@elyracode/ai 0.9.54 → 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",
@@ -7003,6 +7020,24 @@ export const MODELS = {
7003
7020
  contextWindow: 1048576,
7004
7021
  maxTokens: 65536,
7005
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
+ },
7006
7041
  "gemma-4-26b-a4b-it": {
7007
7042
  id: "gemma-4-26b-a4b-it",
7008
7043
  name: "Gemma 4 26B A4B IT",
@@ -7711,7 +7746,7 @@ export const MODELS = {
7711
7746
  cacheWrite: 0,
7712
7747
  },
7713
7748
  contextWindow: 262144,
7714
- maxTokens: 131072,
7749
+ maxTokens: 81920,
7715
7750
  },
7716
7751
  "Qwen/Qwen3-30B-A3B": {
7717
7752
  id: "Qwen/Qwen3-30B-A3B",
@@ -7783,7 +7818,7 @@ export const MODELS = {
7783
7818
  cacheWrite: 0,
7784
7819
  },
7785
7820
  contextWindow: 262144,
7786
- maxTokens: 66536,
7821
+ maxTokens: 65536,
7787
7822
  },
7788
7823
  "Qwen/Qwen3-Coder-Next": {
7789
7824
  id: "Qwen/Qwen3-Coder-Next",
@@ -7819,7 +7854,7 @@ export const MODELS = {
7819
7854
  cacheWrite: 0,
7820
7855
  },
7821
7856
  contextWindow: 262144,
7822
- maxTokens: 66536,
7857
+ maxTokens: 32768,
7823
7858
  },
7824
7859
  "Qwen/Qwen3-Next-80B-A3B-Thinking": {
7825
7860
  id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
@@ -7828,7 +7863,7 @@ export const MODELS = {
7828
7863
  provider: "huggingface",
7829
7864
  baseUrl: "https://router.huggingface.co/v1",
7830
7865
  compat: { "supportsDeveloperRole": false },
7831
- reasoning: false,
7866
+ reasoning: true,
7832
7867
  input: ["text"],
7833
7868
  cost: {
7834
7869
  input: 0.3,
@@ -7837,7 +7872,7 @@ export const MODELS = {
7837
7872
  cacheWrite: 0,
7838
7873
  },
7839
7874
  contextWindow: 262144,
7840
- maxTokens: 131072,
7875
+ maxTokens: 32768,
7841
7876
  },
7842
7877
  "Qwen/Qwen3-VL-235B-A22B-Instruct": {
7843
7878
  id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
@@ -8125,7 +8160,7 @@ export const MODELS = {
8125
8160
  cacheWrite: 0,
8126
8161
  },
8127
8162
  contextWindow: 163840,
8128
- maxTokens: 163840,
8163
+ maxTokens: 32768,
8129
8164
  },
8130
8165
  "deepseek-ai/DeepSeek-V3": {
8131
8166
  id: "deepseek-ai/DeepSeek-V3",
@@ -8307,6 +8342,24 @@ export const MODELS = {
8307
8342
  contextWindow: 1048576,
8308
8343
  maxTokens: 384000,
8309
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
+ },
8310
8363
  "google/gemma-3-12b-it": {
8311
8364
  id: "google/gemma-3-12b-it",
8312
8365
  name: "Gemma 3 12B IT",
@@ -8959,7 +9012,7 @@ export const MODELS = {
8959
9012
  },
8960
9013
  "kimi-for-coding": {
8961
9014
  id: "kimi-for-coding",
8962
- name: "kimi-for-coding",
9015
+ name: "Kimi K2.8 Preview",
8963
9016
  api: "anthropic-messages",
8964
9017
  provider: "kimi-coding",
8965
9018
  baseUrl: "https://api.kimi.com/coding",
@@ -9044,7 +9097,7 @@ export const MODELS = {
9044
9097
  cacheWrite: 0,
9045
9098
  },
9046
9099
  contextWindow: 1000000,
9047
- maxTokens: 512000,
9100
+ maxTokens: 524288,
9048
9101
  },
9049
9102
  },
9050
9103
  "minimax-cn": {
@@ -9057,10 +9110,10 @@ export const MODELS = {
9057
9110
  reasoning: true,
9058
9111
  input: ["text"],
9059
9112
  cost: {
9060
- input: 0.3,
9061
- output: 1.2,
9062
- cacheRead: 0.06,
9063
- cacheWrite: 0.375,
9113
+ input: 0.3137,
9114
+ output: 1.2549,
9115
+ cacheRead: 0.0627,
9116
+ cacheWrite: 0.3922,
9064
9117
  },
9065
9118
  contextWindow: 204800,
9066
9119
  maxTokens: 131072,
@@ -9074,10 +9127,10 @@ export const MODELS = {
9074
9127
  reasoning: true,
9075
9128
  input: ["text"],
9076
9129
  cost: {
9077
- input: 0.6,
9078
- output: 2.4,
9079
- cacheRead: 0.06,
9080
- cacheWrite: 0.375,
9130
+ input: 0.6275,
9131
+ output: 2.5098,
9132
+ cacheRead: 0.0627,
9133
+ cacheWrite: 0.3922,
9081
9134
  },
9082
9135
  contextWindow: 204800,
9083
9136
  maxTokens: 131072,
@@ -9091,13 +9144,13 @@ export const MODELS = {
9091
9144
  reasoning: true,
9092
9145
  input: ["text", "image"],
9093
9146
  cost: {
9094
- input: 0.3,
9095
- output: 1.2,
9096
- cacheRead: 0.06,
9147
+ input: 0.3137,
9148
+ output: 1.2549,
9149
+ cacheRead: 0.0627,
9097
9150
  cacheWrite: 0,
9098
9151
  },
9099
9152
  contextWindow: 1000000,
9100
- maxTokens: 512000,
9153
+ maxTokens: 524288,
9101
9154
  },
9102
9155
  },
9103
9156
  "mistral": {
@@ -9348,9 +9401,9 @@ export const MODELS = {
9348
9401
  reasoning: false,
9349
9402
  input: ["text", "image"],
9350
9403
  cost: {
9351
- input: 0.04,
9352
- output: 0.04,
9353
- cacheRead: 0,
9404
+ input: 0.1,
9405
+ output: 0.1,
9406
+ cacheRead: 0.01,
9354
9407
  cacheWrite: 0,
9355
9408
  },
9356
9409
  contextWindow: 131072,
@@ -9382,9 +9435,9 @@ export const MODELS = {
9382
9435
  reasoning: false,
9383
9436
  input: ["text", "image"],
9384
9437
  cost: {
9385
- input: 0.1,
9386
- output: 0.1,
9387
- cacheRead: 0,
9438
+ input: 0.15,
9439
+ output: 0.15,
9440
+ cacheRead: 0.015,
9388
9441
  cacheWrite: 0,
9389
9442
  },
9390
9443
  contextWindow: 262144,
@@ -9611,23 +9664,6 @@ export const MODELS = {
9611
9664
  contextWindow: 262144,
9612
9665
  maxTokens: 256000,
9613
9666
  },
9614
- "open-mistral-7b": {
9615
- id: "open-mistral-7b",
9616
- name: "Mistral 7B",
9617
- api: "mistral-conversations",
9618
- provider: "mistral",
9619
- baseUrl: "https://api.mistral.ai",
9620
- reasoning: false,
9621
- input: ["text"],
9622
- cost: {
9623
- input: 0.25,
9624
- output: 0.25,
9625
- cacheRead: 0,
9626
- cacheWrite: 0,
9627
- },
9628
- contextWindow: 8000,
9629
- maxTokens: 8000,
9630
- },
9631
9667
  "open-mistral-nemo": {
9632
9668
  id: "open-mistral-nemo",
9633
9669
  name: "Open Mistral Nemo",
@@ -9645,40 +9681,6 @@ export const MODELS = {
9645
9681
  contextWindow: 128000,
9646
9682
  maxTokens: 128000,
9647
9683
  },
9648
- "open-mixtral-8x22b": {
9649
- id: "open-mixtral-8x22b",
9650
- name: "Mixtral 8x22B",
9651
- api: "mistral-conversations",
9652
- provider: "mistral",
9653
- baseUrl: "https://api.mistral.ai",
9654
- reasoning: false,
9655
- input: ["text"],
9656
- cost: {
9657
- input: 2,
9658
- output: 6,
9659
- cacheRead: 0,
9660
- cacheWrite: 0,
9661
- },
9662
- contextWindow: 64000,
9663
- maxTokens: 64000,
9664
- },
9665
- "open-mixtral-8x7b": {
9666
- id: "open-mixtral-8x7b",
9667
- name: "Mixtral 8x7B",
9668
- api: "mistral-conversations",
9669
- provider: "mistral",
9670
- baseUrl: "https://api.mistral.ai",
9671
- reasoning: false,
9672
- input: ["text"],
9673
- cost: {
9674
- input: 0.7,
9675
- output: 0.7,
9676
- cacheRead: 0,
9677
- cacheWrite: 0,
9678
- },
9679
- contextWindow: 32000,
9680
- maxTokens: 32000,
9681
- },
9682
9684
  "pixtral-12b": {
9683
9685
  id: "pixtral-12b",
9684
9686
  name: "Pixtral 12B",
@@ -9740,7 +9742,7 @@ export const MODELS = {
9740
9742
  input: ["text"],
9741
9743
  cost: {
9742
9744
  input: 0.1,
9743
- output: 0.3,
9745
+ output: 0.4,
9744
9746
  cacheRead: 0,
9745
9747
  cacheWrite: 0,
9746
9748
  },
@@ -9867,9 +9869,9 @@ export const MODELS = {
9867
9869
  reasoning: true,
9868
9870
  input: ["text", "image"],
9869
9871
  cost: {
9870
- input: 0.95,
9871
- output: 4,
9872
- cacheRead: 0.16,
9872
+ input: 0.9711,
9873
+ output: 4.0337,
9874
+ cacheRead: 0.1643,
9873
9875
  cacheWrite: 0,
9874
9876
  },
9875
9877
  contextWindow: 262144,
@@ -9885,9 +9887,9 @@ export const MODELS = {
9885
9887
  reasoning: true,
9886
9888
  input: ["text", "image"],
9887
9889
  cost: {
9888
- input: 0.95,
9889
- output: 4,
9890
- cacheRead: 0.19,
9890
+ input: 0.9711,
9891
+ output: 4.0337,
9892
+ cacheRead: 0.1942,
9891
9893
  cacheWrite: 0,
9892
9894
  },
9893
9895
  contextWindow: 262144,
@@ -9903,9 +9905,9 @@ export const MODELS = {
9903
9905
  reasoning: true,
9904
9906
  input: ["text", "image"],
9905
9907
  cost: {
9906
- input: 1.9,
9907
- output: 8,
9908
- cacheRead: 0.38,
9908
+ input: 1.9421,
9909
+ output: 8.0673,
9910
+ cacheRead: 0.3884,
9909
9911
  cacheWrite: 0,
9910
9912
  },
9911
9913
  contextWindow: 262144,
@@ -9921,10 +9923,10 @@ export const MODELS = {
9921
9923
  reasoning: true,
9922
9924
  input: ["text", "image"],
9923
9925
  cost: {
9924
- input: 3,
9925
- output: 15,
9926
- cacheRead: 0.3,
9927
- cacheWrite: 3,
9926
+ input: 2.9879,
9927
+ output: 14.9395,
9928
+ cacheRead: 0.2988,
9929
+ cacheWrite: 2.9879,
9928
9930
  },
9929
9931
  contextWindow: 1048576,
9930
9932
  maxTokens: 1048576,
@@ -10195,24 +10197,6 @@ export const MODELS = {
10195
10197
  contextWindow: 400000,
10196
10198
  maxTokens: 128000,
10197
10199
  },
10198
- "gpt-5.2-chat-latest": {
10199
- id: "gpt-5.2-chat-latest",
10200
- name: "GPT-5.2 Chat",
10201
- api: "openai-responses",
10202
- provider: "openai",
10203
- baseUrl: "https://api.openai.com/v1",
10204
- reasoning: true,
10205
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10206
- input: ["text", "image"],
10207
- cost: {
10208
- input: 1.75,
10209
- output: 14,
10210
- cacheRead: 0.175,
10211
- cacheWrite: 0,
10212
- },
10213
- contextWindow: 128000,
10214
- maxTokens: 16384,
10215
- },
10216
10200
  "gpt-5.2-pro": {
10217
10201
  id: "gpt-5.2-pro",
10218
10202
  name: "GPT-5.2 Pro",
@@ -10231,24 +10215,6 @@ export const MODELS = {
10231
10215
  contextWindow: 400000,
10232
10216
  maxTokens: 128000,
10233
10217
  },
10234
- "gpt-5.3-chat-latest": {
10235
- id: "gpt-5.3-chat-latest",
10236
- name: "GPT-5.3 Chat (latest)",
10237
- api: "openai-responses",
10238
- provider: "openai",
10239
- baseUrl: "https://api.openai.com/v1",
10240
- reasoning: false,
10241
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10242
- input: ["text", "image"],
10243
- cost: {
10244
- input: 1.75,
10245
- output: 14,
10246
- cacheRead: 0.175,
10247
- cacheWrite: 0,
10248
- },
10249
- contextWindow: 128000,
10250
- maxTokens: 16384,
10251
- },
10252
10218
  "gpt-5.3-codex": {
10253
10219
  id: "gpt-5.3-codex",
10254
10220
  name: "GPT-5.3 Codex",
@@ -10868,9 +10834,9 @@ export const MODELS = {
10868
10834
  },
10869
10835
  },
10870
10836
  "opencode": {
10871
- "big-pickle": {
10872
- id: "big-pickle",
10873
- name: "Big Pickle",
10837
+ "beam-free": {
10838
+ id: "beam-free",
10839
+ name: "Beam Free",
10874
10840
  api: "openai-completions",
10875
10841
  provider: "opencode",
10876
10842
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10882,12 +10848,12 @@ export const MODELS = {
10882
10848
  cacheRead: 0,
10883
10849
  cacheWrite: 0,
10884
10850
  },
10885
- contextWindow: 200000,
10886
- maxTokens: 32000,
10851
+ contextWindow: 1048576,
10852
+ maxTokens: 131072,
10887
10853
  },
10888
- "cat-jam-free": {
10889
- id: "cat-jam-free",
10890
- name: "Cat Jam Free",
10854
+ "big-pickle": {
10855
+ id: "big-pickle",
10856
+ name: "Big Pickle",
10891
10857
  api: "openai-completions",
10892
10858
  provider: "opencode",
10893
10859
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10899,8 +10865,8 @@ export const MODELS = {
10899
10865
  cacheRead: 0,
10900
10866
  cacheWrite: 0,
10901
10867
  },
10902
- contextWindow: 262144,
10903
- maxTokens: 131072,
10868
+ contextWindow: 200000,
10869
+ maxTokens: 32000,
10904
10870
  },
10905
10871
  "claude-fable-5": {
10906
10872
  id: "claude-fable-5",
@@ -11238,13 +11204,15 @@ export const MODELS = {
11238
11204
  contextWindow: 1000000,
11239
11205
  maxTokens: 384000,
11240
11206
  },
11241
- "exo-free": {
11242
- id: "exo-free",
11243
- name: "Exo Free",
11207
+ "deepseek-v4.1-flash-free": {
11208
+ id: "deepseek-v4.1-flash-free",
11209
+ name: "DeepSeek V4.1 Flash Free",
11244
11210
  api: "openai-completions",
11245
11211
  provider: "opencode",
11246
11212
  baseUrl: "https://opencode.ai/zen/v1",
11213
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11247
11214
  reasoning: true,
11215
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11248
11216
  input: ["text", "image"],
11249
11217
  cost: {
11250
11218
  input: 0,
@@ -11252,8 +11220,8 @@ export const MODELS = {
11252
11220
  cacheRead: 0,
11253
11221
  cacheWrite: 0,
11254
11222
  },
11255
- contextWindow: 1048576,
11256
- maxTokens: 131072,
11223
+ contextWindow: 200000,
11224
+ maxTokens: 32000,
11257
11225
  },
11258
11226
  "gemini-3-flash": {
11259
11227
  id: "gemini-3-flash",
@@ -11483,19 +11451,36 @@ export const MODELS = {
11483
11451
  contextWindow: 1000000,
11484
11452
  maxTokens: 131072,
11485
11453
  },
11486
- "gpt-5": {
11487
- id: "gpt-5",
11488
- name: "GPT-5",
11489
- api: "openai-responses",
11454
+ "glm-5.3-flash-free": {
11455
+ id: "glm-5.3-flash-free",
11456
+ name: "GLM-5.3-Flash Free",
11457
+ api: "openai-completions",
11490
11458
  provider: "opencode",
11491
11459
  baseUrl: "https://opencode.ai/zen/v1",
11492
11460
  reasoning: true,
11493
- thinkingLevelMap: { "off": null },
11494
11461
  input: ["text", "image"],
11495
11462
  cost: {
11496
- input: 1.07,
11497
- output: 8.5,
11498
- cacheRead: 0.107,
11463
+ input: 0,
11464
+ output: 0,
11465
+ cacheRead: 0,
11466
+ cacheWrite: 0,
11467
+ },
11468
+ contextWindow: 200000,
11469
+ maxTokens: 32000,
11470
+ },
11471
+ "gpt-5": {
11472
+ id: "gpt-5",
11473
+ name: "GPT-5",
11474
+ api: "openai-responses",
11475
+ provider: "opencode",
11476
+ baseUrl: "https://opencode.ai/zen/v1",
11477
+ reasoning: true,
11478
+ thinkingLevelMap: { "off": null },
11479
+ input: ["text", "image"],
11480
+ cost: {
11481
+ input: 1.07,
11482
+ output: 8.5,
11483
+ cacheRead: 0.107,
11499
11484
  cacheWrite: 0,
11500
11485
  },
11501
11486
  contextWindow: 400000,
@@ -12114,6 +12099,23 @@ export const MODELS = {
12114
12099
  contextWindow: 512000,
12115
12100
  maxTokens: 128000,
12116
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
+ },
12117
12119
  "mistral-large-4": {
12118
12120
  id: "mistral-large-4",
12119
12121
  name: "Mistral Large 4",
@@ -12165,18 +12167,18 @@ export const MODELS = {
12165
12167
  contextWindow: 1048576,
12166
12168
  maxTokens: 131072,
12167
12169
  },
12168
- "muse-spark-1.3-contributor-free": {
12169
- id: "muse-spark-1.3-contributor-free",
12170
- name: "Muse Spark 1.3 Free",
12170
+ "muse-wonder-1.0": {
12171
+ id: "muse-wonder-1.0",
12172
+ name: "Muse Wonder",
12171
12173
  api: "openai-responses",
12172
12174
  provider: "opencode",
12173
12175
  baseUrl: "https://opencode.ai/zen/v1",
12174
12176
  reasoning: true,
12175
12177
  input: ["text", "image"],
12176
12178
  cost: {
12177
- input: 0,
12178
- output: 0,
12179
- cacheRead: 0,
12179
+ input: 4,
12180
+ output: 20,
12181
+ cacheRead: 0.2,
12180
12182
  cacheWrite: 0,
12181
12183
  },
12182
12184
  contextWindow: 1048576,
@@ -12216,6 +12218,23 @@ export const MODELS = {
12216
12218
  contextWindow: 262144,
12217
12219
  maxTokens: 262144,
12218
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
+ },
12219
12238
  "qwen3.5-plus": {
12220
12239
  id: "qwen3.5-plus",
12221
12240
  name: "Qwen3.5 Plus",
@@ -12284,45 +12303,11 @@ export const MODELS = {
12284
12303
  contextWindow: 262144,
12285
12304
  maxTokens: 131072,
12286
12305
  },
12287
- "space-bunny-free": {
12288
- id: "space-bunny-free",
12289
- name: "Space Bunny Free",
12290
- api: "openai-completions",
12291
- provider: "opencode",
12292
- baseUrl: "https://opencode.ai/zen/v1",
12293
- reasoning: true,
12294
- input: ["text", "image"],
12295
- cost: {
12296
- input: 0,
12297
- output: 0,
12298
- cacheRead: 0,
12299
- cacheWrite: 0,
12300
- },
12301
- contextWindow: 1048576,
12302
- maxTokens: 524288,
12303
- },
12304
- "step-5-preview-free": {
12305
- id: "step-5-preview-free",
12306
- name: "Step 5 Preview Free",
12307
- api: "openai-completions",
12308
- provider: "opencode",
12309
- baseUrl: "https://opencode.ai/zen/v1",
12310
- reasoning: true,
12311
- input: ["text", "image"],
12312
- cost: {
12313
- input: 0,
12314
- output: 0,
12315
- cacheRead: 0,
12316
- cacheWrite: 0,
12317
- },
12318
- contextWindow: 1000000,
12319
- maxTokens: 65536,
12320
- },
12321
12306
  },
12322
12307
  "opencode-go": {
12323
- "cat-jam-free": {
12324
- id: "cat-jam-free",
12325
- name: "Cat Jam Free",
12308
+ "beam-free": {
12309
+ id: "beam-free",
12310
+ name: "Beam Free",
12326
12311
  api: "openai-completions",
12327
12312
  provider: "opencode-go",
12328
12313
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12334,7 +12319,7 @@ export const MODELS = {
12334
12319
  cacheRead: 0,
12335
12320
  cacheWrite: 0,
12336
12321
  },
12337
- contextWindow: 262144,
12322
+ contextWindow: 1048576,
12338
12323
  maxTokens: 131072,
12339
12324
  },
12340
12325
  "claude-haiku-5-5": {
@@ -12495,23 +12480,6 @@ export const MODELS = {
12495
12480
  contextWindow: 1050000,
12496
12481
  maxTokens: 128000,
12497
12482
  },
12498
- "grok-4.6": {
12499
- id: "grok-4.6",
12500
- name: "Grok 4.6",
12501
- api: "openai-responses",
12502
- provider: "opencode-go",
12503
- baseUrl: "https://opencode.ai/zen/go/v1",
12504
- reasoning: true,
12505
- input: ["text", "image"],
12506
- cost: {
12507
- input: 2,
12508
- output: 6,
12509
- cacheRead: 0.5,
12510
- cacheWrite: 0,
12511
- },
12512
- contextWindow: 500000,
12513
- maxTokens: 500000,
12514
- },
12515
12483
  "grok-4.7": {
12516
12484
  id: "grok-4.7",
12517
12485
  name: "Grok 4.7",
@@ -12699,23 +12667,6 @@ export const MODELS = {
12699
12667
  contextWindow: 1048576,
12700
12668
  maxTokens: 131072,
12701
12669
  },
12702
- "minimax-m2.7": {
12703
- id: "minimax-m2.7",
12704
- name: "MiniMax-M2.7",
12705
- api: "openai-completions",
12706
- provider: "opencode-go",
12707
- baseUrl: "https://opencode.ai/zen/go/v1",
12708
- reasoning: true,
12709
- input: ["text"],
12710
- cost: {
12711
- input: 0.3,
12712
- output: 1.2,
12713
- cacheRead: 0.06,
12714
- cacheWrite: 0.375,
12715
- },
12716
- contextWindow: 204800,
12717
- maxTokens: 131072,
12718
- },
12719
12670
  "minimax-m3": {
12720
12671
  id: "minimax-m3",
12721
12672
  name: "MiniMax-M3",
@@ -12733,6 +12684,23 @@ export const MODELS = {
12733
12684
  contextWindow: 1000000,
12734
12685
  maxTokens: 131072,
12735
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
+ },
12736
12704
  "muse-spark-1.2-contributor": {
12737
12705
  id: "muse-spark-1.2-contributor",
12738
12706
  name: "Muse Spark 1.2 Contributor",
@@ -12818,35 +12786,18 @@ export const MODELS = {
12818
12786
  contextWindow: 1000000,
12819
12787
  maxTokens: 131072,
12820
12788
  },
12821
- "space-bunny": {
12822
- id: "space-bunny",
12823
- name: "Space Bunny",
12789
+ "step-5-preview": {
12790
+ id: "step-5-preview",
12791
+ name: "Step 5 Preview",
12824
12792
  api: "openai-completions",
12825
12793
  provider: "opencode-go",
12826
12794
  baseUrl: "https://opencode.ai/zen/go/v1",
12827
12795
  reasoning: true,
12828
12796
  input: ["text", "image"],
12829
12797
  cost: {
12830
- input: 0.15,
12831
- output: 0.6,
12832
- cacheRead: 0.03,
12833
- cacheWrite: 0,
12834
- },
12835
- contextWindow: 1048576,
12836
- maxTokens: 524288,
12837
- },
12838
- "step-5-preview-free": {
12839
- id: "step-5-preview-free",
12840
- name: "Step 5 Preview Free",
12841
- api: "openai-completions",
12842
- provider: "opencode-go",
12843
- baseUrl: "https://opencode.ai/zen/go/v1",
12844
- reasoning: true,
12845
- input: ["text", "image"],
12846
- cost: {
12847
- input: 0,
12848
- output: 0,
12849
- cacheRead: 0,
12798
+ input: 1,
12799
+ output: 2.7,
12800
+ cacheRead: 0.1,
12850
12801
  cacheWrite: 0,
12851
12802
  },
12852
12803
  contextWindow: 1000000,
@@ -13408,23 +13359,6 @@ export const MODELS = {
13408
13359
  contextWindow: 1000000,
13409
13360
  maxTokens: 128000,
13410
13361
  },
13411
- "anthropic/claude-sonnet-4": {
13412
- id: "anthropic/claude-sonnet-4",
13413
- name: "Anthropic: Claude Sonnet 4",
13414
- api: "openai-completions",
13415
- provider: "openrouter",
13416
- baseUrl: "https://openrouter.ai/api/v1",
13417
- reasoning: true,
13418
- input: ["text", "image"],
13419
- cost: {
13420
- input: 3,
13421
- output: 15,
13422
- cacheRead: 0.3,
13423
- cacheWrite: 3.75,
13424
- },
13425
- contextWindow: 200000,
13426
- maxTokens: 64000,
13427
- },
13428
13362
  "anthropic/claude-sonnet-4.5": {
13429
13363
  id: "anthropic/claude-sonnet-4.5",
13430
13364
  name: "Anthropic: Claude Sonnet 4.5",
@@ -13774,13 +13708,13 @@ export const MODELS = {
13774
13708
  reasoning: false,
13775
13709
  input: ["text"],
13776
13710
  cost: {
13777
- input: 0.32,
13778
- output: 0.8899999999999999,
13711
+ input: 0.2574,
13712
+ output: 1.0287,
13779
13713
  cacheRead: 0,
13780
13714
  cacheWrite: 0,
13781
13715
  },
13782
13716
  contextWindow: 163840,
13783
- maxTokens: 16384,
13717
+ maxTokens: 16000,
13784
13718
  },
13785
13719
  "deepseek/deepseek-chat-v3-0324": {
13786
13720
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13816,23 +13750,6 @@ export const MODELS = {
13816
13750
  contextWindow: 163840,
13817
13751
  maxTokens: 32768,
13818
13752
  },
13819
- "deepseek/deepseek-r1": {
13820
- id: "deepseek/deepseek-r1",
13821
- name: "DeepSeek: R1",
13822
- api: "openai-completions",
13823
- provider: "openrouter",
13824
- baseUrl: "https://openrouter.ai/api/v1",
13825
- reasoning: true,
13826
- input: ["text"],
13827
- cost: {
13828
- input: 0.7,
13829
- output: 2.5,
13830
- cacheRead: 0,
13831
- cacheWrite: 0,
13832
- },
13833
- contextWindow: 64000,
13834
- maxTokens: 16000,
13835
- },
13836
13753
  "deepseek/deepseek-r1-0528": {
13837
13754
  id: "deepseek/deepseek-r1-0528",
13838
13755
  name: "DeepSeek: R1 0528",
@@ -13876,13 +13793,13 @@ export const MODELS = {
13876
13793
  reasoning: true,
13877
13794
  input: ["text"],
13878
13795
  cost: {
13879
- input: 0.25899999999999995,
13880
- output: 0.7999999999999999,
13881
- cacheRead: 0.14,
13796
+ input: 0.28,
13797
+ output: 0.42,
13798
+ cacheRead: 0.028,
13882
13799
  cacheWrite: 0,
13883
13800
  },
13884
13801
  contextWindow: 163840,
13885
- maxTokens: 147456,
13802
+ maxTokens: 65536,
13886
13803
  },
13887
13804
  "deepseek/deepseek-v3.2-exp": {
13888
13805
  id: "deepseek/deepseek-v3.2-exp",
@@ -13931,13 +13848,13 @@ export const MODELS = {
13931
13848
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13932
13849
  input: ["text"],
13933
13850
  cost: {
13934
- input: 0.016,
13935
- output: 0.64,
13936
- cacheRead: 0.016,
13851
+ input: 0.44,
13852
+ output: 1.32,
13853
+ cacheRead: 0.014,
13937
13854
  cacheWrite: 0,
13938
13855
  },
13939
13856
  contextWindow: 1048576,
13940
- maxTokens: 943718,
13857
+ maxTokens: 131072,
13941
13858
  },
13942
13859
  "deepseek/deepseek-v4-flash-vision-exp": {
13943
13860
  id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -13969,9 +13886,9 @@ export const MODELS = {
13969
13886
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13970
13887
  input: ["text"],
13971
13888
  cost: {
13972
- input: 0.43934999999999996,
13973
- output: 0.8786999999999999,
13974
- cacheRead: 0.0366125,
13889
+ input: 0.9552599999999999,
13890
+ output: 1.9105199999999998,
13891
+ cacheRead: 0.07960500000000001,
13975
13892
  cacheWrite: 0,
13976
13893
  },
13977
13894
  contextWindow: 1048576,
@@ -13994,7 +13911,7 @@ export const MODELS = {
13994
13911
  cacheWrite: 0,
13995
13912
  },
13996
13913
  contextWindow: 1048576,
13997
- maxTokens: 393216,
13914
+ maxTokens: 384000,
13998
13915
  },
13999
13916
  "deepseek/deepseek-v4.1-flash": {
14000
13917
  id: "deepseek/deepseek-v4.1-flash",
@@ -14007,14 +13924,33 @@ export const MODELS = {
14007
13924
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14008
13925
  input: ["text", "image"],
14009
13926
  cost: {
14010
- input: 0.02016,
14011
- output: 0.891,
14012
- cacheRead: 0.0054,
13927
+ input: 0.049,
13928
+ output: 0.5249999999999999,
13929
+ cacheRead: 0.001,
14013
13930
  cacheWrite: 0,
14014
13931
  },
14015
13932
  contextWindow: 1048576,
14016
13933
  maxTokens: 943718,
14017
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
+ },
14018
13954
  "deepseek/deepseek-v4.1-flash:batch": {
14019
13955
  id: "deepseek/deepseek-v4.1-flash:batch",
14020
13956
  name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
@@ -14026,13 +13962,13 @@ export const MODELS = {
14026
13962
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14027
13963
  input: ["text", "image"],
14028
13964
  cost: {
14029
- input: 0.112,
14030
- output: 0.33599999999999997,
14031
- cacheRead: 0.00336,
13965
+ input: 0.049999999999999996,
13966
+ output: 0.15,
13967
+ cacheRead: 0.004,
14032
13968
  cacheWrite: 0,
14033
13969
  },
14034
13970
  contextWindow: 1048576,
14035
- maxTokens: 131072,
13971
+ maxTokens: 384000,
14036
13972
  },
14037
13973
  "dots-studio/dots-3-note-preview:free": {
14038
13974
  id: "dots-studio/dots-3-note-preview:free",
@@ -14051,6 +13987,23 @@ export const MODELS = {
14051
13987
  contextWindow: 512000,
14052
13988
  maxTokens: 460800,
14053
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
+ },
14054
14007
  "fireworks/ember-1": {
14055
14008
  id: "fireworks/ember-1",
14056
14009
  name: "Fireworks: Ember-1",
@@ -14119,23 +14072,6 @@ export const MODELS = {
14119
14072
  contextWindow: 1048576,
14120
14073
  maxTokens: 65535,
14121
14074
  },
14122
- "google/gemini-2.5-flash:batch": {
14123
- id: "google/gemini-2.5-flash:batch",
14124
- name: "Google: Gemini 2.5 Flash (batch)",
14125
- api: "openai-completions",
14126
- provider: "openrouter",
14127
- baseUrl: "https://openrouter.ai/api/v1",
14128
- reasoning: true,
14129
- input: ["text", "image"],
14130
- cost: {
14131
- input: 0.15,
14132
- output: 1.25,
14133
- cacheRead: 0.03,
14134
- cacheWrite: 0,
14135
- },
14136
- contextWindow: 1048576,
14137
- maxTokens: 65535,
14138
- },
14139
14075
  "google/gemini-2.5-pro": {
14140
14076
  id: "google/gemini-2.5-pro",
14141
14077
  name: "Google: Gemini 2.5 Pro",
@@ -14170,23 +14106,6 @@ export const MODELS = {
14170
14106
  contextWindow: 1048576,
14171
14107
  maxTokens: 65536,
14172
14108
  },
14173
- "google/gemini-2.5-pro:batch": {
14174
- id: "google/gemini-2.5-pro:batch",
14175
- name: "Google: Gemini 2.5 Pro (batch)",
14176
- api: "openai-completions",
14177
- provider: "openrouter",
14178
- baseUrl: "https://openrouter.ai/api/v1",
14179
- reasoning: true,
14180
- input: ["text", "image"],
14181
- cost: {
14182
- input: 0.625,
14183
- output: 5,
14184
- cacheRead: 0.125,
14185
- cacheWrite: 0,
14186
- },
14187
- contextWindow: 1048576,
14188
- maxTokens: 65536,
14189
- },
14190
14109
  "google/gemini-3-flash-preview": {
14191
14110
  id: "google/gemini-3-flash-preview",
14192
14111
  name: "Google: Gemini 3 Flash Preview",
@@ -14485,9 +14404,9 @@ export const MODELS = {
14485
14404
  reasoning: true,
14486
14405
  input: ["text", "image"],
14487
14406
  cost: {
14488
- input: 0.75,
14489
- output: 3.75,
14490
- cacheRead: 0.075,
14407
+ input: 0.8250000000000001,
14408
+ output: 4.125,
14409
+ cacheRead: 0.0825,
14491
14410
  cacheWrite: 0.0416666666666667,
14492
14411
  },
14493
14412
  contextWindow: 1048576,
@@ -14525,7 +14444,7 @@ export const MODELS = {
14525
14444
  cacheWrite: 0.1875,
14526
14445
  },
14527
14446
  contextWindow: 1048576,
14528
- maxTokens: 65536,
14447
+ maxTokens: 943718,
14529
14448
  },
14530
14449
  "google/gemini-4-argon:batch": {
14531
14450
  id: "google/gemini-4-argon:batch",
@@ -14588,7 +14507,7 @@ export const MODELS = {
14588
14507
  input: ["text", "image"],
14589
14508
  cost: {
14590
14509
  input: 0.08,
14591
- output: 0.44999999999999996,
14510
+ output: 0.35,
14592
14511
  cacheRead: 0.04,
14593
14512
  cacheWrite: 0,
14594
14513
  },
@@ -14604,9 +14523,9 @@ export const MODELS = {
14604
14523
  reasoning: true,
14605
14524
  input: ["text", "image"],
14606
14525
  cost: {
14607
- input: 0.09,
14608
- output: 0.3,
14609
- cacheRead: 0.049999999999999996,
14526
+ input: 0.0765,
14527
+ output: 0.255,
14528
+ cacheRead: 0.042499999999999996,
14610
14529
  cacheWrite: 0,
14611
14530
  },
14612
14531
  contextWindow: 262144,
@@ -14638,9 +14557,9 @@ export const MODELS = {
14638
14557
  reasoning: true,
14639
14558
  input: ["text", "image"],
14640
14559
  cost: {
14641
- input: 0.09,
14642
- output: 0.33999999999999997,
14643
- cacheRead: 0.049999999999999996,
14560
+ input: 0.19999999999999998,
14561
+ output: 0.39999999999999997,
14562
+ cacheRead: 0,
14644
14563
  cacheWrite: 0,
14645
14564
  },
14646
14565
  contextWindow: 262144,
@@ -14711,8 +14630,25 @@ export const MODELS = {
14711
14630
  cacheRead: 0.004,
14712
14631
  cacheWrite: 0,
14713
14632
  },
14714
- contextWindow: 260000,
14715
- maxTokens: 65536,
14633
+ contextWindow: 260000,
14634
+ maxTokens: 65536,
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,
14716
14652
  },
14717
14653
  "inclusionai/ling-3.0-flash": {
14718
14654
  id: "inclusionai/ling-3.0-flash",
@@ -14859,13 +14795,13 @@ export const MODELS = {
14859
14795
  reasoning: false,
14860
14796
  input: ["text"],
14861
14797
  cost: {
14862
- input: 0.59,
14863
- output: 0.7899999999999999,
14864
- cacheRead: 0.295,
14798
+ input: 0.09999999999999999,
14799
+ output: 0.32,
14800
+ cacheRead: 0,
14865
14801
  cacheWrite: 0,
14866
14802
  },
14867
14803
  contextWindow: 131072,
14868
- maxTokens: 32768,
14804
+ maxTokens: 16384,
14869
14805
  },
14870
14806
  "meta-llama/llama-4-maverick": {
14871
14807
  id: "meta-llama/llama-4-maverick",
@@ -14881,7 +14817,7 @@ export const MODELS = {
14881
14817
  cacheRead: 0.049999999999999996,
14882
14818
  cacheWrite: 0,
14883
14819
  },
14884
- contextWindow: 1048576,
14820
+ contextWindow: 524288,
14885
14821
  maxTokens: 16384,
14886
14822
  },
14887
14823
  "meta-llama/llama-4-scout": {
@@ -14893,13 +14829,13 @@ export const MODELS = {
14893
14829
  reasoning: false,
14894
14830
  input: ["text", "image"],
14895
14831
  cost: {
14896
- input: 0.18,
14897
- output: 0.59,
14832
+ input: 0.09999999999999999,
14833
+ output: 0.3,
14898
14834
  cacheRead: 0,
14899
14835
  cacheWrite: 0,
14900
14836
  },
14901
14837
  contextWindow: 1310720,
14902
- maxTokens: 117964,
14838
+ maxTokens: 16384,
14903
14839
  },
14904
14840
  "meta/muse-glimmer-30b": {
14905
14841
  id: "meta/muse-glimmer-30b",
@@ -15003,6 +14939,23 @@ export const MODELS = {
15003
14939
  contextWindow: 1048576,
15004
14940
  maxTokens: 943718,
15005
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
+ },
15006
14959
  "meta/muse-wonder": {
15007
14960
  id: "meta/muse-wonder",
15008
14961
  name: "Meta: Muse Wonder",
@@ -15081,12 +15034,12 @@ export const MODELS = {
15081
15034
  input: ["text"],
15082
15035
  cost: {
15083
15036
  input: 0.27,
15084
- output: 1.08,
15085
- cacheRead: 0.027,
15037
+ output: 0.95,
15038
+ cacheRead: 0.03,
15086
15039
  cacheWrite: 0,
15087
15040
  },
15088
15041
  contextWindow: 204800,
15089
- maxTokens: 128000,
15042
+ maxTokens: 32768,
15090
15043
  },
15091
15044
  "minimax/minimax-m2.7": {
15092
15045
  id: "minimax/minimax-m2.7",
@@ -15122,6 +15075,23 @@ export const MODELS = {
15122
15075
  contextWindow: 1048576,
15123
15076
  maxTokens: 512000,
15124
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
+ },
15125
15095
  "mistralai/codestral-2508": {
15126
15096
  id: "mistralai/codestral-2508",
15127
15097
  name: "Mistral: Codestral 2508",
@@ -15318,9 +15288,9 @@ export const MODELS = {
15318
15288
  reasoning: true,
15319
15289
  input: ["text", "image"],
15320
15290
  cost: {
15321
- input: 0.6799999999999999,
15322
- output: 2.09,
15323
- cacheRead: 0.07,
15291
+ input: 1.3599999999999999,
15292
+ output: 4.18,
15293
+ cacheRead: 0.14,
15324
15294
  cacheWrite: 0,
15325
15295
  },
15326
15296
  contextWindow: 1048576,
@@ -15658,9 +15628,9 @@ export const MODELS = {
15658
15628
  reasoning: true,
15659
15629
  input: ["text", "image"],
15660
15630
  cost: {
15661
- input: 0.7,
15662
- output: 15,
15663
- cacheRead: 0.32,
15631
+ input: 0.23900000000000002,
15632
+ output: 11.936,
15633
+ cacheRead: 0.21,
15664
15634
  cacheWrite: 0,
15665
15635
  },
15666
15636
  contextWindow: 1048576,
@@ -15743,9 +15713,9 @@ export const MODELS = {
15743
15713
  reasoning: true,
15744
15714
  input: ["text"],
15745
15715
  cost: {
15746
- input: 0.08,
15747
- output: 0.44999999999999996,
15748
- cacheRead: 0,
15716
+ input: 0.3,
15717
+ output: 2.4,
15718
+ cacheRead: 0.15,
15749
15719
  cacheWrite: 0,
15750
15720
  },
15751
15721
  contextWindow: 262144,
@@ -15836,6 +15806,40 @@ export const MODELS = {
15836
15806
  contextWindow: 1000000,
15837
15807
  maxTokens: 65536,
15838
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
+ },
15839
15843
  "openai/gpt-3.5-turbo": {
15840
15844
  id: "openai/gpt-3.5-turbo",
15841
15845
  name: "OpenAI: GPT-3.5 Turbo",
@@ -16731,10 +16735,10 @@ export const MODELS = {
16731
16735
  reasoning: true,
16732
16736
  input: ["text", "image"],
16733
16737
  cost: {
16734
- input: 2,
16735
- output: 10,
16736
- cacheRead: 0.19999999999999998,
16737
- cacheWrite: 2.5,
16738
+ input: 4,
16739
+ output: 20,
16740
+ cacheRead: 0.39999999999999997,
16741
+ cacheWrite: 5,
16738
16742
  },
16739
16743
  contextWindow: 1050000,
16740
16744
  maxTokens: 128000,
@@ -16748,10 +16752,10 @@ export const MODELS = {
16748
16752
  reasoning: true,
16749
16753
  input: ["text", "image"],
16750
16754
  cost: {
16751
- input: 2,
16752
- output: 10,
16753
- cacheRead: 0.19999999999999998,
16754
- cacheWrite: 2.5,
16755
+ input: 4,
16756
+ output: 20,
16757
+ cacheRead: 0.39999999999999997,
16758
+ cacheWrite: 5,
16755
16759
  },
16756
16760
  contextWindow: 1050000,
16757
16761
  maxTokens: 128000,
@@ -16765,10 +16769,10 @@ export const MODELS = {
16765
16769
  reasoning: true,
16766
16770
  input: ["text", "image"],
16767
16771
  cost: {
16768
- input: 1,
16769
- output: 5,
16770
- cacheRead: 0.09999999999999999,
16771
- cacheWrite: 1.25,
16772
+ input: 2,
16773
+ output: 10,
16774
+ cacheRead: 0.19999999999999998,
16775
+ cacheWrite: 2.5,
16772
16776
  },
16773
16777
  contextWindow: 1050000,
16774
16778
  maxTokens: 128000,
@@ -16782,10 +16786,10 @@ export const MODELS = {
16782
16786
  reasoning: true,
16783
16787
  input: ["text", "image"],
16784
16788
  cost: {
16785
- input: 1,
16786
- output: 5,
16787
- cacheRead: 0.09999999999999999,
16788
- cacheWrite: 1.25,
16789
+ input: 2,
16790
+ output: 10,
16791
+ cacheRead: 0.19999999999999998,
16792
+ cacheWrite: 2.5,
16789
16793
  },
16790
16794
  contextWindow: 1050000,
16791
16795
  maxTokens: 128000,
@@ -17207,13 +17211,13 @@ export const MODELS = {
17207
17211
  reasoning: true,
17208
17212
  input: ["text"],
17209
17213
  cost: {
17210
- input: 0.037,
17211
- output: 0.16999999999999998,
17212
- cacheRead: 0,
17214
+ input: 0.15,
17215
+ output: 0.6,
17216
+ cacheRead: 0.075,
17213
17217
  cacheWrite: 0,
17214
17218
  },
17215
17219
  contextWindow: 131072,
17216
- maxTokens: 117964,
17220
+ maxTokens: 65536,
17217
17221
  },
17218
17222
  "openai/gpt-oss-120b:batch": {
17219
17223
  id: "openai/gpt-oss-120b:batch",
@@ -17751,7 +17755,7 @@ export const MODELS = {
17751
17755
  reasoning: false,
17752
17756
  input: ["text"],
17753
17757
  cost: {
17754
- input: 0.09999999999999999,
17758
+ input: 0.09,
17755
17759
  output: 0.3,
17756
17760
  cacheRead: 0,
17757
17761
  cacheWrite: 0,
@@ -17853,13 +17857,13 @@ export const MODELS = {
17853
17857
  reasoning: false,
17854
17858
  input: ["text"],
17855
17859
  cost: {
17856
- input: 0.09999999999999999,
17860
+ input: 0.09,
17857
17861
  output: 1.1,
17858
- cacheRead: 0.07,
17862
+ cacheRead: 0,
17859
17863
  cacheWrite: 0,
17860
17864
  },
17861
17865
  contextWindow: 262144,
17862
- maxTokens: 235929,
17866
+ maxTokens: 16384,
17863
17867
  },
17864
17868
  "qwen/qwen3-next-80b-a3b-thinking": {
17865
17869
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -17972,13 +17976,13 @@ export const MODELS = {
17972
17976
  reasoning: true,
17973
17977
  input: ["text", "image"],
17974
17978
  cost: {
17975
- input: 0.26,
17976
- output: 2.6,
17977
- cacheRead: 0,
17979
+ input: 0.27,
17980
+ output: 2.16,
17981
+ cacheRead: 0.27,
17978
17982
  cacheWrite: 0,
17979
17983
  },
17980
17984
  contextWindow: 262144,
17981
- maxTokens: 81920,
17985
+ maxTokens: 65536,
17982
17986
  },
17983
17987
  "qwen/qwen3.5-35b-a3b": {
17984
17988
  id: "qwen/qwen3.5-35b-a3b",
@@ -17989,13 +17993,13 @@ export const MODELS = {
17989
17993
  reasoning: true,
17990
17994
  input: ["text", "image"],
17991
17995
  cost: {
17992
- input: 0.15,
17996
+ input: 0.14,
17993
17997
  output: 1,
17994
17998
  cacheRead: 0.049999999999999996,
17995
17999
  cacheWrite: 0,
17996
18000
  },
17997
18001
  contextWindow: 262144,
17998
- maxTokens: 16384,
18002
+ maxTokens: 81920,
17999
18003
  },
18000
18004
  "qwen/qwen3.5-397b-a17b": {
18001
18005
  id: "qwen/qwen3.5-397b-a17b",
@@ -18006,13 +18010,13 @@ export const MODELS = {
18006
18010
  reasoning: true,
18007
18011
  input: ["text", "image"],
18008
18012
  cost: {
18009
- input: 0.5,
18010
- output: 3.5999999999999996,
18011
- cacheRead: 0.3,
18013
+ input: 0.39,
18014
+ output: 2.34,
18015
+ cacheRead: 0,
18012
18016
  cacheWrite: 0,
18013
18017
  },
18014
18018
  contextWindow: 262144,
18015
- maxTokens: 235929,
18019
+ maxTokens: 65536,
18016
18020
  },
18017
18021
  "qwen/qwen3.5-9b": {
18018
18022
  id: "qwen/qwen3.5-9b",
@@ -18023,13 +18027,13 @@ export const MODELS = {
18023
18027
  reasoning: true,
18024
18028
  input: ["text", "image"],
18025
18029
  cost: {
18026
- input: 0.09999999999999999,
18027
- output: 0.15,
18028
- cacheRead: 0,
18030
+ input: 0.08,
18031
+ output: 0.13,
18032
+ cacheRead: 0.04,
18029
18033
  cacheWrite: 0,
18030
18034
  },
18031
18035
  contextWindow: 262144,
18032
- maxTokens: 32768,
18036
+ maxTokens: 65536,
18033
18037
  },
18034
18038
  "qwen/qwen3.5-flash-02-23": {
18035
18039
  id: "qwen/qwen3.5-flash-02-23",
@@ -18091,13 +18095,13 @@ export const MODELS = {
18091
18095
  reasoning: true,
18092
18096
  input: ["text", "image"],
18093
18097
  cost: {
18094
- input: 0.32,
18095
- output: 3.1999999999999997,
18096
- cacheRead: 0,
18098
+ input: 0.25,
18099
+ output: 2,
18100
+ cacheRead: 0.024999999999999998,
18097
18101
  cacheWrite: 0,
18098
18102
  },
18099
18103
  contextWindow: 262144,
18100
- maxTokens: 81920,
18104
+ maxTokens: 65536,
18101
18105
  },
18102
18106
  "qwen/qwen3.6-35b-a3b": {
18103
18107
  id: "qwen/qwen3.6-35b-a3b",
@@ -18110,11 +18114,11 @@ export const MODELS = {
18110
18114
  cost: {
18111
18115
  input: 0.09999999999999999,
18112
18116
  output: 0.95,
18113
- cacheRead: 0.09999999999999999,
18117
+ cacheRead: 0.049999999999999996,
18114
18118
  cacheWrite: 0,
18115
18119
  },
18116
18120
  contextWindow: 262144,
18117
- maxTokens: 65536,
18121
+ maxTokens: 235929,
18118
18122
  },
18119
18123
  "qwen/qwen3.6-flash": {
18120
18124
  id: "qwen/qwen3.6-flash",
@@ -18201,6 +18205,23 @@ export const MODELS = {
18201
18205
  contextWindow: 1000000,
18202
18206
  maxTokens: 131072,
18203
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
+ },
18204
18225
  "qwen/qwen3.8-2.4t-a95b": {
18205
18226
  id: "qwen/qwen3.8-2.4t-a95b",
18206
18227
  name: "Qwen: Qwen3.8 2.4T A95B",
@@ -18216,7 +18237,7 @@ export const MODELS = {
18216
18237
  cacheWrite: 0,
18217
18238
  },
18218
18239
  contextWindow: 1048576,
18219
- maxTokens: 131072,
18240
+ maxTokens: 909000,
18220
18241
  },
18221
18242
  "qwen/qwen3.8-27b": {
18222
18243
  id: "qwen/qwen3.8-27b",
@@ -18228,12 +18249,12 @@ export const MODELS = {
18228
18249
  input: ["text", "image"],
18229
18250
  cost: {
18230
18251
  input: 0.04,
18231
- output: 2.3,
18232
- cacheRead: 0.019799999999999998,
18252
+ output: 1.35,
18253
+ cacheRead: 0.018,
18233
18254
  cacheWrite: 0,
18234
18255
  },
18235
18256
  contextWindow: 1000000,
18236
- maxTokens: 235929,
18257
+ maxTokens: 65536,
18237
18258
  },
18238
18259
  "qwen/qwen3.8-flash": {
18239
18260
  id: "qwen/qwen3.8-flash",
@@ -18303,6 +18324,23 @@ export const MODELS = {
18303
18324
  contextWindow: 1000000,
18304
18325
  maxTokens: 131072,
18305
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
+ },
18306
18344
  "rekaai/reka-edge": {
18307
18345
  id: "rekaai/reka-edge",
18308
18346
  name: "Reka Edge",
@@ -18450,10 +18488,10 @@ export const MODELS = {
18450
18488
  cost: {
18451
18489
  input: 1,
18452
18490
  output: 2.7,
18453
- cacheRead: 0.049999999999999996,
18491
+ cacheRead: 0.09999999999999999,
18454
18492
  cacheWrite: 0,
18455
18493
  },
18456
- contextWindow: 1000000,
18494
+ contextWindow: 1048576,
18457
18495
  maxTokens: 64000,
18458
18496
  },
18459
18497
  "tencent/hy3": {
@@ -18575,9 +18613,9 @@ export const MODELS = {
18575
18613
  contextWindow: 1000000,
18576
18614
  maxTokens: 4096,
18577
18615
  },
18578
- "unbiased/pareto-26.10-preview": {
18579
- id: "unbiased/pareto-26.10-preview",
18580
- name: "Pareto 26.10 Preview",
18616
+ "unbiased/pareto-26.10": {
18617
+ id: "unbiased/pareto-26.10",
18618
+ name: "Pareto 26.10",
18581
18619
  api: "openai-completions",
18582
18620
  provider: "openrouter",
18583
18621
  baseUrl: "https://openrouter.ai/api/v1",
@@ -18652,9 +18690,9 @@ export const MODELS = {
18652
18690
  reasoning: true,
18653
18691
  input: ["text"],
18654
18692
  cost: {
18655
- input: 0.09,
18656
- output: 0.36,
18657
- cacheRead: 0.018,
18693
+ input: 0.15,
18694
+ output: 0.6,
18695
+ cacheRead: 0.03,
18658
18696
  cacheWrite: 0,
18659
18697
  },
18660
18698
  contextWindow: 524288,
@@ -18788,13 +18826,13 @@ export const MODELS = {
18788
18826
  reasoning: true,
18789
18827
  input: ["text", "image"],
18790
18828
  cost: {
18791
- input: 0.14,
18792
- output: 0.28,
18793
- cacheRead: 0.0028,
18829
+ input: 0.119,
18830
+ output: 0.238,
18831
+ cacheRead: 0.00255,
18794
18832
  cacheWrite: 0,
18795
18833
  },
18796
18834
  contextWindow: 1050000,
18797
- maxTokens: 131072,
18835
+ maxTokens: 945000,
18798
18836
  },
18799
18837
  "xiaomi/mimo-v2.5-pro": {
18800
18838
  id: "xiaomi/mimo-v2.5-pro",
@@ -18805,13 +18843,13 @@ export const MODELS = {
18805
18843
  reasoning: true,
18806
18844
  input: ["text"],
18807
18845
  cost: {
18808
- input: 0.435,
18809
- output: 0.87,
18810
- cacheRead: 0.0036,
18846
+ input: 0.3045,
18847
+ output: 0.609,
18848
+ cacheRead: 0.0028,
18811
18849
  cacheWrite: 0,
18812
18850
  },
18813
18851
  contextWindow: 1050000,
18814
- maxTokens: 131072,
18852
+ maxTokens: 945000,
18815
18853
  },
18816
18854
  "xiaomi/mimo-v2.6-flash": {
18817
18855
  id: "xiaomi/mimo-v2.6-flash",
@@ -18864,6 +18902,23 @@ export const MODELS = {
18864
18902
  contextWindow: 1048576,
18865
18903
  maxTokens: 131072,
18866
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
+ },
18867
18922
  "z-ai/glm-4.5": {
18868
18923
  id: "z-ai/glm-4.5",
18869
18924
  name: "Z.ai: GLM 4.5",
@@ -18924,9 +18979,9 @@ export const MODELS = {
18924
18979
  reasoning: true,
18925
18980
  input: ["text"],
18926
18981
  cost: {
18927
- input: 0.5,
18928
- output: 2,
18929
- cacheRead: 0.09999999999999999,
18982
+ input: 0.55,
18983
+ output: 2.2,
18984
+ cacheRead: 0.11,
18930
18985
  cacheWrite: 0,
18931
18986
  },
18932
18987
  contextWindow: 204800,
@@ -18958,9 +19013,9 @@ export const MODELS = {
18958
19013
  reasoning: true,
18959
19014
  input: ["text"],
18960
19015
  cost: {
18961
- input: 0.6,
18962
- output: 2.2,
18963
- cacheRead: 0.11,
19016
+ input: 0.54,
19017
+ output: 1.9800000000000002,
19018
+ cacheRead: 0.099,
18964
19019
  cacheWrite: 0,
18965
19020
  },
18966
19021
  contextWindow: 204800,
@@ -18998,7 +19053,7 @@ export const MODELS = {
18998
19053
  cacheWrite: 0,
18999
19054
  },
19000
19055
  contextWindow: 204800,
19001
- maxTokens: 128000,
19056
+ maxTokens: 131072,
19002
19057
  },
19003
19058
  "z-ai/glm-5-turbo": {
19004
19059
  id: "z-ai/glm-5-turbo",
@@ -19026,9 +19081,9 @@ export const MODELS = {
19026
19081
  reasoning: true,
19027
19082
  input: ["text"],
19028
19083
  cost: {
19029
- input: 1.33,
19030
- output: 4.18,
19031
- cacheRead: 0.24699999999999997,
19084
+ input: 1.4,
19085
+ output: 4.4,
19086
+ cacheRead: 0.26,
19032
19087
  cacheWrite: 0,
19033
19088
  },
19034
19089
  contextWindow: 204800,
@@ -19043,9 +19098,9 @@ export const MODELS = {
19043
19098
  reasoning: true,
19044
19099
  input: ["text"],
19045
19100
  cost: {
19046
- input: 0.049999999999999996,
19101
+ input: 0.0341,
19047
19102
  output: 7,
19048
- cacheRead: 0.049,
19103
+ cacheRead: 0.032999999999999995,
19049
19104
  cacheWrite: 0,
19050
19105
  },
19051
19106
  contextWindow: 1048576,
@@ -19061,8 +19116,8 @@ export const MODELS = {
19061
19116
  input: ["text"],
19062
19117
  cost: {
19063
19118
  input: 0.079,
19064
- output: 4.8,
19065
- cacheRead: 0.059,
19119
+ output: 1.4,
19120
+ cacheRead: 0.078,
19066
19121
  cacheWrite: 0,
19067
19122
  },
19068
19123
  contextWindow: 1048576,
@@ -19077,13 +19132,13 @@ export const MODELS = {
19077
19132
  reasoning: true,
19078
19133
  input: ["text", "image"],
19079
19134
  cost: {
19080
- input: 0.036,
19081
- output: 0.8999999999999999,
19082
- cacheRead: 0.0108,
19135
+ input: 0.15,
19136
+ output: 0.5,
19137
+ cacheRead: 0.03,
19083
19138
  cacheWrite: 0,
19084
19139
  },
19085
19140
  contextWindow: 1048576,
19086
- maxTokens: 943718,
19141
+ maxTokens: 943717,
19087
19142
  },
19088
19143
  "z-ai/glm-5.3-flash:batch": {
19089
19144
  id: "z-ai/glm-5.3-flash:batch",
@@ -19094,9 +19149,9 @@ export const MODELS = {
19094
19149
  reasoning: true,
19095
19150
  input: ["text", "image"],
19096
19151
  cost: {
19097
- input: 0.06,
19098
- output: 0.19999999999999998,
19099
- cacheRead: 0.012,
19152
+ input: 0.049999999999999996,
19153
+ output: 0.18,
19154
+ cacheRead: 0.01,
19100
19155
  cacheWrite: 0,
19101
19156
  },
19102
19157
  contextWindow: 1048576,
@@ -19248,9 +19303,9 @@ export const MODELS = {
19248
19303
  reasoning: true,
19249
19304
  input: ["text", "image"],
19250
19305
  cost: {
19251
- input: 0.02016,
19252
- output: 0.891,
19253
- cacheRead: 0.0054,
19306
+ input: 0.07,
19307
+ output: 0.5,
19308
+ cacheRead: 0.008,
19254
19309
  cacheWrite: 0,
19255
19310
  },
19256
19311
  contextWindow: 1048576,
@@ -19265,9 +19320,9 @@ export const MODELS = {
19265
19320
  reasoning: true,
19266
19321
  input: ["text"],
19267
19322
  cost: {
19268
- input: 0.14609999999999998,
19323
+ input: 0.22499999999999998,
19269
19324
  output: 8,
19270
- cacheRead: 0.15,
19325
+ cacheRead: 0.22999999999999998,
19271
19326
  cacheWrite: 0,
19272
19327
  },
19273
19328
  contextWindow: 1048576,
@@ -19284,13 +19339,13 @@ export const MODELS = {
19284
19339
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19285
19340
  input: ["text"],
19286
19341
  cost: {
19287
- input: 0.0144,
19288
- output: 0.576,
19289
- cacheRead: 0.0108,
19342
+ input: 0.020999999999999998,
19343
+ output: 0.5279999999999999,
19344
+ cacheRead: 0.0056,
19290
19345
  cacheWrite: 0,
19291
19346
  },
19292
19347
  contextWindow: 1048576,
19293
- maxTokens: 943718,
19348
+ maxTokens: 131072,
19294
19349
  },
19295
19350
  "~google/gemini-flash-latest": {
19296
19351
  id: "~google/gemini-flash-latest",
@@ -19319,12 +19374,12 @@ export const MODELS = {
19319
19374
  input: ["text", "image"],
19320
19375
  cost: {
19321
19376
  input: 2,
19322
- output: 12,
19323
- cacheRead: 0.19999999999999998,
19324
- cacheWrite: 0.375,
19377
+ output: 10,
19378
+ cacheRead: 0.09999999999999999,
19379
+ cacheWrite: 0.1875,
19325
19380
  },
19326
19381
  contextWindow: 1048576,
19327
- maxTokens: 65536,
19382
+ maxTokens: 943718,
19328
19383
  },
19329
19384
  "~moonshotai/kimi-latest": {
19330
19385
  id: "~moonshotai/kimi-latest",
@@ -19335,9 +19390,9 @@ export const MODELS = {
19335
19390
  reasoning: true,
19336
19391
  input: ["text", "image"],
19337
19392
  cost: {
19338
- input: 0.536,
19339
- output: 14,
19340
- cacheRead: 0.3,
19393
+ input: 0.238,
19394
+ output: 16,
19395
+ cacheRead: 0.228,
19341
19396
  cacheWrite: 0,
19342
19397
  },
19343
19398
  contextWindow: 1048576,
@@ -19437,12 +19492,12 @@ export const MODELS = {
19437
19492
  reasoning: false,
19438
19493
  input: ["text", "image"],
19439
19494
  cost: {
19440
- input: 2.5,
19441
- output: 7.5,
19442
- cacheRead: 0.25,
19495
+ input: 0.7999999999999999,
19496
+ output: 3.1999999999999997,
19497
+ cacheRead: 0.03,
19443
19498
  cacheWrite: 0,
19444
19499
  },
19445
- contextWindow: 262144,
19500
+ contextWindow: 1048576,
19446
19501
  maxTokens: 131072,
19447
19502
  },
19448
19503
  "~x-ai/grok-latest": {
@@ -19471,9 +19526,9 @@ export const MODELS = {
19471
19526
  reasoning: true,
19472
19527
  input: ["text", "image"],
19473
19528
  cost: {
19474
- input: 0.036,
19475
- output: 0.8999999999999999,
19476
- cacheRead: 0.0108,
19529
+ input: 0.051691,
19530
+ output: 0.5249999999999999,
19531
+ cacheRead: 0.00375,
19477
19532
  cacheWrite: 0,
19478
19533
  },
19479
19534
  contextWindow: 1048576,
@@ -19488,13 +19543,13 @@ export const MODELS = {
19488
19543
  reasoning: true,
19489
19544
  input: ["text"],
19490
19545
  cost: {
19491
- input: 0.0576,
19492
- output: 4.4,
19493
- cacheRead: 0.053599999999999995,
19546
+ input: 0.079,
19547
+ output: 1.4,
19548
+ cacheRead: 0.078,
19494
19549
  cacheWrite: 0,
19495
19550
  },
19496
19551
  contextWindow: 1048576,
19497
- maxTokens: 131072,
19552
+ maxTokens: 943718,
19498
19553
  },
19499
19554
  },
19500
19555
  "together": {
@@ -19590,7 +19645,7 @@ export const MODELS = {
19590
19645
  cacheWrite: 0,
19591
19646
  },
19592
19647
  contextWindow: 1000000,
19593
- maxTokens: 500000,
19648
+ maxTokens: 65536,
19594
19649
  },
19595
19650
  "Qwen/Qwen3.7-Max": {
19596
19651
  id: "Qwen/Qwen3.7-Max",
@@ -19608,7 +19663,7 @@ export const MODELS = {
19608
19663
  cacheWrite: 0,
19609
19664
  },
19610
19665
  contextWindow: 1000000,
19611
- maxTokens: 500000,
19666
+ maxTokens: 131072,
19612
19667
  },
19613
19668
  "deepseek-ai/DeepSeek-V4-Flash-0731": {
19614
19669
  id: "deepseek-ai/DeepSeek-V4-Flash-0731",
@@ -19685,6 +19740,25 @@ export const MODELS = {
19685
19740
  contextWindow: 131072,
19686
19741
  maxTokens: 131072,
19687
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
+ },
19688
19762
  "moonshotai/Kimi-K3": {
19689
19763
  id: "moonshotai/Kimi-K3",
19690
19764
  name: "Kimi K3",
@@ -19704,6 +19778,25 @@ export const MODELS = {
19704
19778
  contextWindow: 1048576,
19705
19779
  maxTokens: 131072,
19706
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
+ },
19707
19800
  "nvidia/nemotron-3-ultra-550b-a55b": {
19708
19801
  id: "nvidia/nemotron-3-ultra-550b-a55b",
19709
19802
  name: "Nemotron 3 Ultra 550B A55B",
@@ -19742,6 +19835,25 @@ export const MODELS = {
19742
19835
  contextWindow: 131072,
19743
19836
  maxTokens: 131072,
19744
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
+ },
19745
19857
  "thinkingmachines/Inkling": {
19746
19858
  id: "thinkingmachines/Inkling",
19747
19859
  name: "Inkling",
@@ -20715,23 +20827,6 @@ export const MODELS = {
20715
20827
  contextWindow: 1000000,
20716
20828
  maxTokens: 128000,
20717
20829
  },
20718
- "anthropic/claude-sonnet-4": {
20719
- id: "anthropic/claude-sonnet-4",
20720
- name: "Claude Sonnet 4",
20721
- api: "anthropic-messages",
20722
- provider: "vercel-ai-gateway",
20723
- baseUrl: "https://ai-gateway.vercel.sh",
20724
- reasoning: true,
20725
- input: ["text", "image"],
20726
- cost: {
20727
- input: 3,
20728
- output: 15,
20729
- cacheRead: 0.3,
20730
- cacheWrite: 3.75,
20731
- },
20732
- contextWindow: 1000000,
20733
- maxTokens: 64000,
20734
- },
20735
20830
  "anthropic/claude-sonnet-4.5": {
20736
20831
  id: "anthropic/claude-sonnet-4.5",
20737
20832
  name: "Claude Sonnet 4.5",
@@ -21132,14 +21227,48 @@ export const MODELS = {
21132
21227
  reasoning: true,
21133
21228
  input: ["text", "image"],
21134
21229
  cost: {
21135
- input: 0.3,
21136
- output: 1.2,
21137
- cacheRead: 0.007,
21230
+ input: 0.075,
21231
+ output: 0.3,
21232
+ cacheRead: 0.0015,
21138
21233
  cacheWrite: 0,
21139
21234
  },
21140
21235
  contextWindow: 1048576,
21141
21236
  maxTokens: 32768,
21142
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
+ },
21143
21272
  "deepseek/deepseek-v4.1-flash-fast": {
21144
21273
  id: "deepseek/deepseek-v4.1-flash-fast",
21145
21274
  name: "DeepSeek V4.1 Flash Fast",
@@ -21616,6 +21745,23 @@ export const MODELS = {
21616
21745
  contextWindow: 260000,
21617
21746
  maxTokens: 65536,
21618
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
+ },
21619
21765
  "inception/mercury-coder-small": {
21620
21766
  id: "inception/mercury-coder-small",
21621
21767
  name: "Mercury Coder Small Beta",
@@ -21956,6 +22102,23 @@ export const MODELS = {
21956
22102
  contextWindow: 1048576,
21957
22103
  maxTokens: 1048576,
21958
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
+ },
21959
22122
  "meta/muse-wonder-1.0": {
21960
22123
  id: "meta/muse-wonder-1.0",
21961
22124
  name: "Muse Wonder",
@@ -22109,6 +22272,23 @@ export const MODELS = {
22109
22272
  contextWindow: 512000,
22110
22273
  maxTokens: 512000,
22111
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
+ },
22112
22292
  "mistral/codestral": {
22113
22293
  id: "mistral/codestral",
22114
22294
  name: "Mistral Codestral",
@@ -22203,9 +22383,9 @@ export const MODELS = {
22203
22383
  reasoning: true,
22204
22384
  input: ["text", "image"],
22205
22385
  cost: {
22206
- input: 0.6799999999999999,
22207
- output: 2.09,
22208
- cacheRead: 0.07,
22386
+ input: 1.3599999999999999,
22387
+ output: 4.18,
22388
+ cacheRead: 0.14,
22209
22389
  cacheWrite: 0,
22210
22390
  },
22211
22391
  contextWindow: 524288,
@@ -22483,6 +22663,23 @@ export const MODELS = {
22483
22663
  contextWindow: 1000000,
22484
22664
  maxTokens: 65000,
22485
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
+ },
22486
22683
  "nvidia/nemotron-nano-12b-v2-vl": {
22487
22684
  id: "nvidia/nemotron-nano-12b-v2-vl",
22488
22685
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -24051,6 +24248,40 @@ export const MODELS = {
24051
24248
  contextWindow: 131072,
24052
24249
  maxTokens: 131072,
24053
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
+ },
24054
24285
  "sakana/fugu-max": {
24055
24286
  id: "sakana/fugu-max",
24056
24287
  name: "Fugu Max",
@@ -24442,6 +24673,23 @@ export const MODELS = {
24442
24673
  contextWindow: 256000,
24443
24674
  maxTokens: 256000,
24444
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
+ },
24445
24693
  "tencent/hy3": {
24446
24694
  id: "tencent/hy3",
24447
24695
  name: "Hy3",
@@ -24536,9 +24784,9 @@ export const MODELS = {
24536
24784
  reasoning: true,
24537
24785
  input: ["text"],
24538
24786
  cost: {
24539
- input: 0.435,
24540
- output: 0.87,
24541
- cacheRead: 0.0036,
24787
+ input: 0.3045,
24788
+ output: 0.609,
24789
+ cacheRead: 0.0028,
24542
24790
  cacheWrite: 0,
24543
24791
  },
24544
24792
  contextWindow: 1050000,