@kolisachint/hoocode-ai 0.5.80 → 0.5.81

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.
@@ -178,6 +178,24 @@ export const MODELS = {
178
178
  contextWindow: 1000000,
179
179
  maxTokens: 128000,
180
180
  },
181
+ "claude-opus-5-5": {
182
+ id: "claude-opus-5-5",
183
+ name: "Claude Opus 5.5",
184
+ api: "anthropic-messages",
185
+ provider: "anthropic",
186
+ baseUrl: "https://api.anthropic.com",
187
+ reasoning: true,
188
+ thinkingLevelMap: { "xhigh": "xhigh" },
189
+ input: ["text", "image"],
190
+ cost: {
191
+ input: 4,
192
+ output: 20,
193
+ cacheRead: 0.2,
194
+ cacheWrite: 5,
195
+ },
196
+ contextWindow: 1000000,
197
+ maxTokens: 128000,
198
+ },
181
199
  "claude-sonnet-4-5": {
182
200
  id: "claude-sonnet-4-5",
183
201
  name: "Claude Sonnet 4.5 (latest)",
@@ -2085,6 +2103,25 @@ export const MODELS = {
2085
2103
  contextWindow: 500000,
2086
2104
  maxTokens: 128000,
2087
2105
  },
2106
+ "grok-4.7": {
2107
+ id: "grok-4.7",
2108
+ name: "Grok 4.7",
2109
+ api: "openai-completions",
2110
+ provider: "github-copilot",
2111
+ baseUrl: "https://api.individual.githubcopilot.com",
2112
+ 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" },
2113
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2114
+ reasoning: true,
2115
+ input: ["text", "image"],
2116
+ cost: {
2117
+ input: 2,
2118
+ output: 6,
2119
+ cacheRead: 0.5,
2120
+ cacheWrite: 0,
2121
+ },
2122
+ contextWindow: 500000,
2123
+ maxTokens: 128000,
2124
+ },
2088
2125
  "kimi-k2.7-code": {
2089
2126
  id: "kimi-k2.7-code",
2090
2127
  name: "Kimi K2.7 Code",
@@ -4295,6 +4332,24 @@ export const MODELS = {
4295
4332
  contextWindow: 262144,
4296
4333
  maxTokens: 128000,
4297
4334
  },
4335
+ "tencent/Hy4-preview": {
4336
+ id: "tencent/Hy4-preview",
4337
+ name: "Hy4 preview",
4338
+ api: "openai-completions",
4339
+ provider: "huggingface",
4340
+ baseUrl: "https://router.huggingface.co/v1",
4341
+ compat: { "supportsDeveloperRole": false },
4342
+ reasoning: true,
4343
+ input: ["text"],
4344
+ cost: {
4345
+ input: 0.834,
4346
+ output: 2.501,
4347
+ cacheRead: 0,
4348
+ cacheWrite: 0,
4349
+ },
4350
+ contextWindow: 1000000,
4351
+ maxTokens: 64000,
4352
+ },
4298
4353
  "thinkingmachines/Inkling": {
4299
4354
  id: "thinkingmachines/Inkling",
4300
4355
  name: "Inkling",
@@ -7997,9 +8052,9 @@ export const MODELS = {
7997
8052
  contextWindow: 262144,
7998
8053
  maxTokens: 32768,
7999
8054
  },
8000
- "mimo-v2.5-free": {
8001
- id: "mimo-v2.5-free",
8002
- name: "MiMo V2.5 Free",
8055
+ "mimo-v2.6-flash-free": {
8056
+ id: "mimo-v2.6-flash-free",
8057
+ name: "MiMo-V2.6-Flash Free",
8003
8058
  api: "openai-completions",
8004
8059
  provider: "opencode",
8005
8060
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8399,6 +8454,23 @@ export const MODELS = {
8399
8454
  contextWindow: 500000,
8400
8455
  maxTokens: 500000,
8401
8456
  },
8457
+ "grok-4.7": {
8458
+ id: "grok-4.7",
8459
+ name: "Grok 4.7",
8460
+ api: "openai-responses",
8461
+ provider: "opencode-go",
8462
+ baseUrl: "https://opencode.ai/zen/go/v1",
8463
+ reasoning: true,
8464
+ input: ["text", "image"],
8465
+ cost: {
8466
+ input: 2,
8467
+ output: 6,
8468
+ cacheRead: 0.5,
8469
+ cacheWrite: 0,
8470
+ },
8471
+ contextWindow: 500000,
8472
+ maxTokens: 500000,
8473
+ },
8402
8474
  "hy3": {
8403
8475
  id: "hy3",
8404
8476
  name: "Hy3",
@@ -8536,6 +8608,40 @@ export const MODELS = {
8536
8608
  contextWindow: 1048576,
8537
8609
  maxTokens: 128000,
8538
8610
  },
8611
+ "mimo-v2.6-flash": {
8612
+ id: "mimo-v2.6-flash",
8613
+ name: "MiMo-V2.6-Flash",
8614
+ api: "openai-completions",
8615
+ provider: "opencode-go",
8616
+ baseUrl: "https://opencode.ai/zen/go/v1",
8617
+ reasoning: true,
8618
+ input: ["text", "image"],
8619
+ cost: {
8620
+ input: 0.14,
8621
+ output: 0.28,
8622
+ cacheRead: 0.0028,
8623
+ cacheWrite: 0,
8624
+ },
8625
+ contextWindow: 1048576,
8626
+ maxTokens: 131072,
8627
+ },
8628
+ "mimo-v2.6-pro": {
8629
+ id: "mimo-v2.6-pro",
8630
+ name: "MiMo-V2.6-Pro",
8631
+ api: "openai-completions",
8632
+ provider: "opencode-go",
8633
+ baseUrl: "https://opencode.ai/zen/go/v1",
8634
+ reasoning: true,
8635
+ input: ["text", "image"],
8636
+ cost: {
8637
+ input: 0.435,
8638
+ output: 0.87,
8639
+ cacheRead: 0.003625,
8640
+ cacheWrite: 0,
8641
+ },
8642
+ contextWindow: 1048576,
8643
+ maxTokens: 131072,
8644
+ },
8539
8645
  "minimax-m2.7": {
8540
8646
  id: "minimax-m2.7",
8541
8647
  name: "MiniMax-M2.7",
@@ -8548,7 +8654,7 @@ export const MODELS = {
8548
8654
  input: 0.3,
8549
8655
  output: 1.2,
8550
8656
  cacheRead: 0.06,
8551
- cacheWrite: 0,
8657
+ cacheWrite: 0.375,
8552
8658
  },
8553
8659
  contextWindow: 204800,
8554
8660
  maxTokens: 131072,
@@ -8708,7 +8814,7 @@ export const MODELS = {
8708
8814
  cacheRead: 0.19999999999999998,
8709
8815
  cacheWrite: 0,
8710
8816
  },
8711
- contextWindow: 131072,
8817
+ contextWindow: 1048576,
8712
8818
  maxTokens: 32768,
8713
8819
  },
8714
8820
  "aion-labs/aion-3.0": {
@@ -8725,7 +8831,7 @@ export const MODELS = {
8725
8831
  cacheRead: 0.75,
8726
8832
  cacheWrite: 0,
8727
8833
  },
8728
- contextWindow: 131072,
8834
+ contextWindow: 1048576,
8729
8835
  maxTokens: 32768,
8730
8836
  },
8731
8837
  "aion-labs/aion-3.0-mini": {
@@ -8742,7 +8848,7 @@ export const MODELS = {
8742
8848
  cacheRead: 0.18,
8743
8849
  cacheWrite: 0,
8744
8850
  },
8745
- contextWindow: 131072,
8851
+ contextWindow: 1048576,
8746
8852
  maxTokens: 32768,
8747
8853
  },
8748
8854
  "amazon/nova-2-lite-v1": {
@@ -8952,23 +9058,6 @@ export const MODELS = {
8952
9058
  contextWindow: 200000,
8953
9059
  maxTokens: 64000,
8954
9060
  },
8955
- "anthropic/claude-opus-4": {
8956
- id: "anthropic/claude-opus-4",
8957
- name: "Anthropic: Claude Opus 4",
8958
- api: "openai-completions",
8959
- provider: "openrouter",
8960
- baseUrl: "https://openrouter.ai/api/v1",
8961
- reasoning: true,
8962
- input: ["text", "image"],
8963
- cost: {
8964
- input: 15,
8965
- output: 75,
8966
- cacheRead: 1.5,
8967
- cacheWrite: 18.75,
8968
- },
8969
- contextWindow: 200000,
8970
- maxTokens: 32000,
8971
- },
8972
9061
  "anthropic/claude-opus-4.1": {
8973
9062
  id: "anthropic/claude-opus-4.1",
8974
9063
  name: "Anthropic: Claude Opus 4.1",
@@ -9163,6 +9252,42 @@ export const MODELS = {
9163
9252
  contextWindow: 1000000,
9164
9253
  maxTokens: 128000,
9165
9254
  },
9255
+ "anthropic/claude-opus-5.5": {
9256
+ id: "anthropic/claude-opus-5.5",
9257
+ name: "Anthropic: Claude Opus 5.5",
9258
+ api: "openai-completions",
9259
+ provider: "openrouter",
9260
+ baseUrl: "https://openrouter.ai/api/v1",
9261
+ reasoning: true,
9262
+ thinkingLevelMap: { "xhigh": "xhigh" },
9263
+ input: ["text", "image"],
9264
+ cost: {
9265
+ input: 4,
9266
+ output: 20,
9267
+ cacheRead: 0.19999999999999998,
9268
+ cacheWrite: 5,
9269
+ },
9270
+ contextWindow: 1000000,
9271
+ maxTokens: 128000,
9272
+ },
9273
+ "anthropic/claude-opus-5.5:batch": {
9274
+ id: "anthropic/claude-opus-5.5:batch",
9275
+ name: "Anthropic: Claude Opus 5.5 (batch)",
9276
+ api: "openai-completions",
9277
+ provider: "openrouter",
9278
+ baseUrl: "https://openrouter.ai/api/v1",
9279
+ reasoning: true,
9280
+ thinkingLevelMap: { "xhigh": "xhigh" },
9281
+ input: ["text", "image"],
9282
+ cost: {
9283
+ input: 2,
9284
+ output: 10,
9285
+ cacheRead: 0.09999999999999999,
9286
+ cacheWrite: 2.5,
9287
+ },
9288
+ contextWindow: 1000000,
9289
+ maxTokens: 128000,
9290
+ },
9166
9291
  "anthropic/claude-opus-5:batch": {
9167
9292
  id: "anthropic/claude-opus-5:batch",
9168
9293
  name: "Anthropic: Claude Opus 5 (batch)",
@@ -9194,7 +9319,7 @@ export const MODELS = {
9194
9319
  cacheRead: 0.3,
9195
9320
  cacheWrite: 3.75,
9196
9321
  },
9197
- contextWindow: 1000000,
9322
+ contextWindow: 200000,
9198
9323
  maxTokens: 64000,
9199
9324
  },
9200
9325
  "anthropic/claude-sonnet-4.5": {
@@ -9634,9 +9759,9 @@ export const MODELS = {
9634
9759
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9635
9760
  input: ["text"],
9636
9761
  cost: {
9637
- input: 0.04368,
9638
- output: 0.08736,
9639
- cacheRead: 0.008735999999999999,
9762
+ input: 0.049,
9763
+ output: 0.098,
9764
+ cacheRead: 0.0098,
9640
9765
  cacheWrite: 0,
9641
9766
  },
9642
9767
  contextWindow: 1048576,
@@ -9654,51 +9779,13 @@ export const MODELS = {
9654
9779
  input: ["text"],
9655
9780
  cost: {
9656
9781
  input: 0.04,
9657
- output: 0.08,
9782
+ output: 0.64,
9658
9783
  cacheRead: 0.016,
9659
9784
  cacheWrite: 0,
9660
9785
  },
9661
9786
  contextWindow: 1310720,
9662
9787
  maxTokens: 943718,
9663
9788
  },
9664
- "deepseek/deepseek-v4-flash-0731:batch": {
9665
- id: "deepseek/deepseek-v4-flash-0731:batch",
9666
- name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
9667
- api: "openai-completions",
9668
- provider: "openrouter",
9669
- baseUrl: "https://openrouter.ai/api/v1",
9670
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9671
- reasoning: true,
9672
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9673
- input: ["text"],
9674
- cost: {
9675
- input: 0.11,
9676
- output: 0.33,
9677
- cacheRead: 0.0035,
9678
- cacheWrite: 0,
9679
- },
9680
- contextWindow: 1048576,
9681
- maxTokens: 943718,
9682
- },
9683
- "deepseek/deepseek-v4-flash-0731:free": {
9684
- id: "deepseek/deepseek-v4-flash-0731:free",
9685
- name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
9686
- api: "openai-completions",
9687
- provider: "openrouter",
9688
- baseUrl: "https://openrouter.ai/api/v1",
9689
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9690
- reasoning: true,
9691
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9692
- input: ["text"],
9693
- cost: {
9694
- input: 0,
9695
- output: 0,
9696
- cacheRead: 0,
9697
- cacheWrite: 0,
9698
- },
9699
- contextWindow: 1048576,
9700
- maxTokens: 393216,
9701
- },
9702
9789
  "deepseek/deepseek-v4-flash-vision-exp": {
9703
9790
  id: "deepseek/deepseek-v4-flash-vision-exp",
9704
9791
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -9710,28 +9797,9 @@ export const MODELS = {
9710
9797
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9711
9798
  input: ["text", "image"],
9712
9799
  cost: {
9713
- input: 0.21559999999999999,
9714
- output: 0.6468,
9715
- cacheRead: 0.00686,
9716
- cacheWrite: 0,
9717
- },
9718
- contextWindow: 1048576,
9719
- maxTokens: 262144,
9720
- },
9721
- "deepseek/deepseek-v4-flash-vision-exp:batch": {
9722
- id: "deepseek/deepseek-v4-flash-vision-exp:batch",
9723
- name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
9724
- api: "openai-completions",
9725
- provider: "openrouter",
9726
- baseUrl: "https://openrouter.ai/api/v1",
9727
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9728
- reasoning: true,
9729
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9730
- input: ["text", "image"],
9731
- cost: {
9732
- input: 0.11,
9733
- output: 0.33,
9734
- cacheRead: 0.0035,
9800
+ input: 0.22,
9801
+ output: 0.66,
9802
+ cacheRead: 0.007,
9735
9803
  cacheWrite: 0,
9736
9804
  },
9737
9805
  contextWindow: 1048576,
@@ -9748,9 +9816,9 @@ export const MODELS = {
9748
9816
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9749
9817
  input: ["text"],
9750
9818
  cost: {
9751
- input: 0.422298,
9752
- output: 0.844596,
9753
- cacheRead: 0.0351915,
9819
+ input: 0.90741,
9820
+ output: 1.81482,
9821
+ cacheRead: 0.07561749999999999,
9754
9822
  cacheWrite: 0,
9755
9823
  },
9756
9824
  contextWindow: 1048576,
@@ -9767,36 +9835,36 @@ export const MODELS = {
9767
9835
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9768
9836
  input: ["text"],
9769
9837
  cost: {
9770
- input: 0.57816,
9771
- output: 1.73448,
9772
- cacheRead: 0.018396000000000003,
9838
+ input: 0.66,
9839
+ output: 1.9800000000000002,
9840
+ cacheRead: 0.022,
9773
9841
  cacheWrite: 0,
9774
9842
  },
9775
9843
  contextWindow: 1048576,
9776
- maxTokens: 393216,
9844
+ maxTokens: 384000,
9777
9845
  },
9778
- "deepseek/deepseek-v4-pro-0813:batch": {
9779
- id: "deepseek/deepseek-v4-pro-0813:batch",
9780
- name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
9846
+ "deepseek/deepseek-v4.1-flash": {
9847
+ id: "deepseek/deepseek-v4.1-flash",
9848
+ name: "DeepSeek: DeepSeek V4.1 Flash",
9781
9849
  api: "openai-completions",
9782
9850
  provider: "openrouter",
9783
9851
  baseUrl: "https://openrouter.ai/api/v1",
9784
9852
  compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9785
9853
  reasoning: true,
9786
9854
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9787
- input: ["text"],
9855
+ input: ["text", "image"],
9788
9856
  cost: {
9789
- input: 0.66,
9790
- output: 1.9800000000000002,
9791
- cacheRead: 0.022,
9857
+ input: 0.15,
9858
+ output: 0.6,
9859
+ cacheRead: 0.003,
9792
9860
  cacheWrite: 0,
9793
9861
  },
9794
9862
  contextWindow: 1048576,
9795
- maxTokens: 943718,
9863
+ maxTokens: 384000,
9796
9864
  },
9797
- "deepseek/deepseek-v4.1-flash": {
9798
- id: "deepseek/deepseek-v4.1-flash",
9799
- name: "DeepSeek: DeepSeek V4.1 Flash",
9865
+ "deepseek/deepseek-v4.1-flash:batch": {
9866
+ id: "deepseek/deepseek-v4.1-flash:batch",
9867
+ name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
9800
9868
  api: "openai-completions",
9801
9869
  provider: "openrouter",
9802
9870
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9805,13 +9873,13 @@ export const MODELS = {
9805
9873
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9806
9874
  input: ["text", "image"],
9807
9875
  cost: {
9808
- input: 0.15,
9809
- output: 0.6,
9810
- cacheRead: 0.003,
9876
+ input: 0.112,
9877
+ output: 0.33599999999999997,
9878
+ cacheRead: 0.00336,
9811
9879
  cacheWrite: 0,
9812
9880
  },
9813
9881
  contextWindow: 1048576,
9814
- maxTokens: 384000,
9882
+ maxTokens: 131072,
9815
9883
  },
9816
9884
  "dots-studio/dots-3-note-preview:free": {
9817
9885
  id: "dots-studio/dots-3-note-preview:free",
@@ -10527,23 +10595,6 @@ export const MODELS = {
10527
10595
  contextWindow: 262144,
10528
10596
  maxTokens: 32768,
10529
10597
  },
10530
- "kwaipilot/kat-coder-pro-v2": {
10531
- id: "kwaipilot/kat-coder-pro-v2",
10532
- name: "Kwaipilot: KAT-Coder-Pro V2",
10533
- api: "openai-completions",
10534
- provider: "openrouter",
10535
- baseUrl: "https://openrouter.ai/api/v1",
10536
- reasoning: false,
10537
- input: ["text"],
10538
- cost: {
10539
- input: 0.3,
10540
- output: 1.2,
10541
- cacheRead: 0.06,
10542
- cacheWrite: 0,
10543
- },
10544
- contextWindow: 262144,
10545
- maxTokens: 144000,
10546
- },
10547
10598
  "kwaipilot/kat-coder-pro-v2.5": {
10548
10599
  id: "kwaipilot/kat-coder-pro-v2.5",
10549
10600
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -10689,30 +10740,13 @@ export const MODELS = {
10689
10740
  reasoning: true,
10690
10741
  input: ["text", "image"],
10691
10742
  cost: {
10692
- input: 0.35,
10693
- output: 1.5,
10743
+ input: 0.3,
10744
+ output: 1.2,
10694
10745
  cacheRead: 0.04,
10695
10746
  cacheWrite: 0,
10696
10747
  },
10697
10748
  contextWindow: 131072,
10698
- maxTokens: 117964,
10699
- },
10700
- "meta/muse-glimmer-30b:batch": {
10701
- id: "meta/muse-glimmer-30b:batch",
10702
- name: "Meta: Muse Glimmer 30B (batch)",
10703
- api: "openai-completions",
10704
- provider: "openrouter",
10705
- baseUrl: "https://openrouter.ai/api/v1",
10706
- reasoning: true,
10707
- input: ["text", "image"],
10708
- cost: {
10709
- input: 0.175,
10710
- output: 0.75,
10711
- cacheRead: 0.02,
10712
- cacheWrite: 0,
10713
- },
10714
- contextWindow: 131072,
10715
- maxTokens: 117964,
10749
+ maxTokens: 16384,
10716
10750
  },
10717
10751
  "meta/muse-spark-1.1": {
10718
10752
  id: "meta/muse-spark-1.1",
@@ -10901,26 +10935,9 @@ export const MODELS = {
10901
10935
  contextWindow: 1048576,
10902
10936
  maxTokens: 512000,
10903
10937
  },
10904
- "minimax/minimax-m3:batch": {
10905
- id: "minimax/minimax-m3:batch",
10906
- name: "MiniMax: MiniMax M3 (batch)",
10907
- api: "openai-completions",
10908
- provider: "openrouter",
10909
- baseUrl: "https://openrouter.ai/api/v1",
10910
- reasoning: true,
10911
- input: ["text", "image"],
10912
- cost: {
10913
- input: 0.3,
10914
- output: 1.2,
10915
- cacheRead: 0.06,
10916
- cacheWrite: 0,
10917
- },
10918
- contextWindow: 524288,
10919
- maxTokens: 471859,
10920
- },
10921
- "mistralai/codestral-2508": {
10922
- id: "mistralai/codestral-2508",
10923
- name: "Mistral: Codestral 2508",
10938
+ "mistralai/codestral-2508": {
10939
+ id: "mistralai/codestral-2508",
10940
+ name: "Mistral: Codestral 2508",
10924
10941
  api: "openai-completions",
10925
10942
  provider: "openrouter",
10926
10943
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11241,6 +11258,23 @@ export const MODELS = {
11241
11258
  contextWindow: 262144,
11242
11259
  maxTokens: 209715,
11243
11260
  },
11261
+ "mistralai/mistral-small-3.1-24b-instruct": {
11262
+ id: "mistralai/mistral-small-3.1-24b-instruct",
11263
+ name: "Mistral: Mistral Small 3.1 24B",
11264
+ api: "openai-completions",
11265
+ provider: "openrouter",
11266
+ baseUrl: "https://openrouter.ai/api/v1",
11267
+ reasoning: false,
11268
+ input: ["text", "image"],
11269
+ cost: {
11270
+ input: 0.351,
11271
+ output: 0.5549999999999999,
11272
+ cacheRead: 0,
11273
+ cacheWrite: 0,
11274
+ },
11275
+ contextWindow: 128000,
11276
+ maxTokens: 102400,
11277
+ },
11244
11278
  "mistralai/mistral-small-3.2-24b-instruct": {
11245
11279
  id: "mistralai/mistral-small-3.2-24b-instruct",
11246
11280
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11387,7 +11421,7 @@ export const MODELS = {
11387
11421
  input: ["text", "image"],
11388
11422
  cost: {
11389
11423
  input: 0.7062,
11390
- output: 3.21,
11424
+ output: 3.3000000000000003,
11391
11425
  cacheRead: 0.18,
11392
11426
  cacheWrite: 0,
11393
11427
  },
@@ -11403,9 +11437,9 @@ export const MODELS = {
11403
11437
  reasoning: true,
11404
11438
  input: ["text", "image"],
11405
11439
  cost: {
11406
- input: 1.7,
11407
- output: 8.5,
11408
- cacheRead: 0.16999999999999998,
11440
+ input: 3,
11441
+ output: 15,
11442
+ cacheRead: 0.3,
11409
11443
  cacheWrite: 0,
11410
11444
  },
11411
11445
  contextWindow: 1048576,
@@ -11420,13 +11454,13 @@ export const MODELS = {
11420
11454
  reasoning: true,
11421
11455
  input: ["text", "image"],
11422
11456
  cost: {
11423
- input: 3,
11424
- output: 15,
11425
- cacheRead: 0.3,
11457
+ input: 2.2800000000000002,
11458
+ output: 11.399999999999999,
11459
+ cacheRead: 0.228,
11426
11460
  cacheWrite: 0,
11427
11461
  },
11428
11462
  contextWindow: 1048576,
11429
- maxTokens: 943718,
11463
+ maxTokens: 16384,
11430
11464
  },
11431
11465
  "nex-agi/nex-n2.5-mini:free": {
11432
11466
  id: "nex-agi/nex-n2.5-mini:free",
@@ -11445,6 +11479,23 @@ export const MODELS = {
11445
11479
  contextWindow: 262144,
11446
11480
  maxTokens: 235929,
11447
11481
  },
11482
+ "nex-agi/nex-n2.5-pro": {
11483
+ id: "nex-agi/nex-n2.5-pro",
11484
+ name: "Nex AGI: Nex-N2.5-Pro",
11485
+ api: "openai-completions",
11486
+ provider: "openrouter",
11487
+ baseUrl: "https://openrouter.ai/api/v1",
11488
+ reasoning: true,
11489
+ input: ["text", "image"],
11490
+ cost: {
11491
+ input: 0.075,
11492
+ output: 0.25,
11493
+ cacheRead: 0.015,
11494
+ cacheWrite: 0,
11495
+ },
11496
+ contextWindow: 262144,
11497
+ maxTokens: 235929,
11498
+ },
11448
11499
  "nex-agi/nex-n2.5-pro:free": {
11449
11500
  id: "nex-agi/nex-n2.5-pro:free",
11450
11501
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -11471,9 +11522,9 @@ export const MODELS = {
11471
11522
  reasoning: true,
11472
11523
  input: ["text"],
11473
11524
  cost: {
11474
- input: 0.06,
11475
- output: 0.24,
11476
- cacheRead: 0,
11525
+ input: 0.049999999999999996,
11526
+ output: 0.19999999999999998,
11527
+ cacheRead: 0.03,
11477
11528
  cacheWrite: 0,
11478
11529
  },
11479
11530
  contextWindow: 262144,
@@ -12802,6 +12853,142 @@ export const MODELS = {
12802
12853
  contextWindow: 1050000,
12803
12854
  maxTokens: 128000,
12804
12855
  },
12856
+ "openai/gpt-6-luna": {
12857
+ id: "openai/gpt-6-luna",
12858
+ name: "OpenAI: GPT-6 Luna",
12859
+ api: "openai-completions",
12860
+ provider: "openrouter",
12861
+ baseUrl: "https://openrouter.ai/api/v1",
12862
+ reasoning: true,
12863
+ input: ["text", "image"],
12864
+ cost: {
12865
+ input: 0.09999999999999999,
12866
+ output: 0.5,
12867
+ cacheRead: 0.01,
12868
+ cacheWrite: 0.125,
12869
+ },
12870
+ contextWindow: 1050000,
12871
+ maxTokens: 128000,
12872
+ },
12873
+ "openai/gpt-6-luna-pro": {
12874
+ id: "openai/gpt-6-luna-pro",
12875
+ name: "OpenAI: GPT-6 Luna Pro",
12876
+ api: "openai-completions",
12877
+ provider: "openrouter",
12878
+ baseUrl: "https://openrouter.ai/api/v1",
12879
+ reasoning: true,
12880
+ input: ["text", "image"],
12881
+ cost: {
12882
+ input: 0.09999999999999999,
12883
+ output: 0.5,
12884
+ cacheRead: 0.01,
12885
+ cacheWrite: 0.125,
12886
+ },
12887
+ contextWindow: 1050000,
12888
+ maxTokens: 128000,
12889
+ },
12890
+ "openai/gpt-6-luna-pro:batch": {
12891
+ id: "openai/gpt-6-luna-pro:batch",
12892
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
12893
+ api: "openai-completions",
12894
+ provider: "openrouter",
12895
+ baseUrl: "https://openrouter.ai/api/v1",
12896
+ reasoning: true,
12897
+ input: ["text", "image"],
12898
+ cost: {
12899
+ input: 0.049999999999999996,
12900
+ output: 0.25,
12901
+ cacheRead: 0.005,
12902
+ cacheWrite: 0.0625,
12903
+ },
12904
+ contextWindow: 1050000,
12905
+ maxTokens: 128000,
12906
+ },
12907
+ "openai/gpt-6-luna:batch": {
12908
+ id: "openai/gpt-6-luna:batch",
12909
+ name: "OpenAI: GPT-6 Luna (batch)",
12910
+ api: "openai-completions",
12911
+ provider: "openrouter",
12912
+ baseUrl: "https://openrouter.ai/api/v1",
12913
+ reasoning: true,
12914
+ input: ["text", "image"],
12915
+ cost: {
12916
+ input: 0.049999999999999996,
12917
+ output: 0.25,
12918
+ cacheRead: 0.005,
12919
+ cacheWrite: 0.0625,
12920
+ },
12921
+ contextWindow: 1050000,
12922
+ maxTokens: 128000,
12923
+ },
12924
+ "openai/gpt-6-sol": {
12925
+ id: "openai/gpt-6-sol",
12926
+ name: "OpenAI: GPT-6 Sol",
12927
+ api: "openai-completions",
12928
+ provider: "openrouter",
12929
+ baseUrl: "https://openrouter.ai/api/v1",
12930
+ reasoning: true,
12931
+ input: ["text", "image"],
12932
+ cost: {
12933
+ input: 2,
12934
+ output: 10,
12935
+ cacheRead: 0.19999999999999998,
12936
+ cacheWrite: 2.5,
12937
+ },
12938
+ contextWindow: 1050000,
12939
+ maxTokens: 128000,
12940
+ },
12941
+ "openai/gpt-6-sol-pro": {
12942
+ id: "openai/gpt-6-sol-pro",
12943
+ name: "OpenAI: GPT-6 Sol Pro",
12944
+ api: "openai-completions",
12945
+ provider: "openrouter",
12946
+ baseUrl: "https://openrouter.ai/api/v1",
12947
+ reasoning: true,
12948
+ input: ["text", "image"],
12949
+ cost: {
12950
+ input: 2,
12951
+ output: 10,
12952
+ cacheRead: 0.19999999999999998,
12953
+ cacheWrite: 2.5,
12954
+ },
12955
+ contextWindow: 1050000,
12956
+ maxTokens: 128000,
12957
+ },
12958
+ "openai/gpt-6-sol-pro:batch": {
12959
+ id: "openai/gpt-6-sol-pro:batch",
12960
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
12961
+ api: "openai-completions",
12962
+ provider: "openrouter",
12963
+ baseUrl: "https://openrouter.ai/api/v1",
12964
+ reasoning: true,
12965
+ input: ["text", "image"],
12966
+ cost: {
12967
+ input: 1,
12968
+ output: 5,
12969
+ cacheRead: 0.09999999999999999,
12970
+ cacheWrite: 1.25,
12971
+ },
12972
+ contextWindow: 1050000,
12973
+ maxTokens: 128000,
12974
+ },
12975
+ "openai/gpt-6-sol:batch": {
12976
+ id: "openai/gpt-6-sol:batch",
12977
+ name: "OpenAI: GPT-6 Sol (batch)",
12978
+ api: "openai-completions",
12979
+ provider: "openrouter",
12980
+ baseUrl: "https://openrouter.ai/api/v1",
12981
+ reasoning: true,
12982
+ input: ["text", "image"],
12983
+ cost: {
12984
+ input: 1,
12985
+ output: 5,
12986
+ cacheRead: 0.09999999999999999,
12987
+ cacheWrite: 1.25,
12988
+ },
12989
+ contextWindow: 1050000,
12990
+ maxTokens: 128000,
12991
+ },
12805
12992
  "openai/gpt-audio": {
12806
12993
  id: "openai/gpt-audio",
12807
12994
  name: "OpenAI: GPT Audio",
@@ -12870,35 +13057,35 @@ export const MODELS = {
12870
13057
  contextWindow: 131072,
12871
13058
  maxTokens: 65536,
12872
13059
  },
12873
- "openai/gpt-oss-120b:batch": {
12874
- id: "openai/gpt-oss-120b:batch",
12875
- name: "OpenAI: gpt-oss-120b (batch)",
13060
+ "openai/gpt-oss-20b": {
13061
+ id: "openai/gpt-oss-20b",
13062
+ name: "OpenAI: gpt-oss-20b",
12876
13063
  api: "openai-completions",
12877
13064
  provider: "openrouter",
12878
13065
  baseUrl: "https://openrouter.ai/api/v1",
12879
13066
  reasoning: true,
12880
13067
  input: ["text"],
12881
13068
  cost: {
12882
- input: 0.15,
12883
- output: 0.6,
13069
+ input: 0.018,
13070
+ output: 0.09,
12884
13071
  cacheRead: 0,
12885
13072
  cacheWrite: 0,
12886
13073
  },
12887
13074
  contextWindow: 131072,
12888
- maxTokens: 117964,
13075
+ maxTokens: 32768,
12889
13076
  },
12890
- "openai/gpt-oss-20b": {
12891
- id: "openai/gpt-oss-20b",
12892
- name: "OpenAI: gpt-oss-20b",
13077
+ "openai/gpt-oss-20b:batch": {
13078
+ id: "openai/gpt-oss-20b:batch",
13079
+ name: "OpenAI: gpt-oss-20b (batch)",
12893
13080
  api: "openai-completions",
12894
13081
  provider: "openrouter",
12895
13082
  baseUrl: "https://openrouter.ai/api/v1",
12896
13083
  reasoning: true,
12897
13084
  input: ["text"],
12898
13085
  cost: {
12899
- input: 0.03,
12900
- output: 0.13,
12901
- cacheRead: 0.03,
13086
+ input: 0.024,
13087
+ output: 0.112,
13088
+ cacheRead: 0,
12902
13089
  cacheWrite: 0,
12903
13090
  },
12904
13091
  contextWindow: 131072,
@@ -13599,7 +13786,7 @@ export const MODELS = {
13599
13786
  cacheWrite: 0,
13600
13787
  },
13601
13788
  contextWindow: 262144,
13602
- maxTokens: 32768,
13789
+ maxTokens: 235929,
13603
13790
  },
13604
13791
  "qwen/qwen3-vl-235b-a22b-instruct": {
13605
13792
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13644,8 +13831,8 @@ export const MODELS = {
13644
13831
  reasoning: false,
13645
13832
  input: ["text", "image"],
13646
13833
  cost: {
13647
- input: 0.19999999999999998,
13648
- output: 0.7,
13834
+ input: 0.13,
13835
+ output: 0.52,
13649
13836
  cacheRead: 0,
13650
13837
  cacheWrite: 0,
13651
13838
  },
@@ -13763,13 +13950,13 @@ export const MODELS = {
13763
13950
  reasoning: true,
13764
13951
  input: ["text", "image"],
13765
13952
  cost: {
13766
- input: 0.1625,
13767
- output: 1.3,
13768
- cacheRead: 0,
13953
+ input: 0.3125,
13954
+ output: 1.25,
13955
+ cacheRead: 0.15625,
13769
13956
  cacheWrite: 0,
13770
13957
  },
13771
13958
  contextWindow: 262144,
13772
- maxTokens: 65536,
13959
+ maxTokens: 16384,
13773
13960
  },
13774
13961
  "qwen/qwen3.5-397b-a17b": {
13775
13962
  id: "qwen/qwen3.5-397b-a17b",
@@ -13803,24 +13990,7 @@ export const MODELS = {
13803
13990
  cacheWrite: 0,
13804
13991
  },
13805
13992
  contextWindow: 262144,
13806
- maxTokens: 235929,
13807
- },
13808
- "qwen/qwen3.5-9b:batch": {
13809
- id: "qwen/qwen3.5-9b:batch",
13810
- name: "Qwen: Qwen3.5-9B (batch)",
13811
- api: "openai-completions",
13812
- provider: "openrouter",
13813
- baseUrl: "https://openrouter.ai/api/v1",
13814
- reasoning: true,
13815
- input: ["text", "image"],
13816
- cost: {
13817
- input: 0.16999999999999998,
13818
- output: 0.25,
13819
- cacheRead: 0,
13820
- cacheWrite: 0,
13821
- },
13822
- contextWindow: 262144,
13823
- maxTokens: 235929,
13993
+ maxTokens: 32768,
13824
13994
  },
13825
13995
  "qwen/qwen3.5-flash-02-23": {
13826
13996
  id: "qwen/qwen3.5-flash-02-23",
@@ -13882,13 +14052,13 @@ export const MODELS = {
13882
14052
  reasoning: true,
13883
14053
  input: ["text", "image"],
13884
14054
  cost: {
13885
- input: 0.3,
13886
- output: 2,
13887
- cacheRead: 0.03,
14055
+ input: 0.32,
14056
+ output: 2.7,
14057
+ cacheRead: 0.15,
13888
14058
  cacheWrite: 0,
13889
14059
  },
13890
14060
  contextWindow: 262144,
13891
- maxTokens: 65536,
14061
+ maxTokens: 262140,
13892
14062
  },
13893
14063
  "qwen/qwen3.6-35b-a3b": {
13894
14064
  id: "qwen/qwen3.6-35b-a3b",
@@ -13899,8 +14069,8 @@ export const MODELS = {
13899
14069
  reasoning: true,
13900
14070
  input: ["text", "image"],
13901
14071
  cost: {
13902
- input: 0.09999999999999999,
13903
- output: 0.8999999999999999,
14072
+ input: 0.15,
14073
+ output: 1,
13904
14074
  cacheRead: 0.049999999999999996,
13905
14075
  cacheWrite: 0,
13906
14076
  },
@@ -14026,23 +14196,6 @@ export const MODELS = {
14026
14196
  contextWindow: 1048576,
14027
14197
  maxTokens: 131072,
14028
14198
  },
14029
- "qwen/qwen3.8-2.4t-a95b:batch": {
14030
- id: "qwen/qwen3.8-2.4t-a95b:batch",
14031
- name: "Qwen: Qwen3.8 2.4T A95B (batch)",
14032
- api: "openai-completions",
14033
- provider: "openrouter",
14034
- baseUrl: "https://openrouter.ai/api/v1",
14035
- reasoning: true,
14036
- input: ["text"],
14037
- cost: {
14038
- input: 2,
14039
- output: 6,
14040
- cacheRead: 0.25,
14041
- cacheWrite: 0,
14042
- },
14043
- contextWindow: 1010000,
14044
- maxTokens: 909000,
14045
- },
14046
14199
  "qwen/qwen3.8-27b": {
14047
14200
  id: "qwen/qwen3.8-27b",
14048
14201
  name: "Qwen: Qwen3.8 27B",
@@ -14052,9 +14205,9 @@ export const MODELS = {
14052
14205
  reasoning: true,
14053
14206
  input: ["text", "image"],
14054
14207
  cost: {
14055
- input: 0.21400000000000002,
14056
- output: 2.5500000000000003,
14057
- cacheRead: 0.15,
14208
+ input: 0.42,
14209
+ output: 3,
14210
+ cacheRead: 0.08499999999999999,
14058
14211
  cacheWrite: 0,
14059
14212
  },
14060
14213
  contextWindow: 1000000,
@@ -14273,9 +14426,9 @@ export const MODELS = {
14273
14426
  reasoning: true,
14274
14427
  input: ["text"],
14275
14428
  cost: {
14276
- input: 0.13199999999999998,
14277
- output: 0.5279999999999999,
14278
- cacheRead: 0.032999999999999995,
14429
+ input: 0.0825,
14430
+ output: 0.33,
14431
+ cacheRead: 0.020625,
14279
14432
  cacheWrite: 0,
14280
14433
  },
14281
14434
  contextWindow: 262144,
@@ -14366,23 +14519,6 @@ export const MODELS = {
14366
14519
  contextWindow: 1048576,
14367
14520
  maxTokens: 262144,
14368
14521
  },
14369
- "thinkingmachines/inkling:batch": {
14370
- id: "thinkingmachines/inkling:batch",
14371
- name: "Thinking Machines: Inkling (batch)",
14372
- api: "openai-completions",
14373
- provider: "openrouter",
14374
- baseUrl: "https://openrouter.ai/api/v1",
14375
- reasoning: true,
14376
- input: ["text", "image"],
14377
- cost: {
14378
- input: 1,
14379
- output: 4.05,
14380
- cacheRead: 0.16999999999999998,
14381
- cacheWrite: 0,
14382
- },
14383
- contextWindow: 524288,
14384
- maxTokens: 471859,
14385
- },
14386
14522
  "thinkingmachines/inkling:free": {
14387
14523
  id: "thinkingmachines/inkling:free",
14388
14524
  name: "Thinking Machines: Inkling (free)",
@@ -14536,21 +14672,38 @@ export const MODELS = {
14536
14672
  contextWindow: 500000,
14537
14673
  maxTokens: 450000,
14538
14674
  },
14539
- "x-ai/grok-build-0.1": {
14540
- id: "x-ai/grok-build-0.1",
14541
- name: "SpaceXAI: Grok Build 0.1",
14675
+ "x-ai/grok-4.7": {
14676
+ id: "x-ai/grok-4.7",
14677
+ name: "SpaceXAI: Grok 4.7",
14542
14678
  api: "openai-completions",
14543
14679
  provider: "openrouter",
14544
14680
  baseUrl: "https://openrouter.ai/api/v1",
14545
14681
  reasoning: true,
14546
14682
  input: ["text", "image"],
14547
14683
  cost: {
14548
- input: 1,
14549
- output: 2,
14550
- cacheRead: 0.19999999999999998,
14684
+ input: 1.5999999999999999,
14685
+ output: 4.8,
14686
+ cacheRead: 0.39999999999999997,
14551
14687
  cacheWrite: 0,
14552
14688
  },
14553
- contextWindow: 256000,
14689
+ contextWindow: 500000,
14690
+ maxTokens: 450000,
14691
+ },
14692
+ "x-ai/grok-build-0.1": {
14693
+ id: "x-ai/grok-build-0.1",
14694
+ name: "SpaceXAI: Grok Build 0.1",
14695
+ api: "openai-completions",
14696
+ provider: "openrouter",
14697
+ baseUrl: "https://openrouter.ai/api/v1",
14698
+ reasoning: true,
14699
+ input: ["text", "image"],
14700
+ cost: {
14701
+ input: 1,
14702
+ output: 2,
14703
+ cacheRead: 0.19999999999999998,
14704
+ cacheWrite: 0,
14705
+ },
14706
+ contextWindow: 256000,
14554
14707
  maxTokens: 230400,
14555
14708
  },
14556
14709
  "xiaomi/mimo-v2.5": {
@@ -14587,6 +14740,57 @@ export const MODELS = {
14587
14740
  contextWindow: 1050000,
14588
14741
  maxTokens: 131072,
14589
14742
  },
14743
+ "xiaomi/mimo-v2.6-flash": {
14744
+ id: "xiaomi/mimo-v2.6-flash",
14745
+ name: "Xiaomi: MiMo-V2.6-Flash",
14746
+ api: "openai-completions",
14747
+ provider: "openrouter",
14748
+ baseUrl: "https://openrouter.ai/api/v1",
14749
+ reasoning: true,
14750
+ input: ["text", "image"],
14751
+ cost: {
14752
+ input: 0.14,
14753
+ output: 0.28,
14754
+ cacheRead: 0.0028,
14755
+ cacheWrite: 0,
14756
+ },
14757
+ contextWindow: 1048576,
14758
+ maxTokens: 131072,
14759
+ },
14760
+ "xiaomi/mimo-v2.6-pro": {
14761
+ id: "xiaomi/mimo-v2.6-pro",
14762
+ name: "Xiaomi: MiMo-V2.6-Pro",
14763
+ api: "openai-completions",
14764
+ provider: "openrouter",
14765
+ baseUrl: "https://openrouter.ai/api/v1",
14766
+ reasoning: true,
14767
+ input: ["text", "image"],
14768
+ cost: {
14769
+ input: 0.435,
14770
+ output: 0.87,
14771
+ cacheRead: 0.0036,
14772
+ cacheWrite: 0,
14773
+ },
14774
+ contextWindow: 1048576,
14775
+ maxTokens: 131072,
14776
+ },
14777
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
14778
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
14779
+ name: "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
14780
+ api: "openai-completions",
14781
+ provider: "openrouter",
14782
+ baseUrl: "https://openrouter.ai/api/v1",
14783
+ reasoning: true,
14784
+ input: ["text", "image"],
14785
+ cost: {
14786
+ input: 4.35,
14787
+ output: 8.7,
14788
+ cacheRead: 0.036,
14789
+ cacheWrite: 0,
14790
+ },
14791
+ contextWindow: 1048576,
14792
+ maxTokens: 131072,
14793
+ },
14590
14794
  "z-ai/glm-4.5": {
14591
14795
  id: "z-ai/glm-4.5",
14592
14796
  name: "Z.ai: GLM 4.5",
@@ -14766,31 +14970,14 @@ export const MODELS = {
14766
14970
  reasoning: true,
14767
14971
  input: ["text"],
14768
14972
  cost: {
14769
- input: 0.5544,
14770
- output: 1.7424,
14771
- cacheRead: 0.10296000000000001,
14973
+ input: 0.6496,
14974
+ output: 2.0416,
14975
+ cacheRead: 0.12064,
14772
14976
  cacheWrite: 0,
14773
14977
  },
14774
14978
  contextWindow: 1048576,
14775
14979
  maxTokens: 131072,
14776
14980
  },
14777
- "z-ai/glm-5.2:batch": {
14778
- id: "z-ai/glm-5.2:batch",
14779
- name: "Z.ai: GLM 5.2 (batch)",
14780
- api: "openai-completions",
14781
- provider: "openrouter",
14782
- baseUrl: "https://openrouter.ai/api/v1",
14783
- reasoning: true,
14784
- input: ["text"],
14785
- cost: {
14786
- input: 0.7,
14787
- output: 2.2,
14788
- cacheRead: 0.07,
14789
- cacheWrite: 0,
14790
- },
14791
- contextWindow: 1048576,
14792
- maxTokens: 943718,
14793
- },
14794
14981
  "z-ai/glm-5.3": {
14795
14982
  id: "z-ai/glm-5.3",
14796
14983
  name: "Z.ai: GLM 5.3",
@@ -14800,9 +14987,9 @@ export const MODELS = {
14800
14987
  reasoning: true,
14801
14988
  input: ["text"],
14802
14989
  cost: {
14803
- input: 0.9099999999999999,
14804
- output: 2.8600000000000003,
14805
- cacheRead: 0.16899999999999998,
14990
+ input: 0.6537999999999999,
14991
+ output: 2.0547999999999997,
14992
+ cacheRead: 0.12142000000000001,
14806
14993
  cacheWrite: 0,
14807
14994
  },
14808
14995
  contextWindow: 1310720,
@@ -14817,13 +15004,13 @@ export const MODELS = {
14817
15004
  reasoning: true,
14818
15005
  input: ["text", "image"],
14819
15006
  cost: {
14820
- input: 0.09,
14821
- output: 0.3,
14822
- cacheRead: 0.018,
15007
+ input: 0.15,
15008
+ output: 0.5,
15009
+ cacheRead: 0.049999999999999996,
14823
15010
  cacheWrite: 0,
14824
15011
  },
14825
15012
  contextWindow: 1310720,
14826
- maxTokens: 131072,
15013
+ maxTokens: 943718,
14827
15014
  },
14828
15015
  "z-ai/glm-5.3-flash:batch": {
14829
15016
  id: "z-ai/glm-5.3-flash:batch",
@@ -14834,13 +15021,13 @@ export const MODELS = {
14834
15021
  reasoning: true,
14835
15022
  input: ["text", "image"],
14836
15023
  cost: {
14837
- input: 0.075,
14838
- output: 0.25,
14839
- cacheRead: 0.015,
15024
+ input: 0.06,
15025
+ output: 0.19999999999999998,
15026
+ cacheRead: 0.012,
14840
15027
  cacheWrite: 0,
14841
15028
  },
14842
15029
  contextWindow: 1048576,
14843
- maxTokens: 943718,
15030
+ maxTokens: 131072,
14844
15031
  },
14845
15032
  "z-ai/glm-5.3-flashx": {
14846
15033
  id: "z-ai/glm-5.3-flashx",
@@ -14868,13 +15055,13 @@ export const MODELS = {
14868
15055
  reasoning: true,
14869
15056
  input: ["text"],
14870
15057
  cost: {
14871
- input: 0.7,
14872
- output: 2.2,
14873
- cacheRead: 0.13,
15058
+ input: 0.72,
15059
+ output: 2.4,
15060
+ cacheRead: 0.12,
14874
15061
  cacheWrite: 0,
14875
15062
  },
14876
15063
  contextWindow: 1048576,
14877
- maxTokens: 943718,
15064
+ maxTokens: 131072,
14878
15065
  },
14879
15066
  "z-ai/glm-5v-turbo": {
14880
15067
  id: "z-ai/glm-5v-turbo",
@@ -14938,10 +15125,10 @@ export const MODELS = {
14938
15125
  thinkingLevelMap: { "xhigh": "xhigh" },
14939
15126
  input: ["text", "image"],
14940
15127
  cost: {
14941
- input: 5,
14942
- output: 25,
14943
- cacheRead: 0.5,
14944
- cacheWrite: 6.25,
15128
+ input: 4,
15129
+ output: 20,
15130
+ cacheRead: 0.19999999999999998,
15131
+ cacheWrite: 5,
14945
15132
  },
14946
15133
  contextWindow: 1000000,
14947
15134
  maxTokens: 128000,
@@ -14973,9 +15160,9 @@ export const MODELS = {
14973
15160
  reasoning: true,
14974
15161
  input: ["text", "image"],
14975
15162
  cost: {
14976
- input: 0.13,
14977
- output: 0.52,
14978
- cacheRead: 0.0026000000000000003,
15163
+ input: 0.12,
15164
+ output: 0.48,
15165
+ cacheRead: 0.0036,
14979
15166
  cacheWrite: 0,
14980
15167
  },
14981
15168
  contextWindow: 1048576,
@@ -14990,13 +15177,13 @@ export const MODELS = {
14990
15177
  reasoning: true,
14991
15178
  input: ["text"],
14992
15179
  cost: {
14993
- input: 0.57816,
14994
- output: 1.73448,
14995
- cacheRead: 0.018396000000000003,
15180
+ input: 0.5451600000000001,
15181
+ output: 1.6354799999999998,
15182
+ cacheRead: 0.018171999999999997,
14996
15183
  cacheWrite: 0,
14997
15184
  },
14998
15185
  contextWindow: 1048576,
14999
- maxTokens: 393216,
15186
+ maxTokens: 384000,
15000
15187
  },
15001
15188
  "~deepseek/deepseek-v4-flash-latest": {
15002
15189
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -15009,9 +15196,9 @@ export const MODELS = {
15009
15196
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15010
15197
  input: ["text"],
15011
15198
  cost: {
15012
- input: 0.04,
15013
- output: 0.08,
15014
- cacheRead: 0.016,
15199
+ input: 0.03,
15200
+ output: 1,
15201
+ cacheRead: 0.008,
15015
15202
  cacheWrite: 0,
15016
15203
  },
15017
15204
  contextWindow: 1310720,
@@ -15060,9 +15247,9 @@ export const MODELS = {
15060
15247
  reasoning: true,
15061
15248
  input: ["text", "image"],
15062
15249
  cost: {
15063
- input: 1.7,
15064
- output: 8.5,
15065
- cacheRead: 0.16999999999999998,
15250
+ input: 1.5,
15251
+ output: 7.5,
15252
+ cacheRead: 0.15,
15066
15253
  cacheWrite: 0,
15067
15254
  },
15068
15255
  contextWindow: 1048576,
@@ -15094,10 +15281,10 @@ export const MODELS = {
15094
15281
  reasoning: true,
15095
15282
  input: ["text", "image"],
15096
15283
  cost: {
15097
- input: 0.19999999999999998,
15098
- output: 1.2,
15099
- cacheRead: 0.02,
15100
- cacheWrite: 0.25,
15284
+ input: 0.09999999999999999,
15285
+ output: 0.5,
15286
+ cacheRead: 0.01,
15287
+ cacheWrite: 0.125,
15101
15288
  },
15102
15289
  contextWindow: 1050000,
15103
15290
  maxTokens: 128000,
@@ -15162,9 +15349,9 @@ export const MODELS = {
15162
15349
  reasoning: true,
15163
15350
  input: ["text", "image"],
15164
15351
  cost: {
15165
- input: 2,
15166
- output: 6,
15167
- cacheRead: 0.5,
15352
+ input: 1.5999999999999999,
15353
+ output: 4.8,
15354
+ cacheRead: 0.39999999999999997,
15168
15355
  cacheWrite: 0,
15169
15356
  },
15170
15357
  contextWindow: 500000,
@@ -15185,7 +15372,7 @@ export const MODELS = {
15185
15372
  cacheWrite: 0,
15186
15373
  },
15187
15374
  contextWindow: 1310720,
15188
- maxTokens: 131072,
15375
+ maxTokens: 943718,
15189
15376
  },
15190
15377
  "~z-ai/glm-latest": {
15191
15378
  id: "~z-ai/glm-latest",
@@ -15196,9 +15383,9 @@ export const MODELS = {
15196
15383
  reasoning: true,
15197
15384
  input: ["text"],
15198
15385
  cost: {
15199
- input: 0.8917999999999999,
15200
- output: 2.8028,
15201
- cacheRead: 0.16562,
15386
+ input: 0.6537999999999999,
15387
+ output: 2.0547999999999997,
15388
+ cacheRead: 0.12142000000000001,
15202
15389
  cacheWrite: 0,
15203
15390
  },
15204
15391
  contextWindow: 1310720,
@@ -16430,6 +16617,42 @@ export const MODELS = {
16430
16617
  contextWindow: 1000000,
16431
16618
  maxTokens: 128000,
16432
16619
  },
16620
+ "anthropic/claude-opus-5.5": {
16621
+ id: "anthropic/claude-opus-5.5",
16622
+ name: "Claude Opus 5.5",
16623
+ api: "anthropic-messages",
16624
+ provider: "vercel-ai-gateway",
16625
+ baseUrl: "https://ai-gateway.vercel.sh",
16626
+ reasoning: true,
16627
+ thinkingLevelMap: { "xhigh": "xhigh" },
16628
+ input: ["text", "image"],
16629
+ cost: {
16630
+ input: 4,
16631
+ output: 20,
16632
+ cacheRead: 0.19999999999999998,
16633
+ cacheWrite: 5,
16634
+ },
16635
+ contextWindow: 1000000,
16636
+ maxTokens: 128000,
16637
+ },
16638
+ "anthropic/claude-opus-5.5-fast": {
16639
+ id: "anthropic/claude-opus-5.5-fast",
16640
+ name: "Claude Opus 5.5 (Fast)",
16641
+ api: "anthropic-messages",
16642
+ provider: "vercel-ai-gateway",
16643
+ baseUrl: "https://ai-gateway.vercel.sh",
16644
+ reasoning: true,
16645
+ thinkingLevelMap: { "xhigh": "xhigh" },
16646
+ input: ["text", "image"],
16647
+ cost: {
16648
+ input: 8,
16649
+ output: 40,
16650
+ cacheRead: 0.39999999999999997,
16651
+ cacheWrite: 10,
16652
+ },
16653
+ contextWindow: 1000000,
16654
+ maxTokens: 128000,
16655
+ },
16433
16656
  "anthropic/claude-sonnet-4": {
16434
16657
  id: "anthropic/claude-sonnet-4",
16435
16658
  name: "Claude Sonnet 4",
@@ -16765,7 +16988,7 @@ export const MODELS = {
16765
16988
  cost: {
16766
16989
  input: 0.3,
16767
16990
  output: 1.2,
16768
- cacheRead: 0.03,
16991
+ cacheRead: 0.007,
16769
16992
  cacheWrite: 0,
16770
16993
  },
16771
16994
  contextWindow: 1048576,
@@ -17638,6 +17861,23 @@ export const MODELS = {
17638
17861
  contextWindow: 262144,
17639
17862
  maxTokens: 4000,
17640
17863
  },
17864
+ "mixedbread/toast-1": {
17865
+ id: "mixedbread/toast-1",
17866
+ name: "Toast 1",
17867
+ api: "anthropic-messages",
17868
+ provider: "vercel-ai-gateway",
17869
+ baseUrl: "https://ai-gateway.vercel.sh",
17870
+ reasoning: false,
17871
+ input: ["text"],
17872
+ cost: {
17873
+ input: 0.3,
17874
+ output: 0.72,
17875
+ cacheRead: 0.036,
17876
+ cacheWrite: 0,
17877
+ },
17878
+ contextWindow: 131000,
17879
+ maxTokens: 4000,
17880
+ },
17641
17881
  "moonshotai/kimi-k2": {
17642
17882
  id: "moonshotai/kimi-k2",
17643
17883
  name: "Kimi K2 Instruct",
@@ -18917,6 +19157,40 @@ export const MODELS = {
18917
19157
  contextWindow: 256000,
18918
19158
  maxTokens: 32768,
18919
19159
  },
19160
+ "quiverai/arrow-2": {
19161
+ id: "quiverai/arrow-2",
19162
+ name: "Arrow 2",
19163
+ api: "anthropic-messages",
19164
+ provider: "vercel-ai-gateway",
19165
+ baseUrl: "https://ai-gateway.vercel.sh",
19166
+ reasoning: true,
19167
+ input: ["text", "image"],
19168
+ cost: {
19169
+ input: 4,
19170
+ output: 20,
19171
+ cacheRead: 0.39999999999999997,
19172
+ cacheWrite: 5,
19173
+ },
19174
+ contextWindow: 131072,
19175
+ maxTokens: 131072,
19176
+ },
19177
+ "quiverai/arrow-2-telos": {
19178
+ id: "quiverai/arrow-2-telos",
19179
+ name: "Arrow 2 Telos",
19180
+ api: "anthropic-messages",
19181
+ provider: "vercel-ai-gateway",
19182
+ baseUrl: "https://ai-gateway.vercel.sh",
19183
+ reasoning: true,
19184
+ input: ["text", "image"],
19185
+ cost: {
19186
+ input: 6,
19187
+ output: 30,
19188
+ cacheRead: 0.6,
19189
+ cacheWrite: 7.5,
19190
+ },
19191
+ contextWindow: 131072,
19192
+ maxTokens: 131072,
19193
+ },
18920
19194
  "sakana/fugu-max": {
18921
19195
  id: "sakana/fugu-max",
18922
19196
  name: "Fugu Max",
@@ -19172,6 +19446,23 @@ export const MODELS = {
19172
19446
  contextWindow: 500000,
19173
19447
  maxTokens: 500000,
19174
19448
  },
19449
+ "spacexai/grok-4.7": {
19450
+ id: "spacexai/grok-4.7",
19451
+ name: "Grok 4.7",
19452
+ api: "anthropic-messages",
19453
+ provider: "vercel-ai-gateway",
19454
+ baseUrl: "https://ai-gateway.vercel.sh",
19455
+ reasoning: true,
19456
+ input: ["text", "image"],
19457
+ cost: {
19458
+ input: 1.2,
19459
+ output: 3.5999999999999996,
19460
+ cacheRead: 0.3,
19461
+ cacheWrite: 0,
19462
+ },
19463
+ contextWindow: 500000,
19464
+ maxTokens: 500000,
19465
+ },
19175
19466
  "spacexai/grok-build-0.1": {
19176
19467
  id: "spacexai/grok-build-0.1",
19177
19468
  name: "Grok Build 0.1",
@@ -19325,6 +19616,57 @@ export const MODELS = {
19325
19616
  contextWindow: 1050000,
19326
19617
  maxTokens: 131000,
19327
19618
  },
19619
+ "xiaomi/mimo-v2.6-flash": {
19620
+ id: "xiaomi/mimo-v2.6-flash",
19621
+ name: "MiMo V2.6 Flash",
19622
+ api: "anthropic-messages",
19623
+ provider: "vercel-ai-gateway",
19624
+ baseUrl: "https://ai-gateway.vercel.sh",
19625
+ reasoning: true,
19626
+ input: ["text", "image"],
19627
+ cost: {
19628
+ input: 0.14,
19629
+ output: 0.28,
19630
+ cacheRead: 0.0028,
19631
+ cacheWrite: 0,
19632
+ },
19633
+ contextWindow: 1048576,
19634
+ maxTokens: 131072,
19635
+ },
19636
+ "xiaomi/mimo-v2.6-pro": {
19637
+ id: "xiaomi/mimo-v2.6-pro",
19638
+ name: "MiMo V2.6 Pro",
19639
+ api: "anthropic-messages",
19640
+ provider: "vercel-ai-gateway",
19641
+ baseUrl: "https://ai-gateway.vercel.sh",
19642
+ reasoning: true,
19643
+ input: ["text", "image"],
19644
+ cost: {
19645
+ input: 0.435,
19646
+ output: 0.87,
19647
+ cacheRead: 0.0036,
19648
+ cacheWrite: 0,
19649
+ },
19650
+ contextWindow: 1048576,
19651
+ maxTokens: 131072,
19652
+ },
19653
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
19654
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
19655
+ name: "MiMo V2.6 Pro UltraSpeed",
19656
+ api: "anthropic-messages",
19657
+ provider: "vercel-ai-gateway",
19658
+ baseUrl: "https://ai-gateway.vercel.sh",
19659
+ reasoning: true,
19660
+ input: ["text", "image"],
19661
+ cost: {
19662
+ input: 4.35,
19663
+ output: 8.7,
19664
+ cacheRead: 0.036,
19665
+ cacheWrite: 0,
19666
+ },
19667
+ contextWindow: 1048576,
19668
+ maxTokens: 131072,
19669
+ },
19328
19670
  "zai/glm-4.5": {
19329
19671
  id: "zai/glm-4.5",
19330
19672
  name: "GLM 4.5",
@@ -19701,6 +20043,23 @@ export const MODELS = {
19701
20043
  contextWindow: 500000,
19702
20044
  maxTokens: 500000,
19703
20045
  },
20046
+ "grok-4.7": {
20047
+ id: "grok-4.7",
20048
+ name: "Grok 4.7",
20049
+ api: "openai-completions",
20050
+ provider: "xai",
20051
+ baseUrl: "https://api.x.ai/v1",
20052
+ reasoning: true,
20053
+ input: ["text", "image"],
20054
+ cost: {
20055
+ input: 2,
20056
+ output: 6,
20057
+ cacheRead: 0.5,
20058
+ cacheWrite: 0,
20059
+ },
20060
+ contextWindow: 500000,
20061
+ maxTokens: 500000,
20062
+ },
19704
20063
  "grok-build-0.1": {
19705
20064
  id: "grok-build-0.1",
19706
20065
  name: "Grok Build 0.1",
@@ -19839,6 +20198,57 @@ export const MODELS = {
19839
20198
  contextWindow: 1048576,
19840
20199
  maxTokens: 131072,
19841
20200
  },
20201
+ "mimo-v2.6-flash": {
20202
+ id: "mimo-v2.6-flash",
20203
+ name: "MiMo-V2.6-Flash",
20204
+ api: "anthropic-messages",
20205
+ provider: "xiaomi",
20206
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20207
+ reasoning: true,
20208
+ input: ["text", "image"],
20209
+ cost: {
20210
+ input: 0.14,
20211
+ output: 0.28,
20212
+ cacheRead: 0.0028,
20213
+ cacheWrite: 0,
20214
+ },
20215
+ contextWindow: 1048576,
20216
+ maxTokens: 131072,
20217
+ },
20218
+ "mimo-v2.6-pro": {
20219
+ id: "mimo-v2.6-pro",
20220
+ name: "MiMo-V2.6-Pro",
20221
+ api: "anthropic-messages",
20222
+ provider: "xiaomi",
20223
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20224
+ reasoning: true,
20225
+ input: ["text", "image"],
20226
+ cost: {
20227
+ input: 0.435,
20228
+ output: 0.87,
20229
+ cacheRead: 0.0036,
20230
+ cacheWrite: 0,
20231
+ },
20232
+ contextWindow: 1048576,
20233
+ maxTokens: 131072,
20234
+ },
20235
+ "mimo-v2.6-pro-ultraspeed": {
20236
+ id: "mimo-v2.6-pro-ultraspeed",
20237
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20238
+ api: "anthropic-messages",
20239
+ provider: "xiaomi",
20240
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20241
+ reasoning: true,
20242
+ input: ["text", "image"],
20243
+ cost: {
20244
+ input: 4.35,
20245
+ output: 8.7,
20246
+ cacheRead: 0.036,
20247
+ cacheWrite: 0,
20248
+ },
20249
+ contextWindow: 1048576,
20250
+ maxTokens: 131072,
20251
+ },
19842
20252
  },
19843
20253
  "xiaomi-token-plan-ams": {
19844
20254
  "mimo-v2-flash": {
@@ -19943,6 +20353,57 @@ export const MODELS = {
19943
20353
  contextWindow: 1048576,
19944
20354
  maxTokens: 131072,
19945
20355
  },
20356
+ "mimo-v2.6-flash": {
20357
+ id: "mimo-v2.6-flash",
20358
+ name: "MiMo-V2.6-Flash",
20359
+ api: "anthropic-messages",
20360
+ provider: "xiaomi-token-plan-ams",
20361
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20362
+ reasoning: true,
20363
+ input: ["text", "image"],
20364
+ cost: {
20365
+ input: 0.14,
20366
+ output: 0.28,
20367
+ cacheRead: 0.0028,
20368
+ cacheWrite: 0,
20369
+ },
20370
+ contextWindow: 1048576,
20371
+ maxTokens: 131072,
20372
+ },
20373
+ "mimo-v2.6-pro": {
20374
+ id: "mimo-v2.6-pro",
20375
+ name: "MiMo-V2.6-Pro",
20376
+ api: "anthropic-messages",
20377
+ provider: "xiaomi-token-plan-ams",
20378
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20379
+ reasoning: true,
20380
+ input: ["text", "image"],
20381
+ cost: {
20382
+ input: 0.435,
20383
+ output: 0.87,
20384
+ cacheRead: 0.0036,
20385
+ cacheWrite: 0,
20386
+ },
20387
+ contextWindow: 1048576,
20388
+ maxTokens: 131072,
20389
+ },
20390
+ "mimo-v2.6-pro-ultraspeed": {
20391
+ id: "mimo-v2.6-pro-ultraspeed",
20392
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20393
+ api: "anthropic-messages",
20394
+ provider: "xiaomi-token-plan-ams",
20395
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20396
+ reasoning: true,
20397
+ input: ["text", "image"],
20398
+ cost: {
20399
+ input: 4.35,
20400
+ output: 8.7,
20401
+ cacheRead: 0.036,
20402
+ cacheWrite: 0,
20403
+ },
20404
+ contextWindow: 1048576,
20405
+ maxTokens: 131072,
20406
+ },
19946
20407
  },
19947
20408
  "xiaomi-token-plan-cn": {
19948
20409
  "mimo-v2-flash": {
@@ -20047,6 +20508,57 @@ export const MODELS = {
20047
20508
  contextWindow: 1048576,
20048
20509
  maxTokens: 131072,
20049
20510
  },
20511
+ "mimo-v2.6-flash": {
20512
+ id: "mimo-v2.6-flash",
20513
+ name: "MiMo-V2.6-Flash",
20514
+ api: "anthropic-messages",
20515
+ provider: "xiaomi-token-plan-cn",
20516
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20517
+ reasoning: true,
20518
+ input: ["text", "image"],
20519
+ cost: {
20520
+ input: 0.14,
20521
+ output: 0.28,
20522
+ cacheRead: 0.0028,
20523
+ cacheWrite: 0,
20524
+ },
20525
+ contextWindow: 1048576,
20526
+ maxTokens: 131072,
20527
+ },
20528
+ "mimo-v2.6-pro": {
20529
+ id: "mimo-v2.6-pro",
20530
+ name: "MiMo-V2.6-Pro",
20531
+ api: "anthropic-messages",
20532
+ provider: "xiaomi-token-plan-cn",
20533
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20534
+ reasoning: true,
20535
+ input: ["text", "image"],
20536
+ cost: {
20537
+ input: 0.435,
20538
+ output: 0.87,
20539
+ cacheRead: 0.0036,
20540
+ cacheWrite: 0,
20541
+ },
20542
+ contextWindow: 1048576,
20543
+ maxTokens: 131072,
20544
+ },
20545
+ "mimo-v2.6-pro-ultraspeed": {
20546
+ id: "mimo-v2.6-pro-ultraspeed",
20547
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20548
+ api: "anthropic-messages",
20549
+ provider: "xiaomi-token-plan-cn",
20550
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20551
+ reasoning: true,
20552
+ input: ["text", "image"],
20553
+ cost: {
20554
+ input: 4.35,
20555
+ output: 8.7,
20556
+ cacheRead: 0.036,
20557
+ cacheWrite: 0,
20558
+ },
20559
+ contextWindow: 1048576,
20560
+ maxTokens: 131072,
20561
+ },
20050
20562
  },
20051
20563
  "xiaomi-token-plan-sgp": {
20052
20564
  "mimo-v2-flash": {
@@ -20151,6 +20663,57 @@ export const MODELS = {
20151
20663
  contextWindow: 1048576,
20152
20664
  maxTokens: 131072,
20153
20665
  },
20666
+ "mimo-v2.6-flash": {
20667
+ id: "mimo-v2.6-flash",
20668
+ name: "MiMo-V2.6-Flash",
20669
+ api: "anthropic-messages",
20670
+ provider: "xiaomi-token-plan-sgp",
20671
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20672
+ reasoning: true,
20673
+ input: ["text", "image"],
20674
+ cost: {
20675
+ input: 0.14,
20676
+ output: 0.28,
20677
+ cacheRead: 0.0028,
20678
+ cacheWrite: 0,
20679
+ },
20680
+ contextWindow: 1048576,
20681
+ maxTokens: 131072,
20682
+ },
20683
+ "mimo-v2.6-pro": {
20684
+ id: "mimo-v2.6-pro",
20685
+ name: "MiMo-V2.6-Pro",
20686
+ api: "anthropic-messages",
20687
+ provider: "xiaomi-token-plan-sgp",
20688
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20689
+ reasoning: true,
20690
+ input: ["text", "image"],
20691
+ cost: {
20692
+ input: 0.435,
20693
+ output: 0.87,
20694
+ cacheRead: 0.0036,
20695
+ cacheWrite: 0,
20696
+ },
20697
+ contextWindow: 1048576,
20698
+ maxTokens: 131072,
20699
+ },
20700
+ "mimo-v2.6-pro-ultraspeed": {
20701
+ id: "mimo-v2.6-pro-ultraspeed",
20702
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20703
+ api: "anthropic-messages",
20704
+ provider: "xiaomi-token-plan-sgp",
20705
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20706
+ reasoning: true,
20707
+ input: ["text", "image"],
20708
+ cost: {
20709
+ input: 4.35,
20710
+ output: 8.7,
20711
+ cacheRead: 0.036,
20712
+ cacheWrite: 0,
20713
+ },
20714
+ contextWindow: 1048576,
20715
+ maxTokens: 131072,
20716
+ },
20154
20717
  },
20155
20718
  "zai": {
20156
20719
  "glm-4.7": {