@kolisachint/hoocode-ai 0.5.80 → 0.5.82

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)",
@@ -869,6 +887,42 @@ export const MODELS = {
869
887
  contextWindow: 1050000,
870
888
  maxTokens: 128000,
871
889
  },
890
+ "gpt-6-luna": {
891
+ id: "gpt-6-luna",
892
+ name: "GPT-6 Luna",
893
+ api: "azure-openai-responses",
894
+ provider: "azure-openai-responses",
895
+ baseUrl: "",
896
+ reasoning: true,
897
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
898
+ input: ["text", "image"],
899
+ cost: {
900
+ input: 0.1,
901
+ output: 0.5,
902
+ cacheRead: 0.01,
903
+ cacheWrite: 0.125,
904
+ },
905
+ contextWindow: 1050000,
906
+ maxTokens: 128000,
907
+ },
908
+ "gpt-6-sol": {
909
+ id: "gpt-6-sol",
910
+ name: "GPT-6 Sol",
911
+ api: "azure-openai-responses",
912
+ provider: "azure-openai-responses",
913
+ baseUrl: "",
914
+ reasoning: true,
915
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
916
+ input: ["text", "image"],
917
+ cost: {
918
+ input: 2,
919
+ output: 10,
920
+ cacheRead: 0.2,
921
+ cacheWrite: 2.5,
922
+ },
923
+ contextWindow: 1050000,
924
+ maxTokens: 128000,
925
+ },
872
926
  "gpt-realtime-2.1": {
873
927
  id: "gpt-realtime-2.1",
874
928
  name: "GPT-Realtime-2.1",
@@ -2085,6 +2139,25 @@ export const MODELS = {
2085
2139
  contextWindow: 500000,
2086
2140
  maxTokens: 128000,
2087
2141
  },
2142
+ "grok-4.7": {
2143
+ id: "grok-4.7",
2144
+ name: "Grok 4.7",
2145
+ api: "openai-completions",
2146
+ provider: "github-copilot",
2147
+ baseUrl: "https://api.individual.githubcopilot.com",
2148
+ 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" },
2149
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2150
+ reasoning: true,
2151
+ input: ["text", "image"],
2152
+ cost: {
2153
+ input: 2,
2154
+ output: 6,
2155
+ cacheRead: 0.5,
2156
+ cacheWrite: 0,
2157
+ },
2158
+ contextWindow: 500000,
2159
+ maxTokens: 128000,
2160
+ },
2088
2161
  "kimi-k2.7-code": {
2089
2162
  id: "kimi-k2.7-code",
2090
2163
  name: "Kimi K2.7 Code",
@@ -4295,6 +4368,24 @@ export const MODELS = {
4295
4368
  contextWindow: 262144,
4296
4369
  maxTokens: 128000,
4297
4370
  },
4371
+ "tencent/Hy4-preview": {
4372
+ id: "tencent/Hy4-preview",
4373
+ name: "Hy4 preview",
4374
+ api: "openai-completions",
4375
+ provider: "huggingface",
4376
+ baseUrl: "https://router.huggingface.co/v1",
4377
+ compat: { "supportsDeveloperRole": false },
4378
+ reasoning: true,
4379
+ input: ["text"],
4380
+ cost: {
4381
+ input: 0.834,
4382
+ output: 2.501,
4383
+ cacheRead: 0,
4384
+ cacheWrite: 0,
4385
+ },
4386
+ contextWindow: 1000000,
4387
+ maxTokens: 64000,
4388
+ },
4298
4389
  "thinkingmachines/Inkling": {
4299
4390
  id: "thinkingmachines/Inkling",
4300
4391
  name: "Inkling",
@@ -6595,6 +6686,42 @@ export const MODELS = {
6595
6686
  contextWindow: 1050000,
6596
6687
  maxTokens: 128000,
6597
6688
  },
6689
+ "gpt-6-luna": {
6690
+ id: "gpt-6-luna",
6691
+ name: "GPT-6 Luna",
6692
+ api: "openai-responses",
6693
+ provider: "openai",
6694
+ baseUrl: "https://api.openai.com/v1",
6695
+ reasoning: true,
6696
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6697
+ input: ["text", "image"],
6698
+ cost: {
6699
+ input: 0.1,
6700
+ output: 0.5,
6701
+ cacheRead: 0.01,
6702
+ cacheWrite: 0.125,
6703
+ },
6704
+ contextWindow: 1050000,
6705
+ maxTokens: 128000,
6706
+ },
6707
+ "gpt-6-sol": {
6708
+ id: "gpt-6-sol",
6709
+ name: "GPT-6 Sol",
6710
+ api: "openai-responses",
6711
+ provider: "openai",
6712
+ baseUrl: "https://api.openai.com/v1",
6713
+ reasoning: true,
6714
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6715
+ input: ["text", "image"],
6716
+ cost: {
6717
+ input: 2,
6718
+ output: 10,
6719
+ cacheRead: 0.2,
6720
+ cacheWrite: 2.5,
6721
+ },
6722
+ contextWindow: 1050000,
6723
+ maxTokens: 128000,
6724
+ },
6598
6725
  "gpt-realtime-2.1": {
6599
6726
  id: "gpt-realtime-2.1",
6600
6727
  name: "GPT-Realtime-2.1",
@@ -7145,6 +7272,24 @@ export const MODELS = {
7145
7272
  contextWindow: 1000000,
7146
7273
  maxTokens: 128000,
7147
7274
  },
7275
+ "claude-opus-5-5": {
7276
+ id: "claude-opus-5-5",
7277
+ name: "Claude Opus 5.5",
7278
+ api: "anthropic-messages",
7279
+ provider: "opencode",
7280
+ baseUrl: "https://opencode.ai/zen",
7281
+ reasoning: true,
7282
+ thinkingLevelMap: { "xhigh": "xhigh" },
7283
+ input: ["text", "image"],
7284
+ cost: {
7285
+ input: 4,
7286
+ output: 20,
7287
+ cacheRead: 0.2,
7288
+ cacheWrite: 5,
7289
+ },
7290
+ contextWindow: 1000000,
7291
+ maxTokens: 128000,
7292
+ },
7148
7293
  "claude-sonnet-4": {
7149
7294
  id: "claude-sonnet-4",
7150
7295
  name: "Claude Sonnet 4",
@@ -7861,6 +8006,42 @@ export const MODELS = {
7861
8006
  contextWindow: 1050000,
7862
8007
  maxTokens: 128000,
7863
8008
  },
8009
+ "gpt-6-luna": {
8010
+ id: "gpt-6-luna",
8011
+ name: "GPT-6 Luna",
8012
+ api: "openai-responses",
8013
+ provider: "opencode",
8014
+ baseUrl: "https://opencode.ai/zen/v1",
8015
+ reasoning: true,
8016
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8017
+ input: ["text", "image"],
8018
+ cost: {
8019
+ input: 0.1,
8020
+ output: 0.5,
8021
+ cacheRead: 0.01,
8022
+ cacheWrite: 0.125,
8023
+ },
8024
+ contextWindow: 1050000,
8025
+ maxTokens: 128000,
8026
+ },
8027
+ "gpt-6-sol": {
8028
+ id: "gpt-6-sol",
8029
+ name: "GPT-6 Sol",
8030
+ api: "openai-responses",
8031
+ provider: "opencode",
8032
+ baseUrl: "https://opencode.ai/zen/v1",
8033
+ reasoning: true,
8034
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8035
+ input: ["text", "image"],
8036
+ cost: {
8037
+ input: 2,
8038
+ output: 10,
8039
+ cacheRead: 0.2,
8040
+ cacheWrite: 2.5,
8041
+ },
8042
+ contextWindow: 1050000,
8043
+ maxTokens: 128000,
8044
+ },
7864
8045
  "grok-4.5": {
7865
8046
  id: "grok-4.5",
7866
8047
  name: "Grok 4.5",
@@ -7895,6 +8076,23 @@ export const MODELS = {
7895
8076
  contextWindow: 500000,
7896
8077
  maxTokens: 500000,
7897
8078
  },
8079
+ "grok-4.7": {
8080
+ id: "grok-4.7",
8081
+ name: "Grok 4.7 (30% Off)",
8082
+ api: "openai-responses",
8083
+ provider: "opencode",
8084
+ baseUrl: "https://opencode.ai/zen/v1",
8085
+ reasoning: true,
8086
+ input: ["text", "image"],
8087
+ cost: {
8088
+ input: 1.4,
8089
+ output: 4.2,
8090
+ cacheRead: 0.35,
8091
+ cacheWrite: 0,
8092
+ },
8093
+ contextWindow: 500000,
8094
+ maxTokens: 500000,
8095
+ },
7898
8096
  "grok-build-0.1": {
7899
8097
  id: "grok-build-0.1",
7900
8098
  name: "Grok Build 0.1",
@@ -7997,9 +8195,9 @@ export const MODELS = {
7997
8195
  contextWindow: 262144,
7998
8196
  maxTokens: 32768,
7999
8197
  },
8000
- "mimo-v2.5-free": {
8001
- id: "mimo-v2.5-free",
8002
- name: "MiMo V2.5 Free",
8198
+ "mimo-v2.6-flash-free": {
8199
+ id: "mimo-v2.6-flash-free",
8200
+ name: "MiMo-V2.6-Flash Free",
8003
8201
  api: "openai-completions",
8004
8202
  provider: "opencode",
8005
8203
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8399,6 +8597,23 @@ export const MODELS = {
8399
8597
  contextWindow: 500000,
8400
8598
  maxTokens: 500000,
8401
8599
  },
8600
+ "grok-4.7": {
8601
+ id: "grok-4.7",
8602
+ name: "Grok 4.7",
8603
+ api: "openai-responses",
8604
+ provider: "opencode-go",
8605
+ baseUrl: "https://opencode.ai/zen/go/v1",
8606
+ reasoning: true,
8607
+ input: ["text", "image"],
8608
+ cost: {
8609
+ input: 2,
8610
+ output: 6,
8611
+ cacheRead: 0.5,
8612
+ cacheWrite: 0,
8613
+ },
8614
+ contextWindow: 500000,
8615
+ maxTokens: 500000,
8616
+ },
8402
8617
  "hy3": {
8403
8618
  id: "hy3",
8404
8619
  name: "Hy3",
@@ -8536,6 +8751,40 @@ export const MODELS = {
8536
8751
  contextWindow: 1048576,
8537
8752
  maxTokens: 128000,
8538
8753
  },
8754
+ "mimo-v2.6-flash": {
8755
+ id: "mimo-v2.6-flash",
8756
+ name: "MiMo-V2.6-Flash",
8757
+ api: "openai-completions",
8758
+ provider: "opencode-go",
8759
+ baseUrl: "https://opencode.ai/zen/go/v1",
8760
+ reasoning: true,
8761
+ input: ["text", "image"],
8762
+ cost: {
8763
+ input: 0.14,
8764
+ output: 0.28,
8765
+ cacheRead: 0.0028,
8766
+ cacheWrite: 0,
8767
+ },
8768
+ contextWindow: 1048576,
8769
+ maxTokens: 131072,
8770
+ },
8771
+ "mimo-v2.6-pro": {
8772
+ id: "mimo-v2.6-pro",
8773
+ name: "MiMo-V2.6-Pro",
8774
+ api: "openai-completions",
8775
+ provider: "opencode-go",
8776
+ baseUrl: "https://opencode.ai/zen/go/v1",
8777
+ reasoning: true,
8778
+ input: ["text", "image"],
8779
+ cost: {
8780
+ input: 0.435,
8781
+ output: 0.87,
8782
+ cacheRead: 0.003625,
8783
+ cacheWrite: 0,
8784
+ },
8785
+ contextWindow: 1048576,
8786
+ maxTokens: 131072,
8787
+ },
8539
8788
  "minimax-m2.7": {
8540
8789
  id: "minimax-m2.7",
8541
8790
  name: "MiniMax-M2.7",
@@ -8548,7 +8797,7 @@ export const MODELS = {
8548
8797
  input: 0.3,
8549
8798
  output: 1.2,
8550
8799
  cacheRead: 0.06,
8551
- cacheWrite: 0,
8800
+ cacheWrite: 0.375,
8552
8801
  },
8553
8802
  contextWindow: 204800,
8554
8803
  maxTokens: 131072,
@@ -8952,23 +9201,6 @@ export const MODELS = {
8952
9201
  contextWindow: 200000,
8953
9202
  maxTokens: 64000,
8954
9203
  },
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
9204
  "anthropic/claude-opus-4.1": {
8973
9205
  id: "anthropic/claude-opus-4.1",
8974
9206
  name: "Anthropic: Claude Opus 4.1",
@@ -9163,6 +9395,42 @@ export const MODELS = {
9163
9395
  contextWindow: 1000000,
9164
9396
  maxTokens: 128000,
9165
9397
  },
9398
+ "anthropic/claude-opus-5.5": {
9399
+ id: "anthropic/claude-opus-5.5",
9400
+ name: "Anthropic: Claude Opus 5.5",
9401
+ api: "openai-completions",
9402
+ provider: "openrouter",
9403
+ baseUrl: "https://openrouter.ai/api/v1",
9404
+ reasoning: true,
9405
+ thinkingLevelMap: { "xhigh": "xhigh" },
9406
+ input: ["text", "image"],
9407
+ cost: {
9408
+ input: 4,
9409
+ output: 20,
9410
+ cacheRead: 0.19999999999999998,
9411
+ cacheWrite: 5,
9412
+ },
9413
+ contextWindow: 1000000,
9414
+ maxTokens: 128000,
9415
+ },
9416
+ "anthropic/claude-opus-5.5:batch": {
9417
+ id: "anthropic/claude-opus-5.5:batch",
9418
+ name: "Anthropic: Claude Opus 5.5 (batch)",
9419
+ api: "openai-completions",
9420
+ provider: "openrouter",
9421
+ baseUrl: "https://openrouter.ai/api/v1",
9422
+ reasoning: true,
9423
+ thinkingLevelMap: { "xhigh": "xhigh" },
9424
+ input: ["text", "image"],
9425
+ cost: {
9426
+ input: 2,
9427
+ output: 10,
9428
+ cacheRead: 0.09999999999999999,
9429
+ cacheWrite: 2.5,
9430
+ },
9431
+ contextWindow: 1000000,
9432
+ maxTokens: 128000,
9433
+ },
9166
9434
  "anthropic/claude-opus-5:batch": {
9167
9435
  id: "anthropic/claude-opus-5:batch",
9168
9436
  name: "Anthropic: Claude Opus 5 (batch)",
@@ -9194,7 +9462,7 @@ export const MODELS = {
9194
9462
  cacheRead: 0.3,
9195
9463
  cacheWrite: 3.75,
9196
9464
  },
9197
- contextWindow: 1000000,
9465
+ contextWindow: 200000,
9198
9466
  maxTokens: 64000,
9199
9467
  },
9200
9468
  "anthropic/claude-sonnet-4.5": {
@@ -9436,6 +9704,23 @@ export const MODELS = {
9436
9704
  contextWindow: 262144,
9437
9705
  maxTokens: 131072,
9438
9706
  },
9707
+ "cohere/command-a-plus": {
9708
+ id: "cohere/command-a-plus",
9709
+ name: "Cohere: Command A+",
9710
+ api: "openai-completions",
9711
+ provider: "openrouter",
9712
+ baseUrl: "https://openrouter.ai/api/v1",
9713
+ reasoning: true,
9714
+ input: ["text", "image"],
9715
+ cost: {
9716
+ input: 0.3,
9717
+ output: 1.5,
9718
+ cacheRead: 0.15,
9719
+ cacheWrite: 0,
9720
+ },
9721
+ contextWindow: 192000,
9722
+ maxTokens: 64000,
9723
+ },
9439
9724
  "cohere/command-r-08-2024": {
9440
9725
  id: "cohere/command-r-08-2024",
9441
9726
  name: "Cohere: Command R (08-2024)",
@@ -9634,9 +9919,9 @@ export const MODELS = {
9634
9919
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9635
9920
  input: ["text"],
9636
9921
  cost: {
9637
- input: 0.04368,
9638
- output: 0.08736,
9639
- cacheRead: 0.008735999999999999,
9922
+ input: 0.088606,
9923
+ output: 0.177212,
9924
+ cacheRead: 0.017721200000000003,
9640
9925
  cacheWrite: 0,
9641
9926
  },
9642
9927
  contextWindow: 1048576,
@@ -9654,51 +9939,13 @@ export const MODELS = {
9654
9939
  input: ["text"],
9655
9940
  cost: {
9656
9941
  input: 0.04,
9657
- output: 0.08,
9942
+ output: 0.64,
9658
9943
  cacheRead: 0.016,
9659
9944
  cacheWrite: 0,
9660
9945
  },
9661
9946
  contextWindow: 1310720,
9662
9947
  maxTokens: 943718,
9663
9948
  },
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
9949
  "deepseek/deepseek-v4-flash-vision-exp": {
9703
9950
  id: "deepseek/deepseek-v4-flash-vision-exp",
9704
9951
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -9710,28 +9957,9 @@ export const MODELS = {
9710
9957
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9711
9958
  input: ["text", "image"],
9712
9959
  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,
9960
+ input: 0.22,
9961
+ output: 0.66,
9962
+ cacheRead: 0.007,
9735
9963
  cacheWrite: 0,
9736
9964
  },
9737
9965
  contextWindow: 1048576,
@@ -9748,9 +9976,9 @@ export const MODELS = {
9748
9976
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9749
9977
  input: ["text"],
9750
9978
  cost: {
9751
- input: 0.422298,
9752
- output: 0.844596,
9753
- cacheRead: 0.0351915,
9979
+ input: 0.9552599999999999,
9980
+ output: 1.9105199999999998,
9981
+ cacheRead: 0.07960500000000001,
9754
9982
  cacheWrite: 0,
9755
9983
  },
9756
9984
  contextWindow: 1048576,
@@ -9767,36 +9995,36 @@ export const MODELS = {
9767
9995
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9768
9996
  input: ["text"],
9769
9997
  cost: {
9770
- input: 0.57816,
9771
- output: 1.73448,
9772
- cacheRead: 0.018396000000000003,
9998
+ input: 1.32,
9999
+ output: 3.9600000000000004,
10000
+ cacheRead: 0.044,
9773
10001
  cacheWrite: 0,
9774
10002
  },
9775
10003
  contextWindow: 1048576,
9776
- maxTokens: 393216,
10004
+ maxTokens: 384000,
9777
10005
  },
9778
- "deepseek/deepseek-v4-pro-0813:batch": {
9779
- id: "deepseek/deepseek-v4-pro-0813:batch",
9780
- name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
10006
+ "deepseek/deepseek-v4.1-flash": {
10007
+ id: "deepseek/deepseek-v4.1-flash",
10008
+ name: "DeepSeek: DeepSeek V4.1 Flash",
9781
10009
  api: "openai-completions",
9782
10010
  provider: "openrouter",
9783
10011
  baseUrl: "https://openrouter.ai/api/v1",
9784
10012
  compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9785
10013
  reasoning: true,
9786
10014
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9787
- input: ["text"],
10015
+ input: ["text", "image"],
9788
10016
  cost: {
9789
- input: 0.66,
9790
- output: 1.9800000000000002,
9791
- cacheRead: 0.022,
10017
+ input: 0.09999999999999999,
10018
+ output: 0.5,
10019
+ cacheRead: 0.01,
9792
10020
  cacheWrite: 0,
9793
10021
  },
9794
10022
  contextWindow: 1048576,
9795
10023
  maxTokens: 943718,
9796
10024
  },
9797
- "deepseek/deepseek-v4.1-flash": {
9798
- id: "deepseek/deepseek-v4.1-flash",
9799
- name: "DeepSeek: DeepSeek V4.1 Flash",
10025
+ "deepseek/deepseek-v4.1-flash:batch": {
10026
+ id: "deepseek/deepseek-v4.1-flash:batch",
10027
+ name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
9800
10028
  api: "openai-completions",
9801
10029
  provider: "openrouter",
9802
10030
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9805,13 +10033,13 @@ export const MODELS = {
9805
10033
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9806
10034
  input: ["text", "image"],
9807
10035
  cost: {
9808
- input: 0.15,
9809
- output: 0.6,
9810
- cacheRead: 0.003,
10036
+ input: 0.112,
10037
+ output: 0.33599999999999997,
10038
+ cacheRead: 0.00336,
9811
10039
  cacheWrite: 0,
9812
10040
  },
9813
10041
  contextWindow: 1048576,
9814
- maxTokens: 384000,
10042
+ maxTokens: 131072,
9815
10043
  },
9816
10044
  "dots-studio/dots-3-note-preview:free": {
9817
10045
  id: "dots-studio/dots-3-note-preview:free",
@@ -10527,23 +10755,6 @@ export const MODELS = {
10527
10755
  contextWindow: 262144,
10528
10756
  maxTokens: 32768,
10529
10757
  },
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
10758
  "kwaipilot/kat-coder-pro-v2.5": {
10548
10759
  id: "kwaipilot/kat-coder-pro-v2.5",
10549
10760
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -10689,30 +10900,13 @@ export const MODELS = {
10689
10900
  reasoning: true,
10690
10901
  input: ["text", "image"],
10691
10902
  cost: {
10692
- input: 0.35,
10693
- output: 1.5,
10903
+ input: 0.3,
10904
+ output: 1.2,
10694
10905
  cacheRead: 0.04,
10695
10906
  cacheWrite: 0,
10696
10907
  },
10697
10908
  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,
10909
+ maxTokens: 16384,
10716
10910
  },
10717
10911
  "meta/muse-spark-1.1": {
10718
10912
  id: "meta/muse-spark-1.1",
@@ -10901,23 +11095,6 @@ export const MODELS = {
10901
11095
  contextWindow: 1048576,
10902
11096
  maxTokens: 512000,
10903
11097
  },
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
11098
  "mistralai/codestral-2508": {
10922
11099
  id: "mistralai/codestral-2508",
10923
11100
  name: "Mistral: Codestral 2508",
@@ -11241,6 +11418,23 @@ export const MODELS = {
11241
11418
  contextWindow: 262144,
11242
11419
  maxTokens: 209715,
11243
11420
  },
11421
+ "mistralai/mistral-small-3.1-24b-instruct": {
11422
+ id: "mistralai/mistral-small-3.1-24b-instruct",
11423
+ name: "Mistral: Mistral Small 3.1 24B",
11424
+ api: "openai-completions",
11425
+ provider: "openrouter",
11426
+ baseUrl: "https://openrouter.ai/api/v1",
11427
+ reasoning: false,
11428
+ input: ["text", "image"],
11429
+ cost: {
11430
+ input: 0.351,
11431
+ output: 0.5549999999999999,
11432
+ cacheRead: 0,
11433
+ cacheWrite: 0,
11434
+ },
11435
+ contextWindow: 128000,
11436
+ maxTokens: 102400,
11437
+ },
11244
11438
  "mistralai/mistral-small-3.2-24b-instruct": {
11245
11439
  id: "mistralai/mistral-small-3.2-24b-instruct",
11246
11440
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11387,7 +11581,7 @@ export const MODELS = {
11387
11581
  input: ["text", "image"],
11388
11582
  cost: {
11389
11583
  input: 0.7062,
11390
- output: 3.21,
11584
+ output: 3.3000000000000003,
11391
11585
  cacheRead: 0.18,
11392
11586
  cacheWrite: 0,
11393
11587
  },
@@ -11403,9 +11597,9 @@ export const MODELS = {
11403
11597
  reasoning: true,
11404
11598
  input: ["text", "image"],
11405
11599
  cost: {
11406
- input: 1.7,
11407
- output: 8.5,
11408
- cacheRead: 0.16999999999999998,
11600
+ input: 3,
11601
+ output: 15,
11602
+ cacheRead: 0.3,
11409
11603
  cacheWrite: 0,
11410
11604
  },
11411
11605
  contextWindow: 1048576,
@@ -11420,13 +11614,13 @@ export const MODELS = {
11420
11614
  reasoning: true,
11421
11615
  input: ["text", "image"],
11422
11616
  cost: {
11423
- input: 3,
11424
- output: 15,
11425
- cacheRead: 0.3,
11617
+ input: 2.2800000000000002,
11618
+ output: 11.399999999999999,
11619
+ cacheRead: 0.228,
11426
11620
  cacheWrite: 0,
11427
11621
  },
11428
11622
  contextWindow: 1048576,
11429
- maxTokens: 943718,
11623
+ maxTokens: 16384,
11430
11624
  },
11431
11625
  "nex-agi/nex-n2.5-mini:free": {
11432
11626
  id: "nex-agi/nex-n2.5-mini:free",
@@ -11445,6 +11639,23 @@ export const MODELS = {
11445
11639
  contextWindow: 262144,
11446
11640
  maxTokens: 235929,
11447
11641
  },
11642
+ "nex-agi/nex-n2.5-pro": {
11643
+ id: "nex-agi/nex-n2.5-pro",
11644
+ name: "Nex AGI: Nex-N2.5-Pro",
11645
+ api: "openai-completions",
11646
+ provider: "openrouter",
11647
+ baseUrl: "https://openrouter.ai/api/v1",
11648
+ reasoning: true,
11649
+ input: ["text", "image"],
11650
+ cost: {
11651
+ input: 0.075,
11652
+ output: 0.25,
11653
+ cacheRead: 0.015,
11654
+ cacheWrite: 0,
11655
+ },
11656
+ contextWindow: 262144,
11657
+ maxTokens: 235929,
11658
+ },
11448
11659
  "nex-agi/nex-n2.5-pro:free": {
11449
11660
  id: "nex-agi/nex-n2.5-pro:free",
11450
11661
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -11471,9 +11682,9 @@ export const MODELS = {
11471
11682
  reasoning: true,
11472
11683
  input: ["text"],
11473
11684
  cost: {
11474
- input: 0.06,
11475
- output: 0.24,
11476
- cacheRead: 0,
11685
+ input: 0.049999999999999996,
11686
+ output: 0.19999999999999998,
11687
+ cacheRead: 0.03,
11477
11688
  cacheWrite: 0,
11478
11689
  },
11479
11690
  contextWindow: 262144,
@@ -12802,93 +13013,212 @@ export const MODELS = {
12802
13013
  contextWindow: 1050000,
12803
13014
  maxTokens: 128000,
12804
13015
  },
12805
- "openai/gpt-audio": {
12806
- id: "openai/gpt-audio",
12807
- name: "OpenAI: GPT Audio",
13016
+ "openai/gpt-6-luna": {
13017
+ id: "openai/gpt-6-luna",
13018
+ name: "OpenAI: GPT-6 Luna",
12808
13019
  api: "openai-completions",
12809
13020
  provider: "openrouter",
12810
13021
  baseUrl: "https://openrouter.ai/api/v1",
12811
- reasoning: false,
12812
- input: ["text"],
13022
+ reasoning: true,
13023
+ input: ["text", "image"],
12813
13024
  cost: {
12814
- input: 2.5,
12815
- output: 10,
12816
- cacheRead: 0,
12817
- cacheWrite: 0,
13025
+ input: 0.09999999999999999,
13026
+ output: 0.5,
13027
+ cacheRead: 0.01,
13028
+ cacheWrite: 0.125,
12818
13029
  },
12819
- contextWindow: 128000,
12820
- maxTokens: 16384,
13030
+ contextWindow: 1050000,
13031
+ maxTokens: 128000,
12821
13032
  },
12822
- "openai/gpt-audio-mini": {
12823
- id: "openai/gpt-audio-mini",
12824
- name: "OpenAI: GPT Audio Mini",
13033
+ "openai/gpt-6-luna-pro": {
13034
+ id: "openai/gpt-6-luna-pro",
13035
+ name: "OpenAI: GPT-6 Luna Pro",
12825
13036
  api: "openai-completions",
12826
13037
  provider: "openrouter",
12827
13038
  baseUrl: "https://openrouter.ai/api/v1",
12828
- reasoning: false,
12829
- input: ["text"],
13039
+ reasoning: true,
13040
+ input: ["text", "image"],
12830
13041
  cost: {
12831
- input: 0.6,
12832
- output: 2.4,
12833
- cacheRead: 0,
12834
- cacheWrite: 0,
13042
+ input: 0.09999999999999999,
13043
+ output: 0.5,
13044
+ cacheRead: 0.01,
13045
+ cacheWrite: 0.125,
12835
13046
  },
12836
- contextWindow: 128000,
12837
- maxTokens: 16384,
13047
+ contextWindow: 1050000,
13048
+ maxTokens: 128000,
12838
13049
  },
12839
- "openai/gpt-chat-latest": {
12840
- id: "openai/gpt-chat-latest",
12841
- name: "OpenAI: GPT Chat Latest",
13050
+ "openai/gpt-6-luna-pro:batch": {
13051
+ id: "openai/gpt-6-luna-pro:batch",
13052
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
12842
13053
  api: "openai-completions",
12843
13054
  provider: "openrouter",
12844
13055
  baseUrl: "https://openrouter.ai/api/v1",
12845
- reasoning: false,
13056
+ reasoning: true,
12846
13057
  input: ["text", "image"],
12847
13058
  cost: {
12848
- input: 5,
12849
- output: 30,
12850
- cacheRead: 0.5,
12851
- cacheWrite: 0,
13059
+ input: 0.049999999999999996,
13060
+ output: 0.25,
13061
+ cacheRead: 0.005,
13062
+ cacheWrite: 0.0625,
12852
13063
  },
12853
- contextWindow: 400000,
13064
+ contextWindow: 1050000,
12854
13065
  maxTokens: 128000,
12855
13066
  },
12856
- "openai/gpt-oss-120b": {
12857
- id: "openai/gpt-oss-120b",
12858
- name: "OpenAI: gpt-oss-120b",
13067
+ "openai/gpt-6-luna:batch": {
13068
+ id: "openai/gpt-6-luna:batch",
13069
+ name: "OpenAI: GPT-6 Luna (batch)",
12859
13070
  api: "openai-completions",
12860
13071
  provider: "openrouter",
12861
13072
  baseUrl: "https://openrouter.ai/api/v1",
12862
13073
  reasoning: true,
12863
- input: ["text"],
13074
+ input: ["text", "image"],
12864
13075
  cost: {
12865
- input: 0.15,
12866
- output: 0.6,
12867
- cacheRead: 0.075,
12868
- cacheWrite: 0,
13076
+ input: 0.049999999999999996,
13077
+ output: 0.25,
13078
+ cacheRead: 0.005,
13079
+ cacheWrite: 0.0625,
12869
13080
  },
12870
- contextWindow: 131072,
12871
- maxTokens: 65536,
13081
+ contextWindow: 1050000,
13082
+ maxTokens: 128000,
12872
13083
  },
12873
- "openai/gpt-oss-120b:batch": {
12874
- id: "openai/gpt-oss-120b:batch",
12875
- name: "OpenAI: gpt-oss-120b (batch)",
13084
+ "openai/gpt-6-sol": {
13085
+ id: "openai/gpt-6-sol",
13086
+ name: "OpenAI: GPT-6 Sol",
12876
13087
  api: "openai-completions",
12877
13088
  provider: "openrouter",
12878
13089
  baseUrl: "https://openrouter.ai/api/v1",
12879
13090
  reasoning: true,
12880
- input: ["text"],
13091
+ input: ["text", "image"],
12881
13092
  cost: {
12882
- input: 0.15,
12883
- output: 0.6,
12884
- cacheRead: 0,
12885
- cacheWrite: 0,
13093
+ input: 2,
13094
+ output: 10,
13095
+ cacheRead: 0.19999999999999998,
13096
+ cacheWrite: 2.5,
12886
13097
  },
12887
- contextWindow: 131072,
12888
- maxTokens: 117964,
13098
+ contextWindow: 1050000,
13099
+ maxTokens: 128000,
12889
13100
  },
12890
- "openai/gpt-oss-20b": {
12891
- id: "openai/gpt-oss-20b",
13101
+ "openai/gpt-6-sol-pro": {
13102
+ id: "openai/gpt-6-sol-pro",
13103
+ name: "OpenAI: GPT-6 Sol Pro",
13104
+ api: "openai-completions",
13105
+ provider: "openrouter",
13106
+ baseUrl: "https://openrouter.ai/api/v1",
13107
+ reasoning: true,
13108
+ input: ["text", "image"],
13109
+ cost: {
13110
+ input: 2,
13111
+ output: 10,
13112
+ cacheRead: 0.19999999999999998,
13113
+ cacheWrite: 2.5,
13114
+ },
13115
+ contextWindow: 1050000,
13116
+ maxTokens: 128000,
13117
+ },
13118
+ "openai/gpt-6-sol-pro:batch": {
13119
+ id: "openai/gpt-6-sol-pro:batch",
13120
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
13121
+ api: "openai-completions",
13122
+ provider: "openrouter",
13123
+ baseUrl: "https://openrouter.ai/api/v1",
13124
+ reasoning: true,
13125
+ input: ["text", "image"],
13126
+ cost: {
13127
+ input: 1,
13128
+ output: 5,
13129
+ cacheRead: 0.09999999999999999,
13130
+ cacheWrite: 1.25,
13131
+ },
13132
+ contextWindow: 1050000,
13133
+ maxTokens: 128000,
13134
+ },
13135
+ "openai/gpt-6-sol:batch": {
13136
+ id: "openai/gpt-6-sol:batch",
13137
+ name: "OpenAI: GPT-6 Sol (batch)",
13138
+ api: "openai-completions",
13139
+ provider: "openrouter",
13140
+ baseUrl: "https://openrouter.ai/api/v1",
13141
+ reasoning: true,
13142
+ input: ["text", "image"],
13143
+ cost: {
13144
+ input: 1,
13145
+ output: 5,
13146
+ cacheRead: 0.09999999999999999,
13147
+ cacheWrite: 1.25,
13148
+ },
13149
+ contextWindow: 1050000,
13150
+ maxTokens: 128000,
13151
+ },
13152
+ "openai/gpt-audio": {
13153
+ id: "openai/gpt-audio",
13154
+ name: "OpenAI: GPT Audio",
13155
+ api: "openai-completions",
13156
+ provider: "openrouter",
13157
+ baseUrl: "https://openrouter.ai/api/v1",
13158
+ reasoning: false,
13159
+ input: ["text"],
13160
+ cost: {
13161
+ input: 2.5,
13162
+ output: 10,
13163
+ cacheRead: 0,
13164
+ cacheWrite: 0,
13165
+ },
13166
+ contextWindow: 128000,
13167
+ maxTokens: 16384,
13168
+ },
13169
+ "openai/gpt-audio-mini": {
13170
+ id: "openai/gpt-audio-mini",
13171
+ name: "OpenAI: GPT Audio Mini",
13172
+ api: "openai-completions",
13173
+ provider: "openrouter",
13174
+ baseUrl: "https://openrouter.ai/api/v1",
13175
+ reasoning: false,
13176
+ input: ["text"],
13177
+ cost: {
13178
+ input: 0.6,
13179
+ output: 2.4,
13180
+ cacheRead: 0,
13181
+ cacheWrite: 0,
13182
+ },
13183
+ contextWindow: 128000,
13184
+ maxTokens: 16384,
13185
+ },
13186
+ "openai/gpt-chat-latest": {
13187
+ id: "openai/gpt-chat-latest",
13188
+ name: "OpenAI: GPT Chat Latest",
13189
+ api: "openai-completions",
13190
+ provider: "openrouter",
13191
+ baseUrl: "https://openrouter.ai/api/v1",
13192
+ reasoning: false,
13193
+ input: ["text", "image"],
13194
+ cost: {
13195
+ input: 5,
13196
+ output: 30,
13197
+ cacheRead: 0.5,
13198
+ cacheWrite: 0,
13199
+ },
13200
+ contextWindow: 400000,
13201
+ maxTokens: 128000,
13202
+ },
13203
+ "openai/gpt-oss-120b": {
13204
+ id: "openai/gpt-oss-120b",
13205
+ name: "OpenAI: gpt-oss-120b",
13206
+ api: "openai-completions",
13207
+ provider: "openrouter",
13208
+ baseUrl: "https://openrouter.ai/api/v1",
13209
+ reasoning: true,
13210
+ input: ["text"],
13211
+ cost: {
13212
+ input: 0.15,
13213
+ output: 0.6,
13214
+ cacheRead: 0.075,
13215
+ cacheWrite: 0,
13216
+ },
13217
+ contextWindow: 131072,
13218
+ maxTokens: 65536,
13219
+ },
13220
+ "openai/gpt-oss-20b": {
13221
+ id: "openai/gpt-oss-20b",
12892
13222
  name: "OpenAI: gpt-oss-20b",
12893
13223
  api: "openai-completions",
12894
13224
  provider: "openrouter",
@@ -12896,9 +13226,26 @@ export const MODELS = {
12896
13226
  reasoning: true,
12897
13227
  input: ["text"],
12898
13228
  cost: {
12899
- input: 0.03,
12900
- output: 0.13,
12901
- cacheRead: 0.03,
13229
+ input: 0.018,
13230
+ output: 0.09,
13231
+ cacheRead: 0,
13232
+ cacheWrite: 0,
13233
+ },
13234
+ contextWindow: 131072,
13235
+ maxTokens: 32768,
13236
+ },
13237
+ "openai/gpt-oss-20b:batch": {
13238
+ id: "openai/gpt-oss-20b:batch",
13239
+ name: "OpenAI: gpt-oss-20b (batch)",
13240
+ api: "openai-completions",
13241
+ provider: "openrouter",
13242
+ baseUrl: "https://openrouter.ai/api/v1",
13243
+ reasoning: true,
13244
+ input: ["text"],
13245
+ cost: {
13246
+ input: 0.024,
13247
+ output: 0.112,
13248
+ cacheRead: 0,
12902
13249
  cacheWrite: 0,
12903
13250
  },
12904
13251
  contextWindow: 131072,
@@ -13599,7 +13946,7 @@ export const MODELS = {
13599
13946
  cacheWrite: 0,
13600
13947
  },
13601
13948
  contextWindow: 262144,
13602
- maxTokens: 32768,
13949
+ maxTokens: 235929,
13603
13950
  },
13604
13951
  "qwen/qwen3-vl-235b-a22b-instruct": {
13605
13952
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13644,8 +13991,8 @@ export const MODELS = {
13644
13991
  reasoning: false,
13645
13992
  input: ["text", "image"],
13646
13993
  cost: {
13647
- input: 0.19999999999999998,
13648
- output: 0.7,
13994
+ input: 0.13,
13995
+ output: 0.52,
13649
13996
  cacheRead: 0,
13650
13997
  cacheWrite: 0,
13651
13998
  },
@@ -13763,13 +14110,13 @@ export const MODELS = {
13763
14110
  reasoning: true,
13764
14111
  input: ["text", "image"],
13765
14112
  cost: {
13766
- input: 0.1625,
13767
- output: 1.3,
13768
- cacheRead: 0,
14113
+ input: 0.3125,
14114
+ output: 1.25,
14115
+ cacheRead: 0.15625,
13769
14116
  cacheWrite: 0,
13770
14117
  },
13771
14118
  contextWindow: 262144,
13772
- maxTokens: 65536,
14119
+ maxTokens: 16384,
13773
14120
  },
13774
14121
  "qwen/qwen3.5-397b-a17b": {
13775
14122
  id: "qwen/qwen3.5-397b-a17b",
@@ -13803,24 +14150,7 @@ export const MODELS = {
13803
14150
  cacheWrite: 0,
13804
14151
  },
13805
14152
  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,
14153
+ maxTokens: 32768,
13824
14154
  },
13825
14155
  "qwen/qwen3.5-flash-02-23": {
13826
14156
  id: "qwen/qwen3.5-flash-02-23",
@@ -13882,13 +14212,13 @@ export const MODELS = {
13882
14212
  reasoning: true,
13883
14213
  input: ["text", "image"],
13884
14214
  cost: {
13885
- input: 0.3,
13886
- output: 2,
13887
- cacheRead: 0.03,
14215
+ input: 0.32,
14216
+ output: 2.7,
14217
+ cacheRead: 0.15,
13888
14218
  cacheWrite: 0,
13889
14219
  },
13890
14220
  contextWindow: 262144,
13891
- maxTokens: 65536,
14221
+ maxTokens: 262140,
13892
14222
  },
13893
14223
  "qwen/qwen3.6-35b-a3b": {
13894
14224
  id: "qwen/qwen3.6-35b-a3b",
@@ -13899,8 +14229,8 @@ export const MODELS = {
13899
14229
  reasoning: true,
13900
14230
  input: ["text", "image"],
13901
14231
  cost: {
13902
- input: 0.09999999999999999,
13903
- output: 0.8999999999999999,
14232
+ input: 0.15,
14233
+ output: 1,
13904
14234
  cacheRead: 0.049999999999999996,
13905
14235
  cacheWrite: 0,
13906
14236
  },
@@ -14026,23 +14356,6 @@ export const MODELS = {
14026
14356
  contextWindow: 1048576,
14027
14357
  maxTokens: 131072,
14028
14358
  },
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
14359
  "qwen/qwen3.8-27b": {
14047
14360
  id: "qwen/qwen3.8-27b",
14048
14361
  name: "Qwen: Qwen3.8 27B",
@@ -14052,9 +14365,9 @@ export const MODELS = {
14052
14365
  reasoning: true,
14053
14366
  input: ["text", "image"],
14054
14367
  cost: {
14055
- input: 0.21400000000000002,
14056
- output: 2.5500000000000003,
14057
- cacheRead: 0.15,
14368
+ input: 0.42,
14369
+ output: 3,
14370
+ cacheRead: 0.08499999999999999,
14058
14371
  cacheWrite: 0,
14059
14372
  },
14060
14373
  contextWindow: 1000000,
@@ -14111,6 +14424,23 @@ export const MODELS = {
14111
14424
  contextWindow: 1000000,
14112
14425
  maxTokens: 131072,
14113
14426
  },
14427
+ "qwen/qwen3.8-omni-flash": {
14428
+ id: "qwen/qwen3.8-omni-flash",
14429
+ name: "Qwen: Qwen3.8 Omni Flash",
14430
+ api: "openai-completions",
14431
+ provider: "openrouter",
14432
+ baseUrl: "https://openrouter.ai/api/v1",
14433
+ reasoning: true,
14434
+ input: ["text", "image"],
14435
+ cost: {
14436
+ input: 0.15,
14437
+ output: 0.47,
14438
+ cacheRead: 0.016,
14439
+ cacheWrite: 0,
14440
+ },
14441
+ contextWindow: 1000000,
14442
+ maxTokens: 131072,
14443
+ },
14114
14444
  "rekaai/reka-edge": {
14115
14445
  id: "rekaai/reka-edge",
14116
14446
  name: "Reka Edge",
@@ -14366,23 +14696,6 @@ export const MODELS = {
14366
14696
  contextWindow: 1048576,
14367
14697
  maxTokens: 262144,
14368
14698
  },
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
14699
  "thinkingmachines/inkling:free": {
14387
14700
  id: "thinkingmachines/inkling:free",
14388
14701
  name: "Thinking Machines: Inkling (free)",
@@ -14536,6 +14849,23 @@ export const MODELS = {
14536
14849
  contextWindow: 500000,
14537
14850
  maxTokens: 450000,
14538
14851
  },
14852
+ "x-ai/grok-4.7": {
14853
+ id: "x-ai/grok-4.7",
14854
+ name: "SpaceXAI: Grok 4.7",
14855
+ api: "openai-completions",
14856
+ provider: "openrouter",
14857
+ baseUrl: "https://openrouter.ai/api/v1",
14858
+ reasoning: true,
14859
+ input: ["text", "image"],
14860
+ cost: {
14861
+ input: 1.5999999999999999,
14862
+ output: 4.8,
14863
+ cacheRead: 0.39999999999999997,
14864
+ cacheWrite: 0,
14865
+ },
14866
+ contextWindow: 500000,
14867
+ maxTokens: 450000,
14868
+ },
14539
14869
  "x-ai/grok-build-0.1": {
14540
14870
  id: "x-ai/grok-build-0.1",
14541
14871
  name: "SpaceXAI: Grok Build 0.1",
@@ -14587,55 +14917,106 @@ export const MODELS = {
14587
14917
  contextWindow: 1050000,
14588
14918
  maxTokens: 131072,
14589
14919
  },
14590
- "z-ai/glm-4.5": {
14591
- id: "z-ai/glm-4.5",
14592
- name: "Z.ai: GLM 4.5",
14920
+ "xiaomi/mimo-v2.6-flash": {
14921
+ id: "xiaomi/mimo-v2.6-flash",
14922
+ name: "Xiaomi: MiMo-V2.6-Flash",
14593
14923
  api: "openai-completions",
14594
14924
  provider: "openrouter",
14595
14925
  baseUrl: "https://openrouter.ai/api/v1",
14596
14926
  reasoning: true,
14597
- input: ["text"],
14927
+ input: ["text", "image"],
14598
14928
  cost: {
14599
- input: 0.6,
14600
- output: 2.2,
14601
- cacheRead: 0.11,
14929
+ input: 0.14,
14930
+ output: 0.28,
14931
+ cacheRead: 0.0028,
14602
14932
  cacheWrite: 0,
14603
14933
  },
14604
- contextWindow: 131072,
14605
- maxTokens: 98304,
14934
+ contextWindow: 1048576,
14935
+ maxTokens: 131072,
14606
14936
  },
14607
- "z-ai/glm-4.5-air": {
14608
- id: "z-ai/glm-4.5-air",
14609
- name: "Z.ai: GLM 4.5 Air",
14937
+ "xiaomi/mimo-v2.6-pro": {
14938
+ id: "xiaomi/mimo-v2.6-pro",
14939
+ name: "Xiaomi: MiMo-V2.6-Pro",
14610
14940
  api: "openai-completions",
14611
14941
  provider: "openrouter",
14612
14942
  baseUrl: "https://openrouter.ai/api/v1",
14613
14943
  reasoning: true,
14614
- input: ["text"],
14944
+ input: ["text", "image"],
14615
14945
  cost: {
14616
- input: 0.13,
14617
- output: 0.85,
14618
- cacheRead: 0.024999999999999998,
14946
+ input: 0.435,
14947
+ output: 0.87,
14948
+ cacheRead: 0.0036,
14619
14949
  cacheWrite: 0,
14620
14950
  },
14621
- contextWindow: 131072,
14622
- maxTokens: 98304,
14951
+ contextWindow: 1048576,
14952
+ maxTokens: 131072,
14623
14953
  },
14624
- "z-ai/glm-4.5v": {
14625
- id: "z-ai/glm-4.5v",
14626
- name: "Z.ai: GLM 4.5V",
14954
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
14955
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
14956
+ name: "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
14627
14957
  api: "openai-completions",
14628
14958
  provider: "openrouter",
14629
14959
  baseUrl: "https://openrouter.ai/api/v1",
14630
14960
  reasoning: true,
14631
14961
  input: ["text", "image"],
14632
14962
  cost: {
14633
- input: 0.6,
14634
- output: 1.7999999999999998,
14635
- cacheRead: 0.11,
14963
+ input: 4.35,
14964
+ output: 8.7,
14965
+ cacheRead: 0.036,
14636
14966
  cacheWrite: 0,
14637
14967
  },
14638
- contextWindow: 65536,
14968
+ contextWindow: 1048576,
14969
+ maxTokens: 131072,
14970
+ },
14971
+ "z-ai/glm-4.5": {
14972
+ id: "z-ai/glm-4.5",
14973
+ name: "Z.ai: GLM 4.5",
14974
+ api: "openai-completions",
14975
+ provider: "openrouter",
14976
+ baseUrl: "https://openrouter.ai/api/v1",
14977
+ reasoning: true,
14978
+ input: ["text"],
14979
+ cost: {
14980
+ input: 0.6,
14981
+ output: 2.2,
14982
+ cacheRead: 0.11,
14983
+ cacheWrite: 0,
14984
+ },
14985
+ contextWindow: 131072,
14986
+ maxTokens: 98304,
14987
+ },
14988
+ "z-ai/glm-4.5-air": {
14989
+ id: "z-ai/glm-4.5-air",
14990
+ name: "Z.ai: GLM 4.5 Air",
14991
+ api: "openai-completions",
14992
+ provider: "openrouter",
14993
+ baseUrl: "https://openrouter.ai/api/v1",
14994
+ reasoning: true,
14995
+ input: ["text"],
14996
+ cost: {
14997
+ input: 0.13,
14998
+ output: 0.85,
14999
+ cacheRead: 0.024999999999999998,
15000
+ cacheWrite: 0,
15001
+ },
15002
+ contextWindow: 131072,
15003
+ maxTokens: 98304,
15004
+ },
15005
+ "z-ai/glm-4.5v": {
15006
+ id: "z-ai/glm-4.5v",
15007
+ name: "Z.ai: GLM 4.5V",
15008
+ api: "openai-completions",
15009
+ provider: "openrouter",
15010
+ baseUrl: "https://openrouter.ai/api/v1",
15011
+ reasoning: true,
15012
+ input: ["text", "image"],
15013
+ cost: {
15014
+ input: 0.6,
15015
+ output: 1.7999999999999998,
15016
+ cacheRead: 0.11,
15017
+ cacheWrite: 0,
15018
+ },
15019
+ contextWindow: 65536,
14639
15020
  maxTokens: 16384,
14640
15021
  },
14641
15022
  "z-ai/glm-4.6": {
@@ -14766,31 +15147,14 @@ export const MODELS = {
14766
15147
  reasoning: true,
14767
15148
  input: ["text"],
14768
15149
  cost: {
14769
- input: 0.5544,
14770
- output: 1.7424,
14771
- cacheRead: 0.10296000000000001,
15150
+ input: 0.6496,
15151
+ output: 2.0416,
15152
+ cacheRead: 0.12064,
14772
15153
  cacheWrite: 0,
14773
15154
  },
14774
15155
  contextWindow: 1048576,
14775
15156
  maxTokens: 131072,
14776
15157
  },
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
15158
  "z-ai/glm-5.3": {
14795
15159
  id: "z-ai/glm-5.3",
14796
15160
  name: "Z.ai: GLM 5.3",
@@ -14800,9 +15164,9 @@ export const MODELS = {
14800
15164
  reasoning: true,
14801
15165
  input: ["text"],
14802
15166
  cost: {
14803
- input: 0.9099999999999999,
14804
- output: 2.8600000000000003,
14805
- cacheRead: 0.16899999999999998,
15167
+ input: 0.84,
15168
+ output: 2.64,
15169
+ cacheRead: 0.156,
14806
15170
  cacheWrite: 0,
14807
15171
  },
14808
15172
  contextWindow: 1310720,
@@ -14817,13 +15181,13 @@ export const MODELS = {
14817
15181
  reasoning: true,
14818
15182
  input: ["text", "image"],
14819
15183
  cost: {
14820
- input: 0.09,
14821
- output: 0.3,
14822
- cacheRead: 0.018,
15184
+ input: 0.15,
15185
+ output: 0.5,
15186
+ cacheRead: 0.049999999999999996,
14823
15187
  cacheWrite: 0,
14824
15188
  },
14825
15189
  contextWindow: 1310720,
14826
- maxTokens: 131072,
15190
+ maxTokens: 943718,
14827
15191
  },
14828
15192
  "z-ai/glm-5.3-flash:batch": {
14829
15193
  id: "z-ai/glm-5.3-flash:batch",
@@ -14834,13 +15198,13 @@ export const MODELS = {
14834
15198
  reasoning: true,
14835
15199
  input: ["text", "image"],
14836
15200
  cost: {
14837
- input: 0.075,
14838
- output: 0.25,
14839
- cacheRead: 0.015,
15201
+ input: 0.06,
15202
+ output: 0.19999999999999998,
15203
+ cacheRead: 0.012,
14840
15204
  cacheWrite: 0,
14841
15205
  },
14842
15206
  contextWindow: 1048576,
14843
- maxTokens: 943718,
15207
+ maxTokens: 131072,
14844
15208
  },
14845
15209
  "z-ai/glm-5.3-flashx": {
14846
15210
  id: "z-ai/glm-5.3-flashx",
@@ -14868,13 +15232,13 @@ export const MODELS = {
14868
15232
  reasoning: true,
14869
15233
  input: ["text"],
14870
15234
  cost: {
14871
- input: 0.7,
14872
- output: 2.2,
14873
- cacheRead: 0.13,
15235
+ input: 0.72,
15236
+ output: 2.4,
15237
+ cacheRead: 0.12,
14874
15238
  cacheWrite: 0,
14875
15239
  },
14876
15240
  contextWindow: 1048576,
14877
- maxTokens: 943718,
15241
+ maxTokens: 131072,
14878
15242
  },
14879
15243
  "z-ai/glm-5v-turbo": {
14880
15244
  id: "z-ai/glm-5v-turbo",
@@ -14938,10 +15302,10 @@ export const MODELS = {
14938
15302
  thinkingLevelMap: { "xhigh": "xhigh" },
14939
15303
  input: ["text", "image"],
14940
15304
  cost: {
14941
- input: 5,
14942
- output: 25,
14943
- cacheRead: 0.5,
14944
- cacheWrite: 6.25,
15305
+ input: 4,
15306
+ output: 20,
15307
+ cacheRead: 0.19999999999999998,
15308
+ cacheWrite: 5,
14945
15309
  },
14946
15310
  contextWindow: 1000000,
14947
15311
  maxTokens: 128000,
@@ -14973,9 +15337,9 @@ export const MODELS = {
14973
15337
  reasoning: true,
14974
15338
  input: ["text", "image"],
14975
15339
  cost: {
14976
- input: 0.13,
14977
- output: 0.52,
14978
- cacheRead: 0.0026000000000000003,
15340
+ input: 0.09999999999999999,
15341
+ output: 0.5,
15342
+ cacheRead: 0.01,
14979
15343
  cacheWrite: 0,
14980
15344
  },
14981
15345
  contextWindow: 1048576,
@@ -14990,13 +15354,13 @@ export const MODELS = {
14990
15354
  reasoning: true,
14991
15355
  input: ["text"],
14992
15356
  cost: {
14993
- input: 0.57816,
14994
- output: 1.73448,
14995
- cacheRead: 0.018396000000000003,
15357
+ input: 0.39999999999999997,
15358
+ output: 4.300000000000001,
15359
+ cacheRead: 0.032999999999999995,
14996
15360
  cacheWrite: 0,
14997
15361
  },
14998
15362
  contextWindow: 1048576,
14999
- maxTokens: 393216,
15363
+ maxTokens: 384000,
15000
15364
  },
15001
15365
  "~deepseek/deepseek-v4-flash-latest": {
15002
15366
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -15009,9 +15373,9 @@ export const MODELS = {
15009
15373
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15010
15374
  input: ["text"],
15011
15375
  cost: {
15012
- input: 0.04,
15013
- output: 0.08,
15014
- cacheRead: 0.016,
15376
+ input: 0.03,
15377
+ output: 0.7999999999999999,
15378
+ cacheRead: 0.008,
15015
15379
  cacheWrite: 0,
15016
15380
  },
15017
15381
  contextWindow: 1310720,
@@ -15060,9 +15424,9 @@ export const MODELS = {
15060
15424
  reasoning: true,
15061
15425
  input: ["text", "image"],
15062
15426
  cost: {
15063
- input: 1.7,
15064
- output: 8.5,
15065
- cacheRead: 0.16999999999999998,
15427
+ input: 1.4989,
15428
+ output: 10.758,
15429
+ cacheRead: 0.3,
15066
15430
  cacheWrite: 0,
15067
15431
  },
15068
15432
  contextWindow: 1048576,
@@ -15094,10 +15458,10 @@ export const MODELS = {
15094
15458
  reasoning: true,
15095
15459
  input: ["text", "image"],
15096
15460
  cost: {
15097
- input: 0.19999999999999998,
15098
- output: 1.2,
15099
- cacheRead: 0.02,
15100
- cacheWrite: 0.25,
15461
+ input: 0.09999999999999999,
15462
+ output: 0.5,
15463
+ cacheRead: 0.01,
15464
+ cacheWrite: 0.125,
15101
15465
  },
15102
15466
  contextWindow: 1050000,
15103
15467
  maxTokens: 128000,
@@ -15162,9 +15526,9 @@ export const MODELS = {
15162
15526
  reasoning: true,
15163
15527
  input: ["text", "image"],
15164
15528
  cost: {
15165
- input: 2,
15166
- output: 6,
15167
- cacheRead: 0.5,
15529
+ input: 1.5999999999999999,
15530
+ output: 4.8,
15531
+ cacheRead: 0.39999999999999997,
15168
15532
  cacheWrite: 0,
15169
15533
  },
15170
15534
  contextWindow: 500000,
@@ -15196,9 +15560,9 @@ export const MODELS = {
15196
15560
  reasoning: true,
15197
15561
  input: ["text"],
15198
15562
  cost: {
15199
- input: 0.8917999999999999,
15200
- output: 2.8028,
15201
- cacheRead: 0.16562,
15563
+ input: 0.5625,
15564
+ output: 2.5,
15565
+ cacheRead: 0.125,
15202
15566
  cacheWrite: 0,
15203
15567
  },
15204
15568
  contextWindow: 1310720,
@@ -16303,7 +16667,7 @@ export const MODELS = {
16303
16667
  cacheWrite: 18.75,
16304
16668
  },
16305
16669
  contextWindow: 200000,
16306
- maxTokens: 8192,
16670
+ maxTokens: 32000,
16307
16671
  },
16308
16672
  "anthropic/claude-opus-4.5": {
16309
16673
  id: "anthropic/claude-opus-4.5",
@@ -16430,6 +16794,42 @@ export const MODELS = {
16430
16794
  contextWindow: 1000000,
16431
16795
  maxTokens: 128000,
16432
16796
  },
16797
+ "anthropic/claude-opus-5.5": {
16798
+ id: "anthropic/claude-opus-5.5",
16799
+ name: "Claude Opus 5.5",
16800
+ api: "anthropic-messages",
16801
+ provider: "vercel-ai-gateway",
16802
+ baseUrl: "https://ai-gateway.vercel.sh",
16803
+ reasoning: true,
16804
+ thinkingLevelMap: { "xhigh": "xhigh" },
16805
+ input: ["text", "image"],
16806
+ cost: {
16807
+ input: 4,
16808
+ output: 20,
16809
+ cacheRead: 0.19999999999999998,
16810
+ cacheWrite: 5,
16811
+ },
16812
+ contextWindow: 1000000,
16813
+ maxTokens: 128000,
16814
+ },
16815
+ "anthropic/claude-opus-5.5-fast": {
16816
+ id: "anthropic/claude-opus-5.5-fast",
16817
+ name: "Claude Opus 5.5 (Fast)",
16818
+ api: "anthropic-messages",
16819
+ provider: "vercel-ai-gateway",
16820
+ baseUrl: "https://ai-gateway.vercel.sh",
16821
+ reasoning: true,
16822
+ thinkingLevelMap: { "xhigh": "xhigh" },
16823
+ input: ["text", "image"],
16824
+ cost: {
16825
+ input: 8,
16826
+ output: 40,
16827
+ cacheRead: 0.39999999999999997,
16828
+ cacheWrite: 10,
16829
+ },
16830
+ contextWindow: 1000000,
16831
+ maxTokens: 128000,
16832
+ },
16433
16833
  "anthropic/claude-sonnet-4": {
16434
16834
  id: "anthropic/claude-sonnet-4",
16435
16835
  name: "Claude Sonnet 4",
@@ -16445,7 +16845,7 @@ export const MODELS = {
16445
16845
  cacheWrite: 3.75,
16446
16846
  },
16447
16847
  contextWindow: 1000000,
16448
- maxTokens: 8192,
16848
+ maxTokens: 64000,
16449
16849
  },
16450
16850
  "anthropic/claude-sonnet-4.5": {
16451
16851
  id: "anthropic/claude-sonnet-4.5",
@@ -16765,7 +17165,7 @@ export const MODELS = {
16765
17165
  cost: {
16766
17166
  input: 0.3,
16767
17167
  output: 1.2,
16768
- cacheRead: 0.03,
17168
+ cacheRead: 0.007,
16769
17169
  cacheWrite: 0,
16770
17170
  },
16771
17171
  contextWindow: 1048576,
@@ -16786,7 +17186,7 @@ export const MODELS = {
16786
17186
  cacheWrite: 0,
16787
17187
  },
16788
17188
  contextWindow: 1000000,
16789
- maxTokens: 65536,
17189
+ maxTokens: 65535,
16790
17190
  },
16791
17191
  "google/gemini-2.5-flash-lite": {
16792
17192
  id: "google/gemini-2.5-flash-lite",
@@ -16803,7 +17203,7 @@ export const MODELS = {
16803
17203
  cacheWrite: 0,
16804
17204
  },
16805
17205
  contextWindow: 1048576,
16806
- maxTokens: 65536,
17206
+ maxTokens: 65535,
16807
17207
  },
16808
17208
  "google/gemini-2.5-pro": {
16809
17209
  id: "google/gemini-2.5-pro",
@@ -16820,7 +17220,7 @@ export const MODELS = {
16820
17220
  cacheWrite: 0,
16821
17221
  },
16822
17222
  contextWindow: 1048576,
16823
- maxTokens: 65536,
17223
+ maxTokens: 65535,
16824
17224
  },
16825
17225
  "google/gemini-3-flash": {
16826
17226
  id: "google/gemini-3-flash",
@@ -16939,7 +17339,7 @@ export const MODELS = {
16939
17339
  cacheWrite: 0,
16940
17340
  },
16941
17341
  contextWindow: 1000000,
16942
- maxTokens: 65536,
17342
+ maxTokens: 65535,
16943
17343
  },
16944
17344
  "google/gemini-3.8-flash": {
16945
17345
  id: "google/gemini-3.8-flash",
@@ -16956,7 +17356,7 @@ export const MODELS = {
16956
17356
  cacheWrite: 0,
16957
17357
  },
16958
17358
  contextWindow: 1000000,
16959
- maxTokens: 65536,
17359
+ maxTokens: 65535,
16960
17360
  },
16961
17361
  "google/gemma-4-26b-a4b-it": {
16962
17362
  id: "google/gemma-4-26b-a4b-it",
@@ -17638,6 +18038,23 @@ export const MODELS = {
17638
18038
  contextWindow: 262144,
17639
18039
  maxTokens: 4000,
17640
18040
  },
18041
+ "mixedbread/toast-1": {
18042
+ id: "mixedbread/toast-1",
18043
+ name: "Toast 1",
18044
+ api: "anthropic-messages",
18045
+ provider: "vercel-ai-gateway",
18046
+ baseUrl: "https://ai-gateway.vercel.sh",
18047
+ reasoning: false,
18048
+ input: ["text"],
18049
+ cost: {
18050
+ input: 0.3,
18051
+ output: 0.72,
18052
+ cacheRead: 0.036,
18053
+ cacheWrite: 0,
18054
+ },
18055
+ contextWindow: 131000,
18056
+ maxTokens: 4000,
18057
+ },
17641
18058
  "moonshotai/kimi-k2": {
17642
18059
  id: "moonshotai/kimi-k2",
17643
18060
  name: "Kimi K2 Instruct",
@@ -18696,6 +19113,74 @@ export const MODELS = {
18696
19113
  contextWindow: 1050000,
18697
19114
  maxTokens: 128000,
18698
19115
  },
19116
+ "openai/gpt-6-luna": {
19117
+ id: "openai/gpt-6-luna",
19118
+ name: "GPT-6 Luna",
19119
+ api: "anthropic-messages",
19120
+ provider: "vercel-ai-gateway",
19121
+ baseUrl: "https://ai-gateway.vercel.sh",
19122
+ reasoning: true,
19123
+ input: ["text", "image"],
19124
+ cost: {
19125
+ input: 0.09999999999999999,
19126
+ output: 0.5,
19127
+ cacheRead: 0.01,
19128
+ cacheWrite: 0.125,
19129
+ },
19130
+ contextWindow: 1050000,
19131
+ maxTokens: 128000,
19132
+ },
19133
+ "openai/gpt-6-luna-fast": {
19134
+ id: "openai/gpt-6-luna-fast",
19135
+ name: "GPT-6 Luna (Fast)",
19136
+ api: "anthropic-messages",
19137
+ provider: "vercel-ai-gateway",
19138
+ baseUrl: "https://ai-gateway.vercel.sh",
19139
+ reasoning: true,
19140
+ input: ["text", "image"],
19141
+ cost: {
19142
+ input: 0.19999999999999998,
19143
+ output: 1,
19144
+ cacheRead: 0.02,
19145
+ cacheWrite: 0.25,
19146
+ },
19147
+ contextWindow: 1050000,
19148
+ maxTokens: 128000,
19149
+ },
19150
+ "openai/gpt-6-sol": {
19151
+ id: "openai/gpt-6-sol",
19152
+ name: "GPT-6 Sol",
19153
+ api: "anthropic-messages",
19154
+ provider: "vercel-ai-gateway",
19155
+ baseUrl: "https://ai-gateway.vercel.sh",
19156
+ reasoning: true,
19157
+ input: ["text", "image"],
19158
+ cost: {
19159
+ input: 2,
19160
+ output: 10,
19161
+ cacheRead: 0.19999999999999998,
19162
+ cacheWrite: 2.5,
19163
+ },
19164
+ contextWindow: 1050000,
19165
+ maxTokens: 128000,
19166
+ },
19167
+ "openai/gpt-6-sol-fast": {
19168
+ id: "openai/gpt-6-sol-fast",
19169
+ name: "GPT-6 Sol (Fast)",
19170
+ api: "anthropic-messages",
19171
+ provider: "vercel-ai-gateway",
19172
+ baseUrl: "https://ai-gateway.vercel.sh",
19173
+ reasoning: true,
19174
+ input: ["text", "image"],
19175
+ cost: {
19176
+ input: 4,
19177
+ output: 20,
19178
+ cacheRead: 0.39999999999999997,
19179
+ cacheWrite: 5,
19180
+ },
19181
+ contextWindow: 1050000,
19182
+ maxTokens: 128000,
19183
+ },
18699
19184
  "openai/gpt-oss-120b": {
18700
19185
  id: "openai/gpt-oss-120b",
18701
19186
  name: "GPT OSS 120B",
@@ -18917,6 +19402,40 @@ export const MODELS = {
18917
19402
  contextWindow: 256000,
18918
19403
  maxTokens: 32768,
18919
19404
  },
19405
+ "quiverai/arrow-2": {
19406
+ id: "quiverai/arrow-2",
19407
+ name: "Arrow 2",
19408
+ api: "anthropic-messages",
19409
+ provider: "vercel-ai-gateway",
19410
+ baseUrl: "https://ai-gateway.vercel.sh",
19411
+ reasoning: true,
19412
+ input: ["text", "image"],
19413
+ cost: {
19414
+ input: 4,
19415
+ output: 20,
19416
+ cacheRead: 0.39999999999999997,
19417
+ cacheWrite: 5,
19418
+ },
19419
+ contextWindow: 131072,
19420
+ maxTokens: 131072,
19421
+ },
19422
+ "quiverai/arrow-2-telos": {
19423
+ id: "quiverai/arrow-2-telos",
19424
+ name: "Arrow 2 Telos",
19425
+ api: "anthropic-messages",
19426
+ provider: "vercel-ai-gateway",
19427
+ baseUrl: "https://ai-gateway.vercel.sh",
19428
+ reasoning: true,
19429
+ input: ["text", "image"],
19430
+ cost: {
19431
+ input: 6,
19432
+ output: 30,
19433
+ cacheRead: 0.6,
19434
+ cacheWrite: 7.5,
19435
+ },
19436
+ contextWindow: 131072,
19437
+ maxTokens: 131072,
19438
+ },
18920
19439
  "sakana/fugu-max": {
18921
19440
  id: "sakana/fugu-max",
18922
19441
  name: "Fugu Max",
@@ -19172,6 +19691,23 @@ export const MODELS = {
19172
19691
  contextWindow: 500000,
19173
19692
  maxTokens: 500000,
19174
19693
  },
19694
+ "spacexai/grok-4.7": {
19695
+ id: "spacexai/grok-4.7",
19696
+ name: "Grok 4.7",
19697
+ api: "anthropic-messages",
19698
+ provider: "vercel-ai-gateway",
19699
+ baseUrl: "https://ai-gateway.vercel.sh",
19700
+ reasoning: true,
19701
+ input: ["text", "image"],
19702
+ cost: {
19703
+ input: 1.2,
19704
+ output: 3.5999999999999996,
19705
+ cacheRead: 0.3,
19706
+ cacheWrite: 0,
19707
+ },
19708
+ contextWindow: 500000,
19709
+ maxTokens: 500000,
19710
+ },
19175
19711
  "spacexai/grok-build-0.1": {
19176
19712
  id: "spacexai/grok-build-0.1",
19177
19713
  name: "Grok Build 0.1",
@@ -19325,6 +19861,57 @@ export const MODELS = {
19325
19861
  contextWindow: 1050000,
19326
19862
  maxTokens: 131000,
19327
19863
  },
19864
+ "xiaomi/mimo-v2.6-flash": {
19865
+ id: "xiaomi/mimo-v2.6-flash",
19866
+ name: "MiMo V2.6 Flash",
19867
+ api: "anthropic-messages",
19868
+ provider: "vercel-ai-gateway",
19869
+ baseUrl: "https://ai-gateway.vercel.sh",
19870
+ reasoning: true,
19871
+ input: ["text", "image"],
19872
+ cost: {
19873
+ input: 0.14,
19874
+ output: 0.28,
19875
+ cacheRead: 0.0028,
19876
+ cacheWrite: 0,
19877
+ },
19878
+ contextWindow: 1048576,
19879
+ maxTokens: 131072,
19880
+ },
19881
+ "xiaomi/mimo-v2.6-pro": {
19882
+ id: "xiaomi/mimo-v2.6-pro",
19883
+ name: "MiMo V2.6 Pro",
19884
+ api: "anthropic-messages",
19885
+ provider: "vercel-ai-gateway",
19886
+ baseUrl: "https://ai-gateway.vercel.sh",
19887
+ reasoning: true,
19888
+ input: ["text", "image"],
19889
+ cost: {
19890
+ input: 0.435,
19891
+ output: 0.87,
19892
+ cacheRead: 0.0036,
19893
+ cacheWrite: 0,
19894
+ },
19895
+ contextWindow: 1048576,
19896
+ maxTokens: 131072,
19897
+ },
19898
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
19899
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
19900
+ name: "MiMo V2.6 Pro UltraSpeed",
19901
+ api: "anthropic-messages",
19902
+ provider: "vercel-ai-gateway",
19903
+ baseUrl: "https://ai-gateway.vercel.sh",
19904
+ reasoning: true,
19905
+ input: ["text", "image"],
19906
+ cost: {
19907
+ input: 4.35,
19908
+ output: 8.7,
19909
+ cacheRead: 0.036,
19910
+ cacheWrite: 0,
19911
+ },
19912
+ contextWindow: 1048576,
19913
+ maxTokens: 131072,
19914
+ },
19328
19915
  "zai/glm-4.5": {
19329
19916
  id: "zai/glm-4.5",
19330
19917
  name: "GLM 4.5",
@@ -19701,6 +20288,23 @@ export const MODELS = {
19701
20288
  contextWindow: 500000,
19702
20289
  maxTokens: 500000,
19703
20290
  },
20291
+ "grok-4.7": {
20292
+ id: "grok-4.7",
20293
+ name: "Grok 4.7",
20294
+ api: "openai-completions",
20295
+ provider: "xai",
20296
+ baseUrl: "https://api.x.ai/v1",
20297
+ reasoning: true,
20298
+ input: ["text", "image"],
20299
+ cost: {
20300
+ input: 2,
20301
+ output: 6,
20302
+ cacheRead: 0.5,
20303
+ cacheWrite: 0,
20304
+ },
20305
+ contextWindow: 500000,
20306
+ maxTokens: 500000,
20307
+ },
19704
20308
  "grok-build-0.1": {
19705
20309
  id: "grok-build-0.1",
19706
20310
  name: "Grok Build 0.1",
@@ -19839,6 +20443,57 @@ export const MODELS = {
19839
20443
  contextWindow: 1048576,
19840
20444
  maxTokens: 131072,
19841
20445
  },
20446
+ "mimo-v2.6-flash": {
20447
+ id: "mimo-v2.6-flash",
20448
+ name: "MiMo-V2.6-Flash",
20449
+ api: "anthropic-messages",
20450
+ provider: "xiaomi",
20451
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20452
+ reasoning: true,
20453
+ input: ["text", "image"],
20454
+ cost: {
20455
+ input: 0.14,
20456
+ output: 0.28,
20457
+ cacheRead: 0.0028,
20458
+ cacheWrite: 0,
20459
+ },
20460
+ contextWindow: 1048576,
20461
+ maxTokens: 131072,
20462
+ },
20463
+ "mimo-v2.6-pro": {
20464
+ id: "mimo-v2.6-pro",
20465
+ name: "MiMo-V2.6-Pro",
20466
+ api: "anthropic-messages",
20467
+ provider: "xiaomi",
20468
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20469
+ reasoning: true,
20470
+ input: ["text", "image"],
20471
+ cost: {
20472
+ input: 0.435,
20473
+ output: 0.87,
20474
+ cacheRead: 0.0036,
20475
+ cacheWrite: 0,
20476
+ },
20477
+ contextWindow: 1048576,
20478
+ maxTokens: 131072,
20479
+ },
20480
+ "mimo-v2.6-pro-ultraspeed": {
20481
+ id: "mimo-v2.6-pro-ultraspeed",
20482
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20483
+ api: "anthropic-messages",
20484
+ provider: "xiaomi",
20485
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
20486
+ reasoning: true,
20487
+ input: ["text", "image"],
20488
+ cost: {
20489
+ input: 4.35,
20490
+ output: 8.7,
20491
+ cacheRead: 0.036,
20492
+ cacheWrite: 0,
20493
+ },
20494
+ contextWindow: 1048576,
20495
+ maxTokens: 131072,
20496
+ },
19842
20497
  },
19843
20498
  "xiaomi-token-plan-ams": {
19844
20499
  "mimo-v2-flash": {
@@ -19943,6 +20598,57 @@ export const MODELS = {
19943
20598
  contextWindow: 1048576,
19944
20599
  maxTokens: 131072,
19945
20600
  },
20601
+ "mimo-v2.6-flash": {
20602
+ id: "mimo-v2.6-flash",
20603
+ name: "MiMo-V2.6-Flash",
20604
+ api: "anthropic-messages",
20605
+ provider: "xiaomi-token-plan-ams",
20606
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20607
+ reasoning: true,
20608
+ input: ["text", "image"],
20609
+ cost: {
20610
+ input: 0.14,
20611
+ output: 0.28,
20612
+ cacheRead: 0.0028,
20613
+ cacheWrite: 0,
20614
+ },
20615
+ contextWindow: 1048576,
20616
+ maxTokens: 131072,
20617
+ },
20618
+ "mimo-v2.6-pro": {
20619
+ id: "mimo-v2.6-pro",
20620
+ name: "MiMo-V2.6-Pro",
20621
+ api: "anthropic-messages",
20622
+ provider: "xiaomi-token-plan-ams",
20623
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20624
+ reasoning: true,
20625
+ input: ["text", "image"],
20626
+ cost: {
20627
+ input: 0.435,
20628
+ output: 0.87,
20629
+ cacheRead: 0.0036,
20630
+ cacheWrite: 0,
20631
+ },
20632
+ contextWindow: 1048576,
20633
+ maxTokens: 131072,
20634
+ },
20635
+ "mimo-v2.6-pro-ultraspeed": {
20636
+ id: "mimo-v2.6-pro-ultraspeed",
20637
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20638
+ api: "anthropic-messages",
20639
+ provider: "xiaomi-token-plan-ams",
20640
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
20641
+ reasoning: true,
20642
+ input: ["text", "image"],
20643
+ cost: {
20644
+ input: 4.35,
20645
+ output: 8.7,
20646
+ cacheRead: 0.036,
20647
+ cacheWrite: 0,
20648
+ },
20649
+ contextWindow: 1048576,
20650
+ maxTokens: 131072,
20651
+ },
19946
20652
  },
19947
20653
  "xiaomi-token-plan-cn": {
19948
20654
  "mimo-v2-flash": {
@@ -20047,6 +20753,57 @@ export const MODELS = {
20047
20753
  contextWindow: 1048576,
20048
20754
  maxTokens: 131072,
20049
20755
  },
20756
+ "mimo-v2.6-flash": {
20757
+ id: "mimo-v2.6-flash",
20758
+ name: "MiMo-V2.6-Flash",
20759
+ api: "anthropic-messages",
20760
+ provider: "xiaomi-token-plan-cn",
20761
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20762
+ reasoning: true,
20763
+ input: ["text", "image"],
20764
+ cost: {
20765
+ input: 0.14,
20766
+ output: 0.28,
20767
+ cacheRead: 0.0028,
20768
+ cacheWrite: 0,
20769
+ },
20770
+ contextWindow: 1048576,
20771
+ maxTokens: 131072,
20772
+ },
20773
+ "mimo-v2.6-pro": {
20774
+ id: "mimo-v2.6-pro",
20775
+ name: "MiMo-V2.6-Pro",
20776
+ api: "anthropic-messages",
20777
+ provider: "xiaomi-token-plan-cn",
20778
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20779
+ reasoning: true,
20780
+ input: ["text", "image"],
20781
+ cost: {
20782
+ input: 0.435,
20783
+ output: 0.87,
20784
+ cacheRead: 0.0036,
20785
+ cacheWrite: 0,
20786
+ },
20787
+ contextWindow: 1048576,
20788
+ maxTokens: 131072,
20789
+ },
20790
+ "mimo-v2.6-pro-ultraspeed": {
20791
+ id: "mimo-v2.6-pro-ultraspeed",
20792
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20793
+ api: "anthropic-messages",
20794
+ provider: "xiaomi-token-plan-cn",
20795
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
20796
+ reasoning: true,
20797
+ input: ["text", "image"],
20798
+ cost: {
20799
+ input: 4.35,
20800
+ output: 8.7,
20801
+ cacheRead: 0.036,
20802
+ cacheWrite: 0,
20803
+ },
20804
+ contextWindow: 1048576,
20805
+ maxTokens: 131072,
20806
+ },
20050
20807
  },
20051
20808
  "xiaomi-token-plan-sgp": {
20052
20809
  "mimo-v2-flash": {
@@ -20151,6 +20908,57 @@ export const MODELS = {
20151
20908
  contextWindow: 1048576,
20152
20909
  maxTokens: 131072,
20153
20910
  },
20911
+ "mimo-v2.6-flash": {
20912
+ id: "mimo-v2.6-flash",
20913
+ name: "MiMo-V2.6-Flash",
20914
+ api: "anthropic-messages",
20915
+ provider: "xiaomi-token-plan-sgp",
20916
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20917
+ reasoning: true,
20918
+ input: ["text", "image"],
20919
+ cost: {
20920
+ input: 0.14,
20921
+ output: 0.28,
20922
+ cacheRead: 0.0028,
20923
+ cacheWrite: 0,
20924
+ },
20925
+ contextWindow: 1048576,
20926
+ maxTokens: 131072,
20927
+ },
20928
+ "mimo-v2.6-pro": {
20929
+ id: "mimo-v2.6-pro",
20930
+ name: "MiMo-V2.6-Pro",
20931
+ api: "anthropic-messages",
20932
+ provider: "xiaomi-token-plan-sgp",
20933
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20934
+ reasoning: true,
20935
+ input: ["text", "image"],
20936
+ cost: {
20937
+ input: 0.435,
20938
+ output: 0.87,
20939
+ cacheRead: 0.0036,
20940
+ cacheWrite: 0,
20941
+ },
20942
+ contextWindow: 1048576,
20943
+ maxTokens: 131072,
20944
+ },
20945
+ "mimo-v2.6-pro-ultraspeed": {
20946
+ id: "mimo-v2.6-pro-ultraspeed",
20947
+ name: "MiMo-V2.6-Pro-UltraSpeed",
20948
+ api: "anthropic-messages",
20949
+ provider: "xiaomi-token-plan-sgp",
20950
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
20951
+ reasoning: true,
20952
+ input: ["text", "image"],
20953
+ cost: {
20954
+ input: 4.35,
20955
+ output: 8.7,
20956
+ cacheRead: 0.036,
20957
+ cacheWrite: 0,
20958
+ },
20959
+ contextWindow: 1048576,
20960
+ maxTokens: 131072,
20961
+ },
20154
20962
  },
20155
20963
  "zai": {
20156
20964
  "glm-4.7": {