@elyracode/ai 0.9.53 → 0.9.55

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.
@@ -3988,24 +3988,6 @@ export const MODELS = {
3988
3988
  contextWindow: 400000,
3989
3989
  maxTokens: 128000,
3990
3990
  },
3991
- "gpt-5.2-chat-latest": {
3992
- id: "gpt-5.2-chat-latest",
3993
- name: "GPT-5.2 Chat",
3994
- api: "azure-openai-responses",
3995
- provider: "azure-openai-responses",
3996
- baseUrl: "",
3997
- reasoning: true,
3998
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3999
- input: ["text", "image"],
4000
- cost: {
4001
- input: 1.75,
4002
- output: 14,
4003
- cacheRead: 0.175,
4004
- cacheWrite: 0,
4005
- },
4006
- contextWindow: 128000,
4007
- maxTokens: 16384,
4008
- },
4009
3991
  "gpt-5.2-pro": {
4010
3992
  id: "gpt-5.2-pro",
4011
3993
  name: "GPT-5.2 Pro",
@@ -4024,24 +4006,6 @@ export const MODELS = {
4024
4006
  contextWindow: 400000,
4025
4007
  maxTokens: 128000,
4026
4008
  },
4027
- "gpt-5.3-chat-latest": {
4028
- id: "gpt-5.3-chat-latest",
4029
- name: "GPT-5.3 Chat (latest)",
4030
- api: "azure-openai-responses",
4031
- provider: "azure-openai-responses",
4032
- baseUrl: "",
4033
- reasoning: false,
4034
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4035
- input: ["text", "image"],
4036
- cost: {
4037
- input: 1.75,
4038
- output: 14,
4039
- cacheRead: 0.175,
4040
- cacheWrite: 0,
4041
- },
4042
- contextWindow: 128000,
4043
- maxTokens: 16384,
4044
- },
4045
4009
  "gpt-5.3-codex": {
4046
4010
  id: "gpt-5.3-codex",
4047
4011
  name: "GPT-5.3 Codex",
@@ -5238,6 +5202,25 @@ export const MODELS = {
5238
5202
  contextWindow: 1048576,
5239
5203
  maxTokens: 1048576,
5240
5204
  },
5205
+ "@cf/deepseek-ai/deepseek-v4.1-flash-1017": {
5206
+ id: "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
5207
+ name: "Deepseek V4.1 Flash 1017",
5208
+ api: "openai-completions",
5209
+ provider: "cloudflare-workers-ai",
5210
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
5211
+ compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
5212
+ reasoning: true,
5213
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
5214
+ input: ["text", "image"],
5215
+ cost: {
5216
+ input: 0.3,
5217
+ output: 1.2,
5218
+ cacheRead: 0.006,
5219
+ cacheWrite: 0,
5220
+ },
5221
+ contextWindow: 1048576,
5222
+ maxTokens: 1048576,
5223
+ },
5241
5224
  "@cf/google/gemma-4-26b-a4b-it": {
5242
5225
  id: "@cf/google/gemma-4-26b-a4b-it",
5243
5226
  name: "Gemma 4 26B A4B IT",
@@ -5585,6 +5568,23 @@ export const MODELS = {
5585
5568
  contextWindow: 1000000,
5586
5569
  maxTokens: 384000,
5587
5570
  },
5571
+ "accounts/fireworks/models/deepseek-v4p1-flash-1017": {
5572
+ id: "accounts/fireworks/models/deepseek-v4p1-flash-1017",
5573
+ name: "DeepSeek V4.1 Flash 1017",
5574
+ api: "anthropic-messages",
5575
+ provider: "fireworks",
5576
+ baseUrl: "https://api.fireworks.ai/inference",
5577
+ reasoning: true,
5578
+ input: ["text", "image"],
5579
+ cost: {
5580
+ input: 0.3,
5581
+ output: 1.2,
5582
+ cacheRead: 0.006,
5583
+ cacheWrite: 0,
5584
+ },
5585
+ contextWindow: 1000000,
5586
+ maxTokens: 384000,
5587
+ },
5588
5588
  "accounts/fireworks/models/ember-1": {
5589
5589
  id: "accounts/fireworks/models/ember-1",
5590
5590
  name: "Ember-1",
@@ -5704,6 +5704,23 @@ export const MODELS = {
5704
5704
  contextWindow: 512000,
5705
5705
  maxTokens: 512000,
5706
5706
  },
5707
+ "accounts/fireworks/models/muse-spark-open": {
5708
+ id: "accounts/fireworks/models/muse-spark-open",
5709
+ name: "Muse Spark Open",
5710
+ api: "anthropic-messages",
5711
+ provider: "fireworks",
5712
+ baseUrl: "https://api.fireworks.ai/inference",
5713
+ reasoning: true,
5714
+ input: ["text", "image"],
5715
+ cost: {
5716
+ input: 1.25,
5717
+ output: 4.25,
5718
+ cacheRead: 0.15,
5719
+ cacheWrite: 0,
5720
+ },
5721
+ contextWindow: 1048576,
5722
+ maxTokens: 131072,
5723
+ },
5707
5724
  "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5708
5725
  id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5709
5726
  name: "Nemotron 3 Ultra 550B A55B",
@@ -6230,6 +6247,25 @@ export const MODELS = {
6230
6247
  contextWindow: 1000000,
6231
6248
  maxTokens: 64000,
6232
6249
  },
6250
+ "gemini-4-argon": {
6251
+ id: "gemini-4-argon",
6252
+ name: "Gemini 4 Argon",
6253
+ api: "openai-completions",
6254
+ provider: "github-copilot",
6255
+ baseUrl: "https://api.individual.githubcopilot.com",
6256
+ 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" },
6257
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6258
+ reasoning: true,
6259
+ input: ["text", "image"],
6260
+ cost: {
6261
+ input: 2,
6262
+ output: 10,
6263
+ cacheRead: 0.1,
6264
+ cacheWrite: 0,
6265
+ },
6266
+ contextWindow: 1048576,
6267
+ maxTokens: 65536,
6268
+ },
6233
6269
  "gpt-5-mini": {
6234
6270
  id: "gpt-5-mini",
6235
6271
  name: "GPT-5 Mini",
@@ -6984,6 +7020,24 @@ export const MODELS = {
6984
7020
  contextWindow: 1048576,
6985
7021
  maxTokens: 65536,
6986
7022
  },
7023
+ "gemini-pro-latest": {
7024
+ id: "gemini-pro-latest",
7025
+ name: "Gemini Pro Latest",
7026
+ api: "google-generative-ai",
7027
+ provider: "google",
7028
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
7029
+ reasoning: true,
7030
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7031
+ input: ["text", "image"],
7032
+ cost: {
7033
+ input: 2,
7034
+ output: 12,
7035
+ cacheRead: 0.2,
7036
+ cacheWrite: 0,
7037
+ },
7038
+ contextWindow: 1048576,
7039
+ maxTokens: 65536,
7040
+ },
6987
7041
  "gemma-4-26b-a4b-it": {
6988
7042
  id: "gemma-4-26b-a4b-it",
6989
7043
  name: "Gemma 4 26B A4B IT",
@@ -7692,7 +7746,7 @@ export const MODELS = {
7692
7746
  cacheWrite: 0,
7693
7747
  },
7694
7748
  contextWindow: 262144,
7695
- maxTokens: 131072,
7749
+ maxTokens: 81920,
7696
7750
  },
7697
7751
  "Qwen/Qwen3-30B-A3B": {
7698
7752
  id: "Qwen/Qwen3-30B-A3B",
@@ -7764,7 +7818,7 @@ export const MODELS = {
7764
7818
  cacheWrite: 0,
7765
7819
  },
7766
7820
  contextWindow: 262144,
7767
- maxTokens: 66536,
7821
+ maxTokens: 65536,
7768
7822
  },
7769
7823
  "Qwen/Qwen3-Coder-Next": {
7770
7824
  id: "Qwen/Qwen3-Coder-Next",
@@ -7800,7 +7854,7 @@ export const MODELS = {
7800
7854
  cacheWrite: 0,
7801
7855
  },
7802
7856
  contextWindow: 262144,
7803
- maxTokens: 66536,
7857
+ maxTokens: 32768,
7804
7858
  },
7805
7859
  "Qwen/Qwen3-Next-80B-A3B-Thinking": {
7806
7860
  id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
@@ -7809,7 +7863,7 @@ export const MODELS = {
7809
7863
  provider: "huggingface",
7810
7864
  baseUrl: "https://router.huggingface.co/v1",
7811
7865
  compat: { "supportsDeveloperRole": false },
7812
- reasoning: false,
7866
+ reasoning: true,
7813
7867
  input: ["text"],
7814
7868
  cost: {
7815
7869
  input: 0.3,
@@ -7818,7 +7872,7 @@ export const MODELS = {
7818
7872
  cacheWrite: 0,
7819
7873
  },
7820
7874
  contextWindow: 262144,
7821
- maxTokens: 131072,
7875
+ maxTokens: 32768,
7822
7876
  },
7823
7877
  "Qwen/Qwen3-VL-235B-A22B-Instruct": {
7824
7878
  id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
@@ -8106,7 +8160,7 @@ export const MODELS = {
8106
8160
  cacheWrite: 0,
8107
8161
  },
8108
8162
  contextWindow: 163840,
8109
- maxTokens: 163840,
8163
+ maxTokens: 32768,
8110
8164
  },
8111
8165
  "deepseek-ai/DeepSeek-V3": {
8112
8166
  id: "deepseek-ai/DeepSeek-V3",
@@ -8288,6 +8342,24 @@ export const MODELS = {
8288
8342
  contextWindow: 1048576,
8289
8343
  maxTokens: 384000,
8290
8344
  },
8345
+ "deepseek-ai/DeepSeek-V4.1-Flash-1017": {
8346
+ id: "deepseek-ai/DeepSeek-V4.1-Flash-1017",
8347
+ name: "DeepSeek V4.1 Flash 1017",
8348
+ api: "openai-completions",
8349
+ provider: "huggingface",
8350
+ baseUrl: "https://router.huggingface.co/v1",
8351
+ compat: { "supportsDeveloperRole": false },
8352
+ reasoning: true,
8353
+ input: ["text", "image"],
8354
+ cost: {
8355
+ input: 0.3,
8356
+ output: 1.2,
8357
+ cacheRead: 0,
8358
+ cacheWrite: 0,
8359
+ },
8360
+ contextWindow: 1048576,
8361
+ maxTokens: 384000,
8362
+ },
8291
8363
  "google/gemma-3-12b-it": {
8292
8364
  id: "google/gemma-3-12b-it",
8293
8365
  name: "Gemma 3 12B IT",
@@ -8940,7 +9012,7 @@ export const MODELS = {
8940
9012
  },
8941
9013
  "kimi-for-coding": {
8942
9014
  id: "kimi-for-coding",
8943
- name: "kimi-for-coding",
9015
+ name: "Kimi K2.8 Preview",
8944
9016
  api: "anthropic-messages",
8945
9017
  provider: "kimi-coding",
8946
9018
  baseUrl: "https://api.kimi.com/coding",
@@ -9025,7 +9097,7 @@ export const MODELS = {
9025
9097
  cacheWrite: 0,
9026
9098
  },
9027
9099
  contextWindow: 1000000,
9028
- maxTokens: 512000,
9100
+ maxTokens: 524288,
9029
9101
  },
9030
9102
  },
9031
9103
  "minimax-cn": {
@@ -9038,10 +9110,10 @@ export const MODELS = {
9038
9110
  reasoning: true,
9039
9111
  input: ["text"],
9040
9112
  cost: {
9041
- input: 0.3,
9042
- output: 1.2,
9043
- cacheRead: 0.06,
9044
- cacheWrite: 0.375,
9113
+ input: 0.3137,
9114
+ output: 1.2549,
9115
+ cacheRead: 0.0627,
9116
+ cacheWrite: 0.3922,
9045
9117
  },
9046
9118
  contextWindow: 204800,
9047
9119
  maxTokens: 131072,
@@ -9055,10 +9127,10 @@ export const MODELS = {
9055
9127
  reasoning: true,
9056
9128
  input: ["text"],
9057
9129
  cost: {
9058
- input: 0.6,
9059
- output: 2.4,
9060
- cacheRead: 0.06,
9061
- cacheWrite: 0.375,
9130
+ input: 0.6275,
9131
+ output: 2.5098,
9132
+ cacheRead: 0.0627,
9133
+ cacheWrite: 0.3922,
9062
9134
  },
9063
9135
  contextWindow: 204800,
9064
9136
  maxTokens: 131072,
@@ -9072,13 +9144,13 @@ export const MODELS = {
9072
9144
  reasoning: true,
9073
9145
  input: ["text", "image"],
9074
9146
  cost: {
9075
- input: 0.3,
9076
- output: 1.2,
9077
- cacheRead: 0.06,
9147
+ input: 0.3137,
9148
+ output: 1.2549,
9149
+ cacheRead: 0.0627,
9078
9150
  cacheWrite: 0,
9079
9151
  },
9080
9152
  contextWindow: 1000000,
9081
- maxTokens: 512000,
9153
+ maxTokens: 524288,
9082
9154
  },
9083
9155
  },
9084
9156
  "mistral": {
@@ -9329,9 +9401,9 @@ export const MODELS = {
9329
9401
  reasoning: false,
9330
9402
  input: ["text", "image"],
9331
9403
  cost: {
9332
- input: 0.04,
9333
- output: 0.04,
9334
- cacheRead: 0,
9404
+ input: 0.1,
9405
+ output: 0.1,
9406
+ cacheRead: 0.01,
9335
9407
  cacheWrite: 0,
9336
9408
  },
9337
9409
  contextWindow: 131072,
@@ -9363,9 +9435,9 @@ export const MODELS = {
9363
9435
  reasoning: false,
9364
9436
  input: ["text", "image"],
9365
9437
  cost: {
9366
- input: 0.1,
9367
- output: 0.1,
9368
- cacheRead: 0,
9438
+ input: 0.15,
9439
+ output: 0.15,
9440
+ cacheRead: 0.015,
9369
9441
  cacheWrite: 0,
9370
9442
  },
9371
9443
  contextWindow: 262144,
@@ -9592,23 +9664,6 @@ export const MODELS = {
9592
9664
  contextWindow: 262144,
9593
9665
  maxTokens: 256000,
9594
9666
  },
9595
- "open-mistral-7b": {
9596
- id: "open-mistral-7b",
9597
- name: "Mistral 7B",
9598
- api: "mistral-conversations",
9599
- provider: "mistral",
9600
- baseUrl: "https://api.mistral.ai",
9601
- reasoning: false,
9602
- input: ["text"],
9603
- cost: {
9604
- input: 0.25,
9605
- output: 0.25,
9606
- cacheRead: 0,
9607
- cacheWrite: 0,
9608
- },
9609
- contextWindow: 8000,
9610
- maxTokens: 8000,
9611
- },
9612
9667
  "open-mistral-nemo": {
9613
9668
  id: "open-mistral-nemo",
9614
9669
  name: "Open Mistral Nemo",
@@ -9626,40 +9681,6 @@ export const MODELS = {
9626
9681
  contextWindow: 128000,
9627
9682
  maxTokens: 128000,
9628
9683
  },
9629
- "open-mixtral-8x22b": {
9630
- id: "open-mixtral-8x22b",
9631
- name: "Mixtral 8x22B",
9632
- api: "mistral-conversations",
9633
- provider: "mistral",
9634
- baseUrl: "https://api.mistral.ai",
9635
- reasoning: false,
9636
- input: ["text"],
9637
- cost: {
9638
- input: 2,
9639
- output: 6,
9640
- cacheRead: 0,
9641
- cacheWrite: 0,
9642
- },
9643
- contextWindow: 64000,
9644
- maxTokens: 64000,
9645
- },
9646
- "open-mixtral-8x7b": {
9647
- id: "open-mixtral-8x7b",
9648
- name: "Mixtral 8x7B",
9649
- api: "mistral-conversations",
9650
- provider: "mistral",
9651
- baseUrl: "https://api.mistral.ai",
9652
- reasoning: false,
9653
- input: ["text"],
9654
- cost: {
9655
- input: 0.7,
9656
- output: 0.7,
9657
- cacheRead: 0,
9658
- cacheWrite: 0,
9659
- },
9660
- contextWindow: 32000,
9661
- maxTokens: 32000,
9662
- },
9663
9684
  "pixtral-12b": {
9664
9685
  id: "pixtral-12b",
9665
9686
  name: "Pixtral 12B",
@@ -9721,7 +9742,7 @@ export const MODELS = {
9721
9742
  input: ["text"],
9722
9743
  cost: {
9723
9744
  input: 0.1,
9724
- output: 0.3,
9745
+ output: 0.4,
9725
9746
  cacheRead: 0,
9726
9747
  cacheWrite: 0,
9727
9748
  },
@@ -9848,9 +9869,9 @@ export const MODELS = {
9848
9869
  reasoning: true,
9849
9870
  input: ["text", "image"],
9850
9871
  cost: {
9851
- input: 0.95,
9852
- output: 4,
9853
- cacheRead: 0.16,
9872
+ input: 0.9711,
9873
+ output: 4.0337,
9874
+ cacheRead: 0.1643,
9854
9875
  cacheWrite: 0,
9855
9876
  },
9856
9877
  contextWindow: 262144,
@@ -9866,9 +9887,9 @@ export const MODELS = {
9866
9887
  reasoning: true,
9867
9888
  input: ["text", "image"],
9868
9889
  cost: {
9869
- input: 0.95,
9870
- output: 4,
9871
- cacheRead: 0.19,
9890
+ input: 0.9711,
9891
+ output: 4.0337,
9892
+ cacheRead: 0.1942,
9872
9893
  cacheWrite: 0,
9873
9894
  },
9874
9895
  contextWindow: 262144,
@@ -9884,9 +9905,9 @@ export const MODELS = {
9884
9905
  reasoning: true,
9885
9906
  input: ["text", "image"],
9886
9907
  cost: {
9887
- input: 1.9,
9888
- output: 8,
9889
- cacheRead: 0.38,
9908
+ input: 1.9421,
9909
+ output: 8.0673,
9910
+ cacheRead: 0.3884,
9890
9911
  cacheWrite: 0,
9891
9912
  },
9892
9913
  contextWindow: 262144,
@@ -9902,10 +9923,10 @@ export const MODELS = {
9902
9923
  reasoning: true,
9903
9924
  input: ["text", "image"],
9904
9925
  cost: {
9905
- input: 3,
9906
- output: 15,
9907
- cacheRead: 0.3,
9908
- cacheWrite: 3,
9926
+ input: 2.9879,
9927
+ output: 14.9395,
9928
+ cacheRead: 0.2988,
9929
+ cacheWrite: 2.9879,
9909
9930
  },
9910
9931
  contextWindow: 1048576,
9911
9932
  maxTokens: 1048576,
@@ -10176,24 +10197,6 @@ export const MODELS = {
10176
10197
  contextWindow: 400000,
10177
10198
  maxTokens: 128000,
10178
10199
  },
10179
- "gpt-5.2-chat-latest": {
10180
- id: "gpt-5.2-chat-latest",
10181
- name: "GPT-5.2 Chat",
10182
- api: "openai-responses",
10183
- provider: "openai",
10184
- baseUrl: "https://api.openai.com/v1",
10185
- reasoning: true,
10186
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10187
- input: ["text", "image"],
10188
- cost: {
10189
- input: 1.75,
10190
- output: 14,
10191
- cacheRead: 0.175,
10192
- cacheWrite: 0,
10193
- },
10194
- contextWindow: 128000,
10195
- maxTokens: 16384,
10196
- },
10197
10200
  "gpt-5.2-pro": {
10198
10201
  id: "gpt-5.2-pro",
10199
10202
  name: "GPT-5.2 Pro",
@@ -10212,24 +10215,6 @@ export const MODELS = {
10212
10215
  contextWindow: 400000,
10213
10216
  maxTokens: 128000,
10214
10217
  },
10215
- "gpt-5.3-chat-latest": {
10216
- id: "gpt-5.3-chat-latest",
10217
- name: "GPT-5.3 Chat (latest)",
10218
- api: "openai-responses",
10219
- provider: "openai",
10220
- baseUrl: "https://api.openai.com/v1",
10221
- reasoning: false,
10222
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10223
- input: ["text", "image"],
10224
- cost: {
10225
- input: 1.75,
10226
- output: 14,
10227
- cacheRead: 0.175,
10228
- cacheWrite: 0,
10229
- },
10230
- contextWindow: 128000,
10231
- maxTokens: 16384,
10232
- },
10233
10218
  "gpt-5.3-codex": {
10234
10219
  id: "gpt-5.3-codex",
10235
10220
  name: "GPT-5.3 Codex",
@@ -10849,9 +10834,9 @@ export const MODELS = {
10849
10834
  },
10850
10835
  },
10851
10836
  "opencode": {
10852
- "big-pickle": {
10853
- id: "big-pickle",
10854
- name: "Big Pickle",
10837
+ "beam-free": {
10838
+ id: "beam-free",
10839
+ name: "Beam Free",
10855
10840
  api: "openai-completions",
10856
10841
  provider: "opencode",
10857
10842
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10863,12 +10848,12 @@ export const MODELS = {
10863
10848
  cacheRead: 0,
10864
10849
  cacheWrite: 0,
10865
10850
  },
10866
- contextWindow: 200000,
10867
- maxTokens: 32000,
10851
+ contextWindow: 1048576,
10852
+ maxTokens: 131072,
10868
10853
  },
10869
- "cat-jam-free": {
10870
- id: "cat-jam-free",
10871
- name: "Cat Jam Free",
10854
+ "big-pickle": {
10855
+ id: "big-pickle",
10856
+ name: "Big Pickle",
10872
10857
  api: "openai-completions",
10873
10858
  provider: "opencode",
10874
10859
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10880,8 +10865,8 @@ export const MODELS = {
10880
10865
  cacheRead: 0,
10881
10866
  cacheWrite: 0,
10882
10867
  },
10883
- contextWindow: 262144,
10884
- maxTokens: 131072,
10868
+ contextWindow: 200000,
10869
+ maxTokens: 32000,
10885
10870
  },
10886
10871
  "claude-fable-5": {
10887
10872
  id: "claude-fable-5",
@@ -11219,13 +11204,15 @@ export const MODELS = {
11219
11204
  contextWindow: 1000000,
11220
11205
  maxTokens: 384000,
11221
11206
  },
11222
- "exo-free": {
11223
- id: "exo-free",
11224
- name: "Exo Free",
11207
+ "deepseek-v4.1-flash-free": {
11208
+ id: "deepseek-v4.1-flash-free",
11209
+ name: "DeepSeek V4.1 Flash Free",
11225
11210
  api: "openai-completions",
11226
11211
  provider: "opencode",
11227
11212
  baseUrl: "https://opencode.ai/zen/v1",
11213
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11228
11214
  reasoning: true,
11215
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11229
11216
  input: ["text", "image"],
11230
11217
  cost: {
11231
11218
  input: 0,
@@ -11233,8 +11220,8 @@ export const MODELS = {
11233
11220
  cacheRead: 0,
11234
11221
  cacheWrite: 0,
11235
11222
  },
11236
- contextWindow: 1048576,
11237
- maxTokens: 131072,
11223
+ contextWindow: 200000,
11224
+ maxTokens: 32000,
11238
11225
  },
11239
11226
  "gemini-3-flash": {
11240
11227
  id: "gemini-3-flash",
@@ -11464,6 +11451,23 @@ export const MODELS = {
11464
11451
  contextWindow: 1000000,
11465
11452
  maxTokens: 131072,
11466
11453
  },
11454
+ "glm-5.3-flash-free": {
11455
+ id: "glm-5.3-flash-free",
11456
+ name: "GLM-5.3-Flash Free",
11457
+ api: "openai-completions",
11458
+ provider: "opencode",
11459
+ baseUrl: "https://opencode.ai/zen/v1",
11460
+ reasoning: true,
11461
+ input: ["text", "image"],
11462
+ cost: {
11463
+ input: 0,
11464
+ output: 0,
11465
+ cacheRead: 0,
11466
+ cacheWrite: 0,
11467
+ },
11468
+ contextWindow: 200000,
11469
+ maxTokens: 32000,
11470
+ },
11467
11471
  "gpt-5": {
11468
11472
  id: "gpt-5",
11469
11473
  name: "GPT-5",
@@ -12010,40 +12014,6 @@ export const MODELS = {
12010
12014
  contextWindow: 1048576,
12011
12015
  maxTokens: 131072,
12012
12016
  },
12013
- "ling-3.0-flash-fin-free": {
12014
- id: "ling-3.0-flash-fin-free",
12015
- name: "Ling 3.0 Flash Fin Free",
12016
- api: "openai-completions",
12017
- provider: "opencode",
12018
- baseUrl: "https://opencode.ai/zen/v1",
12019
- reasoning: true,
12020
- input: ["text"],
12021
- cost: {
12022
- input: 0,
12023
- output: 0,
12024
- cacheRead: 0,
12025
- cacheWrite: 0,
12026
- },
12027
- contextWindow: 262144,
12028
- maxTokens: 32768,
12029
- },
12030
- "ling-3.1-flash-free": {
12031
- id: "ling-3.1-flash-free",
12032
- name: "Ling 3.1 Flash Free",
12033
- api: "openai-completions",
12034
- provider: "opencode",
12035
- baseUrl: "https://opencode.ai/zen/v1",
12036
- reasoning: true,
12037
- input: ["text"],
12038
- cost: {
12039
- input: 0,
12040
- output: 0,
12041
- cacheRead: 0,
12042
- cacheWrite: 0,
12043
- },
12044
- contextWindow: 262144,
12045
- maxTokens: 32768,
12046
- },
12047
12017
  "longcat-2.5-preview-free": {
12048
12018
  id: "longcat-2.5-preview-free",
12049
12019
  name: "LongCat 2.5 Preview Free",
@@ -12129,6 +12099,23 @@ export const MODELS = {
12129
12099
  contextWindow: 512000,
12130
12100
  maxTokens: 128000,
12131
12101
  },
12102
+ "minimax-m3.1-flash-free": {
12103
+ id: "minimax-m3.1-flash-free",
12104
+ name: "MiniMax M3.1 Flash Free",
12105
+ api: "openai-completions",
12106
+ provider: "opencode",
12107
+ baseUrl: "https://opencode.ai/zen/v1",
12108
+ reasoning: true,
12109
+ input: ["text", "image"],
12110
+ cost: {
12111
+ input: 0,
12112
+ output: 0,
12113
+ cacheRead: 0,
12114
+ cacheWrite: 0,
12115
+ },
12116
+ contextWindow: 1000000,
12117
+ maxTokens: 512000,
12118
+ },
12132
12119
  "mistral-large-4": {
12133
12120
  id: "mistral-large-4",
12134
12121
  name: "Mistral Large 4",
@@ -12180,18 +12167,18 @@ export const MODELS = {
12180
12167
  contextWindow: 1048576,
12181
12168
  maxTokens: 131072,
12182
12169
  },
12183
- "muse-spark-1.3-contributor-free": {
12184
- id: "muse-spark-1.3-contributor-free",
12185
- name: "Muse Spark 1.3 Free",
12170
+ "muse-wonder-1.0": {
12171
+ id: "muse-wonder-1.0",
12172
+ name: "Muse Wonder",
12186
12173
  api: "openai-responses",
12187
12174
  provider: "opencode",
12188
12175
  baseUrl: "https://opencode.ai/zen/v1",
12189
12176
  reasoning: true,
12190
12177
  input: ["text", "image"],
12191
12178
  cost: {
12192
- input: 0,
12193
- output: 0,
12194
- cacheRead: 0,
12179
+ input: 4,
12180
+ output: 20,
12181
+ cacheRead: 0.2,
12195
12182
  cacheWrite: 0,
12196
12183
  },
12197
12184
  contextWindow: 1048576,
@@ -12231,6 +12218,23 @@ export const MODELS = {
12231
12218
  contextWindow: 262144,
12232
12219
  maxTokens: 262144,
12233
12220
  },
12221
+ "nemotron-3.5-super-vl-free": {
12222
+ id: "nemotron-3.5-super-vl-free",
12223
+ name: "Nemotron 3.5 Super VL Free",
12224
+ api: "openai-completions",
12225
+ provider: "opencode",
12226
+ baseUrl: "https://opencode.ai/zen/v1",
12227
+ reasoning: true,
12228
+ input: ["text", "image"],
12229
+ cost: {
12230
+ input: 0,
12231
+ output: 0,
12232
+ cacheRead: 0,
12233
+ cacheWrite: 0,
12234
+ },
12235
+ contextWindow: 1048576,
12236
+ maxTokens: 131072,
12237
+ },
12234
12238
  "qwen3.5-plus": {
12235
12239
  id: "qwen3.5-plus",
12236
12240
  name: "Qwen3.5 Plus",
@@ -12299,45 +12303,11 @@ export const MODELS = {
12299
12303
  contextWindow: 262144,
12300
12304
  maxTokens: 131072,
12301
12305
  },
12302
- "space-bunny-free": {
12303
- id: "space-bunny-free",
12304
- name: "Space Bunny 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: 1048576,
12317
- maxTokens: 524288,
12318
- },
12319
- "step-5-preview-free": {
12320
- id: "step-5-preview-free",
12321
- name: "Step 5 Preview Free",
12322
- api: "openai-completions",
12323
- provider: "opencode",
12324
- baseUrl: "https://opencode.ai/zen/v1",
12325
- reasoning: true,
12326
- input: ["text", "image"],
12327
- cost: {
12328
- input: 0,
12329
- output: 0,
12330
- cacheRead: 0,
12331
- cacheWrite: 0,
12332
- },
12333
- contextWindow: 1000000,
12334
- maxTokens: 65536,
12335
- },
12336
12306
  },
12337
12307
  "opencode-go": {
12338
- "cat-jam-free": {
12339
- id: "cat-jam-free",
12340
- name: "Cat Jam Free",
12308
+ "beam-free": {
12309
+ id: "beam-free",
12310
+ name: "Beam Free",
12341
12311
  api: "openai-completions",
12342
12312
  provider: "opencode-go",
12343
12313
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12349,7 +12319,7 @@ export const MODELS = {
12349
12319
  cacheRead: 0,
12350
12320
  cacheWrite: 0,
12351
12321
  },
12352
- contextWindow: 262144,
12322
+ contextWindow: 1048576,
12353
12323
  maxTokens: 131072,
12354
12324
  },
12355
12325
  "claude-haiku-5-5": {
@@ -12369,44 +12339,6 @@ export const MODELS = {
12369
12339
  contextWindow: 1000000,
12370
12340
  maxTokens: 128000,
12371
12341
  },
12372
- "deepseek-v4-flash": {
12373
- id: "deepseek-v4-flash",
12374
- name: "DeepSeek V4 Flash",
12375
- api: "openai-completions",
12376
- provider: "opencode-go",
12377
- baseUrl: "https://opencode.ai/zen/go/v1",
12378
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12379
- reasoning: true,
12380
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12381
- input: ["text"],
12382
- cost: {
12383
- input: 0.15,
12384
- output: 0.6,
12385
- cacheRead: 0.003,
12386
- cacheWrite: 0,
12387
- },
12388
- contextWindow: 1000000,
12389
- maxTokens: 384000,
12390
- },
12391
- "deepseek-v4-flash-vision-exp": {
12392
- id: "deepseek-v4-flash-vision-exp",
12393
- name: "DeepSeek V4 Flash Vision Exp",
12394
- api: "openai-completions",
12395
- provider: "opencode-go",
12396
- baseUrl: "https://opencode.ai/zen/go/v1",
12397
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12398
- reasoning: true,
12399
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12400
- input: ["text", "image"],
12401
- cost: {
12402
- input: 0.15,
12403
- output: 0.6,
12404
- cacheRead: 0.003,
12405
- cacheWrite: 0,
12406
- },
12407
- contextWindow: 1000000,
12408
- maxTokens: 384000,
12409
- },
12410
12342
  "deepseek-v4-pro": {
12411
12343
  id: "deepseek-v4-pro",
12412
12344
  name: "DeepSeek V4 Pro (New)",
@@ -12445,6 +12377,23 @@ export const MODELS = {
12445
12377
  contextWindow: 1000000,
12446
12378
  maxTokens: 384000,
12447
12379
  },
12380
+ "gemini-4-argon-contributor": {
12381
+ id: "gemini-4-argon-contributor",
12382
+ name: "Gemini 4 Argon Contributor",
12383
+ api: "google-generative-ai",
12384
+ provider: "opencode-go",
12385
+ baseUrl: "https://opencode.ai/zen/go/v1",
12386
+ reasoning: true,
12387
+ input: ["text", "image"],
12388
+ cost: {
12389
+ input: 4,
12390
+ output: 20,
12391
+ cacheRead: 0.2,
12392
+ cacheWrite: 0,
12393
+ },
12394
+ contextWindow: 1048576,
12395
+ maxTokens: 65536,
12396
+ },
12448
12397
  "glm-5.2": {
12449
12398
  id: "glm-5.2",
12450
12399
  name: "GLM-5.2",
@@ -12531,23 +12480,6 @@ export const MODELS = {
12531
12480
  contextWindow: 1050000,
12532
12481
  maxTokens: 128000,
12533
12482
  },
12534
- "grok-4.6": {
12535
- id: "grok-4.6",
12536
- name: "Grok 4.6",
12537
- api: "openai-responses",
12538
- provider: "opencode-go",
12539
- baseUrl: "https://opencode.ai/zen/go/v1",
12540
- reasoning: true,
12541
- input: ["text", "image"],
12542
- cost: {
12543
- input: 2,
12544
- output: 6,
12545
- cacheRead: 0.5,
12546
- cacheWrite: 0,
12547
- },
12548
- contextWindow: 500000,
12549
- maxTokens: 500000,
12550
- },
12551
12483
  "grok-4.7": {
12552
12484
  id: "grok-4.7",
12553
12485
  name: "Grok 4.7",
@@ -12735,23 +12667,6 @@ export const MODELS = {
12735
12667
  contextWindow: 1048576,
12736
12668
  maxTokens: 131072,
12737
12669
  },
12738
- "minimax-m2.7": {
12739
- id: "minimax-m2.7",
12740
- name: "MiniMax-M2.7",
12741
- api: "openai-completions",
12742
- provider: "opencode-go",
12743
- baseUrl: "https://opencode.ai/zen/go/v1",
12744
- reasoning: true,
12745
- input: ["text"],
12746
- cost: {
12747
- input: 0.3,
12748
- output: 1.2,
12749
- cacheRead: 0.06,
12750
- cacheWrite: 0.375,
12751
- },
12752
- contextWindow: 204800,
12753
- maxTokens: 131072,
12754
- },
12755
12670
  "minimax-m3": {
12756
12671
  id: "minimax-m3",
12757
12672
  name: "MiniMax-M3",
@@ -12769,6 +12684,23 @@ export const MODELS = {
12769
12684
  contextWindow: 1000000,
12770
12685
  maxTokens: 131072,
12771
12686
  },
12687
+ "minimax-m3.1-flash-free": {
12688
+ id: "minimax-m3.1-flash-free",
12689
+ name: "MiniMax M3.1 Flash Free",
12690
+ api: "openai-completions",
12691
+ provider: "opencode-go",
12692
+ baseUrl: "https://opencode.ai/zen/go/v1",
12693
+ reasoning: true,
12694
+ input: ["text", "image"],
12695
+ cost: {
12696
+ input: 0,
12697
+ output: 0,
12698
+ cacheRead: 0,
12699
+ cacheWrite: 0,
12700
+ },
12701
+ contextWindow: 1000000,
12702
+ maxTokens: 512000,
12703
+ },
12772
12704
  "muse-spark-1.2-contributor": {
12773
12705
  id: "muse-spark-1.2-contributor",
12774
12706
  name: "Muse Spark 1.2 Contributor",
@@ -12854,35 +12786,18 @@ export const MODELS = {
12854
12786
  contextWindow: 1000000,
12855
12787
  maxTokens: 131072,
12856
12788
  },
12857
- "space-bunny": {
12858
- id: "space-bunny",
12859
- name: "Space Bunny",
12860
- api: "openai-completions",
12861
- provider: "opencode-go",
12862
- baseUrl: "https://opencode.ai/zen/go/v1",
12863
- reasoning: true,
12864
- input: ["text", "image"],
12865
- cost: {
12866
- input: 0.15,
12867
- output: 0.6,
12868
- cacheRead: 0.03,
12869
- cacheWrite: 0,
12870
- },
12871
- contextWindow: 1048576,
12872
- maxTokens: 524288,
12873
- },
12874
- "step-5-preview-free": {
12875
- id: "step-5-preview-free",
12876
- name: "Step 5 Preview Free",
12789
+ "step-5-preview": {
12790
+ id: "step-5-preview",
12791
+ name: "Step 5 Preview",
12877
12792
  api: "openai-completions",
12878
12793
  provider: "opencode-go",
12879
12794
  baseUrl: "https://opencode.ai/zen/go/v1",
12880
12795
  reasoning: true,
12881
12796
  input: ["text", "image"],
12882
12797
  cost: {
12883
- input: 0,
12884
- output: 0,
12885
- cacheRead: 0,
12798
+ input: 1,
12799
+ output: 2.7,
12800
+ cacheRead: 0.1,
12886
12801
  cacheWrite: 0,
12887
12802
  },
12888
12803
  contextWindow: 1000000,
@@ -13444,23 +13359,6 @@ export const MODELS = {
13444
13359
  contextWindow: 1000000,
13445
13360
  maxTokens: 128000,
13446
13361
  },
13447
- "anthropic/claude-sonnet-4": {
13448
- id: "anthropic/claude-sonnet-4",
13449
- name: "Anthropic: Claude Sonnet 4",
13450
- api: "openai-completions",
13451
- provider: "openrouter",
13452
- baseUrl: "https://openrouter.ai/api/v1",
13453
- reasoning: true,
13454
- input: ["text", "image"],
13455
- cost: {
13456
- input: 3,
13457
- output: 15,
13458
- cacheRead: 0.3,
13459
- cacheWrite: 3.75,
13460
- },
13461
- contextWindow: 200000,
13462
- maxTokens: 64000,
13463
- },
13464
13362
  "anthropic/claude-sonnet-4.5": {
13465
13363
  id: "anthropic/claude-sonnet-4.5",
13466
13364
  name: "Anthropic: Claude Sonnet 4.5",
@@ -13810,13 +13708,13 @@ export const MODELS = {
13810
13708
  reasoning: false,
13811
13709
  input: ["text"],
13812
13710
  cost: {
13813
- input: 0.32,
13814
- output: 0.8899999999999999,
13711
+ input: 0.2574,
13712
+ output: 1.0287,
13815
13713
  cacheRead: 0,
13816
13714
  cacheWrite: 0,
13817
13715
  },
13818
13716
  contextWindow: 163840,
13819
- maxTokens: 16384,
13717
+ maxTokens: 16000,
13820
13718
  },
13821
13719
  "deepseek/deepseek-chat-v3-0324": {
13822
13720
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13852,23 +13750,6 @@ export const MODELS = {
13852
13750
  contextWindow: 163840,
13853
13751
  maxTokens: 32768,
13854
13752
  },
13855
- "deepseek/deepseek-r1": {
13856
- id: "deepseek/deepseek-r1",
13857
- name: "DeepSeek: R1",
13858
- api: "openai-completions",
13859
- provider: "openrouter",
13860
- baseUrl: "https://openrouter.ai/api/v1",
13861
- reasoning: true,
13862
- input: ["text"],
13863
- cost: {
13864
- input: 0.7,
13865
- output: 2.5,
13866
- cacheRead: 0,
13867
- cacheWrite: 0,
13868
- },
13869
- contextWindow: 64000,
13870
- maxTokens: 16000,
13871
- },
13872
13753
  "deepseek/deepseek-r1-0528": {
13873
13754
  id: "deepseek/deepseek-r1-0528",
13874
13755
  name: "DeepSeek: R1 0528",
@@ -13912,13 +13793,13 @@ export const MODELS = {
13912
13793
  reasoning: true,
13913
13794
  input: ["text"],
13914
13795
  cost: {
13915
- input: 0.25899999999999995,
13916
- output: 0.7999999999999999,
13917
- cacheRead: 0.14,
13796
+ input: 0.28,
13797
+ output: 0.42,
13798
+ cacheRead: 0.028,
13918
13799
  cacheWrite: 0,
13919
13800
  },
13920
13801
  contextWindow: 163840,
13921
- maxTokens: 147456,
13802
+ maxTokens: 65536,
13922
13803
  },
13923
13804
  "deepseek/deepseek-v3.2-exp": {
13924
13805
  id: "deepseek/deepseek-v3.2-exp",
@@ -13967,13 +13848,13 @@ export const MODELS = {
13967
13848
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13968
13849
  input: ["text"],
13969
13850
  cost: {
13970
- input: 0.016,
13971
- output: 0.64,
13972
- cacheRead: 0.016,
13851
+ input: 0.44,
13852
+ output: 1.32,
13853
+ cacheRead: 0.014,
13973
13854
  cacheWrite: 0,
13974
13855
  },
13975
13856
  contextWindow: 1048576,
13976
- maxTokens: 943718,
13857
+ maxTokens: 131072,
13977
13858
  },
13978
13859
  "deepseek/deepseek-v4-flash-vision-exp": {
13979
13860
  id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -14005,9 +13886,9 @@ export const MODELS = {
14005
13886
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14006
13887
  input: ["text"],
14007
13888
  cost: {
14008
- input: 0.40716,
14009
- output: 0.81432,
14010
- cacheRead: 0.03393,
13889
+ input: 0.9552599999999999,
13890
+ output: 1.9105199999999998,
13891
+ cacheRead: 0.07960500000000001,
14011
13892
  cacheWrite: 0,
14012
13893
  },
14013
13894
  contextWindow: 1048576,
@@ -14030,7 +13911,7 @@ export const MODELS = {
14030
13911
  cacheWrite: 0,
14031
13912
  },
14032
13913
  contextWindow: 1048576,
14033
- maxTokens: 393216,
13914
+ maxTokens: 384000,
14034
13915
  },
14035
13916
  "deepseek/deepseek-v4.1-flash": {
14036
13917
  id: "deepseek/deepseek-v4.1-flash",
@@ -14043,14 +13924,33 @@ export const MODELS = {
14043
13924
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14044
13925
  input: ["text", "image"],
14045
13926
  cost: {
14046
- input: 0.0441,
14047
- output: 0.765,
14048
- cacheRead: 0.0054,
13927
+ input: 0.049,
13928
+ output: 0.5249999999999999,
13929
+ cacheRead: 0.001,
14049
13930
  cacheWrite: 0,
14050
13931
  },
14051
13932
  contextWindow: 1048576,
14052
13933
  maxTokens: 943718,
14053
13934
  },
13935
+ "deepseek/deepseek-v4.1-flash-1017": {
13936
+ id: "deepseek/deepseek-v4.1-flash-1017",
13937
+ name: "DeepSeek: DeepSeek V4.1 Flash 1017",
13938
+ api: "openai-completions",
13939
+ provider: "openrouter",
13940
+ baseUrl: "https://openrouter.ai/api/v1",
13941
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
13942
+ reasoning: true,
13943
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13944
+ input: ["text", "image"],
13945
+ cost: {
13946
+ input: 0.15,
13947
+ output: 0.6,
13948
+ cacheRead: 0.003,
13949
+ cacheWrite: 0,
13950
+ },
13951
+ contextWindow: 1048576,
13952
+ maxTokens: 393216,
13953
+ },
14054
13954
  "deepseek/deepseek-v4.1-flash:batch": {
14055
13955
  id: "deepseek/deepseek-v4.1-flash:batch",
14056
13956
  name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
@@ -14062,13 +13962,13 @@ export const MODELS = {
14062
13962
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14063
13963
  input: ["text", "image"],
14064
13964
  cost: {
14065
- input: 0.112,
14066
- output: 0.33599999999999997,
14067
- cacheRead: 0.00336,
13965
+ input: 0.049999999999999996,
13966
+ output: 0.15,
13967
+ cacheRead: 0.004,
14068
13968
  cacheWrite: 0,
14069
13969
  },
14070
13970
  contextWindow: 1048576,
14071
- maxTokens: 131072,
13971
+ maxTokens: 384000,
14072
13972
  },
14073
13973
  "dots-studio/dots-3-note-preview:free": {
14074
13974
  id: "dots-studio/dots-3-note-preview:free",
@@ -14087,6 +13987,23 @@ export const MODELS = {
14087
13987
  contextWindow: 512000,
14088
13988
  maxTokens: 460800,
14089
13989
  },
13990
+ "elorian/glimpse": {
13991
+ id: "elorian/glimpse",
13992
+ name: "Elorian: Glimpse",
13993
+ api: "openai-completions",
13994
+ provider: "openrouter",
13995
+ baseUrl: "https://openrouter.ai/api/v1",
13996
+ reasoning: true,
13997
+ input: ["text", "image"],
13998
+ cost: {
13999
+ input: 0.6,
14000
+ output: 3,
14001
+ cacheRead: 0.06,
14002
+ cacheWrite: 0,
14003
+ },
14004
+ contextWindow: 262144,
14005
+ maxTokens: 256000,
14006
+ },
14090
14007
  "fireworks/ember-1": {
14091
14008
  id: "fireworks/ember-1",
14092
14009
  name: "Fireworks: Ember-1",
@@ -14155,23 +14072,6 @@ export const MODELS = {
14155
14072
  contextWindow: 1048576,
14156
14073
  maxTokens: 65535,
14157
14074
  },
14158
- "google/gemini-2.5-flash:batch": {
14159
- id: "google/gemini-2.5-flash:batch",
14160
- name: "Google: Gemini 2.5 Flash (batch)",
14161
- api: "openai-completions",
14162
- provider: "openrouter",
14163
- baseUrl: "https://openrouter.ai/api/v1",
14164
- reasoning: true,
14165
- input: ["text", "image"],
14166
- cost: {
14167
- input: 0.15,
14168
- output: 1.25,
14169
- cacheRead: 0.03,
14170
- cacheWrite: 0,
14171
- },
14172
- contextWindow: 1048576,
14173
- maxTokens: 65535,
14174
- },
14175
14075
  "google/gemini-2.5-pro": {
14176
14076
  id: "google/gemini-2.5-pro",
14177
14077
  name: "Google: Gemini 2.5 Pro",
@@ -14206,23 +14106,6 @@ export const MODELS = {
14206
14106
  contextWindow: 1048576,
14207
14107
  maxTokens: 65536,
14208
14108
  },
14209
- "google/gemini-2.5-pro:batch": {
14210
- id: "google/gemini-2.5-pro:batch",
14211
- name: "Google: Gemini 2.5 Pro (batch)",
14212
- api: "openai-completions",
14213
- provider: "openrouter",
14214
- baseUrl: "https://openrouter.ai/api/v1",
14215
- reasoning: true,
14216
- input: ["text", "image"],
14217
- cost: {
14218
- input: 0.625,
14219
- output: 5,
14220
- cacheRead: 0.125,
14221
- cacheWrite: 0,
14222
- },
14223
- contextWindow: 1048576,
14224
- maxTokens: 65536,
14225
- },
14226
14109
  "google/gemini-3-flash-preview": {
14227
14110
  id: "google/gemini-3-flash-preview",
14228
14111
  name: "Google: Gemini 3 Flash Preview",
@@ -14521,9 +14404,9 @@ export const MODELS = {
14521
14404
  reasoning: true,
14522
14405
  input: ["text", "image"],
14523
14406
  cost: {
14524
- input: 0.75,
14525
- output: 3.75,
14526
- cacheRead: 0.075,
14407
+ input: 0.8250000000000001,
14408
+ output: 4.125,
14409
+ cacheRead: 0.0825,
14527
14410
  cacheWrite: 0.0416666666666667,
14528
14411
  },
14529
14412
  contextWindow: 1048576,
@@ -14561,7 +14444,7 @@ export const MODELS = {
14561
14444
  cacheWrite: 0.1875,
14562
14445
  },
14563
14446
  contextWindow: 1048576,
14564
- maxTokens: 65536,
14447
+ maxTokens: 943718,
14565
14448
  },
14566
14449
  "google/gemini-4-argon:batch": {
14567
14450
  id: "google/gemini-4-argon:batch",
@@ -14624,7 +14507,7 @@ export const MODELS = {
14624
14507
  input: ["text", "image"],
14625
14508
  cost: {
14626
14509
  input: 0.08,
14627
- output: 0.44999999999999996,
14510
+ output: 0.35,
14628
14511
  cacheRead: 0.04,
14629
14512
  cacheWrite: 0,
14630
14513
  },
@@ -14674,9 +14557,9 @@ export const MODELS = {
14674
14557
  reasoning: true,
14675
14558
  input: ["text", "image"],
14676
14559
  cost: {
14677
- input: 0.09,
14678
- output: 0.33999999999999997,
14679
- cacheRead: 0.049999999999999996,
14560
+ input: 0.19999999999999998,
14561
+ output: 0.39999999999999997,
14562
+ cacheRead: 0,
14680
14563
  cacheWrite: 0,
14681
14564
  },
14682
14565
  contextWindow: 262144,
@@ -14750,6 +14633,23 @@ export const MODELS = {
14750
14633
  contextWindow: 260000,
14751
14634
  maxTokens: 65536,
14752
14635
  },
14636
+ "inception/mercury-3": {
14637
+ id: "inception/mercury-3",
14638
+ name: "Inception: Mercury 3",
14639
+ api: "openai-completions",
14640
+ provider: "openrouter",
14641
+ baseUrl: "https://openrouter.ai/api/v1",
14642
+ reasoning: true,
14643
+ input: ["text"],
14644
+ cost: {
14645
+ input: 0.09999999999999999,
14646
+ output: 0.35,
14647
+ cacheRead: 0.01,
14648
+ cacheWrite: 0,
14649
+ },
14650
+ contextWindow: 1000000,
14651
+ maxTokens: 131072,
14652
+ },
14753
14653
  "inclusionai/ling-3.0-flash": {
14754
14654
  id: "inclusionai/ling-3.0-flash",
14755
14655
  name: "inclusionAI: Ling 3.0 Flash",
@@ -14895,13 +14795,13 @@ export const MODELS = {
14895
14795
  reasoning: false,
14896
14796
  input: ["text"],
14897
14797
  cost: {
14898
- input: 0.59,
14899
- output: 0.7899999999999999,
14900
- cacheRead: 0.295,
14798
+ input: 0.09999999999999999,
14799
+ output: 0.32,
14800
+ cacheRead: 0,
14901
14801
  cacheWrite: 0,
14902
14802
  },
14903
14803
  contextWindow: 131072,
14904
- maxTokens: 32768,
14804
+ maxTokens: 16384,
14905
14805
  },
14906
14806
  "meta-llama/llama-4-maverick": {
14907
14807
  id: "meta-llama/llama-4-maverick",
@@ -14917,7 +14817,7 @@ export const MODELS = {
14917
14817
  cacheRead: 0.049999999999999996,
14918
14818
  cacheWrite: 0,
14919
14819
  },
14920
- contextWindow: 1048576,
14820
+ contextWindow: 524288,
14921
14821
  maxTokens: 16384,
14922
14822
  },
14923
14823
  "meta-llama/llama-4-scout": {
@@ -14929,13 +14829,13 @@ export const MODELS = {
14929
14829
  reasoning: false,
14930
14830
  input: ["text", "image"],
14931
14831
  cost: {
14932
- input: 0.18,
14933
- output: 0.59,
14832
+ input: 0.09999999999999999,
14833
+ output: 0.3,
14934
14834
  cacheRead: 0,
14935
14835
  cacheWrite: 0,
14936
14836
  },
14937
14837
  contextWindow: 1310720,
14938
- maxTokens: 117964,
14838
+ maxTokens: 16384,
14939
14839
  },
14940
14840
  "meta/muse-glimmer-30b": {
14941
14841
  id: "meta/muse-glimmer-30b",
@@ -15039,6 +14939,23 @@ export const MODELS = {
15039
14939
  contextWindow: 1048576,
15040
14940
  maxTokens: 943718,
15041
14941
  },
14942
+ "meta/muse-spark-open": {
14943
+ id: "meta/muse-spark-open",
14944
+ name: "Meta: Muse Spark Open",
14945
+ api: "openai-completions",
14946
+ provider: "openrouter",
14947
+ baseUrl: "https://openrouter.ai/api/v1",
14948
+ reasoning: true,
14949
+ input: ["text", "image"],
14950
+ cost: {
14951
+ input: 1.25,
14952
+ output: 4.25,
14953
+ cacheRead: 0.15,
14954
+ cacheWrite: 0,
14955
+ },
14956
+ contextWindow: 1048576,
14957
+ maxTokens: 943718,
14958
+ },
15042
14959
  "meta/muse-wonder": {
15043
14960
  id: "meta/muse-wonder",
15044
14961
  name: "Meta: Muse Wonder",
@@ -15082,13 +14999,13 @@ export const MODELS = {
15082
14999
  reasoning: true,
15083
15000
  input: ["text"],
15084
15001
  cost: {
15085
- input: 0.3,
15086
- output: 1.2,
15002
+ input: 0.255,
15003
+ output: 1.02,
15087
15004
  cacheRead: 0,
15088
15005
  cacheWrite: 0,
15089
15006
  },
15090
15007
  contextWindow: 204800,
15091
- maxTokens: 176947,
15008
+ maxTokens: 131072,
15092
15009
  },
15093
15010
  "minimax/minimax-m2.1": {
15094
15011
  id: "minimax/minimax-m2.1",
@@ -15117,12 +15034,12 @@ export const MODELS = {
15117
15034
  input: ["text"],
15118
15035
  cost: {
15119
15036
  input: 0.27,
15120
- output: 1.08,
15121
- cacheRead: 0.027,
15037
+ output: 0.95,
15038
+ cacheRead: 0.03,
15122
15039
  cacheWrite: 0,
15123
15040
  },
15124
15041
  contextWindow: 204800,
15125
- maxTokens: 128000,
15042
+ maxTokens: 32768,
15126
15043
  },
15127
15044
  "minimax/minimax-m2.7": {
15128
15045
  id: "minimax/minimax-m2.7",
@@ -15158,6 +15075,23 @@ export const MODELS = {
15158
15075
  contextWindow: 1048576,
15159
15076
  maxTokens: 512000,
15160
15077
  },
15078
+ "minimax/minimax-m3.1-flash:free": {
15079
+ id: "minimax/minimax-m3.1-flash:free",
15080
+ name: "MiniMax: MiniMax M3.1 Flash (free)",
15081
+ api: "openai-completions",
15082
+ provider: "openrouter",
15083
+ baseUrl: "https://openrouter.ai/api/v1",
15084
+ reasoning: true,
15085
+ input: ["text", "image"],
15086
+ cost: {
15087
+ input: 0,
15088
+ output: 0,
15089
+ cacheRead: 0,
15090
+ cacheWrite: 0,
15091
+ },
15092
+ contextWindow: 1000000,
15093
+ maxTokens: 524288,
15094
+ },
15161
15095
  "mistralai/codestral-2508": {
15162
15096
  id: "mistralai/codestral-2508",
15163
15097
  name: "Mistral: Codestral 2508",
@@ -15354,9 +15288,9 @@ export const MODELS = {
15354
15288
  reasoning: true,
15355
15289
  input: ["text", "image"],
15356
15290
  cost: {
15357
- input: 0.6799999999999999,
15358
- output: 2.09,
15359
- cacheRead: 0.07,
15291
+ input: 1.3599999999999999,
15292
+ output: 4.18,
15293
+ cacheRead: 0.14,
15360
15294
  cacheWrite: 0,
15361
15295
  },
15362
15296
  contextWindow: 1048576,
@@ -15694,9 +15628,9 @@ export const MODELS = {
15694
15628
  reasoning: true,
15695
15629
  input: ["text", "image"],
15696
15630
  cost: {
15697
- input: 0.73,
15698
- output: 10,
15699
- cacheRead: 0.55,
15631
+ input: 0.23900000000000002,
15632
+ output: 11.936,
15633
+ cacheRead: 0.21,
15700
15634
  cacheWrite: 0,
15701
15635
  },
15702
15636
  contextWindow: 1048576,
@@ -15779,9 +15713,9 @@ export const MODELS = {
15779
15713
  reasoning: true,
15780
15714
  input: ["text"],
15781
15715
  cost: {
15782
- input: 0.08,
15783
- output: 0.44999999999999996,
15784
- cacheRead: 0,
15716
+ input: 0.3,
15717
+ output: 2.4,
15718
+ cacheRead: 0.15,
15785
15719
  cacheWrite: 0,
15786
15720
  },
15787
15721
  contextWindow: 262144,
@@ -15872,6 +15806,40 @@ export const MODELS = {
15872
15806
  contextWindow: 1000000,
15873
15807
  maxTokens: 65536,
15874
15808
  },
15809
+ "nvidia/nemotron-3.5-super-vl": {
15810
+ id: "nvidia/nemotron-3.5-super-vl",
15811
+ name: "NVIDIA: Nemotron 3.5 Super VL",
15812
+ api: "openai-completions",
15813
+ provider: "openrouter",
15814
+ baseUrl: "https://openrouter.ai/api/v1",
15815
+ reasoning: true,
15816
+ input: ["text", "image"],
15817
+ cost: {
15818
+ input: 0.15,
15819
+ output: 0.5,
15820
+ cacheRead: 0.02,
15821
+ cacheWrite: 0,
15822
+ },
15823
+ contextWindow: 1048576,
15824
+ maxTokens: 235929,
15825
+ },
15826
+ "nvidia/nemotron-3.5-super-vl:free": {
15827
+ id: "nvidia/nemotron-3.5-super-vl:free",
15828
+ name: "NVIDIA: Nemotron 3.5 Super VL (free)",
15829
+ api: "openai-completions",
15830
+ provider: "openrouter",
15831
+ baseUrl: "https://openrouter.ai/api/v1",
15832
+ reasoning: true,
15833
+ input: ["text", "image"],
15834
+ cost: {
15835
+ input: 0,
15836
+ output: 0,
15837
+ cacheRead: 0,
15838
+ cacheWrite: 0,
15839
+ },
15840
+ contextWindow: 1000000,
15841
+ maxTokens: 131072,
15842
+ },
15875
15843
  "openai/gpt-3.5-turbo": {
15876
15844
  id: "openai/gpt-3.5-turbo",
15877
15845
  name: "OpenAI: GPT-3.5 Turbo",
@@ -16767,10 +16735,10 @@ export const MODELS = {
16767
16735
  reasoning: true,
16768
16736
  input: ["text", "image"],
16769
16737
  cost: {
16770
- input: 2,
16771
- output: 10,
16772
- cacheRead: 0.19999999999999998,
16773
- cacheWrite: 2.5,
16738
+ input: 4,
16739
+ output: 20,
16740
+ cacheRead: 0.39999999999999997,
16741
+ cacheWrite: 5,
16774
16742
  },
16775
16743
  contextWindow: 1050000,
16776
16744
  maxTokens: 128000,
@@ -16784,10 +16752,10 @@ export const MODELS = {
16784
16752
  reasoning: true,
16785
16753
  input: ["text", "image"],
16786
16754
  cost: {
16787
- input: 2,
16788
- output: 10,
16789
- cacheRead: 0.19999999999999998,
16790
- cacheWrite: 2.5,
16755
+ input: 4,
16756
+ output: 20,
16757
+ cacheRead: 0.39999999999999997,
16758
+ cacheWrite: 5,
16791
16759
  },
16792
16760
  contextWindow: 1050000,
16793
16761
  maxTokens: 128000,
@@ -16801,10 +16769,10 @@ export const MODELS = {
16801
16769
  reasoning: true,
16802
16770
  input: ["text", "image"],
16803
16771
  cost: {
16804
- input: 1,
16805
- output: 5,
16806
- cacheRead: 0.09999999999999999,
16807
- cacheWrite: 1.25,
16772
+ input: 2,
16773
+ output: 10,
16774
+ cacheRead: 0.19999999999999998,
16775
+ cacheWrite: 2.5,
16808
16776
  },
16809
16777
  contextWindow: 1050000,
16810
16778
  maxTokens: 128000,
@@ -16818,10 +16786,10 @@ export const MODELS = {
16818
16786
  reasoning: true,
16819
16787
  input: ["text", "image"],
16820
16788
  cost: {
16821
- input: 1,
16822
- output: 5,
16823
- cacheRead: 0.09999999999999999,
16824
- cacheWrite: 1.25,
16789
+ input: 2,
16790
+ output: 10,
16791
+ cacheRead: 0.19999999999999998,
16792
+ cacheWrite: 2.5,
16825
16793
  },
16826
16794
  contextWindow: 1050000,
16827
16795
  maxTokens: 128000,
@@ -17540,6 +17508,23 @@ export const MODELS = {
17540
17508
  contextWindow: 200000,
17541
17509
  maxTokens: 4096,
17542
17510
  },
17511
+ "openrouter/pareto-code": {
17512
+ id: "openrouter/pareto-code",
17513
+ name: "Pareto Code Router",
17514
+ api: "openai-completions",
17515
+ provider: "openrouter",
17516
+ baseUrl: "https://openrouter.ai/api/v1",
17517
+ reasoning: true,
17518
+ input: ["text"],
17519
+ cost: {
17520
+ input: -1000000,
17521
+ output: -1000000,
17522
+ cacheRead: 0,
17523
+ cacheWrite: 0,
17524
+ },
17525
+ contextWindow: 2000000,
17526
+ maxTokens: 4096,
17527
+ },
17543
17528
  "perceptron/perceptron-mk1.5": {
17544
17529
  id: "perceptron/perceptron-mk1.5",
17545
17530
  name: "Perceptron: Perceptron Mk1.5",
@@ -17770,7 +17755,7 @@ export const MODELS = {
17770
17755
  reasoning: false,
17771
17756
  input: ["text"],
17772
17757
  cost: {
17773
- input: 0.09999999999999999,
17758
+ input: 0.09,
17774
17759
  output: 0.3,
17775
17760
  cacheRead: 0,
17776
17761
  cacheWrite: 0,
@@ -17872,13 +17857,13 @@ export const MODELS = {
17872
17857
  reasoning: false,
17873
17858
  input: ["text"],
17874
17859
  cost: {
17875
- input: 0.09999999999999999,
17860
+ input: 0.09,
17876
17861
  output: 1.1,
17877
- cacheRead: 0.07,
17862
+ cacheRead: 0,
17878
17863
  cacheWrite: 0,
17879
17864
  },
17880
17865
  contextWindow: 262144,
17881
- maxTokens: 235929,
17866
+ maxTokens: 16384,
17882
17867
  },
17883
17868
  "qwen/qwen3-next-80b-a3b-thinking": {
17884
17869
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -17991,13 +17976,13 @@ export const MODELS = {
17991
17976
  reasoning: true,
17992
17977
  input: ["text", "image"],
17993
17978
  cost: {
17994
- input: 0.26,
17995
- output: 2.6,
17996
- cacheRead: 0,
17979
+ input: 0.27,
17980
+ output: 2.16,
17981
+ cacheRead: 0.27,
17997
17982
  cacheWrite: 0,
17998
17983
  },
17999
17984
  contextWindow: 262144,
18000
- maxTokens: 81920,
17985
+ maxTokens: 65536,
18001
17986
  },
18002
17987
  "qwen/qwen3.5-35b-a3b": {
18003
17988
  id: "qwen/qwen3.5-35b-a3b",
@@ -18008,13 +17993,13 @@ export const MODELS = {
18008
17993
  reasoning: true,
18009
17994
  input: ["text", "image"],
18010
17995
  cost: {
18011
- input: 0.15,
17996
+ input: 0.14,
18012
17997
  output: 1,
18013
17998
  cacheRead: 0.049999999999999996,
18014
17999
  cacheWrite: 0,
18015
18000
  },
18016
18001
  contextWindow: 262144,
18017
- maxTokens: 16384,
18002
+ maxTokens: 81920,
18018
18003
  },
18019
18004
  "qwen/qwen3.5-397b-a17b": {
18020
18005
  id: "qwen/qwen3.5-397b-a17b",
@@ -18025,13 +18010,13 @@ export const MODELS = {
18025
18010
  reasoning: true,
18026
18011
  input: ["text", "image"],
18027
18012
  cost: {
18028
- input: 0.55,
18029
- output: 3.5,
18030
- cacheRead: 0.22499999999999998,
18013
+ input: 0.39,
18014
+ output: 2.34,
18015
+ cacheRead: 0,
18031
18016
  cacheWrite: 0,
18032
18017
  },
18033
18018
  contextWindow: 262144,
18034
- maxTokens: 235929,
18019
+ maxTokens: 65536,
18035
18020
  },
18036
18021
  "qwen/qwen3.5-9b": {
18037
18022
  id: "qwen/qwen3.5-9b",
@@ -18042,13 +18027,13 @@ export const MODELS = {
18042
18027
  reasoning: true,
18043
18028
  input: ["text", "image"],
18044
18029
  cost: {
18045
- input: 0.09999999999999999,
18046
- output: 0.15,
18047
- cacheRead: 0,
18030
+ input: 0.08,
18031
+ output: 0.13,
18032
+ cacheRead: 0.04,
18048
18033
  cacheWrite: 0,
18049
18034
  },
18050
18035
  contextWindow: 262144,
18051
- maxTokens: 32768,
18036
+ maxTokens: 65536,
18052
18037
  },
18053
18038
  "qwen/qwen3.5-flash-02-23": {
18054
18039
  id: "qwen/qwen3.5-flash-02-23",
@@ -18110,13 +18095,13 @@ export const MODELS = {
18110
18095
  reasoning: true,
18111
18096
  input: ["text", "image"],
18112
18097
  cost: {
18113
- input: 0.32,
18114
- output: 3.1999999999999997,
18115
- cacheRead: 0,
18098
+ input: 0.25,
18099
+ output: 2,
18100
+ cacheRead: 0.024999999999999998,
18116
18101
  cacheWrite: 0,
18117
18102
  },
18118
18103
  contextWindow: 262144,
18119
- maxTokens: 81920,
18104
+ maxTokens: 65536,
18120
18105
  },
18121
18106
  "qwen/qwen3.6-35b-a3b": {
18122
18107
  id: "qwen/qwen3.6-35b-a3b",
@@ -18129,11 +18114,11 @@ export const MODELS = {
18129
18114
  cost: {
18130
18115
  input: 0.09999999999999999,
18131
18116
  output: 0.95,
18132
- cacheRead: 0.09999999999999999,
18117
+ cacheRead: 0.049999999999999996,
18133
18118
  cacheWrite: 0,
18134
18119
  },
18135
18120
  contextWindow: 262144,
18136
- maxTokens: 65536,
18121
+ maxTokens: 235929,
18137
18122
  },
18138
18123
  "qwen/qwen3.6-flash": {
18139
18124
  id: "qwen/qwen3.6-flash",
@@ -18220,6 +18205,23 @@ export const MODELS = {
18220
18205
  contextWindow: 1000000,
18221
18206
  maxTokens: 131072,
18222
18207
  },
18208
+ "qwen/qwen3.7-plus:batch": {
18209
+ id: "qwen/qwen3.7-plus:batch",
18210
+ name: "Qwen: Qwen3.7 Plus (batch)",
18211
+ api: "openai-completions",
18212
+ provider: "openrouter",
18213
+ baseUrl: "https://openrouter.ai/api/v1",
18214
+ reasoning: true,
18215
+ input: ["text", "image"],
18216
+ cost: {
18217
+ input: 0.22999999999999998,
18218
+ output: 0.9199999999999999,
18219
+ cacheRead: 0,
18220
+ cacheWrite: 0,
18221
+ },
18222
+ contextWindow: 262144,
18223
+ maxTokens: 131072,
18224
+ },
18223
18225
  "qwen/qwen3.8-2.4t-a95b": {
18224
18226
  id: "qwen/qwen3.8-2.4t-a95b",
18225
18227
  name: "Qwen: Qwen3.8 2.4T A95B",
@@ -18235,7 +18237,7 @@ export const MODELS = {
18235
18237
  cacheWrite: 0,
18236
18238
  },
18237
18239
  contextWindow: 1048576,
18238
- maxTokens: 131072,
18240
+ maxTokens: 909000,
18239
18241
  },
18240
18242
  "qwen/qwen3.8-27b": {
18241
18243
  id: "qwen/qwen3.8-27b",
@@ -18247,12 +18249,12 @@ export const MODELS = {
18247
18249
  input: ["text", "image"],
18248
18250
  cost: {
18249
18251
  input: 0.04,
18250
- output: 2.3,
18251
- cacheRead: 0.019799999999999998,
18252
+ output: 1.35,
18253
+ cacheRead: 0.018,
18252
18254
  cacheWrite: 0,
18253
18255
  },
18254
18256
  contextWindow: 1000000,
18255
- maxTokens: 235929,
18257
+ maxTokens: 65536,
18256
18258
  },
18257
18259
  "qwen/qwen3.8-flash": {
18258
18260
  id: "qwen/qwen3.8-flash",
@@ -18322,6 +18324,23 @@ export const MODELS = {
18322
18324
  contextWindow: 1000000,
18323
18325
  maxTokens: 131072,
18324
18326
  },
18327
+ "reflection/beam-1.0-501b-a23b": {
18328
+ id: "reflection/beam-1.0-501b-a23b",
18329
+ name: "Reflection: Beam 1.0 501B A23B",
18330
+ api: "openai-completions",
18331
+ provider: "openrouter",
18332
+ baseUrl: "https://openrouter.ai/api/v1",
18333
+ reasoning: true,
18334
+ input: ["text"],
18335
+ cost: {
18336
+ input: 0.3,
18337
+ output: 1,
18338
+ cacheRead: 0.04,
18339
+ cacheWrite: 0,
18340
+ },
18341
+ contextWindow: 1048576,
18342
+ maxTokens: 943718,
18343
+ },
18325
18344
  "rekaai/reka-edge": {
18326
18345
  id: "rekaai/reka-edge",
18327
18346
  name: "Reka Edge",
@@ -18469,10 +18488,10 @@ export const MODELS = {
18469
18488
  cost: {
18470
18489
  input: 1,
18471
18490
  output: 2.7,
18472
- cacheRead: 0.049999999999999996,
18491
+ cacheRead: 0.09999999999999999,
18473
18492
  cacheWrite: 0,
18474
18493
  },
18475
- contextWindow: 1000000,
18494
+ contextWindow: 1048576,
18476
18495
  maxTokens: 64000,
18477
18496
  },
18478
18497
  "tencent/hy3": {
@@ -18484,9 +18503,9 @@ export const MODELS = {
18484
18503
  reasoning: true,
18485
18504
  input: ["text"],
18486
18505
  cost: {
18487
- input: 0.0825,
18488
- output: 0.33,
18489
- cacheRead: 0.020625,
18506
+ input: 0.13199999999999998,
18507
+ output: 0.5279999999999999,
18508
+ cacheRead: 0.032999999999999995,
18490
18509
  cacheWrite: 0,
18491
18510
  },
18492
18511
  contextWindow: 262144,
@@ -18501,9 +18520,9 @@ export const MODELS = {
18501
18520
  reasoning: true,
18502
18521
  input: ["text"],
18503
18522
  cost: {
18504
- input: 0.7505999999999999,
18505
- output: 2.2509,
18506
- cacheRead: 0.0378,
18523
+ input: 0.834,
18524
+ output: 2.501,
18525
+ cacheRead: 0.041999999999999996,
18507
18526
  cacheWrite: 0,
18508
18527
  },
18509
18528
  contextWindow: 1048576,
@@ -18594,38 +18613,38 @@ export const MODELS = {
18594
18613
  contextWindow: 1000000,
18595
18614
  maxTokens: 4096,
18596
18615
  },
18597
- "unbiased/pareto": {
18598
- id: "unbiased/pareto",
18599
- name: "Pareto",
18616
+ "unbiased/pareto-26.10": {
18617
+ id: "unbiased/pareto-26.10",
18618
+ name: "Pareto 26.10",
18600
18619
  api: "openai-completions",
18601
18620
  provider: "openrouter",
18602
18621
  baseUrl: "https://openrouter.ai/api/v1",
18603
18622
  reasoning: false,
18604
18623
  input: ["text", "image"],
18605
18624
  cost: {
18606
- input: 2.5,
18607
- output: 7.5,
18608
- cacheRead: 0.25,
18625
+ input: 0.7999999999999999,
18626
+ output: 3.1999999999999997,
18627
+ cacheRead: 0.03,
18609
18628
  cacheWrite: 0,
18610
18629
  },
18611
- contextWindow: 262144,
18630
+ contextWindow: 1048576,
18612
18631
  maxTokens: 131072,
18613
18632
  },
18614
- "unbiased/pareto-26.10-preview": {
18615
- id: "unbiased/pareto-26.10-preview",
18616
- name: "Pareto 26.10 Preview",
18633
+ "unbiased/pareto-26.9": {
18634
+ id: "unbiased/pareto-26.9",
18635
+ name: "Pareto 26.9",
18617
18636
  api: "openai-completions",
18618
18637
  provider: "openrouter",
18619
18638
  baseUrl: "https://openrouter.ai/api/v1",
18620
18639
  reasoning: false,
18621
18640
  input: ["text", "image"],
18622
18641
  cost: {
18623
- input: 0.7999999999999999,
18624
- output: 3.1999999999999997,
18625
- cacheRead: 0.03,
18642
+ input: 2.5,
18643
+ output: 7.5,
18644
+ cacheRead: 0.25,
18626
18645
  cacheWrite: 0,
18627
18646
  },
18628
- contextWindow: 1048576,
18647
+ contextWindow: 262144,
18629
18648
  maxTokens: 131072,
18630
18649
  },
18631
18650
  "upstage/solar-mini4": {
@@ -18671,9 +18690,9 @@ export const MODELS = {
18671
18690
  reasoning: true,
18672
18691
  input: ["text"],
18673
18692
  cost: {
18674
- input: 0.09,
18675
- output: 0.36,
18676
- cacheRead: 0.018,
18693
+ input: 0.15,
18694
+ output: 0.6,
18695
+ cacheRead: 0.03,
18677
18696
  cacheWrite: 0,
18678
18697
  },
18679
18698
  contextWindow: 524288,
@@ -18807,13 +18826,13 @@ export const MODELS = {
18807
18826
  reasoning: true,
18808
18827
  input: ["text", "image"],
18809
18828
  cost: {
18810
- input: 0.14,
18811
- output: 0.28,
18812
- cacheRead: 0.0028,
18829
+ input: 0.119,
18830
+ output: 0.238,
18831
+ cacheRead: 0.00255,
18813
18832
  cacheWrite: 0,
18814
18833
  },
18815
18834
  contextWindow: 1050000,
18816
- maxTokens: 131072,
18835
+ maxTokens: 945000,
18817
18836
  },
18818
18837
  "xiaomi/mimo-v2.5-pro": {
18819
18838
  id: "xiaomi/mimo-v2.5-pro",
@@ -18824,13 +18843,13 @@ export const MODELS = {
18824
18843
  reasoning: true,
18825
18844
  input: ["text"],
18826
18845
  cost: {
18827
- input: 0.435,
18828
- output: 0.87,
18829
- cacheRead: 0.0036,
18846
+ input: 0.3045,
18847
+ output: 0.609,
18848
+ cacheRead: 0.0028,
18830
18849
  cacheWrite: 0,
18831
18850
  },
18832
18851
  contextWindow: 1050000,
18833
- maxTokens: 131072,
18852
+ maxTokens: 945000,
18834
18853
  },
18835
18854
  "xiaomi/mimo-v2.6-flash": {
18836
18855
  id: "xiaomi/mimo-v2.6-flash",
@@ -18883,6 +18902,23 @@ export const MODELS = {
18883
18902
  contextWindow: 1048576,
18884
18903
  maxTokens: 131072,
18885
18904
  },
18905
+ "xingchen-agi/xing4.0-29b-a4b:free": {
18906
+ id: "xingchen-agi/xing4.0-29b-a4b:free",
18907
+ name: "XingChen: Xing4.0 29B A4B (free)",
18908
+ api: "openai-completions",
18909
+ provider: "openrouter",
18910
+ baseUrl: "https://openrouter.ai/api/v1",
18911
+ reasoning: true,
18912
+ input: ["text"],
18913
+ cost: {
18914
+ input: 0,
18915
+ output: 0,
18916
+ cacheRead: 0,
18917
+ cacheWrite: 0,
18918
+ },
18919
+ contextWindow: 262144,
18920
+ maxTokens: 235929,
18921
+ },
18886
18922
  "z-ai/glm-4.5": {
18887
18923
  id: "z-ai/glm-4.5",
18888
18924
  name: "Z.ai: GLM 4.5",
@@ -18943,9 +18979,9 @@ export const MODELS = {
18943
18979
  reasoning: true,
18944
18980
  input: ["text"],
18945
18981
  cost: {
18946
- input: 0.5,
18947
- output: 2,
18948
- cacheRead: 0.09999999999999999,
18982
+ input: 0.55,
18983
+ output: 2.2,
18984
+ cacheRead: 0.11,
18949
18985
  cacheWrite: 0,
18950
18986
  },
18951
18987
  contextWindow: 204800,
@@ -18977,9 +19013,9 @@ export const MODELS = {
18977
19013
  reasoning: true,
18978
19014
  input: ["text"],
18979
19015
  cost: {
18980
- input: 0.6,
18981
- output: 2.2,
18982
- cacheRead: 0.11,
19016
+ input: 0.54,
19017
+ output: 1.9800000000000002,
19018
+ cacheRead: 0.099,
18983
19019
  cacheWrite: 0,
18984
19020
  },
18985
19021
  contextWindow: 204800,
@@ -19017,7 +19053,7 @@ export const MODELS = {
19017
19053
  cacheWrite: 0,
19018
19054
  },
19019
19055
  contextWindow: 204800,
19020
- maxTokens: 128000,
19056
+ maxTokens: 131072,
19021
19057
  },
19022
19058
  "z-ai/glm-5-turbo": {
19023
19059
  id: "z-ai/glm-5-turbo",
@@ -19045,13 +19081,13 @@ export const MODELS = {
19045
19081
  reasoning: true,
19046
19082
  input: ["text"],
19047
19083
  cost: {
19048
- input: 0.966,
19049
- output: 3.036,
19050
- cacheRead: 0.1794,
19084
+ input: 1.4,
19085
+ output: 4.4,
19086
+ cacheRead: 0.26,
19051
19087
  cacheWrite: 0,
19052
19088
  },
19053
19089
  contextWindow: 204800,
19054
- maxTokens: 128000,
19090
+ maxTokens: 131072,
19055
19091
  },
19056
19092
  "z-ai/glm-5.2": {
19057
19093
  id: "z-ai/glm-5.2",
@@ -19062,9 +19098,9 @@ export const MODELS = {
19062
19098
  reasoning: true,
19063
19099
  input: ["text"],
19064
19100
  cost: {
19065
- input: 0.06,
19101
+ input: 0.0341,
19066
19102
  output: 7,
19067
- cacheRead: 0.059,
19103
+ cacheRead: 0.032999999999999995,
19068
19104
  cacheWrite: 0,
19069
19105
  },
19070
19106
  contextWindow: 1048576,
@@ -19080,8 +19116,8 @@ export const MODELS = {
19080
19116
  input: ["text"],
19081
19117
  cost: {
19082
19118
  input: 0.079,
19083
- output: 4.8,
19084
- cacheRead: 0.059,
19119
+ output: 1.4,
19120
+ cacheRead: 0.078,
19085
19121
  cacheWrite: 0,
19086
19122
  },
19087
19123
  contextWindow: 1048576,
@@ -19096,13 +19132,13 @@ export const MODELS = {
19096
19132
  reasoning: true,
19097
19133
  input: ["text", "image"],
19098
19134
  cost: {
19099
- input: 0.026099999999999998,
19100
- output: 0.8999999999999999,
19101
- cacheRead: 0.0108,
19135
+ input: 0.15,
19136
+ output: 0.5,
19137
+ cacheRead: 0.03,
19102
19138
  cacheWrite: 0,
19103
19139
  },
19104
19140
  contextWindow: 1048576,
19105
- maxTokens: 943718,
19141
+ maxTokens: 943717,
19106
19142
  },
19107
19143
  "z-ai/glm-5.3-flash:batch": {
19108
19144
  id: "z-ai/glm-5.3-flash:batch",
@@ -19113,9 +19149,9 @@ export const MODELS = {
19113
19149
  reasoning: true,
19114
19150
  input: ["text", "image"],
19115
19151
  cost: {
19116
- input: 0.06,
19117
- output: 0.19999999999999998,
19118
- cacheRead: 0.012,
19152
+ input: 0.049999999999999996,
19153
+ output: 0.18,
19154
+ cacheRead: 0.01,
19119
19155
  cacheWrite: 0,
19120
19156
  },
19121
19157
  contextWindow: 1048576,
@@ -19267,9 +19303,9 @@ export const MODELS = {
19267
19303
  reasoning: true,
19268
19304
  input: ["text", "image"],
19269
19305
  cost: {
19270
- input: 0.0441,
19271
- output: 0.765,
19272
- cacheRead: 0.0054,
19306
+ input: 0.07,
19307
+ output: 0.5,
19308
+ cacheRead: 0.008,
19273
19309
  cacheWrite: 0,
19274
19310
  },
19275
19311
  contextWindow: 1048576,
@@ -19284,9 +19320,9 @@ export const MODELS = {
19284
19320
  reasoning: true,
19285
19321
  input: ["text"],
19286
19322
  cost: {
19287
- input: 0.24947999999999998,
19288
- output: 0.7484400000000001,
19289
- cacheRead: 0.007937999999999999,
19323
+ input: 0.22499999999999998,
19324
+ output: 8,
19325
+ cacheRead: 0.22999999999999998,
19290
19326
  cacheWrite: 0,
19291
19327
  },
19292
19328
  contextWindow: 1048576,
@@ -19303,13 +19339,13 @@ export const MODELS = {
19303
19339
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19304
19340
  input: ["text"],
19305
19341
  cost: {
19306
- input: 0.0144,
19307
- output: 0.576,
19308
- cacheRead: 0.0108,
19342
+ input: 0.020999999999999998,
19343
+ output: 0.5279999999999999,
19344
+ cacheRead: 0.0056,
19309
19345
  cacheWrite: 0,
19310
19346
  },
19311
19347
  contextWindow: 1048576,
19312
- maxTokens: 943718,
19348
+ maxTokens: 131072,
19313
19349
  },
19314
19350
  "~google/gemini-flash-latest": {
19315
19351
  id: "~google/gemini-flash-latest",
@@ -19338,12 +19374,12 @@ export const MODELS = {
19338
19374
  input: ["text", "image"],
19339
19375
  cost: {
19340
19376
  input: 2,
19341
- output: 12,
19342
- cacheRead: 0.19999999999999998,
19343
- cacheWrite: 0.375,
19377
+ output: 10,
19378
+ cacheRead: 0.09999999999999999,
19379
+ cacheWrite: 0.1875,
19344
19380
  },
19345
19381
  contextWindow: 1048576,
19346
- maxTokens: 65536,
19382
+ maxTokens: 943718,
19347
19383
  },
19348
19384
  "~moonshotai/kimi-latest": {
19349
19385
  id: "~moonshotai/kimi-latest",
@@ -19354,9 +19390,9 @@ export const MODELS = {
19354
19390
  reasoning: true,
19355
19391
  input: ["text", "image"],
19356
19392
  cost: {
19357
- input: 0.72,
19358
- output: 24,
19359
- cacheRead: 0.3,
19393
+ input: 0.238,
19394
+ output: 16,
19395
+ cacheRead: 0.228,
19360
19396
  cacheWrite: 0,
19361
19397
  },
19362
19398
  contextWindow: 1048576,
@@ -19447,6 +19483,23 @@ export const MODELS = {
19447
19483
  contextWindow: 1050000,
19448
19484
  maxTokens: 128000,
19449
19485
  },
19486
+ "~unbiased/pareto-latest": {
19487
+ id: "~unbiased/pareto-latest",
19488
+ name: "Pareto Latest",
19489
+ api: "openai-completions",
19490
+ provider: "openrouter",
19491
+ baseUrl: "https://openrouter.ai/api/v1",
19492
+ reasoning: false,
19493
+ input: ["text", "image"],
19494
+ cost: {
19495
+ input: 0.7999999999999999,
19496
+ output: 3.1999999999999997,
19497
+ cacheRead: 0.03,
19498
+ cacheWrite: 0,
19499
+ },
19500
+ contextWindow: 1048576,
19501
+ maxTokens: 131072,
19502
+ },
19450
19503
  "~x-ai/grok-latest": {
19451
19504
  id: "~x-ai/grok-latest",
19452
19505
  name: "xAI: Grok Latest",
@@ -19473,9 +19526,9 @@ export const MODELS = {
19473
19526
  reasoning: true,
19474
19527
  input: ["text", "image"],
19475
19528
  cost: {
19476
- input: 0.026099999999999998,
19477
- output: 0.8999999999999999,
19478
- cacheRead: 0.0108,
19529
+ input: 0.051691,
19530
+ output: 0.5249999999999999,
19531
+ cacheRead: 0.00375,
19479
19532
  cacheWrite: 0,
19480
19533
  },
19481
19534
  contextWindow: 1048576,
@@ -19491,8 +19544,8 @@ export const MODELS = {
19491
19544
  input: ["text"],
19492
19545
  cost: {
19493
19546
  input: 0.079,
19494
- output: 4.8,
19495
- cacheRead: 0.059,
19547
+ output: 1.4,
19548
+ cacheRead: 0.078,
19496
19549
  cacheWrite: 0,
19497
19550
  },
19498
19551
  contextWindow: 1048576,
@@ -19592,7 +19645,7 @@ export const MODELS = {
19592
19645
  cacheWrite: 0,
19593
19646
  },
19594
19647
  contextWindow: 1000000,
19595
- maxTokens: 500000,
19648
+ maxTokens: 65536,
19596
19649
  },
19597
19650
  "Qwen/Qwen3.7-Max": {
19598
19651
  id: "Qwen/Qwen3.7-Max",
@@ -19610,7 +19663,7 @@ export const MODELS = {
19610
19663
  cacheWrite: 0,
19611
19664
  },
19612
19665
  contextWindow: 1000000,
19613
- maxTokens: 500000,
19666
+ maxTokens: 131072,
19614
19667
  },
19615
19668
  "deepseek-ai/DeepSeek-V4-Flash-0731": {
19616
19669
  id: "deepseek-ai/DeepSeek-V4-Flash-0731",
@@ -19687,6 +19740,25 @@ export const MODELS = {
19687
19740
  contextWindow: 131072,
19688
19741
  maxTokens: 131072,
19689
19742
  },
19743
+ "meta-models/Muse-Spark-Open-816B-A42B": {
19744
+ id: "meta-models/Muse-Spark-Open-816B-A42B",
19745
+ name: "Muse Spark Open",
19746
+ api: "openai-completions",
19747
+ provider: "together",
19748
+ baseUrl: "https://api.together.ai/v1",
19749
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19750
+ reasoning: true,
19751
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19752
+ input: ["text", "image"],
19753
+ cost: {
19754
+ input: 1.25,
19755
+ output: 4.25,
19756
+ cacheRead: 0.15,
19757
+ cacheWrite: 0,
19758
+ },
19759
+ contextWindow: 1048576,
19760
+ maxTokens: 131072,
19761
+ },
19690
19762
  "moonshotai/Kimi-K3": {
19691
19763
  id: "moonshotai/Kimi-K3",
19692
19764
  name: "Kimi K3",
@@ -19706,6 +19778,25 @@ export const MODELS = {
19706
19778
  contextWindow: 1048576,
19707
19779
  maxTokens: 131072,
19708
19780
  },
19781
+ "nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
19782
+ id: "nvidia/NVIDIA-Nemotron-3.5-Super-VL",
19783
+ name: "Nemotron 3.5 Super VL 120B A12B",
19784
+ api: "openai-completions",
19785
+ provider: "together",
19786
+ baseUrl: "https://api.together.ai/v1",
19787
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19788
+ reasoning: true,
19789
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19790
+ input: ["text", "image"],
19791
+ cost: {
19792
+ input: 0.15,
19793
+ output: 0.5,
19794
+ cacheRead: 0.02,
19795
+ cacheWrite: 0,
19796
+ },
19797
+ contextWindow: 262144,
19798
+ maxTokens: 262144,
19799
+ },
19709
19800
  "nvidia/nemotron-3-ultra-550b-a55b": {
19710
19801
  id: "nvidia/nemotron-3-ultra-550b-a55b",
19711
19802
  name: "Nemotron 3 Ultra 550B A55B",
@@ -19744,6 +19835,25 @@ export const MODELS = {
19744
19835
  contextWindow: 131072,
19745
19836
  maxTokens: 131072,
19746
19837
  },
19838
+ "reflection/Beam-1.0-501B-A23B": {
19839
+ id: "reflection/Beam-1.0-501B-A23B",
19840
+ name: "Beam 1.0 501B A23B",
19841
+ api: "openai-completions",
19842
+ provider: "together",
19843
+ baseUrl: "https://api.together.ai/v1",
19844
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19845
+ reasoning: true,
19846
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19847
+ input: ["text"],
19848
+ cost: {
19849
+ input: 0.4,
19850
+ output: 1.2,
19851
+ cacheRead: 0.04,
19852
+ cacheWrite: 0,
19853
+ },
19854
+ contextWindow: 1048576,
19855
+ maxTokens: 131072,
19856
+ },
19747
19857
  "thinkingmachines/Inkling": {
19748
19858
  id: "thinkingmachines/Inkling",
19749
19859
  name: "Inkling",
@@ -20717,23 +20827,6 @@ export const MODELS = {
20717
20827
  contextWindow: 1000000,
20718
20828
  maxTokens: 128000,
20719
20829
  },
20720
- "anthropic/claude-sonnet-4": {
20721
- id: "anthropic/claude-sonnet-4",
20722
- name: "Claude Sonnet 4",
20723
- api: "anthropic-messages",
20724
- provider: "vercel-ai-gateway",
20725
- baseUrl: "https://ai-gateway.vercel.sh",
20726
- reasoning: true,
20727
- input: ["text", "image"],
20728
- cost: {
20729
- input: 3,
20730
- output: 15,
20731
- cacheRead: 0.3,
20732
- cacheWrite: 3.75,
20733
- },
20734
- contextWindow: 1000000,
20735
- maxTokens: 64000,
20736
- },
20737
20830
  "anthropic/claude-sonnet-4.5": {
20738
20831
  id: "anthropic/claude-sonnet-4.5",
20739
20832
  name: "Claude Sonnet 4.5",
@@ -21134,14 +21227,48 @@ export const MODELS = {
21134
21227
  reasoning: true,
21135
21228
  input: ["text", "image"],
21136
21229
  cost: {
21137
- input: 0.3,
21138
- output: 1.2,
21139
- cacheRead: 0.007,
21230
+ input: 0.075,
21231
+ output: 0.3,
21232
+ cacheRead: 0.0015,
21140
21233
  cacheWrite: 0,
21141
21234
  },
21142
21235
  contextWindow: 1048576,
21143
21236
  maxTokens: 32768,
21144
21237
  },
21238
+ "deepseek/deepseek-v4.1-flash-1017": {
21239
+ id: "deepseek/deepseek-v4.1-flash-1017",
21240
+ name: "DeepSeek V4.1 Flash 1017",
21241
+ api: "anthropic-messages",
21242
+ provider: "vercel-ai-gateway",
21243
+ baseUrl: "https://ai-gateway.vercel.sh",
21244
+ reasoning: true,
21245
+ input: ["text", "image"],
21246
+ cost: {
21247
+ input: 0.075,
21248
+ output: 0.3,
21249
+ cacheRead: 0.0015,
21250
+ cacheWrite: 0,
21251
+ },
21252
+ contextWindow: 1048576,
21253
+ maxTokens: 1048576,
21254
+ },
21255
+ "deepseek/deepseek-v4.1-flash-1017-fast": {
21256
+ id: "deepseek/deepseek-v4.1-flash-1017-fast",
21257
+ name: "DeepSeek V4.1 Flash 1017 Fast",
21258
+ api: "anthropic-messages",
21259
+ provider: "vercel-ai-gateway",
21260
+ baseUrl: "https://ai-gateway.vercel.sh",
21261
+ reasoning: true,
21262
+ input: ["text", "image"],
21263
+ cost: {
21264
+ input: 0.6,
21265
+ output: 2.4,
21266
+ cacheRead: 0.014,
21267
+ cacheWrite: 0,
21268
+ },
21269
+ contextWindow: 1048576,
21270
+ maxTokens: 262144,
21271
+ },
21145
21272
  "deepseek/deepseek-v4.1-flash-fast": {
21146
21273
  id: "deepseek/deepseek-v4.1-flash-fast",
21147
21274
  name: "DeepSeek V4.1 Flash Fast",
@@ -21618,6 +21745,23 @@ export const MODELS = {
21618
21745
  contextWindow: 260000,
21619
21746
  maxTokens: 65536,
21620
21747
  },
21748
+ "inception/mercury-3": {
21749
+ id: "inception/mercury-3",
21750
+ name: "Mercury 3",
21751
+ api: "anthropic-messages",
21752
+ provider: "vercel-ai-gateway",
21753
+ baseUrl: "https://ai-gateway.vercel.sh",
21754
+ reasoning: true,
21755
+ input: ["text"],
21756
+ cost: {
21757
+ input: 0.09999999999999999,
21758
+ output: 0.35,
21759
+ cacheRead: 0.01,
21760
+ cacheWrite: 0,
21761
+ },
21762
+ contextWindow: 1000000,
21763
+ maxTokens: 131072,
21764
+ },
21621
21765
  "inception/mercury-coder-small": {
21622
21766
  id: "inception/mercury-coder-small",
21623
21767
  name: "Mercury Coder Small Beta",
@@ -21746,9 +21890,9 @@ export const MODELS = {
21746
21890
  reasoning: true,
21747
21891
  input: ["text"],
21748
21892
  cost: {
21749
- input: 0.09999999999999999,
21750
- output: 1,
21751
- cacheRead: 0.049999999999999996,
21893
+ input: 0.049999999999999996,
21894
+ output: 0.7,
21895
+ cacheRead: 0.024999999999999998,
21752
21896
  cacheWrite: 0,
21753
21897
  },
21754
21898
  contextWindow: 128000,
@@ -21958,6 +22102,23 @@ export const MODELS = {
21958
22102
  contextWindow: 1048576,
21959
22103
  maxTokens: 1048576,
21960
22104
  },
22105
+ "meta/muse-spark-open": {
22106
+ id: "meta/muse-spark-open",
22107
+ name: "Muse Spark Open",
22108
+ api: "anthropic-messages",
22109
+ provider: "vercel-ai-gateway",
22110
+ baseUrl: "https://ai-gateway.vercel.sh",
22111
+ reasoning: true,
22112
+ input: ["text", "image"],
22113
+ cost: {
22114
+ input: 1.25,
22115
+ output: 4.25,
22116
+ cacheRead: 0.15,
22117
+ cacheWrite: 0,
22118
+ },
22119
+ contextWindow: 1048576,
22120
+ maxTokens: 1048576,
22121
+ },
21961
22122
  "meta/muse-wonder-1.0": {
21962
22123
  id: "meta/muse-wonder-1.0",
21963
22124
  name: "Muse Wonder",
@@ -22111,6 +22272,23 @@ export const MODELS = {
22111
22272
  contextWindow: 512000,
22112
22273
  maxTokens: 512000,
22113
22274
  },
22275
+ "minimax/minimax-m3.1-flash": {
22276
+ id: "minimax/minimax-m3.1-flash",
22277
+ name: "MiniMax-M3.1-Flash",
22278
+ api: "anthropic-messages",
22279
+ provider: "vercel-ai-gateway",
22280
+ baseUrl: "https://ai-gateway.vercel.sh",
22281
+ reasoning: true,
22282
+ input: ["text", "image"],
22283
+ cost: {
22284
+ input: 0,
22285
+ output: 0,
22286
+ cacheRead: 0,
22287
+ cacheWrite: 0,
22288
+ },
22289
+ contextWindow: 1000000,
22290
+ maxTokens: 524288,
22291
+ },
22114
22292
  "mistral/codestral": {
22115
22293
  id: "mistral/codestral",
22116
22294
  name: "Mistral Codestral",
@@ -22205,9 +22383,9 @@ export const MODELS = {
22205
22383
  reasoning: true,
22206
22384
  input: ["text", "image"],
22207
22385
  cost: {
22208
- input: 0.6799999999999999,
22209
- output: 2.09,
22210
- cacheRead: 0.07,
22386
+ input: 1.3599999999999999,
22387
+ output: 4.18,
22388
+ cacheRead: 0.14,
22211
22389
  cacheWrite: 0,
22212
22390
  },
22213
22391
  contextWindow: 524288,
@@ -22485,6 +22663,23 @@ export const MODELS = {
22485
22663
  contextWindow: 1000000,
22486
22664
  maxTokens: 65000,
22487
22665
  },
22666
+ "nvidia/nemotron-3.5-super-vl": {
22667
+ id: "nvidia/nemotron-3.5-super-vl",
22668
+ name: "NVIDIA Nemotron 3.5 Super VL",
22669
+ api: "anthropic-messages",
22670
+ provider: "vercel-ai-gateway",
22671
+ baseUrl: "https://ai-gateway.vercel.sh",
22672
+ reasoning: true,
22673
+ input: ["text", "image"],
22674
+ cost: {
22675
+ input: 0.19999999999999998,
22676
+ output: 0.5,
22677
+ cacheRead: 0.04,
22678
+ cacheWrite: 0,
22679
+ },
22680
+ contextWindow: 1048576,
22681
+ maxTokens: 1048576,
22682
+ },
22488
22683
  "nvidia/nemotron-nano-12b-v2-vl": {
22489
22684
  id: "nvidia/nemotron-nano-12b-v2-vl",
22490
22685
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -24053,6 +24248,40 @@ export const MODELS = {
24053
24248
  contextWindow: 131072,
24054
24249
  maxTokens: 131072,
24055
24250
  },
24251
+ "reflection/beam": {
24252
+ id: "reflection/beam",
24253
+ name: "Beam 1.0",
24254
+ api: "anthropic-messages",
24255
+ provider: "vercel-ai-gateway",
24256
+ baseUrl: "https://ai-gateway.vercel.sh",
24257
+ reasoning: true,
24258
+ input: ["text"],
24259
+ cost: {
24260
+ input: 0,
24261
+ output: 0,
24262
+ cacheRead: 0,
24263
+ cacheWrite: 0,
24264
+ },
24265
+ contextWindow: 1048576,
24266
+ maxTokens: 131072,
24267
+ },
24268
+ "reflection/beam-free": {
24269
+ id: "reflection/beam-free",
24270
+ name: "Beam 1.0 (Free)",
24271
+ api: "anthropic-messages",
24272
+ provider: "vercel-ai-gateway",
24273
+ baseUrl: "https://ai-gateway.vercel.sh",
24274
+ reasoning: true,
24275
+ input: ["text"],
24276
+ cost: {
24277
+ input: 0,
24278
+ output: 0,
24279
+ cacheRead: 0,
24280
+ cacheWrite: 0,
24281
+ },
24282
+ contextWindow: 1048576,
24283
+ maxTokens: 131072,
24284
+ },
24056
24285
  "sakana/fugu-max": {
24057
24286
  id: "sakana/fugu-max",
24058
24287
  name: "Fugu Max",
@@ -24444,6 +24673,23 @@ export const MODELS = {
24444
24673
  contextWindow: 256000,
24445
24674
  maxTokens: 256000,
24446
24675
  },
24676
+ "stepfun/step-5-preview": {
24677
+ id: "stepfun/step-5-preview",
24678
+ name: "Step 5 Preview",
24679
+ api: "anthropic-messages",
24680
+ provider: "vercel-ai-gateway",
24681
+ baseUrl: "https://ai-gateway.vercel.sh",
24682
+ reasoning: true,
24683
+ input: ["text", "image"],
24684
+ cost: {
24685
+ input: 1,
24686
+ output: 2.7,
24687
+ cacheRead: 0.09999999999999999,
24688
+ cacheWrite: 0,
24689
+ },
24690
+ contextWindow: 1048576,
24691
+ maxTokens: 1048576,
24692
+ },
24447
24693
  "tencent/hy3": {
24448
24694
  id: "tencent/hy3",
24449
24695
  name: "Hy3",
@@ -24538,9 +24784,9 @@ export const MODELS = {
24538
24784
  reasoning: true,
24539
24785
  input: ["text"],
24540
24786
  cost: {
24541
- input: 0.435,
24542
- output: 0.87,
24543
- cacheRead: 0.0036,
24787
+ input: 0.3045,
24788
+ output: 0.609,
24789
+ cacheRead: 0.0028,
24544
24790
  cacheWrite: 0,
24545
24791
  },
24546
24792
  contextWindow: 1050000,