maxTokens: 128000,
6372
+ },
6283
6373
  "claude-haiku-4.5": {
6284
6374
  id: "claude-haiku-4.5",
6285
6375
  name: "Claude Haiku 4.5 (latest)",
@@ -6471,6 +6561,44 @@ export const MODELS = {
6471
6561
  contextWindow: 1048576,
6472
6562
  maxTokens: 65536,
6473
6563
  },
6564
+ "gemini-4-carbon": {
6565
+ id: "gemini-4-carbon",
6566
+ name: "Gemini 4 Carbon",
6567
+ api: "openai-completions",
6568
+ provider: "github-copilot",
6569
+ baseUrl: "https://api.individual.githubcopilot.com",
6570
+ 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" },
6571
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6572
+ reasoning: true,
6573
+ input: ["text", "image"],
6574
+ cost: {
6575
+ input: 2,
6576
+ output: 10,
6577
+ cacheRead: 0.1,
6578
+ cacheWrite: 0,
6579
+ },
6580
+ contextWindow: 1048576,
6581
+ maxTokens: 65536,
6582
+ },
6583
+ "gemini-4-hydrogen": {
6584
+ id: "gemini-4-hydrogen",
6585
+ name: "Gemini 4 Hydrogen",
6586
+ api: "openai-completions",
6587
+ provider: "github-copilot",
6588
+ baseUrl: "https://api.individual.githubcopilot.com",
6589
+ 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" },
6590
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6591
+ reasoning: true,
6592
+ input: ["text", "image"],
6593
+ cost: {
6594
+ input: 1.5,
6595
+ output: 7.5,
6596
+ cacheRead: 0.075,
6597
+ cacheWrite: 0,
6598
+ },
6599
+ contextWindow: 1048576,
6600
+ maxTokens: 65536,
6601
+ },
6474
6602
  "gpt-5.3-codex": {
6475
6603
  id: "gpt-5.3-codex",
6476
6604
  name: "GPT-5.3 Codex",
@@ -6735,7 +6863,7 @@ export const MODELS = {
6735
6863
  cacheWrite: 0,
6736
6864
  },
6737
6865
  contextWindow: 1048576,
6738
- maxTokens: 131072,
6866
+ maxTokens: 1048576,
6739
6867
  },
6740
6868
  "mai-code-1.1-flash": {
6741
6869
  id: "mai-code-1.1-flash",
@@ -6907,7 +7035,7 @@ export const MODELS = {
6907
7035
  input: ["text", "image"],
6908
7036
  cost: {
6909
7037
  input: 0.25,
6910
- output: 30,
7038
+ output: 1.5,
6911
7039
  cacheRead: 0,
6912
7040
  cacheWrite: 0,
6913
7041
  },
@@ -7094,6 +7222,42 @@ export const MODELS = {
7094
7222
  contextWindow: 1048576,
7095
7223
  maxTokens: 32768,
7096
7224
  },
7225
+ "gemini-4-carbon": {
7226
+ id: "gemini-4-carbon",
7227
+ name: "Gemini 4 Carbon",
7228
+ api: "google-generative-ai",
7229
+ provider: "google",
7230
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
7231
+ reasoning: true,
7232
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7233
+ input: ["text", "image"],
7234
+ cost: {
7235
+ input: 2,
7236
+ output: 10,
7237
+ cacheRead: 0.1,
7238
+ cacheWrite: 0,
7239
+ },
7240
+ contextWindow: 1048576,
7241
+ maxTokens: 32768,
7242
+ },
7243
+ "gemini-4-hydrogen": {
7244
+ id: "gemini-4-hydrogen",
7245
+ name: "Gemini 4 Hydrogen",
7246
+ api: "google-generative-ai",
7247
+ provider: "google",
7248
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
7249
+ reasoning: true,
7250
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7251
+ input: ["text", "image"],
7252
+ cost: {
7253
+ input: 1.5,
7254
+ output: 7.5,
7255
+ cacheRead: 0.075,
7256
+ cacheWrite: 0,
7257
+ },
7258
+ contextWindow: 1048576,
7259
+ maxTokens: 65536,
7260
+ },
7097
7261
  "gemini-flash-latest": {
7098
7262
  id: "gemini-flash-latest",
7099
7263
  name: "Gemini Flash Latest",
@@ -7404,7 +7568,7 @@ export const MODELS = {
7404
7568
  input: ["text", "image"],
7405
7569
  cost: {
7406
7570
  input: 0.25,
7407
- output: 30,
7571
+ output: 1.5,
7408
7572
  cacheRead: 0.025,
7409
7573
  cacheWrite: 0,
7410
7574
  },
@@ -7555,6 +7719,42 @@ export const MODELS = {
7555
7719
  contextWindow: 1048576,
7556
7720
  maxTokens: 65536,
7557
7721
  },
7722
+ "gemini-4-carbon": {
7723
+ id: "gemini-4-carbon",
7724
+ name: "Gemini 4 Carbon (Vertex)",
7725
+ api: "google-vertex",
7726
+ provider: "google-vertex",
7727
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7728
+ reasoning: true,
7729
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7730
+ input: ["text", "image"],
7731
+ cost: {
7732
+ input: 2,
7733
+ output: 10,
7734
+ cacheRead: 0.1,
7735
+ cacheWrite: 0,
7736
+ },
7737
+ contextWindow: 1048576,
7738
+ maxTokens: 65536,
7739
+ },
7740
+ "gemini-4-hydrogen": {
7741
+ id: "gemini-4-hydrogen",
7742
+ name: "Gemini 4 Hydrogen (Vertex)",
7743
+ api: "google-vertex",
7744
+ provider: "google-vertex",
7745
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
7746
+ reasoning: true,
7747
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7748
+ input: ["text", "image"],
7749
+ cost: {
7750
+ input: 1.5,
7751
+ output: 7.5,
7752
+ cacheRead: 0.075,
7753
+ cacheWrite: 0,
7754
+ },
7755
+ contextWindow: 1048576,
7756
+ maxTokens: 65536,
7757
+ },
7558
7758
  },
7559
7759
  "groq": {
7560
7760
  "llama-3.1-8b-instant": {
@@ -8738,7 +8938,25 @@ export const MODELS = {
8738
8938
  cacheWrite: 0,
8739
8939
  },
8740
8940
  contextWindow: 1000000,
8741
- maxTokens: 131072,
8941
+ maxTokens: 1000000,
8942
+ },
8943
+ "moonshotai/Kimi-K3.1-Pro": {
8944
+ id: "moonshotai/Kimi-K3.1-Pro",
8945
+ name: "Kimi K3.1 Pro",
8946
+ api: "openai-completions",
8947
+ provider: "huggingface",
8948
+ baseUrl: "https://router.huggingface.co/v1",
8949
+ compat: { "supportsDeveloperRole": false },
8950
+ reasoning: true,
8951
+ input: ["text", "image"],
8952
+ cost: {
8953
+ input: 2,
8954
+ output: 10,
8955
+ cacheRead: 0,
8956
+ cacheWrite: 0,
8957
+ },
8958
+ contextWindow: 1048576,
8959
+ maxTokens: 1048576,
8742
8960
  },
8743
8961
  "openai/gpt-oss-120b": {
8744
8962
  id: "openai/gpt-oss-120b",
@@ -8756,7 +8974,7 @@ export const MODELS = {
8756
8974
  cacheWrite: 0,
8757
8975
  },
8758
8976
  contextWindow: 131072,
8759
- maxTokens: 32768,
8977
+ maxTokens: 131072,
8760
8978
  },
8761
8979
  "openai/gpt-oss-20b": {
8762
8980
  id: "openai/gpt-oss-20b",
@@ -8774,7 +8992,7 @@ export const MODELS = {
8774
8992
  cacheWrite: 0,
8775
8993
  },
8776
8994
  contextWindow: 131072,
8777
- maxTokens: 32768,
8995
+ maxTokens: 131072,
8778
8996
  },
8779
8997
  "stepfun-ai/Step-3.5-Flash": {
8780
8998
  id: "stepfun-ai/Step-3.5-Flash",
@@ -8866,6 +9084,24 @@ export const MODELS = {
8866
9084
  contextWindow: 1048576,
8867
9085
  maxTokens: 1048576,
8868
9086
  },
9087
+ "thinkingmachines/Inkling-2-Small": {
9088
+ id: "thinkingmachines/Inkling-2-Small",
9089
+ name: "Inkling 2 Small",
9090
+ api: "openai-completions",
9091
+ provider: "huggingface",
9092
+ baseUrl: "https://router.huggingface.co/v1",
9093
+ compat: { "supportsDeveloperRole": false },
9094
+ reasoning: true,
9095
+ input: ["text", "image"],
9096
+ cost: {
9097
+ input: 0.3,
9098
+ output: 1,
9099
+ cacheRead: 0,
9100
+ cacheWrite: 0,
9101
+ },
9102
+ contextWindow: 1048576,
9103
+ maxTokens: 131072,
9104
+ },
8869
9105
  "thinkingmachines/Inkling-Small": {
8870
9106
  id: "thinkingmachines/Inkling-Small",
8871
9107
  name: "Inkling Small",
@@ -8882,7 +9118,25 @@ export const MODELS = {
8882
9118
  cacheWrite: 0,
8883
9119
  },
8884
9120
  contextWindow: 524288,
8885
- maxTokens: 1048576,
9121
+ maxTokens: 524288,
9122
+ },
9123
+ "zai-org/GLM-4.5": {
9124
+ id: "zai-org/GLM-4.5",
9125
+ name: "GLM-4.5",
9126
+ api: "openai-completions",
9127
+ provider: "huggingface",
9128
+ baseUrl: "https://router.huggingface.co/v1",
9129
+ compat: { "supportsDeveloperRole": false },
9130
+ reasoning: true,
9131
+ input: ["text"],
9132
+ cost: {
9133
+ input: 0.6,
9134
+ output: 2.2,
9135
+ cacheRead: 0,
9136
+ cacheWrite: 0,
9137
+ },
9138
+ contextWindow: 131072,
9139
+ maxTokens: 98304,
8886
9140
  },
8887
9141
  "zai-org/GLM-4.5-Air": {
8888
9142
  id: "zai-org/GLM-4.5-Air",
@@ -8938,9 +9192,9 @@ export const MODELS = {
8938
9192
  contextWindow: 204800,
8939
9193
  maxTokens: 131072,
8940
9194
  },
8941
- "zai-org/GLM-4.6V-Flash": {
8942
- id: "zai-org/GLM-4.6V-Flash",
8943
- name: "GLM-4.6V-Flash",
9195
+ "zai-org/GLM-4.6V": {
9196
+ id: "zai-org/GLM-4.6V",
9197
+ name: "GLM-4.6V",
8944
9198
  api: "openai-completions",
8945
9199
  provider: "huggingface",
8946
9200
  baseUrl: "https://router.huggingface.co/v1",
@@ -8956,8 +9210,26 @@ export const MODELS = {
8956
9210
  contextWindow: 131072,
8957
9211
  maxTokens: 32768,
8958
9212
  },
8959
- "zai-org/GLM-4.7": {
8960
- id: "zai-org/GLM-4.7",
9213
+ "zai-org/GLM-4.6V-Flash": {
9214
+ id: "zai-org/GLM-4.6V-Flash",
9215
+ name: "GLM-4.6V-Flash",
9216
+ api: "openai-completions",
9217
+ provider: "huggingface",
9218
+ baseUrl: "https://router.huggingface.co/v1",
9219
+ compat: { "supportsDeveloperRole": false },
9220
+ reasoning: true,
9221
+ input: ["text", "image"],
9222
+ cost: {
9223
+ input: 0.3,
9224
+ output: 0.9,
9225
+ cacheRead: 0,
9226
+ cacheWrite: 0,
9227
+ },
9228
+ contextWindow: 131072,
9229
+ maxTokens: 32768,
9230
+ },
9231
+ "zai-org/GLM-4.7": {
9232
+ id: "zai-org/GLM-4.7",
8961
9233
  name: "GLM-4.7",
8962
9234
  api: "openai-completions",
8963
9235
  provider: "huggingface",
@@ -9100,7 +9372,7 @@ export const MODELS = {
9100
9372
  cacheWrite: 0,
9101
9373
  },
9102
9374
  contextWindow: 1048576,
9103
- maxTokens: 131072,
9375
+ maxTokens: 1048576,
9104
9376
  },
9105
9377
  "k3-256k": {
9106
9378
  id: "k3-256k",
@@ -9118,7 +9390,7 @@ export const MODELS = {
9118
9390
  cacheWrite: 0,
9119
9391
  },
9120
9392
  contextWindow: 262144,
9121
- maxTokens: 131072,
9393
+ maxTokens: 262144,
9122
9394
  },
9123
9395
  "k3.1-pro": {
9124
9396
  id: "k3.1-pro",
@@ -9136,7 +9408,7 @@ export const MODELS = {
9136
9408
  cacheWrite: 0,
9137
9409
  },
9138
9410
  contextWindow: 1048576,
9139
- maxTokens: 131072,
9411
+ maxTokens: 1048576,
9140
9412
  },
9141
9413
  "k3.1-pro-highspeed": {
9142
9414
  id: "k3.1-pro-highspeed",
@@ -9154,7 +9426,7 @@ export const MODELS = {
9154
9426
  cacheWrite: 0,
9155
9427
  },
9156
9428
  contextWindow: 1048576,
9157
- maxTokens: 131072,
9429
+ maxTokens: 1048576,
9158
9430
  },
9159
9431
  "kimi-for-coding": {
9160
9432
  id: "kimi-for-coding",
@@ -9341,7 +9613,7 @@ export const MODELS = {
9341
9613
  provider: "mistral",
9342
9614
  baseUrl: "https://api.mistral.ai",
9343
9615
  reasoning: true,
9344
- input: ["text"],
9616
+ input: ["text", "image"],
9345
9617
  cost: {
9346
9618
  input: 0.3,
9347
9619
  output: 1.2,
@@ -9502,7 +9774,7 @@ export const MODELS = {
9502
9774
  cacheWrite: 0,
9503
9775
  },
9504
9776
  contextWindow: 131072,
9505
- maxTokens: 262144,
9777
+ maxTokens: 131072,
9506
9778
  },
9507
9779
  "ministral-3b-latest": {
9508
9780
  id: "ministral-3b-latest",
@@ -9612,15 +9884,15 @@ export const MODELS = {
9612
9884
  api: "mistral-conversations",
9613
9885
  provider: "mistral",
9614
9886
  baseUrl: "https://api.mistral.ai",
9615
- reasoning: false,
9887
+ reasoning: true,
9616
9888
  input: ["text", "image"],
9617
9889
  cost: {
9618
- input: 0.5,
9619
- output: 1.5,
9620
- cacheRead: 0.05,
9890
+ input: 0.7,
9891
+ output: 2.1,
9892
+ cacheRead: 0.07,
9621
9893
  cacheWrite: 0,
9622
9894
  },
9623
- contextWindow: 262144,
9895
+ contextWindow: 1048576,
9624
9896
  maxTokens: 262144,
9625
9897
  },
9626
9898
  "mistral-medium-2505": {
@@ -10683,6 +10955,40 @@ export const MODELS = {
10683
10955
  contextWindow: 1050000,
10684
10956
  maxTokens: 128000,
10685
10957
  },
10958
+ "gpt-6.2-astra": {
10959
+ id: "gpt-6.2-astra",
10960
+ name: "GPT-6.2 Astra",
10961
+ api: "openai-responses",
10962
+ provider: "openai",
10963
+ baseUrl: "https://api.openai.com/v1",
10964
+ reasoning: true,
10965
+ input: ["text", "image"],
10966
+ cost: {
10967
+ input: 8,
10968
+ output: 40,
10969
+ cacheRead: 0.4,
10970
+ cacheWrite: 10,
10971
+ },
10972
+ contextWindow: 1050000,
10973
+ maxTokens: 128000,
10974
+ },
10975
+ "gpt-6.2-sol": {
10976
+ id: "gpt-6.2-sol",
10977
+ name: "GPT-6.2 Sol",
10978
+ api: "openai-responses",
10979
+ provider: "openai",
10980
+ baseUrl: "https://api.openai.com/v1",
10981
+ reasoning: true,
10982
+ input: ["text", "image"],
10983
+ cost: {
10984
+ input: 2,
10985
+ output: 10,
10986
+ cacheRead: 0.1,
10987
+ cacheWrite: 2.5,
10988
+ },
10989
+ contextWindow: 1050000,
10990
+ maxTokens: 128000,
10991
+ },
10686
10992
  "gpt-daybreak-blue-latest": {
10687
10993
  id: "gpt-daybreak-blue-latest",
10688
10994
  name: "Daybreak Blue",
@@ -11336,7 +11642,7 @@ export const MODELS = {
11336
11642
  },
11337
11643
  "deepseek-v4.1-flash": {
11338
11644
  id: "deepseek-v4.1-flash",
11339
- name: "DeepSeek V4.1 Flash",
11645
+ name: "DeepSeek V4.1 Flash 1017",
11340
11646
  api: "openai-completions",
11341
11647
  provider: "opencode",
11342
11648
  baseUrl: "https://opencode.ai/zen/v1",
@@ -11532,6 +11838,40 @@ export const MODELS = {
11532
11838
  contextWindow: 1048576,
11533
11839
  maxTokens: 65536,
11534
11840
  },
11841
+ "gemini-4-carbon": {
11842
+ id: "gemini-4-carbon",
11843
+ name: "Gemini 4 Carbon",
11844
+ api: "google-generative-ai",
11845
+ provider: "opencode",
11846
+ baseUrl: "https://opencode.ai/zen/v1",
11847
+ reasoning: true,
11848
+ input: ["text", "image"],
11849
+ cost: {
11850
+ input: 2,
11851
+ output: 10,
11852
+ cacheRead: 0.1,
11853
+ cacheWrite: 0,
11854
+ },
11855
+ contextWindow: 1048576,
11856
+ maxTokens: 65536,
11857
+ },
11858
+ "gemini-4-hydrogen": {
11859
+ id: "gemini-4-hydrogen",
11860
+ name: "Gemini 4 Hydrogen",
11861
+ api: "google-generative-ai",
11862
+ provider: "opencode",
11863
+ baseUrl: "https://opencode.ai/zen/v1",
11864
+ reasoning: true,
11865
+ input: ["text", "image"],
11866
+ cost: {
11867
+ input: 1.5,
11868
+ output: 7.5,
11869
+ cacheRead: 0.075,
11870
+ cacheWrite: 0,
11871
+ },
11872
+ contextWindow: 1048576,
11873
+ maxTokens: 65536,
11874
+ },
11535
11875
  "glm-5": {
11536
11876
  id: "glm-5",
11537
11877
  name: "GLM-5",
@@ -11617,23 +11957,6 @@ export const MODELS = {
11617
11957
  contextWindow: 1000000,
11618
11958
  maxTokens: 131072,
11619
11959
  },
11620
- "glm-5.3-flash-free": {
11621
- id: "glm-5.3-flash-free",
11622
- name: "GLM-5.3-Flash Free",
11623
- api: "openai-completions",
11624
- provider: "opencode",
11625
- baseUrl: "https://opencode.ai/zen/v1",
11626
- reasoning: true,
11627
- input: ["text", "image"],
11628
- cost: {
11629
- input: 0,
11630
- output: 0,
11631
- cacheRead: 0,
11632
- cacheWrite: 0,
11633
- },
11634
- contextWindow: 200000,
11635
- maxTokens: 32000,
11636
- },
11637
11960
  "gpt-5": {
11638
11961
  id: "gpt-5",
11639
11962
  name: "GPT-5",
@@ -12044,6 +12367,40 @@ export const MODELS = {
12044
12367
  contextWindow: 1050000,
12045
12368
  maxTokens: 128000,
12046
12369
  },
12370
+ "gpt-6.2-astra": {
12371
+ id: "gpt-6.2-astra",
12372
+ name: "GPT-6.2 Astra",
12373
+ api: "openai-responses",
12374
+ provider: "opencode",
12375
+ baseUrl: "https://opencode.ai/zen/v1",
12376
+ reasoning: true,
12377
+ input: ["text", "image"],
12378
+ cost: {
12379
+ input: 8,
12380
+ output: 40,
12381
+ cacheRead: 0.4,
12382
+ cacheWrite: 10,
12383
+ },
12384
+ contextWindow: 1050000,
12385
+ maxTokens: 128000,
12386
+ },
12387
+ "gpt-6.2-sol": {
12388
+ id: "gpt-6.2-sol",
12389
+ name: "GPT-6.2 Sol",
12390
+ api: "openai-responses",
12391
+ provider: "opencode",
12392
+ baseUrl: "https://opencode.ai/zen/v1",
12393
+ reasoning: true,
12394
+ input: ["text", "image"],
12395
+ cost: {
12396
+ input: 2,
12397
+ output: 10,
12398
+ cacheRead: 0.1,
12399
+ cacheWrite: 2.5,
12400
+ },
12401
+ contextWindow: 1050000,
12402
+ maxTokens: 128000,
12403
+ },
12047
12404
  "grok-4.5": {
12048
12405
  id: "grok-4.5",
12049
12406
  name: "Grok 4.5",
@@ -12112,6 +12469,23 @@ export const MODELS = {
12112
12469
  contextWindow: 256000,
12113
12470
  maxTokens: 256000,
12114
12471
  },
12472
+ "hy4-flash-free": {
12473
+ id: "hy4-flash-free",
12474
+ name: "Hy4 flash Free",
12475
+ api: "openai-completions",
12476
+ provider: "opencode",
12477
+ baseUrl: "https://opencode.ai/zen/v1",
12478
+ reasoning: true,
12479
+ input: ["text", "image"],
12480
+ cost: {
12481
+ input: 0,
12482
+ output: 0,
12483
+ cacheRead: 0,
12484
+ cacheWrite: 0,
12485
+ },
12486
+ contextWindow: 1048576,
12487
+ maxTokens: 65536,
12488
+ },
12115
12489
  "iceman-free": {
12116
12490
  id: "iceman-free",
12117
12491
  name: "Iceman Free",
@@ -12212,7 +12586,7 @@ export const MODELS = {
12212
12586
  cacheWrite: 3,
12213
12587
  },
12214
12588
  contextWindow: 1048576,
12215
- maxTokens: 131072,
12589
+ maxTokens: 1048576,
12216
12590
  },
12217
12591
  "longcat-2.5-free": {
12218
12592
  id: "longcat-2.5-free",
@@ -12299,23 +12673,6 @@ export const MODELS = {
12299
12673
  contextWindow: 512000,
12300
12674
  maxTokens: 128000,
12301
12675
  },
12302
- "minimax-m3.1-flash-free": {
12303
- id: "minimax-m3.1-flash-free",
12304
- name: "MiniMax M3.1 Flash Free",
12305
- api: "openai-completions",
12306
- provider: "opencode",
12307
- baseUrl: "https://opencode.ai/zen/v1",
12308
- reasoning: true,
12309
- input: ["text", "image"],
12310
- cost: {
12311
- input: 0,
12312
- output: 0,
12313
- cacheRead: 0,
12314
- cacheWrite: 0,
12315
- },
12316
- contextWindow: 1000000,
12317
- maxTokens: 512000,
12318
- },
12319
12676
  "mistral-large-4": {
12320
12677
  id: "mistral-large-4",
12321
12678
  name: "Mistral Large 4",
@@ -12560,7 +12917,7 @@ export const MODELS = {
12560
12917
  },
12561
12918
  "deepseek-v4.1-flash": {
12562
12919
  id: "deepseek-v4.1-flash",
12563
- name: "DeepSeek V4.1 Flash",
12920
+ name: "DeepSeek V4.1 Flash 1017",
12564
12921
  api: "openai-completions",
12565
12922
  provider: "opencode-go",
12566
12923
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12731,6 +13088,23 @@ export const MODELS = {
12731
13088
  contextWindow: 1048576,
12732
13089
  maxTokens: 65536,
12733
13090
  },
13091
+ "hy4-flash-free": {
13092
+ id: "hy4-flash-free",
13093
+ name: "Hy4 flash Free",
13094
+ api: "openai-completions",
13095
+ provider: "opencode-go",
13096
+ baseUrl: "https://opencode.ai/zen/go/v1",
13097
+ reasoning: true,
13098
+ input: ["text", "image"],
13099
+ cost: {
13100
+ input: 0,
13101
+ output: 0,
13102
+ cacheRead: 0,
13103
+ cacheWrite: 0,
13104
+ },
13105
+ contextWindow: 1048576,
13106
+ maxTokens: 65536,
13107
+ },
12734
13108
  "hy4-preview": {
12735
13109
  id: "hy4-preview",
12736
13110
  name: "Hy4 preview",
@@ -12797,7 +13171,7 @@ export const MODELS = {
12797
13171
  cacheWrite: 3,
12798
13172
  },
12799
13173
  contextWindow: 1048576,
12800
- maxTokens: 131072,
13174
+ maxTokens: 1048576,
12801
13175
  },
12802
13176
  "kimi-k3.1-pro": {
12803
13177
  id: "kimi-k3.1-pro",
@@ -12814,7 +13188,7 @@ export const MODELS = {
12814
13188
  cacheWrite: 2,
12815
13189
  },
12816
13190
  contextWindow: 1048576,
12817
- maxTokens: 131072,
13191
+ maxTokens: 1048576,
12818
13192
  },
12819
13193
  "longcat-2.0": {
12820
13194
  id: "longcat-2.0",
@@ -13037,6 +13411,23 @@ export const MODELS = {
13037
13411
  contextWindow: 1000000,
13038
13412
  maxTokens: 131072,
13039
13413
  },
13414
+ "qwen4-max": {
13415
+ id: "qwen4-max",
13416
+ name: "Qwen4 Max",
13417
+ api: "anthropic-messages",
13418
+ provider: "opencode-go",
13419
+ baseUrl: "https://opencode.ai/zen/go",
13420
+ reasoning: true,
13421
+ input: ["text", "image"],
13422
+ cost: {
13423
+ input: 1.5,
13424
+ output: 4.5,
13425
+ cacheRead: 0.075,
13426
+ cacheWrite: 1.875,
13427
+ },
13428
+ contextWindow: 1000000,
13429
+ maxTokens: 262144,
13430
+ },
13040
13431
  "step-5-preview": {
13041
13432
  id: "step-5-preview",
13042
13433
  name: "Step 5 Preview",
@@ -13803,39 +14194,39 @@ export const MODELS = {
13803
14194
  contextWindow: 2000000,
13804
14195
  maxTokens: 30000,
13805
14196
  },
13806
- "bytedance-seed/seed-1.6": {
13807
- id: "bytedance-seed/seed-1.6",
13808
- name: "ByteDance Seed: Seed 1.6",
14197
+ "baidu/ernie-5.5-flash-preview:free": {
14198
+ id: "baidu/ernie-5.5-flash-preview:free",
14199
+ name: "Baidu: ERNIE-5.5-Flash-Preview (free)",
13809
14200
  api: "openai-completions",
13810
14201
  provider: "openrouter",
13811
14202
  baseUrl: "https://openrouter.ai/api/v1",
13812
14203
  reasoning: true,
13813
- input: ["text", "image"],
14204
+ input: ["text"],
13814
14205
  cost: {
13815
- input: 0.25,
13816
- output: 2,
14206
+ input: 0,
14207
+ output: 0,
13817
14208
  cacheRead: 0,
13818
14209
  cacheWrite: 0,
13819
14210
  },
13820
- contextWindow: 262144,
13821
- maxTokens: 32768,
14211
+ contextWindow: 1024000,
14212
+ maxTokens: 921600,
13822
14213
  },
13823
- "bytedance-seed/seed-1.6-flash": {
13824
- id: "bytedance-seed/seed-1.6-flash",
13825
- name: "ByteDance Seed: Seed 1.6 Flash",
14214
+ "baidu/ernie-light-dt-1.0-intl": {
14215
+ id: "baidu/ernie-light-dt-1.0-intl",
14216
+ name: "Baidu: ERNIE-Light-DT-1.0",
13826
14217
  api: "openai-completions",
13827
14218
  provider: "openrouter",
13828
14219
  baseUrl: "https://openrouter.ai/api/v1",
13829
14220
  reasoning: true,
13830
- input: ["text", "image"],
14221
+ input: ["text"],
13831
14222
  cost: {
13832
- input: 0.075,
13833
- output: 0.3,
13834
- cacheRead: 0,
14223
+ input: 1.13,
14224
+ output: 3.9400000000000004,
14225
+ cacheRead: 0.113,
13835
14226
  cacheWrite: 0,
13836
14227
  },
13837
- contextWindow: 262144,
13838
- maxTokens: 32768,
14228
+ contextWindow: 1024000,
14229
+ maxTokens: 131072,
13839
14230
  },
13840
14231
  "bytedance-seed/seed-2-1-turbo": {
13841
14232
  id: "bytedance-seed/seed-2-1-turbo",
@@ -13854,23 +14245,6 @@ export const MODELS = {
13854
14245
  contextWindow: 262144,
13855
14246
  maxTokens: 235929,
13856
14247
  },
13857
- "bytedance-seed/seed-2.0-code": {
13858
- id: "bytedance-seed/seed-2.0-code",
13859
- name: "ByteDance Seed: Seed-2.0-Code",
13860
- api: "openai-completions",
13861
- provider: "openrouter",
13862
- baseUrl: "https://openrouter.ai/api/v1",
13863
- reasoning: true,
13864
- input: ["text", "image"],
13865
- cost: {
13866
- input: 0.5,
13867
- output: 3,
13868
- cacheRead: 0,
13869
- cacheWrite: 0,
13870
- },
13871
- contextWindow: 262144,
13872
- maxTokens: 131072,
13873
- },
13874
14248
  "bytedance-seed/seed-2.0-lite": {
13875
14249
  id: "bytedance-seed/seed-2.0-lite",
13876
14250
  name: "ByteDance Seed: Seed-2.0-Lite",
@@ -14016,13 +14390,13 @@ export const MODELS = {
14016
14390
  reasoning: false,
14017
14391
  input: ["text"],
14018
14392
  cost: {
14019
- input: 0.32,
14020
- output: 0.8899999999999999,
14393
+ input: 0.2574,
14394
+ output: 1.0287,
14021
14395
  cacheRead: 0,
14022
14396
  cacheWrite: 0,
14023
14397
  },
14024
14398
  contextWindow: 163840,
14025
- maxTokens: 16384,
14399
+ maxTokens: 16000,
14026
14400
  },
14027
14401
  "deepseek/deepseek-chat-v3-0324": {
14028
14402
  id: "deepseek/deepseek-chat-v3-0324",
@@ -14137,13 +14511,13 @@ export const MODELS = {
14137
14511
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14138
14512
  input: ["text"],
14139
14513
  cost: {
14140
- input: 0.091,
14141
- output: 0.182,
14142
- cacheRead: 0.0182,
14514
+ input: 0.09,
14515
+ output: 0.18,
14516
+ cacheRead: 0.018,
14143
14517
  cacheWrite: 0,
14144
14518
  },
14145
14519
  contextWindow: 1048576,
14146
- maxTokens: 943717,
14520
+ maxTokens: 393216,
14147
14521
  },
14148
14522
  "deepseek/deepseek-v4-flash-0731": {
14149
14523
  id: "deepseek/deepseek-v4-flash-0731",
@@ -14156,13 +14530,13 @@ export const MODELS = {
14156
14530
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14157
14531
  input: ["text"],
14158
14532
  cost: {
14159
- input: 0.0434,
14160
- output: 0.3,
14161
- cacheRead: 0.035,
14533
+ input: 0.06,
14534
+ output: 0.18,
14535
+ cacheRead: 0.015,
14162
14536
  cacheWrite: 0,
14163
14537
  },
14164
14538
  contextWindow: 1048576,
14165
- maxTokens: 943718,
14539
+ maxTokens: 384000,
14166
14540
  },
14167
14541
  "deepseek/deepseek-v4-flash-0731:batch": {
14168
14542
  id: "deepseek/deepseek-v4-flash-0731:batch",
@@ -14213,13 +14587,13 @@ export const MODELS = {
14213
14587
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14214
14588
  input: ["text"],
14215
14589
  cost: {
14216
- input: 0.9552599999999999,
14217
- output: 1.9105199999999998,
14218
- cacheRead: 0.07960500000000001,
14590
+ input: 0.8999999999999999,
14591
+ output: 1.5,
14592
+ cacheRead: 0.25,
14219
14593
  cacheWrite: 0,
14220
14594
  },
14221
14595
  contextWindow: 1048576,
14222
- maxTokens: 384000,
14596
+ maxTokens: 393216,
14223
14597
  },
14224
14598
  "deepseek/deepseek-v4-pro-0813": {
14225
14599
  id: "deepseek/deepseek-v4-pro-0813",
@@ -14251,9 +14625,9 @@ export const MODELS = {
14251
14625
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14252
14626
  input: ["text", "image"],
14253
14627
  cost: {
14254
- input: 0.006,
14255
- output: 0.5,
14256
- cacheRead: 0.005,
14628
+ input: 0.051,
14629
+ output: 0.5670000000000001,
14630
+ cacheRead: 0.018,
14257
14631
  cacheWrite: 0,
14258
14632
  },
14259
14633
  contextWindow: 1048576,
@@ -14270,9 +14644,9 @@ export const MODELS = {
14270
14644
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14271
14645
  input: ["text", "image"],
14272
14646
  cost: {
14273
- input: 0.006,
14647
+ input: 0.036,
14274
14648
  output: 0.5,
14275
- cacheRead: 0.005,
14649
+ cacheRead: 0.01,
14276
14650
  cacheWrite: 0,
14277
14651
  },
14278
14652
  contextWindow: 1048576,
@@ -14289,9 +14663,9 @@ export const MODELS = {
14289
14663
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14290
14664
  input: ["text", "image"],
14291
14665
  cost: {
14292
- input: 0.011,
14293
- output: 0.19999999999999998,
14294
- cacheRead: 0.002,
14666
+ input: 0.036,
14667
+ output: 0.15,
14668
+ cacheRead: 0.003,
14295
14669
  cacheWrite: 0,
14296
14670
  },
14297
14671
  contextWindow: 1048576,
@@ -14792,6 +15166,74 @@ export const MODELS = {
14792
15166
  contextWindow: 1048576,
14793
15167
  maxTokens: 943718,
14794
15168
  },
15169
+ "google/gemini-4-carbon": {
15170
+ id: "google/gemini-4-carbon",
15171
+ name: "Google: Gemini 4 Carbon",
15172
+ api: "openai-completions",
15173
+ provider: "openrouter",
15174
+ baseUrl: "https://openrouter.ai/api/v1",
15175
+ reasoning: true,
15176
+ input: ["text", "image"],
15177
+ cost: {
15178
+ input: 2,
15179
+ output: 10,
15180
+ cacheRead: 0.09999999999999999,
15181
+ cacheWrite: 0.1875,
15182
+ },
15183
+ contextWindow: 1048576,
15184
+ maxTokens: 943718,
15185
+ },
15186
+ "google/gemini-4-carbon:batch": {
15187
+ id: "google/gemini-4-carbon:batch",
15188
+ name: "Google: Gemini 4 Carbon (batch)",
15189
+ api: "openai-completions",
15190
+ provider: "openrouter",
15191
+ baseUrl: "https://openrouter.ai/api/v1",
15192
+ reasoning: true,
15193
+ input: ["text", "image"],
15194
+ cost: {
15195
+ input: 1,
15196
+ output: 5,
15197
+ cacheRead: 0.049999999999999996,
15198
+ cacheWrite: 0.1875,
15199
+ },
15200
+ contextWindow: 1048576,
15201
+ maxTokens: 943718,
15202
+ },
15203
+ "google/gemini-4-hydrogen": {
15204
+ id: "google/gemini-4-hydrogen",
15205
+ name: "Google: Gemini 4 Hydrogen",
15206
+ api: "openai-completions",
15207
+ provider: "openrouter",
15208
+ baseUrl: "https://openrouter.ai/api/v1",
15209
+ reasoning: true,
15210
+ input: ["text", "image"],
15211
+ cost: {
15212
+ input: 1.5,
15213
+ output: 7.5,
15214
+ cacheRead: 0.075,
15215
+ cacheWrite: 0.0833333333333333,
15216
+ },
15217
+ contextWindow: 1048576,
15218
+ maxTokens: 943718,
15219
+ },
15220
+ "google/gemini-4-hydrogen:batch": {
15221
+ id: "google/gemini-4-hydrogen:batch",
15222
+ name: "Google: Gemini 4 Hydrogen (batch)",
15223
+ api: "openai-completions",
15224
+ provider: "openrouter",
15225
+ baseUrl: "https://openrouter.ai/api/v1",
15226
+ reasoning: true,
15227
+ input: ["text", "image"],
15228
+ cost: {
15229
+ input: 0.75,
15230
+ output: 3.75,
15231
+ cacheRead: 0.0375,
15232
+ cacheWrite: 0.0833333333333333,
15233
+ },
15234
+ contextWindow: 1048576,
15235
+ maxTokens: 943718,
15236
+ },
14795
15237
  "google/gemini-nano-banana-2.1": {
14796
15238
  id: "google/gemini-nano-banana-2.1",
14797
15239
  name: "Google: Nano Banana 2.1",
@@ -14852,13 +15294,13 @@ export const MODELS = {
14852
15294
  reasoning: true,
14853
15295
  input: ["text", "image"],
14854
15296
  cost: {
14855
- input: 0.08,
14856
- output: 0.09999999999999999,
14857
- cacheRead: 0.046,
15297
+ input: 0.09,
15298
+ output: 0.3,
15299
+ cacheRead: 0.049999999999999996,
14858
15300
  cacheWrite: 0,
14859
15301
  },
14860
15302
  contextWindow: 262144,
14861
- maxTokens: 128000,
15303
+ maxTokens: 235929,
14862
15304
  },
14863
15305
  "google/gemma-4-26b-a4b-it:free": {
14864
15306
  id: "google/gemma-4-26b-a4b-it:free",
@@ -14921,7 +15363,7 @@ export const MODELS = {
14921
15363
  input: ["text"],
14922
15364
  cost: {
14923
15365
  input: 0.06,
14924
- output: 0.25,
15366
+ output: 0.15,
14925
15367
  cacheRead: 0.015,
14926
15368
  cacheWrite: 0,
14927
15369
  },
@@ -14996,39 +15438,39 @@ export const MODELS = {
14996
15438
  contextWindow: 1000000,
14997
15439
  maxTokens: 262144,
14998
15440
  },
14999
- "liquid/lfm-2.5-2.6b": {
15000
- id: "liquid/lfm-2.5-2.6b",
15001
- name: "LiquidAI: LFM2.5-2.6B",
15441
+ "inclusionai/ling-3.2-flash:free": {
15442
+ id: "inclusionai/ling-3.2-flash:free",
15443
+ name: "inclusionAI: Ling 3.2 Flash (free)",
15002
15444
  api: "openai-completions",
15003
15445
  provider: "openrouter",
15004
15446
  baseUrl: "https://openrouter.ai/api/v1",
15005
15447
  reasoning: true,
15006
- input: ["text"],
15448
+ input: ["text", "image"],
15007
15449
  cost: {
15008
- input: 0.35,
15009
- output: 0.5,
15010
- cacheRead: 0.04,
15450
+ input: 0,
15451
+ output: 0,
15452
+ cacheRead: 0,
15011
15453
  cacheWrite: 0,
15012
15454
  },
15013
- contextWindow: 128000,
15014
- maxTokens: 8192,
15455
+ contextWindow: 1048576,
15456
+ maxTokens: 262144,
15015
15457
  },
15016
- "liquid/lfm-2.5-2.6b:free": {
15017
- id: "liquid/lfm-2.5-2.6b:free",
15018
- name: "LiquidAI: LFM2.5-2.6B (free)",
15458
+ "kt/midm-k-3.0-pro": {
15459
+ id: "kt/midm-k-3.0-pro",
15460
+ name: "KT: Mi:dm K 3.0 Pro",
15019
15461
  api: "openai-completions",
15020
15462
  provider: "openrouter",
15021
15463
  baseUrl: "https://openrouter.ai/api/v1",
15022
15464
  reasoning: true,
15023
15465
  input: ["text"],
15024
15466
  cost: {
15025
- input: 0,
15026
- output: 0,
15027
- cacheRead: 0,
15467
+ input: 0.19999999999999998,
15468
+ output: 0.7999999999999999,
15469
+ cacheRead: 0.04,
15028
15470
  cacheWrite: 0,
15029
15471
  },
15030
- contextWindow: 65536,
15031
- maxTokens: 8192,
15472
+ contextWindow: 261795,
15473
+ maxTokens: 235615,
15032
15474
  },
15033
15475
  "liquid/lfm-2.5-24b-a2b": {
15034
15476
  id: "liquid/lfm-2.5-24b-a2b",
@@ -15098,6 +15540,23 @@ export const MODELS = {
15098
15540
  contextWindow: 1048756,
15099
15541
  maxTokens: 262144,
15100
15542
  },
15543
+ "meta-llama/llama-3.1-70b-instruct": {
15544
+ id: "meta-llama/llama-3.1-70b-instruct",
15545
+ name: "Meta: Llama 3.1 70B Instruct",
15546
+ api: "openai-completions",
15547
+ provider: "openrouter",
15548
+ baseUrl: "https://openrouter.ai/api/v1",
15549
+ reasoning: false,
15550
+ input: ["text"],
15551
+ cost: {
15552
+ input: 0.72,
15553
+ output: 0.72,
15554
+ cacheRead: 0,
15555
+ cacheWrite: 0,
15556
+ },
15557
+ contextWindow: 131072,
15558
+ maxTokens: 8192,
15559
+ },
15101
15560
  "meta-llama/llama-3.1-8b-instruct": {
15102
15561
  id: "meta-llama/llama-3.1-8b-instruct",
15103
15562
  name: "Meta: Llama 3.1 8B Instruct",
@@ -15192,13 +15651,13 @@ export const MODELS = {
15192
15651
  reasoning: true,
15193
15652
  input: ["text", "image"],
15194
15653
  cost: {
15195
- input: 0.3,
15196
- output: 1.2,
15654
+ input: 0.35,
15655
+ output: 1.5,
15197
15656
  cacheRead: 0.04,
15198
15657
  cacheWrite: 0,
15199
15658
  },
15200
15659
  contextWindow: 131072,
15201
- maxTokens: 16384,
15660
+ maxTokens: 117964,
15202
15661
  },
15203
15662
  "meta/muse-glimmer-30b:batch": {
15204
15663
  id: "meta/muse-glimmer-30b:batch",
@@ -15317,7 +15776,7 @@ export const MODELS = {
15317
15776
  cacheWrite: 0,
15318
15777
  },
15319
15778
  contextWindow: 1048576,
15320
- maxTokens: 131072,
15779
+ maxTokens: 943718,
15321
15780
  },
15322
15781
  "meta/muse-wonder": {
15323
15782
  id: "meta/muse-wonder",
@@ -15345,13 +15804,13 @@ export const MODELS = {
15345
15804
  reasoning: true,
15346
15805
  input: ["text"],
15347
15806
  cost: {
15348
- input: 0.3,
15807
+ input: 0.295,
15349
15808
  output: 1.2,
15350
15809
  cacheRead: 0.06,
15351
15810
  cacheWrite: 0,
15352
15811
  },
15353
- contextWindow: 200000,
15354
- maxTokens: 58982,
15812
+ contextWindow: 198000,
15813
+ maxTokens: 176947,
15355
15814
  },
15356
15815
  "minimax/minimax-m2.7": {
15357
15816
  id: "minimax/minimax-m2.7",
@@ -15583,9 +16042,9 @@ export const MODELS = {
15583
16042
  reasoning: false,
15584
16043
  input: ["text", "image"],
15585
16044
  cost: {
15586
- input: 0.39999999999999997,
15587
- output: 2,
15588
- cacheRead: 0.04,
16045
+ input: 0.44,
16046
+ output: 2.2,
16047
+ cacheRead: 0.044,
15589
16048
  cacheWrite: 0,
15590
16049
  },
15591
16050
  contextWindow: 131072,
@@ -15634,9 +16093,9 @@ export const MODELS = {
15634
16093
  reasoning: false,
15635
16094
  input: ["text", "image"],
15636
16095
  cost: {
15637
- input: 0.39999999999999997,
15638
- output: 2,
15639
- cacheRead: 0.04,
16096
+ input: 0.44,
16097
+ output: 2.2,
16098
+ cacheRead: 0.044,
15640
16099
  cacheWrite: 0,
15641
16100
  },
15642
16101
  contextWindow: 131072,
@@ -15719,13 +16178,13 @@ export const MODELS = {
15719
16178
  reasoning: false,
15720
16179
  input: ["text", "image"],
15721
16180
  cost: {
15722
- input: 0.09999999999999999,
15723
- output: 0.3,
15724
- cacheRead: 0.01,
16181
+ input: 0.075,
16182
+ output: 0.19999999999999998,
16183
+ cacheRead: 0,
15725
16184
  cacheWrite: 0,
15726
16185
  },
15727
16186
  contextWindow: 256000,
15728
- maxTokens: 26214,
16187
+ maxTokens: 16384,
15729
16188
  },
15730
16189
  "mistralai/mixtral-8x22b-instruct": {
15731
16190
  id: "mistralai/mixtral-8x22b-instruct",
@@ -15855,9 +16314,9 @@ export const MODELS = {
15855
16314
  reasoning: true,
15856
16315
  input: ["text", "image"],
15857
16316
  cost: {
15858
- input: 0.6,
15859
- output: 3.5,
15860
- cacheRead: 0.16,
16317
+ input: 0.7,
16318
+ output: 3.75,
16319
+ cacheRead: 0.16999999999999998,
15861
16320
  cacheWrite: 0,
15862
16321
  },
15863
16322
  contextWindow: 262144,
@@ -15889,8 +16348,8 @@ export const MODELS = {
15889
16348
  reasoning: true,
15890
16349
  input: ["text", "image"],
15891
16350
  cost: {
15892
- input: 2,
15893
- output: 10,
16351
+ input: 0.2403,
16352
+ output: 8.402299999999999,
15894
16353
  cacheRead: 0.19999999999999998,
15895
16354
  cacheWrite: 0,
15896
16355
  },
@@ -15914,6 +16373,23 @@ export const MODELS = {
15914
16373
  contextWindow: 1048576,
15915
16374
  maxTokens: 16384,
15916
16375
  },
16376
+ "motif-technologies/motif-3": {
16377
+ id: "motif-technologies/motif-3",
16378
+ name: "Motif Technologies: Motif 3",
16379
+ api: "openai-completions",
16380
+ provider: "openrouter",
16381
+ baseUrl: "https://openrouter.ai/api/v1",
16382
+ reasoning: true,
16383
+ input: ["text"],
16384
+ cost: {
16385
+ input: 0.3,
16386
+ output: 1.2,
16387
+ cacheRead: 0.06,
16388
+ cacheWrite: 0,
16389
+ },
16390
+ contextWindow: 262144,
16391
+ maxTokens: 235929,
16392
+ },
15917
16393
  "nex-agi/nex-n2.5-pro": {
15918
16394
  id: "nex-agi/nex-n2.5-pro",
15919
16395
  name: "Nex AGI: Nex-N2.5-Pro",
@@ -15996,7 +16472,7 @@ export const MODELS = {
15996
16472
  cacheRead: 0,
15997
16473
  cacheWrite: 0,
15998
16474
  },
15999
- contextWindow: 1048576,
16475
+ contextWindow: 262144,
16000
16476
  maxTokens: 16384,
16001
16477
  },
16002
16478
  "nvidia/nemotron-3-ultra-550b-a55b": {
@@ -16008,13 +16484,13 @@ export const MODELS = {
16008
16484
  reasoning: true,
16009
16485
  input: ["text"],
16010
16486
  cost: {
16011
- input: 0.6,
16012
- output: 2.4,
16013
- cacheRead: 0.12,
16487
+ input: 0.5,
16488
+ output: 2.2,
16489
+ cacheRead: 0.09999999999999999,
16014
16490
  cacheWrite: 0,
16015
16491
  },
16016
16492
  contextWindow: 262144,
16017
- maxTokens: 182520,
16493
+ maxTokens: 16384,
16018
16494
  },
16019
16495
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
16020
16496
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -16047,7 +16523,7 @@ export const MODELS = {
16047
16523
  cacheRead: 0.04,
16048
16524
  cacheWrite: 0,
16049
16525
  },
16050
- contextWindow: 262144,
16526
+ contextWindow: 1048576,
16051
16527
  maxTokens: 235929,
16052
16528
  },
16053
16529
  "nvidia/nemotron-3.5-lightning:free": {
@@ -16077,12 +16553,12 @@ export const MODELS = {
16077
16553
  input: ["text", "image"],
16078
16554
  cost: {
16079
16555
  input: 0.15,
16080
- output: 0.47,
16556
+ output: 0.5,
16081
16557
  cacheRead: 0.02,
16082
16558
  cacheWrite: 0,
16083
16559
  },
16084
16560
  contextWindow: 1048576,
16085
- maxTokens: 943718,
16561
+ maxTokens: 235929,
16086
16562
  },
16087
16563
  "nvidia/nemotron-3.5-super-vl:free": {
16088
16564
  id: "nvidia/nemotron-3.5-super-vl:free",
@@ -17446,87 +17922,223 @@ export const MODELS = {
17446
17922
  contextWindow: 1050000,
17447
17923
  maxTokens: 128000,
17448
17924
  },
17449
- "openai/gpt-audio": {
17450
- id: "openai/gpt-audio",
17451
- name: "OpenAI: GPT Audio",
17925
+ "openai/gpt-6.2-astra": {
17926
+ id: "openai/gpt-6.2-astra",
17927
+ name: "OpenAI: GPT-6.2 Astra",
17452
17928
  api: "openai-completions",
17453
17929
  provider: "openrouter",
17454
17930
  baseUrl: "https://openrouter.ai/api/v1",
17455
- reasoning: false,
17456
- input: ["text"],
17931
+ reasoning: true,
17932
+ input: ["text", "image"],
17457
17933
  cost: {
17458
- input: 2.5,
17459
- output: 10,
17460
- cacheRead: 0,
17461
- cacheWrite: 0,
17934
+ input: 8,
17935
+ output: 40,
17936
+ cacheRead: 0.39999999999999997,
17937
+ cacheWrite: 10,
17462
17938
  },
17463
- contextWindow: 128000,
17464
- maxTokens: 16384,
17939
+ contextWindow: 1050000,
17940
+ maxTokens: 128000,
17465
17941
  },
17466
- "openai/gpt-audio-mini": {
17467
- id: "openai/gpt-audio-mini",
17468
- name: "OpenAI: GPT Audio Mini",
17942
+ "openai/gpt-6.2-astra-pro": {
17943
+ id: "openai/gpt-6.2-astra-pro",
17944
+ name: "OpenAI: GPT-6.2 Astra Pro",
17469
17945
  api: "openai-completions",
17470
17946
  provider: "openrouter",
17471
17947
  baseUrl: "https://openrouter.ai/api/v1",
17472
- reasoning: false,
17473
- input: ["text"],
17948
+ reasoning: true,
17949
+ input: ["text", "image"],
17474
17950
  cost: {
17475
- input: 0.6,
17476
- output: 2.4,
17477
- cacheRead: 0,
17478
- cacheWrite: 0,
17951
+ input: 8,
17952
+ output: 40,
17953
+ cacheRead: 0.39999999999999997,
17954
+ cacheWrite: 10,
17479
17955
  },
17480
- contextWindow: 128000,
17481
- maxTokens: 16384,
17956
+ contextWindow: 1050000,
17957
+ maxTokens: 128000,
17482
17958
  },
17483
- "openai/gpt-chat-latest": {
17484
- id: "openai/gpt-chat-latest",
17485
- name: "OpenAI: GPT Chat Latest",
17959
+ "openai/gpt-6.2-astra-pro:batch": {
17960
+ id: "openai/gpt-6.2-astra-pro:batch",
17961
+ name: "OpenAI: GPT-6.2 Astra Pro (batch)",
17486
17962
  api: "openai-completions",
17487
17963
  provider: "openrouter",
17488
17964
  baseUrl: "https://openrouter.ai/api/v1",
17489
- reasoning: false,
17965
+ reasoning: true,
17490
17966
  input: ["text", "image"],
17491
17967
  cost: {
17492
- input: 5,
17493
- output: 30,
17494
- cacheRead: 0.5,
17495
- cacheWrite: 0,
17968
+ input: 4,
17969
+ output: 20,
17970
+ cacheRead: 0.19999999999999998,
17971
+ cacheWrite: 5,
17496
17972
  },
17497
- contextWindow: 400000,
17973
+ contextWindow: 1050000,
17498
17974
  maxTokens: 128000,
17499
17975
  },
17500
- "openai/gpt-oss-120b": {
17501
- id: "openai/gpt-oss-120b",
17502
- name: "OpenAI: gpt-oss-120b",
17976
+ "openai/gpt-6.2-astra:batch": {
17977
+ id: "openai/gpt-6.2-astra:batch",
17978
+ name: "OpenAI: GPT-6.2 Astra (batch)",
17503
17979
  api: "openai-completions",
17504
17980
  provider: "openrouter",
17505
17981
  baseUrl: "https://openrouter.ai/api/v1",
17506
17982
  reasoning: true,
17507
- input: ["text"],
17983
+ input: ["text", "image"],
17508
17984
  cost: {
17509
- input: 0.15,
17510
- output: 0.6,
17511
- cacheRead: 0.075,
17512
- cacheWrite: 0,
17985
+ input: 4,
17986
+ output: 20,
17987
+ cacheRead: 0.19999999999999998,
17988
+ cacheWrite: 5,
17513
17989
  },
17514
- contextWindow: 131072,
17515
- maxTokens: 65536,
17990
+ contextWindow: 1050000,
17991
+ maxTokens: 128000,
17516
17992
  },
17517
- "openai/gpt-oss-120b:batch": {
17518
- id: "openai/gpt-oss-120b:batch",
17519
- name: "OpenAI: gpt-oss-120b (batch)",
17993
+ "openai/gpt-6.2-sol": {
17994
+ id: "openai/gpt-6.2-sol",
17995
+ name: "OpenAI: GPT-6.2 Sol",
17520
17996
  api: "openai-completions",
17521
17997
  provider: "openrouter",
17522
17998
  baseUrl: "https://openrouter.ai/api/v1",
17523
17999
  reasoning: true,
17524
- input: ["text"],
18000
+ input: ["text", "image"],
17525
18001
  cost: {
17526
- input: 0.0296,
17527
- output: 0.136,
17528
- cacheRead: 0,
17529
- cacheWrite: 0,
18002
+ input: 2,
18003
+ output: 10,
18004
+ cacheRead: 0.09999999999999999,
18005
+ cacheWrite: 2.5,
18006
+ },
18007
+ contextWindow: 1050000,
18008
+ maxTokens: 128000,
18009
+ },
18010
+ "openai/gpt-6.2-sol-pro": {
18011
+ id: "openai/gpt-6.2-sol-pro",
18012
+ name: "OpenAI: GPT-6.2 Sol Pro",
18013
+ api: "openai-completions",
18014
+ provider: "openrouter",
18015
+ baseUrl: "https://openrouter.ai/api/v1",
18016
+ reasoning: true,
18017
+ input: ["text", "image"],
18018
+ cost: {
18019
+ input: 2,
18020
+ output: 10,
18021
+ cacheRead: 0.09999999999999999,
18022
+ cacheWrite: 2.5,
18023
+ },
18024
+ contextWindow: 1050000,
18025
+ maxTokens: 128000,
18026
+ },
18027
+ "openai/gpt-6.2-sol-pro:batch": {
18028
+ id: "openai/gpt-6.2-sol-pro:batch",
18029
+ name: "OpenAI: GPT-6.2 Sol Pro (batch)",
18030
+ api: "openai-completions",
18031
+ provider: "openrouter",
18032
+ baseUrl: "https://openrouter.ai/api/v1",
18033
+ reasoning: true,
18034
+ input: ["text", "image"],
18035
+ cost: {
18036
+ input: 1,
18037
+ output: 5,
18038
+ cacheRead: 0.049999999999999996,
18039
+ cacheWrite: 1.25,
18040
+ },
18041
+ contextWindow: 1050000,
18042
+ maxTokens: 128000,
18043
+ },
18044
+ "openai/gpt-6.2-sol:batch": {
18045
+ id: "openai/gpt-6.2-sol:batch",
18046
+ name: "OpenAI: GPT-6.2 Sol (batch)",
18047
+ api: "openai-completions",
18048
+ provider: "openrouter",
18049
+ baseUrl: "https://openrouter.ai/api/v1",
18050
+ reasoning: true,
18051
+ input: ["text", "image"],
18052
+ cost: {
18053
+ input: 1,
18054
+ output: 5,
18055
+ cacheRead: 0.049999999999999996,
18056
+ cacheWrite: 1.25,
18057
+ },
18058
+ contextWindow: 1050000,
18059
+ maxTokens: 128000,
18060
+ },
18061
+ "openai/gpt-audio": {
18062
+ id: "openai/gpt-audio",
18063
+ name: "OpenAI: GPT Audio",
18064
+ api: "openai-completions",
18065
+ provider: "openrouter",
18066
+ baseUrl: "https://openrouter.ai/api/v1",
18067
+ reasoning: false,
18068
+ input: ["text"],
18069
+ cost: {
18070
+ input: 2.5,
18071
+ output: 10,
18072
+ cacheRead: 0,
18073
+ cacheWrite: 0,
18074
+ },
18075
+ contextWindow: 128000,
18076
+ maxTokens: 16384,
18077
+ },
18078
+ "openai/gpt-audio-mini": {
18079
+ id: "openai/gpt-audio-mini",
18080
+ name: "OpenAI: GPT Audio Mini",
18081
+ api: "openai-completions",
18082
+ provider: "openrouter",
18083
+ baseUrl: "https://openrouter.ai/api/v1",
18084
+ reasoning: false,
18085
+ input: ["text"],
18086
+ cost: {
18087
+ input: 0.6,
18088
+ output: 2.4,
18089
+ cacheRead: 0,
18090
+ cacheWrite: 0,
18091
+ },
18092
+ contextWindow: 128000,
18093
+ maxTokens: 16384,
18094
+ },
18095
+ "openai/gpt-chat-latest": {
18096
+ id: "openai/gpt-chat-latest",
18097
+ name: "OpenAI: GPT Chat Latest",
18098
+ api: "openai-completions",
18099
+ provider: "openrouter",
18100
+ baseUrl: "https://openrouter.ai/api/v1",
18101
+ reasoning: false,
18102
+ input: ["text", "image"],
18103
+ cost: {
18104
+ input: 5,
18105
+ output: 30,
18106
+ cacheRead: 0.5,
18107
+ cacheWrite: 0,
18108
+ },
18109
+ contextWindow: 400000,
18110
+ maxTokens: 128000,
18111
+ },
18112
+ "openai/gpt-oss-120b": {
18113
+ id: "openai/gpt-oss-120b",
18114
+ name: "OpenAI: gpt-oss-120b",
18115
+ api: "openai-completions",
18116
+ provider: "openrouter",
18117
+ baseUrl: "https://openrouter.ai/api/v1",
18118
+ reasoning: true,
18119
+ input: ["text"],
18120
+ cost: {
18121
+ input: 0.15,
18122
+ output: 0.6,
18123
+ cacheRead: 0.075,
18124
+ cacheWrite: 0,
18125
+ },
18126
+ contextWindow: 131072,
18127
+ maxTokens: 65536,
18128
+ },
18129
+ "openai/gpt-oss-120b:batch": {
18130
+ id: "openai/gpt-oss-120b:batch",
18131
+ name: "OpenAI: gpt-oss-120b (batch)",
18132
+ api: "openai-completions",
18133
+ provider: "openrouter",
18134
+ baseUrl: "https://openrouter.ai/api/v1",
18135
+ reasoning: true,
18136
+ input: ["text"],
18137
+ cost: {
18138
+ input: 0.0296,
18139
+ output: 0.136,
18140
+ cacheRead: 0,
18141
+ cacheWrite: 0,
17530
18142
  },
17531
18143
  contextWindow: 131072,
17532
18144
  maxTokens: 117964,
@@ -17546,7 +18158,7 @@ export const MODELS = {
17546
18158
  cacheWrite: 0,
17547
18159
  },
17548
18160
  contextWindow: 131072,
17549
- maxTokens: 32768,
18161
+ maxTokens: 117964,
17550
18162
  },
17551
18163
  "openai/gpt-oss-20b:batch": {
17552
18164
  id: "openai/gpt-oss-20b:batch",
@@ -17761,7 +18373,7 @@ export const MODELS = {
17761
18373
  reasoning: true,
17762
18374
  input: ["text", "image"],
17763
18375
  cost: {
17764
- input: 0.049999999999999996,
18376
+ input: 0.06,
17765
18377
  output: 0.5,
17766
18378
  cacheRead: 0.003,
17767
18379
  cacheWrite: 0,
@@ -17769,6 +18381,23 @@ export const MODELS = {
17769
18381
  contextWindow: 1048576,
17770
18382
  maxTokens: 131072,
17771
18383
  },
18384
+ "particle-ai/particle-1:free": {
18385
+ id: "particle-ai/particle-1:free",
18386
+ name: "Particle AI: Particle-1 (free)",
18387
+ api: "openai-completions",
18388
+ provider: "openrouter",
18389
+ baseUrl: "https://openrouter.ai/api/v1",
18390
+ reasoning: true,
18391
+ input: ["text", "image"],
18392
+ cost: {
18393
+ input: 0,
18394
+ output: 0,
18395
+ cacheRead: 0,
18396
+ cacheWrite: 0,
18397
+ },
18398
+ contextWindow: 1048576,
18399
+ maxTokens: 131072,
18400
+ },
17772
18401
  "perceptron/perceptron-mk1.5": {
17773
18402
  id: "perceptron/perceptron-mk1.5",
17774
18403
  name: "Perceptron: Perceptron Mk1.5",
@@ -17837,23 +18466,6 @@ export const MODELS = {
17837
18466
  contextWindow: 32768,
17838
18467
  maxTokens: 16384,
17839
18468
  },
17840
- "qwen/qwen-2.5-7b-instruct": {
17841
- id: "qwen/qwen-2.5-7b-instruct",
17842
- name: "Qwen: Qwen2.5 7B Instruct",
17843
- api: "openai-completions",
17844
- provider: "openrouter",
17845
- baseUrl: "https://openrouter.ai/api/v1",
17846
- reasoning: false,
17847
- input: ["text"],
17848
- cost: {
17849
- input: 0.09999999999999999,
17850
- output: 0.19999999999999998,
17851
- cacheRead: 0,
17852
- cacheWrite: 0,
17853
- },
17854
- contextWindow: 32768,
17855
- maxTokens: 29491,
17856
- },
17857
18469
  "qwen/qwen-plus": {
17858
18470
  id: "qwen/qwen-plus",
17859
18471
  name: "Qwen: Qwen-Plus",
@@ -17880,13 +18492,13 @@ export const MODELS = {
17880
18492
  reasoning: true,
17881
18493
  input: ["text"],
17882
18494
  cost: {
17883
- input: 0.09999999999999999,
17884
- output: 0.22,
18495
+ input: 0.12,
18496
+ output: 0.24,
17885
18497
  cacheRead: 0,
17886
18498
  cacheWrite: 0,
17887
18499
  },
17888
18500
  contextWindow: 40960,
17889
- maxTokens: 36864,
18501
+ maxTokens: 16384,
17890
18502
  },
17891
18503
  "qwen/qwen3-235b-a22b-2507": {
17892
18504
  id: "qwen/qwen3-235b-a22b-2507",
@@ -18050,13 +18662,13 @@ export const MODELS = {
18050
18662
  reasoning: false,
18051
18663
  input: ["text"],
18052
18664
  cost: {
18053
- input: 0.09,
18665
+ input: 0.09999999999999999,
18054
18666
  output: 1.1,
18055
- cacheRead: 0,
18667
+ cacheRead: 0.07,
18056
18668
  cacheWrite: 0,
18057
18669
  },
18058
18670
  contextWindow: 262144,
18059
- maxTokens: 16384,
18671
+ maxTokens: 235929,
18060
18672
  },
18061
18673
  "qwen/qwen3-vl-235b-a22b-instruct": {
18062
18674
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -18092,23 +18704,6 @@ export const MODELS = {
18092
18704
  contextWindow: 262144,
18093
18705
  maxTokens: 16384,
18094
18706
  },
18095
- "qwen/qwen3-vl-30b-a3b-thinking": {
18096
- id: "qwen/qwen3-vl-30b-a3b-thinking",
18097
- name: "Qwen: Qwen3 VL 30B A3B Thinking",
18098
- api: "openai-completions",
18099
- provider: "openrouter",
18100
- baseUrl: "https://openrouter.ai/api/v1",
18101
- reasoning: true,
18102
- input: ["text", "image"],
18103
- cost: {
18104
- input: 0.29,
18105
- output: 1,
18106
- cacheRead: 0,
18107
- cacheWrite: 0,
18108
- },
18109
- contextWindow: 262144,
18110
- maxTokens: 235929,
18111
- },
18112
18707
  "qwen/qwen3-vl-8b-instruct": {
18113
18708
  id: "qwen/qwen3-vl-8b-instruct",
18114
18709
  name: "Qwen: Qwen3 VL 8B Instruct",
@@ -18152,13 +18747,13 @@ export const MODELS = {
18152
18747
  reasoning: true,
18153
18748
  input: ["text", "image"],
18154
18749
  cost: {
18155
- input: 0.26,
18156
- output: 2.6,
18750
+ input: 0.3,
18751
+ output: 2.4,
18157
18752
  cacheRead: 0,
18158
18753
  cacheWrite: 0,
18159
18754
  },
18160
18755
  contextWindow: 262144,
18161
- maxTokens: 81920,
18756
+ maxTokens: 65536,
18162
18757
  },
18163
18758
  "qwen/qwen3.5-35b-a3b": {
18164
18759
  id: "qwen/qwen3.5-35b-a3b",
@@ -18186,13 +18781,13 @@ export const MODELS = {
18186
18781
  reasoning: true,
18187
18782
  input: ["text", "image"],
18188
18783
  cost: {
18189
- input: 0.6,
18190
- output: 3.5999999999999996,
18191
- cacheRead: 0.12,
18784
+ input: 0.44999999999999996,
18785
+ output: 3,
18786
+ cacheRead: 0.22,
18192
18787
  cacheWrite: 0,
18193
18788
  },
18194
18789
  contextWindow: 262144,
18195
- maxTokens: 64000,
18790
+ maxTokens: 81920,
18196
18791
  },
18197
18792
  "qwen/qwen3.5-9b": {
18198
18793
  id: "qwen/qwen3.5-9b",
@@ -18203,13 +18798,13 @@ export const MODELS = {
18203
18798
  reasoning: true,
18204
18799
  input: ["text", "image"],
18205
18800
  cost: {
18206
- input: 0.16999999999999998,
18207
- output: 0.25,
18208
- cacheRead: 0,
18801
+ input: 0.154,
18802
+ output: 0.226,
18803
+ cacheRead: 0.13799999999999998,
18209
18804
  cacheWrite: 0,
18210
18805
  },
18211
18806
  contextWindow: 262144,
18212
- maxTokens: 235929,
18807
+ maxTokens: 40960,
18213
18808
  },
18214
18809
  "qwen/qwen3.5-flash-02-23": {
18215
18810
  id: "qwen/qwen3.5-flash-02-23",
@@ -18424,12 +19019,12 @@ export const MODELS = {
18424
19019
  reasoning: true,
18425
19020
  input: ["text", "image"],
18426
19021
  cost: {
18427
- input: 0.15,
18428
- output: 1.875,
18429
- cacheRead: 0.0375,
19022
+ input: 0.06,
19023
+ output: 2.2,
19024
+ cacheRead: 0.059,
18430
19025
  cacheWrite: 0,
18431
19026
  },
18432
- contextWindow: 1048575,
19027
+ contextWindow: 1024000,
18433
19028
  maxTokens: 235929,
18434
19029
  },
18435
19030
  "qwen/qwen3.8-27b:batch": {
@@ -18534,6 +19129,23 @@ export const MODELS = {
18534
19129
  contextWindow: 1000000,
18535
19130
  maxTokens: 131072,
18536
19131
  },
19132
+ "qwen/qwen4-max": {
19133
+ id: "qwen/qwen4-max",
19134
+ name: "Qwen: Qwen4 Max",
19135
+ api: "openai-completions",
19136
+ provider: "openrouter",
19137
+ baseUrl: "https://openrouter.ai/api/v1",
19138
+ reasoning: true,
19139
+ input: ["text", "image"],
19140
+ cost: {
19141
+ input: 1.4249999999999998,
19142
+ output: 4.2749999999999995,
19143
+ cacheRead: 0.07125000000000001,
19144
+ cacheWrite: 1.78125,
19145
+ },
19146
+ contextWindow: 1000000,
19147
+ maxTokens: 131072,
19148
+ },
18537
19149
  "recursive/flint-v1.0:free": {
18538
19150
  id: "recursive/flint-v1.0:free",
18539
19151
  name: "Recursive: Flint (free)",
@@ -18611,9 +19223,9 @@ export const MODELS = {
18611
19223
  reasoning: true,
18612
19224
  input: ["text"],
18613
19225
  cost: {
18614
- input: 0.19999999999999998,
18615
- output: 0.6,
18616
- cacheRead: 0.049999999999999996,
19226
+ input: 0.09999999999999999,
19227
+ output: 0.3,
19228
+ cacheRead: 0.024999999999999998,
18617
19229
  cacheWrite: 0,
18618
19230
  },
18619
19231
  contextWindow: 1048576,
@@ -18687,23 +19299,6 @@ export const MODELS = {
18687
19299
  contextWindow: 262144,
18688
19300
  maxTokens: 65536,
18689
19301
  },
18690
- "stepfun/step-3.5-flash": {
18691
- id: "stepfun/step-3.5-flash",
18692
- name: "StepFun: Step 3.5 Flash",
18693
- api: "openai-completions",
18694
- provider: "openrouter",
18695
- baseUrl: "https://openrouter.ai/api/v1",
18696
- reasoning: true,
18697
- input: ["text"],
18698
- cost: {
18699
- input: 0.09999999999999999,
18700
- output: 0.3,
18701
- cacheRead: 0,
18702
- cacheWrite: 0,
18703
- },
18704
- contextWindow: 262144,
18705
- maxTokens: 65536,
18706
- },
18707
19302
  "stepfun/step-3.7-flash": {
18708
19303
  id: "stepfun/step-3.7-flash",
18709
19304
  name: "StepFun: Step 3.7 Flash",
@@ -18772,6 +19367,23 @@ export const MODELS = {
18772
19367
  contextWindow: 1048576,
18773
19368
  maxTokens: 65536,
18774
19369
  },
19370
+ "tencent/hy4-flash": {
19371
+ id: "tencent/hy4-flash",
19372
+ name: "Tencent: Hy4 flash",
19373
+ api: "openai-completions",
19374
+ provider: "openrouter",
19375
+ baseUrl: "https://openrouter.ai/api/v1",
19376
+ reasoning: true,
19377
+ input: ["text", "image"],
19378
+ cost: {
19379
+ input: 0.035,
19380
+ output: 0.14049999999999999,
19381
+ cacheRead: 0.0015,
19382
+ cacheWrite: 0,
19383
+ },
19384
+ contextWindow: 1048576,
19385
+ maxTokens: 65536,
19386
+ },
18775
19387
  "tencent/hy4-preview": {
18776
19388
  id: "tencent/hy4-preview",
18777
19389
  name: "Tencent: Hy4 preview",
@@ -18806,6 +19418,23 @@ export const MODELS = {
18806
19418
  contextWindow: 524288,
18807
19419
  maxTokens: 471859,
18808
19420
  },
19421
+ "thinkingmachines/inkling-2-small": {
19422
+ id: "thinkingmachines/inkling-2-small",
19423
+ name: "Thinking Machines: Inkling 2 Small",
19424
+ api: "openai-completions",
19425
+ provider: "openrouter",
19426
+ baseUrl: "https://openrouter.ai/api/v1",
19427
+ reasoning: true,
19428
+ input: ["text", "image"],
19429
+ cost: {
19430
+ input: 0.3,
19431
+ output: 1,
19432
+ cacheRead: 0.03,
19433
+ cacheWrite: 0,
19434
+ },
19435
+ contextWindow: 1048576,
19436
+ maxTokens: 943718,
19437
+ },
18809
19438
  "thinkingmachines/inkling-2-small:free": {
18810
19439
  id: "thinkingmachines/inkling-2-small:free",
18811
19440
  name: "Thinking Machines: Inkling 2 Small (free)",
@@ -18891,6 +19520,23 @@ export const MODELS = {
18891
19520
  contextWindow: 1048576,
18892
19521
  maxTokens: 131072,
18893
19522
  },
19523
+ "unbiased/pareto-26.10-preview": {
19524
+ id: "unbiased/pareto-26.10-preview",
19525
+ name: "Pareto 26.10 Preview",
19526
+ api: "openai-completions",
19527
+ provider: "openrouter",
19528
+ baseUrl: "https://openrouter.ai/api/v1",
19529
+ reasoning: false,
19530
+ input: ["text", "image"],
19531
+ cost: {
19532
+ input: 0.7999999999999999,
19533
+ output: 3.1999999999999997,
19534
+ cacheRead: 0.03,
19535
+ cacheWrite: 0,
19536
+ },
19537
+ contextWindow: 1048576,
19538
+ maxTokens: 131072,
19539
+ },
18894
19540
  "unbiased/pareto-26.9": {
18895
19541
  id: "unbiased/pareto-26.9",
18896
19542
  name: "Pareto 26.9",
@@ -19126,7 +19772,7 @@ export const MODELS = {
19126
19772
  cacheRead: 0.096,
19127
19773
  cacheWrite: 0,
19128
19774
  },
19129
- contextWindow: 1024000,
19775
+ contextWindow: 262144,
19130
19776
  maxTokens: 235929,
19131
19777
  },
19132
19778
  "xiaomi/mimo-v2.6-flash": {
@@ -19180,23 +19826,6 @@ export const MODELS = {
19180
19826
  contextWindow: 1048576,
19181
19827
  maxTokens: 131072,
19182
19828
  },
19183
- "xingchen-agi/xing4.0-29b-a4b:free": {
19184
- id: "xingchen-agi/xing4.0-29b-a4b:free",
19185
- name: "XingChen: Xing4.0 29B A4B (free)",
19186
- api: "openai-completions",
19187
- provider: "openrouter",
19188
- baseUrl: "https://openrouter.ai/api/v1",
19189
- reasoning: true,
19190
- input: ["text"],
19191
- cost: {
19192
- input: 0,
19193
- output: 0,
19194
- cacheRead: 0,
19195
- cacheWrite: 0,
19196
- },
19197
- contextWindow: 262144,
19198
- maxTokens: 235929,
19199
- },
19200
19829
  "z-ai/glm-4.5": {
19201
19830
  id: "z-ai/glm-4.5",
19202
19831
  name: "Z.ai: GLM 4.5",
@@ -19223,9 +19852,9 @@ export const MODELS = {
19223
19852
  reasoning: true,
19224
19853
  input: ["text"],
19225
19854
  cost: {
19226
- input: 0.19999999999999998,
19227
- output: 1.1,
19228
- cacheRead: 0.03,
19855
+ input: 0.13,
19856
+ output: 0.85,
19857
+ cacheRead: 0.024999999999999998,
19229
19858
  cacheWrite: 0,
19230
19859
  },
19231
19860
  contextWindow: 131072,
@@ -19276,7 +19905,7 @@ export const MODELS = {
19276
19905
  cost: {
19277
19906
  input: 0.3,
19278
19907
  output: 0.8999999999999999,
19279
- cacheRead: 0.055,
19908
+ cacheRead: 0.049999999999999996,
19280
19909
  cacheWrite: 0,
19281
19910
  },
19282
19911
  contextWindow: 131072,
@@ -19291,9 +19920,9 @@ export const MODELS = {
19291
19920
  reasoning: true,
19292
19921
  input: ["text"],
19293
19922
  cost: {
19294
- input: 0.6,
19295
- output: 2.2,
19296
- cacheRead: 0.11,
19923
+ input: 0.39999999999999997,
19924
+ output: 1.75,
19925
+ cacheRead: 0.08,
19297
19926
  cacheWrite: 0,
19298
19927
  },
19299
19928
  contextWindow: 204800,
@@ -19365,7 +19994,7 @@ export const MODELS = {
19365
19994
  cacheWrite: 0,
19366
19995
  },
19367
19996
  contextWindow: 204800,
19368
- maxTokens: 131072,
19997
+ maxTokens: 182476,
19369
19998
  },
19370
19999
  "z-ai/glm-5.2": {
19371
20000
  id: "z-ai/glm-5.2",
@@ -19376,9 +20005,9 @@ export const MODELS = {
19376
20005
  reasoning: true,
19377
20006
  input: ["text"],
19378
20007
  cost: {
19379
- input: 0.0070999999999999995,
20008
+ input: 0.007,
19380
20009
  output: 6.8,
19381
- cacheRead: 0.0061,
20010
+ cacheRead: 0.006,
19382
20011
  cacheWrite: 0,
19383
20012
  },
19384
20013
  contextWindow: 1048576,
@@ -19393,9 +20022,9 @@ export const MODELS = {
19393
20022
  reasoning: true,
19394
20023
  input: ["text"],
19395
20024
  cost: {
19396
- input: 0.527,
19397
- output: 1.0750000000000002,
19398
- cacheRead: 0.17800000000000002,
20025
+ input: 0.322,
20026
+ output: 0.989,
20027
+ cacheRead: 0.109,
19399
20028
  cacheWrite: 0,
19400
20029
  },
19401
20030
  contextWindow: 1048576,
@@ -19444,9 +20073,9 @@ export const MODELS = {
19444
20073
  reasoning: true,
19445
20074
  input: ["text", "image"],
19446
20075
  cost: {
19447
- input: 0.03,
19448
- output: 0.061000000000000006,
19449
- cacheRead: 0.013000000000000001,
20076
+ input: 0.024,
20077
+ output: 0.06899999999999999,
20078
+ cacheRead: 0.01,
19450
20079
  cacheWrite: 0,
19451
20080
  },
19452
20081
  contextWindow: 1048576,
@@ -19495,9 +20124,9 @@ export const MODELS = {
19495
20124
  reasoning: true,
19496
20125
  input: ["text"],
19497
20126
  cost: {
19498
- input: 2.8,
19499
- output: 8.8,
19500
- cacheRead: 0.56,
20127
+ input: 1.68,
20128
+ output: 5.28,
20129
+ cacheRead: 0.33599999999999997,
19501
20130
  cacheWrite: 0,
19502
20131
  },
19503
20132
  contextWindow: 1000000,
@@ -19512,13 +20141,13 @@ export const MODELS = {
19512
20141
  reasoning: true,
19513
20142
  input: ["text"],
19514
20143
  cost: {
19515
- input: 0.44999999999999996,
19516
- output: 2,
19517
- cacheRead: 0.09999999999999999,
20144
+ input: 0.28099999999999997,
20145
+ output: 1.25,
20146
+ cacheRead: 0.062,
19518
20147
  cacheWrite: 0,
19519
20148
  },
19520
20149
  contextWindow: 1048576,
19521
- maxTokens: 131072,
20150
+ maxTokens: 943718,
19522
20151
  },
19523
20152
  "z-ai/glm-5v-turbo": {
19524
20153
  id: "z-ai/glm-5v-turbo",
@@ -19615,9 +20244,9 @@ export const MODELS = {
19615
20244
  reasoning: true,
19616
20245
  input: ["text", "image"],
19617
20246
  cost: {
19618
- input: 0.006,
20247
+ input: 0.036,
19619
20248
  output: 0.5,
19620
- cacheRead: 0.005,
20249
+ cacheRead: 0.01,
19621
20250
  cacheWrite: 0,
19622
20251
  },
19623
20252
  contextWindow: 1048576,
@@ -19668,13 +20297,13 @@ export const MODELS = {
19668
20297
  reasoning: true,
19669
20298
  input: ["text", "image"],
19670
20299
  cost: {
19671
- input: 0.75,
19672
- output: 3.75,
20300
+ input: 1.5,
20301
+ output: 7.5,
19673
20302
  cacheRead: 0.075,
19674
- cacheWrite: 0.0416666666666667,
20303
+ cacheWrite: 0.0833333333333333,
19675
20304
  },
19676
20305
  contextWindow: 1048576,
19677
- maxTokens: 65536,
20306
+ maxTokens: 943718,
19678
20307
  },
19679
20308
  "~google/gemini-pro-latest": {
19680
20309
  id: "~google/gemini-pro-latest",
@@ -19703,7 +20332,7 @@ export const MODELS = {
19703
20332
  input: ["text", "image"],
19704
20333
  cost: {
19705
20334
  input: 0.18239999999999998,
19706
- output: 10.5601,
20335
+ output: 11.0055,
19707
20336
  cacheRead: 0.18,
19708
20337
  cacheWrite: 0,
19709
20338
  },
@@ -19719,10 +20348,10 @@ export const MODELS = {
19719
20348
  reasoning: true,
19720
20349
  input: ["text", "image"],
19721
20350
  cost: {
19722
- input: 10,
19723
- output: 50,
19724
- cacheRead: 1,
19725
- cacheWrite: 12.5,
20351
+ input: 8,
20352
+ output: 40,
20353
+ cacheRead: 0.39999999999999997,
20354
+ cacheWrite: 10,
19726
20355
  },
19727
20356
  contextWindow: 1050000,
19728
20357
  maxTokens: 128000,
@@ -19838,8 +20467,8 @@ export const MODELS = {
19838
20467
  reasoning: true,
19839
20468
  input: ["text", "image"],
19840
20469
  cost: {
19841
- input: 0.0335,
19842
- output: 0.083,
20470
+ input: 0.0399,
20471
+ output: 0.0784,
19843
20472
  cacheRead: 0.03,
19844
20473
  cacheWrite: 0,
19845
20474
  },
@@ -20015,7 +20644,7 @@ export const MODELS = {
20015
20644
  cacheWrite: 0,
20016
20645
  },
20017
20646
  contextWindow: 1048576,
20018
- maxTokens: 131072,
20647
+ maxTokens: 1048576,
20019
20648
  },
20020
20649
  "moonshotai/Kimi-K3.1-Pro": {
20021
20650
  id: "moonshotai/Kimi-K3.1-Pro",
@@ -20034,7 +20663,7 @@ export const MODELS = {
20034
20663
  cacheWrite: 0,
20035
20664
  },
20036
20665
  contextWindow: 1048576,
20037
- maxTokens: 131072,
20666
+ maxTokens: 1048576,
20038
20667
  },
20039
20668
  "nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
20040
20669
  id: "nvidia/NVIDIA-Nemotron-3.5-Super-VL",
@@ -20188,23 +20817,6 @@ export const MODELS = {
20188
20817
  contextWindow: 40960,
20189
20818
  maxTokens: 16384,
20190
20819
  },
20191
- "alibaba/qwen-3-235b": {
20192
- id: "alibaba/qwen-3-235b",
20193
- name: "Qwen3 235B A22B",
20194
- api: "anthropic-messages",
20195
- provider: "vercel-ai-gateway",
20196
- baseUrl: "https://ai-gateway.vercel.sh",
20197
- reasoning: false,
20198
- input: ["text"],
20199
- cost: {
20200
- input: 0.22,
20201
- output: 0.88,
20202
- cacheRead: 0,
20203
- cacheWrite: 0,
20204
- },
20205
- contextWindow: 262144,
20206
- maxTokens: 16384,
20207
- },
20208
20820
  "alibaba/qwen-3-30b": {
20209
20821
  id: "alibaba/qwen-3-30b",
20210
20822
  name: "Qwen3-30B-A3B",
@@ -20239,23 +20851,6 @@ export const MODELS = {
20239
20851
  contextWindow: 128000,
20240
20852
  maxTokens: 8192,
20241
20853
  },
20242
- "alibaba/qwen3-coder": {
20243
- id: "alibaba/qwen3-coder",
20244
- name: "Qwen3 Coder 480B A35B Instruct",
20245
- api: "anthropic-messages",
20246
- provider: "vercel-ai-gateway",
20247
- baseUrl: "https://ai-gateway.vercel.sh",
20248
- reasoning: false,
20249
- input: ["text"],
20250
- cost: {
20251
- input: 0.22,
20252
- output: 1.7999999999999998,
20253
- cacheRead: 0.022,
20254
- cacheWrite: 0,
20255
- },
20256
- contextWindow: 262144,
20257
- maxTokens: 32768,
20258
- },
20259
20854
  "alibaba/qwen3-coder-30b-a3b": {
20260
20855
  id: "alibaba/qwen3-coder-30b-a3b",
20261
20856
  name: "Qwen 3 Coder 30B A3B Instruct",
@@ -20316,30 +20911,13 @@ export const MODELS = {
20316
20911
  reasoning: false,
20317
20912
  input: ["text"],
20318
20913
  cost: {
20319
- input: 0.15,
20320
- output: 1.2,
20321
- cacheRead: 0,
20322
- cacheWrite: 0,
20323
- },
20324
- contextWindow: 262114,
20325
- maxTokens: 262114,
20326
- },
20327
- "alibaba/qwen3-next-80b-a3b-thinking": {
20328
- id: "alibaba/qwen3-next-80b-a3b-thinking",
20329
- name: "Qwen3 Next 80B A3B Thinking",
20330
- api: "anthropic-messages",
20331
- provider: "vercel-ai-gateway",
20332
- baseUrl: "https://ai-gateway.vercel.sh",
20333
- reasoning: true,
20334
- input: ["text"],
20335
- cost: {
20336
- input: 0.15,
20337
- output: 1.2,
20914
+ input: 0.09,
20915
+ output: 1.1,
20338
20916
  cacheRead: 0,
20339
20917
  cacheWrite: 0,
20340
20918
  },
20341
20919
  contextWindow: 262144,
20342
- maxTokens: 262144,
20920
+ maxTokens: 32768,
20343
20921
  },
20344
20922
  "alibaba/qwen3-vl-instruct": {
20345
20923
  id: "alibaba/qwen3-vl-instruct",
@@ -20409,6 +20987,23 @@ export const MODELS = {
20409
20987
  contextWindow: 256000,
20410
20988
  maxTokens: 256000,
20411
20989
  },
20990
+ "alibaba/qwen3.6-35b-a3b": {
20991
+ id: "alibaba/qwen3.6-35b-a3b",
20992
+ name: "Qwen 3.6 35B A3B",
20993
+ api: "anthropic-messages",
20994
+ provider: "vercel-ai-gateway",
20995
+ baseUrl: "https://ai-gateway.vercel.sh",
20996
+ reasoning: true,
20997
+ input: ["text", "image"],
20998
+ cost: {
20999
+ input: 0.375,
21000
+ output: 2.25,
21001
+ cacheRead: 0,
21002
+ cacheWrite: 0,
21003
+ },
21004
+ contextWindow: 262144,
21005
+ maxTokens: 65536,
21006
+ },
20412
21007
  "alibaba/qwen3.6-plus": {
20413
21008
  id: "alibaba/qwen3.6-plus",
20414
21009
  name: "Qwen 3.6 Plus",
@@ -20492,7 +21087,7 @@ export const MODELS = {
20492
21087
  cacheWrite: 0,
20493
21088
  },
20494
21089
  contextWindow: 262144,
20495
- maxTokens: 128000,
21090
+ maxTokens: 131072,
20496
21091
  },
20497
21092
  "alibaba/qwen3.8-27b": {
20498
21093
  id: "alibaba/qwen3.8-27b",
@@ -20504,7 +21099,7 @@ export const MODELS = {
20504
21099
  input: ["text", "image"],
20505
21100
  cost: {
20506
21101
  input: 0.06,
20507
- output: 2.3,
21102
+ output: 2.2,
20508
21103
  cacheRead: 0.059,
20509
21104
  cacheWrite: 0,
20510
21105
  },
@@ -20540,9 +21135,9 @@ export const MODELS = {
20540
21135
  input: 2,
20541
21136
  output: 6,
20542
21137
  cacheRead: 0.25,
20543
- cacheWrite: 0,
21138
+ cacheWrite: 2.5,
20544
21139
  },
20545
- contextWindow: 262144,
21140
+ contextWindow: 1000000,
20546
21141
  maxTokens: 128000,
20547
21142
  },
20548
21143
  "alibaba/qwen3.8-max-0902": {
@@ -20596,6 +21191,23 @@ export const MODELS = {
20596
21191
  contextWindow: 1000000,
20597
21192
  maxTokens: 131072,
20598
21193
  },
21194
+ "alibaba/qwen4-max": {
21195
+ id: "alibaba/qwen4-max",
21196
+ name: "Qwen 4 Max",
21197
+ api: "anthropic-messages",
21198
+ provider: "vercel-ai-gateway",
21199
+ baseUrl: "https://ai-gateway.vercel.sh",
21200
+ reasoning: true,
21201
+ input: ["text", "image"],
21202
+ cost: {
21203
+ input: 1.5,
21204
+ output: 4.5,
21205
+ cacheRead: 0.075,
21206
+ cacheWrite: 1.875,
21207
+ },
21208
+ contextWindow: 1000000,
21209
+ maxTokens: 384000,
21210
+ },
20599
21211
  "amazon/nova-2-lite": {
20600
21212
  id: "amazon/nova-2-lite",
20601
21213
  name: "Nova 2 Lite",
@@ -21261,40 +21873,6 @@ export const MODELS = {
21261
21873
  contextWindow: 1000000,
21262
21874
  maxTokens: 128000,
21263
21875
  },
21264
- "bytedance/seed-1.6": {
21265
- id: "bytedance/seed-1.6",
21266
- name: "Seed 1.6",
21267
- api: "anthropic-messages",
21268
- provider: "vercel-ai-gateway",
21269
- baseUrl: "https://ai-gateway.vercel.sh",
21270
- reasoning: true,
21271
- input: ["text", "image"],
21272
- cost: {
21273
- input: 0.25,
21274
- output: 2,
21275
- cacheRead: 0.049999999999999996,
21276
- cacheWrite: 0,
21277
- },
21278
- contextWindow: 256000,
21279
- maxTokens: 32000,
21280
- },
21281
- "bytedance/seed-1.8": {
21282
- id: "bytedance/seed-1.8",
21283
- name: "Bytedance Seed 1.8",
21284
- api: "anthropic-messages",
21285
- provider: "vercel-ai-gateway",
21286
- baseUrl: "https://ai-gateway.vercel.sh",
21287
- reasoning: true,
21288
- input: ["text", "image"],
21289
- cost: {
21290
- input: 0.25,
21291
- output: 2,
21292
- cacheRead: 0.049999999999999996,
21293
- cacheWrite: 0,
21294
- },
21295
- contextWindow: 256000,
21296
- maxTokens: 64000,
21297
- },
21298
21876
  "bytedance/seed-2.1-turbo": {
21299
21877
  id: "bytedance/seed-2.1-turbo",
21300
21878
  name: "Seed 2.1 Turbo",
@@ -21510,11 +22088,11 @@ export const MODELS = {
21510
22088
  cost: {
21511
22089
  input: 0.3,
21512
22090
  output: 1.2,
21513
- cacheRead: 0.007,
22091
+ cacheRead: 0.006,
21514
22092
  cacheWrite: 0,
21515
22093
  },
21516
22094
  contextWindow: 1048576,
21517
- maxTokens: 32768,
22095
+ maxTokens: 1048576,
21518
22096
  },
21519
22097
  "deepseek/deepseek-v4.1-flash-1017": {
21520
22098
  id: "deepseek/deepseek-v4.1-flash-1017",
@@ -21941,90 +22519,90 @@ export const MODELS = {
21941
22519
  contextWindow: 1000000,
21942
22520
  maxTokens: 1000000,
21943
22521
  },
21944
- "google/gemma-4-26b-a4b-it": {
21945
- id: "google/gemma-4-26b-a4b-it",
21946
- name: "Google Gemma 4 26B A4B",
22522
+ "google/gemini-4-carbon": {
22523
+ id: "google/gemini-4-carbon",
22524
+ name: "Gemini 4 Carbon",
21947
22525
  api: "anthropic-messages",
21948
22526
  provider: "vercel-ai-gateway",
21949
22527
  baseUrl: "https://ai-gateway.vercel.sh",
21950
22528
  reasoning: true,
21951
22529
  input: ["text", "image"],
21952
22530
  cost: {
21953
- input: 0.15,
21954
- output: 0.6,
21955
- cacheRead: 0.015,
22531
+ input: 2,
22532
+ output: 10,
22533
+ cacheRead: 0.09999999999999999,
21956
22534
  cacheWrite: 0,
21957
22535
  },
21958
- contextWindow: 262144,
21959
- maxTokens: 131072,
22536
+ contextWindow: 1000000,
22537
+ maxTokens: 1000000,
21960
22538
  },
21961
- "google/gemma-4-31b-it": {
21962
- id: "google/gemma-4-31b-it",
21963
- name: "Gemma 4 31B IT",
22539
+ "google/gemini-4-hydrogen": {
22540
+ id: "google/gemini-4-hydrogen",
22541
+ name: "Gemini 4 Hydrogen",
21964
22542
  api: "anthropic-messages",
21965
22543
  provider: "vercel-ai-gateway",
21966
22544
  baseUrl: "https://ai-gateway.vercel.sh",
21967
22545
  reasoning: true,
21968
22546
  input: ["text", "image"],
21969
22547
  cost: {
21970
- input: 0.14,
21971
- output: 0.39999999999999997,
21972
- cacheRead: 0,
22548
+ input: 1.5,
22549
+ output: 7.5,
22550
+ cacheRead: 0.075,
21973
22551
  cacheWrite: 0,
21974
22552
  },
21975
- contextWindow: 262144,
21976
- maxTokens: 131072,
22553
+ contextWindow: 1000000,
22554
+ maxTokens: 1000000,
21977
22555
  },
21978
- "humansand/ampersand-v0.1": {
21979
- id: "humansand/ampersand-v0.1",
21980
- name: "Ampersand v0.1",
22556
+ "google/gemma-4-26b-a4b-it": {
22557
+ id: "google/gemma-4-26b-a4b-it",
22558
+ name: "Google Gemma 4 26B A4B",
21981
22559
  api: "anthropic-messages",
21982
22560
  provider: "vercel-ai-gateway",
21983
22561
  baseUrl: "https://ai-gateway.vercel.sh",
21984
22562
  reasoning: true,
21985
- input: ["text"],
22563
+ input: ["text", "image"],
21986
22564
  cost: {
21987
- input: 0,
21988
- output: 0,
21989
- cacheRead: 0,
22565
+ input: 0.15,
22566
+ output: 0.6,
22567
+ cacheRead: 0.015,
21990
22568
  cacheWrite: 0,
21991
22569
  },
21992
- contextWindow: 1000000,
21993
- maxTokens: 32768,
22570
+ contextWindow: 262144,
22571
+ maxTokens: 131072,
21994
22572
  },
21995
- "inception/mercury-2": {
21996
- id: "inception/mercury-2",
21997
- name: "Mercury 2",
22573
+ "google/gemma-4-31b-it": {
22574
+ id: "google/gemma-4-31b-it",
22575
+ name: "Gemma 4 31B IT",
21998
22576
  api: "anthropic-messages",
21999
22577
  provider: "vercel-ai-gateway",
22000
22578
  baseUrl: "https://ai-gateway.vercel.sh",
22001
22579
  reasoning: true,
22002
- input: ["text"],
22580
+ input: ["text", "image"],
22003
22581
  cost: {
22004
- input: 0.25,
22005
- output: 0.75,
22006
- cacheRead: 0.024999999999999998,
22582
+ input: 0.14,
22583
+ output: 0.39999999999999997,
22584
+ cacheRead: 0,
22007
22585
  cacheWrite: 0,
22008
22586
  },
22009
- contextWindow: 128000,
22010
- maxTokens: 128000,
22587
+ contextWindow: 262144,
22588
+ maxTokens: 131072,
22011
22589
  },
22012
- "inception/mercury-2.5": {
22013
- id: "inception/mercury-2.5",
22014
- name: "Mercury 2.5",
22590
+ "humansand/ampersand-v0.1": {
22591
+ id: "humansand/ampersand-v0.1",
22592
+ name: "Ampersand v0.1",
22015
22593
  api: "anthropic-messages",
22016
22594
  provider: "vercel-ai-gateway",
22017
22595
  baseUrl: "https://ai-gateway.vercel.sh",
22018
22596
  reasoning: true,
22019
22597
  input: ["text"],
22020
22598
  cost: {
22021
- input: 0.04,
22022
- output: 0.15,
22023
- cacheRead: 0.004,
22599
+ input: 0,
22600
+ output: 0,
22601
+ cacheRead: 0,
22024
22602
  cacheWrite: 0,
22025
22603
  },
22026
- contextWindow: 260000,
22027
- maxTokens: 65536,
22604
+ contextWindow: 1000000,
22605
+ maxTokens: 32768,
22028
22606
  },
22029
22607
  "inception/mercury-3": {
22030
22608
  id: "inception/mercury-3",
@@ -22043,23 +22621,6 @@ export const MODELS = {
22043
22621
  contextWindow: 1000000,
22044
22622
  maxTokens: 131072,
22045
22623
  },
22046
- "inception/mercury-coder-small": {
22047
- id: "inception/mercury-coder-small",
22048
- name: "Mercury Coder Small Beta",
22049
- api: "anthropic-messages",
22050
- provider: "vercel-ai-gateway",
22051
- baseUrl: "https://ai-gateway.vercel.sh",
22052
- reasoning: false,
22053
- input: ["text"],
22054
- cost: {
22055
- input: 0.25,
22056
- output: 1,
22057
- cacheRead: 0,
22058
- cacheWrite: 0,
22059
- },
22060
- contextWindow: 32000,
22061
- maxTokens: 16384,
22062
- },
22063
22624
  "inclusionai/ling-3.0-flash": {
22064
22625
  id: "inclusionai/ling-3.0-flash",
22065
22626
  name: "Ling 3.0 Flash",
@@ -22451,23 +23012,6 @@ export const MODELS = {
22451
23012
  contextWindow: 1048576,
22452
23013
  maxTokens: 1048576,
22453
23014
  },
22454
- "minimax/minimax-m2": {
22455
- id: "minimax/minimax-m2",
22456
- name: "MiniMax M2",
22457
- api: "anthropic-messages",
22458
- provider: "vercel-ai-gateway",
22459
- baseUrl: "https://ai-gateway.vercel.sh",
22460
- reasoning: true,
22461
- input: ["text"],
22462
- cost: {
22463
- input: 0.3,
22464
- output: 1.2,
22465
- cacheRead: 0.03,
22466
- cacheWrite: 0.375,
22467
- },
22468
- contextWindow: 205000,
22469
- maxTokens: 205000,
22470
- },
22471
23015
  "minimax/minimax-m2.1": {
22472
23016
  id: "minimax/minimax-m2.1",
22473
23017
  name: "MiniMax M2.1",
@@ -22479,25 +23023,8 @@ export const MODELS = {
22479
23023
  cost: {
22480
23024
  input: 0.3,
22481
23025
  output: 1.2,
22482
- cacheRead: 0.03,
22483
- cacheWrite: 0.375,
22484
- },
22485
- contextWindow: 204800,
22486
- maxTokens: 131072,
22487
- },
22488
- "minimax/minimax-m2.1-lightning": {
22489
- id: "minimax/minimax-m2.1-lightning",
22490
- name: "MiniMax M2.1 Lightning",
22491
- api: "anthropic-messages",
22492
- provider: "vercel-ai-gateway",
22493
- baseUrl: "https://ai-gateway.vercel.sh",
22494
- reasoning: true,
22495
- input: ["text"],
22496
- cost: {
22497
- input: 0.3,
22498
- output: 2.4,
22499
- cacheRead: 0.03,
22500
- cacheWrite: 0.375,
23026
+ cacheRead: 0.15,
23027
+ cacheWrite: 0,
22501
23028
  },
22502
23029
  contextWindow: 204800,
22503
23030
  maxTokens: 131072,
@@ -22513,28 +23040,11 @@ export const MODELS = {
22513
23040
  cost: {
22514
23041
  input: 0.3,
22515
23042
  output: 1.2,
22516
- cacheRead: 0.03,
22517
- cacheWrite: 0.375,
22518
- },
22519
- contextWindow: 204800,
22520
- maxTokens: 131000,
22521
- },
22522
- "minimax/minimax-m2.5-highspeed": {
22523
- id: "minimax/minimax-m2.5-highspeed",
22524
- name: "MiniMax M2.5 High Speed",
22525
- api: "anthropic-messages",
22526
- provider: "vercel-ai-gateway",
22527
- baseUrl: "https://ai-gateway.vercel.sh",
22528
- reasoning: true,
22529
- input: ["text"],
22530
- cost: {
22531
- input: 0.6,
22532
- output: 2.4,
22533
- cacheRead: 0.03,
22534
- cacheWrite: 0.375,
23043
+ cacheRead: 0,
23044
+ cacheWrite: 0,
22535
23045
  },
22536
- contextWindow: 204800,
22537
- maxTokens: 131000,
23046
+ contextWindow: 1000000,
23047
+ maxTokens: 8192,
22538
23048
  },
22539
23049
  "minimax/minimax-m2.7": {
22540
23050
  id: "minimax/minimax-m2.7",
@@ -22545,30 +23055,13 @@ export const MODELS = {
22545
23055
  reasoning: true,
22546
23056
  input: ["text"],
22547
23057
  cost: {
22548
- input: 0.3,
22549
- output: 1.2,
22550
- cacheRead: 0.06,
22551
- cacheWrite: 0.375,
22552
- },
22553
- contextWindow: 204800,
22554
- maxTokens: 131000,
22555
- },
22556
- "minimax/minimax-m2.7-highspeed": {
22557
- id: "minimax/minimax-m2.7-highspeed",
22558
- name: "MiniMax M2.7 High Speed",
22559
- api: "anthropic-messages",
22560
- provider: "vercel-ai-gateway",
22561
- baseUrl: "https://ai-gateway.vercel.sh",
22562
- reasoning: true,
22563
- input: ["text"],
22564
- cost: {
22565
- input: 0.6,
22566
- output: 2.4,
22567
- cacheRead: 0.06,
22568
- cacheWrite: 0.375,
23058
+ input: 0.21,
23059
+ output: 0.84,
23060
+ cacheRead: 0.041999999999999996,
23061
+ cacheWrite: 0,
22569
23062
  },
22570
- contextWindow: 204800,
22571
- maxTokens: 131100,
23063
+ contextWindow: 196608,
23064
+ maxTokens: 196608,
22572
23065
  },
22573
23066
  "minimax/minimax-m3": {
22574
23067
  id: "minimax/minimax-m3",
@@ -22584,8 +23077,8 @@ export const MODELS = {
22584
23077
  cacheRead: 0.06,
22585
23078
  cacheWrite: 0,
22586
23079
  },
22587
- contextWindow: 512000,
22588
- maxTokens: 512000,
23080
+ contextWindow: 1000000,
23081
+ maxTokens: 1000000,
22589
23082
  },
22590
23083
  "minimax/minimax-m3.1-flash": {
22591
23084
  id: "minimax/minimax-m3.1-flash",
@@ -22601,8 +23094,8 @@ export const MODELS = {
22601
23094
  cacheRead: 0.015,
22602
23095
  cacheWrite: 0,
22603
23096
  },
22604
- contextWindow: 1048576,
22605
- maxTokens: 1048576,
23097
+ contextWindow: 1000000,
23098
+ maxTokens: 524288,
22606
23099
  },
22607
23100
  "mistral/codestral": {
22608
23101
  id: "mistral/codestral",
@@ -22885,13 +23378,13 @@ export const MODELS = {
22885
23378
  reasoning: true,
22886
23379
  input: ["text", "image"],
22887
23380
  cost: {
22888
- input: 4.5,
23381
+ input: 6,
22889
23382
  output: 22.5,
22890
- cacheRead: 0.44999999999999996,
23383
+ cacheRead: 0.6,
22891
23384
  cacheWrite: 0,
22892
23385
  },
22893
23386
  contextWindow: 1000000,
22894
- maxTokens: 131072,
23387
+ maxTokens: 1000000,
22895
23388
  },
22896
23389
  "moonshotai/kimi-k3.1-pro": {
22897
23390
  id: "moonshotai/kimi-k3.1-pro",
@@ -22922,28 +23415,11 @@ export const MODELS = {
22922
23415
  input: 4,
22923
23416
  output: 20,
22924
23417
  cacheRead: 0.19999999999999998,
22925
- cacheWrite: 4,
23418
+ cacheWrite: 5,
22926
23419
  },
22927
23420
  contextWindow: 1048576,
22928
23421
  maxTokens: 1048576,
22929
23422
  },
22930
- "nvidia/nemotron-3-nano-30b-a3b": {
22931
- id: "nvidia/nemotron-3-nano-30b-a3b",
22932
- name: "Nemotron 3 Nano 30B A3B",
22933
- api: "anthropic-messages",
22934
- provider: "vercel-ai-gateway",
22935
- baseUrl: "https://ai-gateway.vercel.sh",
22936
- reasoning: true,
22937
- input: ["text"],
22938
- cost: {
22939
- input: 0.049999999999999996,
22940
- output: 0.19999999999999998,
22941
- cacheRead: 0.024999999999999998,
22942
- cacheWrite: 0,
22943
- },
22944
- contextWindow: 262144,
22945
- maxTokens: 262144,
22946
- },
22947
23423
  "nvidia/nemotron-3-super-120b-a12b": {
22948
23424
  id: "nvidia/nemotron-3-super-120b-a12b",
22949
23425
  name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -24325,6 +24801,74 @@ export const MODELS = {
24325
24801
  contextWindow: 1050000,
24326
24802
  maxTokens: 128000,
24327
24803
  },
24804
+ "openai/gpt-6.2-astra": {
24805
+ id: "openai/gpt-6.2-astra",
24806
+ name: "GPT-6.2 Astra",
24807
+ api: "anthropic-messages",
24808
+ provider: "vercel-ai-gateway",
24809
+ baseUrl: "https://ai-gateway.vercel.sh",
24810
+ reasoning: true,
24811
+ input: ["text", "image"],
24812
+ cost: {
24813
+ input: 8,
24814
+ output: 40,
24815
+ cacheRead: 0.39999999999999997,
24816
+ cacheWrite: 10,
24817
+ },
24818
+ contextWindow: 1050000,
24819
+ maxTokens: 128000,
24820
+ },
24821
+ "openai/gpt-6.2-astra-fast": {
24822
+ id: "openai/gpt-6.2-astra-fast",
24823
+ name: "GPT-6.2 Astra (Fast)",
24824
+ api: "anthropic-messages",
24825
+ provider: "vercel-ai-gateway",
24826
+ baseUrl: "https://ai-gateway.vercel.sh",
24827
+ reasoning: true,
24828
+ input: ["text", "image"],
24829
+ cost: {
24830
+ input: 16,
24831
+ output: 80,
24832
+ cacheRead: 0.7999999999999999,
24833
+ cacheWrite: 20,
24834
+ },
24835
+ contextWindow: 1050000,
24836
+ maxTokens: 128000,
24837
+ },
24838
+ "openai/gpt-6.2-sol": {
24839
+ id: "openai/gpt-6.2-sol",
24840
+ name: "GPT-6.2 Sol",
24841
+ api: "anthropic-messages",
24842
+ provider: "vercel-ai-gateway",
24843
+ baseUrl: "https://ai-gateway.vercel.sh",
24844
+ reasoning: true,
24845
+ input: ["text", "image"],
24846
+ cost: {
24847
+ input: 2,
24848
+ output: 10,
24849
+ cacheRead: 0.09999999999999999,
24850
+ cacheWrite: 2.5,
24851
+ },
24852
+ contextWindow: 1050000,
24853
+ maxTokens: 128000,
24854
+ },
24855
+ "openai/gpt-6.2-sol-fast": {
24856
+ id: "openai/gpt-6.2-sol-fast",
24857
+ name: "GPT-6.2 Sol (Fast)",
24858
+ api: "anthropic-messages",
24859
+ provider: "vercel-ai-gateway",
24860
+ baseUrl: "https://ai-gateway.vercel.sh",
24861
+ reasoning: true,
24862
+ input: ["text", "image"],
24863
+ cost: {
24864
+ input: 4,
24865
+ output: 20,
24866
+ cacheRead: 0.19999999999999998,
24867
+ cacheWrite: 5,
24868
+ },
24869
+ contextWindow: 1050000,
24870
+ maxTokens: 128000,
24871
+ },
24328
24872
  "openai/gpt-oss-120b": {
24329
24873
  id: "openai/gpt-oss-120b",
24330
24874
  name: "GPT OSS 120B",
@@ -24495,38 +25039,38 @@ export const MODELS = {
24495
25039
  contextWindow: 200000,
24496
25040
  maxTokens: 100000,
24497
25041
  },
24498
- "particle/particle-1": {
24499
- id: "particle/particle-1",
24500
- name: "Particle-1",
25042
+ "paperinstruments/ultramarine-1-flash": {
25043
+ id: "paperinstruments/ultramarine-1-flash",
25044
+ name: "Ultramarine 1 Flash",
24501
25045
  api: "anthropic-messages",
24502
25046
  provider: "vercel-ai-gateway",
24503
25047
  baseUrl: "https://ai-gateway.vercel.sh",
24504
25048
  reasoning: true,
24505
25049
  input: ["text", "image"],
24506
25050
  cost: {
24507
- input: 0.125,
25051
+ input: 0.15,
24508
25052
  output: 0.5,
24509
- cacheRead: 0.015,
25053
+ cacheRead: 0.03,
24510
25054
  cacheWrite: 0,
24511
25055
  },
24512
25056
  contextWindow: 1048576,
24513
- maxTokens: 131072,
25057
+ maxTokens: 131000,
24514
25058
  },
24515
- "poolside/laguna-s-2.1": {
24516
- id: "poolside/laguna-s-2.1",
24517
- name: "Laguna S 2.1",
25059
+ "particle/particle-1": {
25060
+ id: "particle/particle-1",
25061
+ name: "Particle-1",
24518
25062
  api: "anthropic-messages",
24519
25063
  provider: "vercel-ai-gateway",
24520
25064
  baseUrl: "https://ai-gateway.vercel.sh",
24521
25065
  reasoning: true,
24522
- input: ["text"],
25066
+ input: ["text", "image"],
24523
25067
  cost: {
24524
- input: 0.09,
24525
- output: 0.18,
24526
- cacheRead: 0.009,
25068
+ input: 0.125,
25069
+ output: 0.5,
25070
+ cacheRead: 0.015,
24527
25071
  cacheWrite: 0,
24528
25072
  },
24529
- contextWindow: 1000000,
25073
+ contextWindow: 1048576,
24530
25074
  maxTokens: 131072,
24531
25075
  },
24532
25076
  "quiverai/arrow-2": {
@@ -24563,6 +25107,23 @@ export const MODELS = {
24563
25107
  contextWindow: 131072,
24564
25108
  maxTokens: 131072,
24565
25109
  },
25110
+ "recursive/flint-v1.0": {
25111
+ id: "recursive/flint-v1.0",
25112
+ name: "Flint",
25113
+ api: "anthropic-messages",
25114
+ provider: "vercel-ai-gateway",
25115
+ baseUrl: "https://ai-gateway.vercel.sh",
25116
+ reasoning: true,
25117
+ input: ["text"],
25118
+ cost: {
25119
+ input: 0,
25120
+ output: 0,
25121
+ cacheRead: 0,
25122
+ cacheWrite: 0,
25123
+ },
25124
+ contextWindow: 262144,
25125
+ maxTokens: 262144,
25126
+ },
24566
25127
  "reflection/beam": {
24567
25128
  id: "reflection/beam",
24568
25129
  name: "Beam 1.0",
@@ -24985,8 +25546,8 @@ export const MODELS = {
24985
25546
  cacheRead: 0.09999999999999999,
24986
25547
  cacheWrite: 0,
24987
25548
  },
24988
- contextWindow: 1048576,
24989
- maxTokens: 1048576,
25549
+ contextWindow: 1000000,
25550
+ maxTokens: 1000000,
24990
25551
  },
24991
25552
  "tencent/hy3": {
24992
25553
  id: "tencent/hy3",
@@ -25022,6 +25583,23 @@ export const MODELS = {
25022
25583
  contextWindow: 1024000,
25023
25584
  maxTokens: 64000,
25024
25585
  },
25586
+ "tencent/hy4-flash": {
25587
+ id: "tencent/hy4-flash",
25588
+ name: "Tencent Hy4 Flash",
25589
+ api: "anthropic-messages",
25590
+ provider: "vercel-ai-gateway",
25591
+ baseUrl: "https://ai-gateway.vercel.sh",
25592
+ reasoning: true,
25593
+ input: ["text", "image"],
25594
+ cost: {
25595
+ input: 0.035,
25596
+ output: 0.14049999999999999,
25597
+ cacheRead: 0.0015,
25598
+ cacheWrite: 0,
25599
+ },
25600
+ contextWindow: 1024000,
25601
+ maxTokens: 64000,
25602
+ },
25025
25603
  "tencent/hy4-preview": {
25026
25604
  id: "tencent/hy4-preview",
25027
25605
  name: "Tencent Hy4 Preview",
@@ -25056,6 +25634,23 @@ export const MODELS = {
25056
25634
  contextWindow: 256000,
25057
25635
  maxTokens: 256000,
25058
25636
  },
25637
+ "thinkingmachines/inkling-2-small": {
25638
+ id: "thinkingmachines/inkling-2-small",
25639
+ name: "Inkling 2 Small",
25640
+ api: "anthropic-messages",
25641
+ provider: "vercel-ai-gateway",
25642
+ baseUrl: "https://ai-gateway.vercel.sh",
25643
+ reasoning: true,
25644
+ input: ["text", "image"],
25645
+ cost: {
25646
+ input: 0.3,
25647
+ output: 1,
25648
+ cacheRead: 0.03,
25649
+ cacheWrite: 0,
25650
+ },
25651
+ contextWindow: 1048576,
25652
+ maxTokens: 262144,
25653
+ },
25059
25654
  "thinkingmachines/inkling-small": {
25060
25655
  id: "thinkingmachines/inkling-small",
25061
25656
  name: "Inkling Small",