omk-ai 1.2.0 → 1.2.2

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.
Files changed (45) hide show
  1. package/CHANGELOG.md +24 -0
  2. package/dist/models.d.ts.map +1 -1
  3. package/dist/models.generated.d.ts +1463 -362
  4. package/dist/models.generated.d.ts.map +1 -1
  5. package/dist/models.generated.js +1299 -411
  6. package/dist/models.generated.js.map +1 -1
  7. package/dist/models.js +4 -1
  8. package/dist/models.js.map +1 -1
  9. package/dist/provider-response-types.d.ts +15 -0
  10. package/dist/provider-response-types.d.ts.map +1 -0
  11. package/dist/provider-response-types.js +2 -0
  12. package/dist/provider-response-types.js.map +1 -0
  13. package/dist/providers/anthropic.d.ts.map +1 -1
  14. package/dist/providers/anthropic.js +2 -23
  15. package/dist/providers/anthropic.js.map +1 -1
  16. package/dist/providers/bedrock-thinking.d.ts.map +1 -1
  17. package/dist/providers/bedrock-thinking.js +2 -2
  18. package/dist/providers/bedrock-thinking.js.map +1 -1
  19. package/dist/providers/google-shared.d.ts.map +1 -1
  20. package/dist/providers/google-shared.js +13 -6
  21. package/dist/providers/google-shared.js.map +1 -1
  22. package/dist/providers/grok-thinking.d.ts.map +1 -1
  23. package/dist/providers/grok-thinking.js +10 -0
  24. package/dist/providers/grok-thinking.js.map +1 -1
  25. package/dist/providers/openai-completions.d.ts.map +1 -1
  26. package/dist/providers/openai-completions.js +15 -25
  27. package/dist/providers/openai-completions.js.map +1 -1
  28. package/dist/providers/openai-responses-shared.d.ts.map +1 -1
  29. package/dist/providers/openai-responses-shared.js +10 -23
  30. package/dist/providers/openai-responses-shared.js.map +1 -1
  31. package/dist/providers/provider-stop-reasons.d.ts +9 -0
  32. package/dist/providers/provider-stop-reasons.d.ts.map +1 -0
  33. package/dist/providers/provider-stop-reasons.js +63 -0
  34. package/dist/providers/provider-stop-reasons.js.map +1 -0
  35. package/dist/types.d.ts +4 -14
  36. package/dist/types.d.ts.map +1 -1
  37. package/dist/types.js.map +1 -1
  38. package/dist/utils/claude-code-identity.d.ts +4 -4
  39. package/dist/utils/claude-code-identity.d.ts.map +1 -1
  40. package/dist/utils/claude-code-identity.js +1 -1
  41. package/dist/utils/claude-code-identity.js.map +1 -1
  42. package/dist/utils/validation.d.ts.map +1 -1
  43. package/dist/utils/validation.js +9 -21
  44. package/dist/utils/validation.js.map +1 -1
  45. package/package.json +1 -1
@@ -229,6 +229,24 @@ export const MODELS = {
229
229
  contextWindow: 1000000,
230
230
  maxTokens: 128000,
231
231
  },
232
+ "anthropic.claude-opus-5-5": {
233
+ id: "anthropic.claude-opus-5-5",
234
+ name: "Claude Opus 5.5",
235
+ api: "bedrock-converse-stream",
236
+ provider: "amazon-bedrock",
237
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
238
+ reasoning: true,
239
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
240
+ input: ["text", "image"],
241
+ cost: {
242
+ input: 4,
243
+ output: 20,
244
+ cacheRead: 0.2,
245
+ cacheWrite: 5,
246
+ },
247
+ contextWindow: 1000000,
248
+ maxTokens: 128000,
249
+ },
232
250
  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
233
251
  id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
234
252
  name: "Claude Sonnet 4.5",
@@ -438,6 +456,24 @@ export const MODELS = {
438
456
  contextWindow: 1000000,
439
457
  maxTokens: 128000,
440
458
  },
459
+ "au.anthropic.claude-opus-5-5": {
460
+ id: "au.anthropic.claude-opus-5-5",
461
+ name: "Claude Opus 5.5 (AU)",
462
+ api: "bedrock-converse-stream",
463
+ provider: "amazon-bedrock",
464
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
465
+ reasoning: true,
466
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
467
+ input: ["text", "image"],
468
+ cost: {
469
+ input: 4.4,
470
+ output: 22,
471
+ cacheRead: 0.22,
472
+ cacheWrite: 5.5,
473
+ },
474
+ contextWindow: 1000000,
475
+ maxTokens: 128000,
476
+ },
441
477
  "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
442
478
  id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
443
479
  name: "Claude Sonnet 4.5 (AU)",
@@ -733,6 +769,24 @@ export const MODELS = {
733
769
  contextWindow: 1000000,
734
770
  maxTokens: 128000,
735
771
  },
772
+ "eu.anthropic.claude-opus-5-5": {
773
+ id: "eu.anthropic.claude-opus-5-5",
774
+ name: "Claude Opus 5.5 (EU)",
775
+ api: "bedrock-converse-stream",
776
+ provider: "amazon-bedrock",
777
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
778
+ reasoning: true,
779
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
780
+ input: ["text", "image"],
781
+ cost: {
782
+ input: 4.4,
783
+ output: 22,
784
+ cacheRead: 0.22,
785
+ cacheWrite: 5.5,
786
+ },
787
+ contextWindow: 1000000,
788
+ maxTokens: 128000,
789
+ },
736
790
  "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
737
791
  id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
738
792
  name: "Claude Sonnet 4 (EU)",
@@ -978,6 +1032,24 @@ export const MODELS = {
978
1032
  contextWindow: 1000000,
979
1033
  maxTokens: 128000,
980
1034
  },
1035
+ "global.anthropic.claude-opus-5-5": {
1036
+ id: "global.anthropic.claude-opus-5-5",
1037
+ name: "Claude Opus 5.5 (Global)",
1038
+ api: "bedrock-converse-stream",
1039
+ provider: "amazon-bedrock",
1040
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1041
+ reasoning: true,
1042
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
1043
+ input: ["text", "image"],
1044
+ cost: {
1045
+ input: 4,
1046
+ output: 20,
1047
+ cacheRead: 0.2,
1048
+ cacheWrite: 5,
1049
+ },
1050
+ contextWindow: 1000000,
1051
+ maxTokens: 128000,
1052
+ },
981
1053
  "global.anthropic.claude-sonnet-4-20250514-v1:0": {
982
1054
  id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
983
1055
  name: "Claude Sonnet 4 (Global)",
@@ -1311,6 +1383,24 @@ export const MODELS = {
1311
1383
  contextWindow: 1000000,
1312
1384
  maxTokens: 128000,
1313
1385
  },
1386
+ "jp.anthropic.claude-opus-5-5": {
1387
+ id: "jp.anthropic.claude-opus-5-5",
1388
+ name: "Claude Opus 5.5 (JP)",
1389
+ api: "bedrock-converse-stream",
1390
+ provider: "amazon-bedrock",
1391
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1392
+ reasoning: true,
1393
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
1394
+ input: ["text", "image"],
1395
+ cost: {
1396
+ input: 4.4,
1397
+ output: 22,
1398
+ cacheRead: 0.22,
1399
+ cacheWrite: 5.5,
1400
+ },
1401
+ contextWindow: 1000000,
1402
+ maxTokens: 128000,
1403
+ },
1314
1404
  "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1315
1405
  id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
1316
1406
  name: "Claude Sonnet 4.5 (JP)",
@@ -2361,6 +2451,24 @@ export const MODELS = {
2361
2451
  contextWindow: 1000000,
2362
2452
  maxTokens: 128000,
2363
2453
  },
2454
+ "us.anthropic.claude-opus-5-5": {
2455
+ id: "us.anthropic.claude-opus-5-5",
2456
+ name: "Claude Opus 5.5 (US)",
2457
+ api: "bedrock-converse-stream",
2458
+ provider: "amazon-bedrock",
2459
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2460
+ reasoning: true,
2461
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
2462
+ input: ["text", "image"],
2463
+ cost: {
2464
+ input: 4.4,
2465
+ output: 22,
2466
+ cacheRead: 0.22,
2467
+ cacheWrite: 5.5,
2468
+ },
2469
+ contextWindow: 1000000,
2470
+ maxTokens: 128000,
2471
+ },
2364
2472
  "us.anthropic.claude-sonnet-4-20250514-v1:0": {
2365
2473
  id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
2366
2474
  name: "Claude Sonnet 4 (US)",
@@ -3016,6 +3124,25 @@ export const MODELS = {
3016
3124
  contextWindow: 1000000,
3017
3125
  maxTokens: 128000,
3018
3126
  },
3127
+ "claude-opus-5-5": {
3128
+ id: "claude-opus-5-5",
3129
+ name: "Claude Opus 5.5",
3130
+ api: "anthropic-messages",
3131
+ provider: "anthropic",
3132
+ baseUrl: "https://api.anthropic.com",
3133
+ compat: { "forceAdaptiveThinking": true },
3134
+ reasoning: true,
3135
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
3136
+ input: ["text", "image"],
3137
+ cost: {
3138
+ input: 4,
3139
+ output: 20,
3140
+ cacheRead: 0.2,
3141
+ cacheWrite: 5,
3142
+ },
3143
+ contextWindow: 1000000,
3144
+ maxTokens: 128000,
3145
+ },
3019
3146
  "claude-sonnet-4-5": {
3020
3147
  id: "claude-sonnet-4-5",
3021
3148
  name: "Claude Sonnet 4.5 (latest)",
@@ -3709,6 +3836,42 @@ export const MODELS = {
3709
3836
  contextWindow: 1050000,
3710
3837
  maxTokens: 128000,
3711
3838
  },
3839
+ "gpt-6-luna": {
3840
+ id: "gpt-6-luna",
3841
+ name: "GPT-6 Luna",
3842
+ api: "azure-openai-responses",
3843
+ provider: "azure-openai-responses",
3844
+ baseUrl: "",
3845
+ reasoning: true,
3846
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
3847
+ input: ["text", "image"],
3848
+ cost: {
3849
+ input: 0.1,
3850
+ output: 0.5,
3851
+ cacheRead: 0.01,
3852
+ cacheWrite: 0.125,
3853
+ },
3854
+ contextWindow: 1050000,
3855
+ maxTokens: 128000,
3856
+ },
3857
+ "gpt-6-sol": {
3858
+ id: "gpt-6-sol",
3859
+ name: "GPT-6 Sol",
3860
+ api: "azure-openai-responses",
3861
+ provider: "azure-openai-responses",
3862
+ baseUrl: "",
3863
+ reasoning: true,
3864
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
3865
+ input: ["text", "image"],
3866
+ cost: {
3867
+ input: 2,
3868
+ output: 10,
3869
+ cacheRead: 0.2,
3870
+ cacheWrite: 2.5,
3871
+ },
3872
+ contextWindow: 1050000,
3873
+ maxTokens: 128000,
3874
+ },
3712
3875
  "gpt-realtime-2.1": {
3713
3876
  id: "gpt-realtime-2.1",
3714
3877
  name: "GPT-Realtime-2.1",
@@ -4769,7 +4932,7 @@ export const MODELS = {
4769
4932
  cacheWrite: 0,
4770
4933
  },
4771
4934
  contextWindow: 1310720,
4772
- maxTokens: 1310720,
4935
+ maxTokens: 1048576,
4773
4936
  },
4774
4937
  "@cf/zai-org/glm-5.3-flash": {
4775
4938
  id: "@cf/zai-org/glm-5.3-flash",
@@ -13574,6 +13737,26 @@ export const MODELS = {
13574
13737
  contextWindow: 500000,
13575
13738
  maxTokens: 128000,
13576
13739
  },
13740
+ "grok-4.7": {
13741
+ id: "grok-4.7",
13742
+ name: "Grok 4.7",
13743
+ api: "openai-completions",
13744
+ provider: "github-copilot",
13745
+ baseUrl: "https://api.individual.githubcopilot.com",
13746
+ 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" },
13747
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
13748
+ reasoning: true,
13749
+ thinkingLevelMap: { "xhigh": "xhigh" },
13750
+ input: ["text", "image"],
13751
+ cost: {
13752
+ input: 2,
13753
+ output: 6,
13754
+ cacheRead: 0.5,
13755
+ cacheWrite: 0,
13756
+ },
13757
+ contextWindow: 500000,
13758
+ maxTokens: 128000,
13759
+ },
13577
13760
  "kimi-k2.7-code": {
13578
13761
  id: "kimi-k2.7-code",
13579
13762
  name: "Kimi K2.7 Code",
@@ -15664,6 +15847,24 @@ export const MODELS = {
15664
15847
  contextWindow: 262144,
15665
15848
  maxTokens: 128000,
15666
15849
  },
15850
+ "tencent/Hy4-preview": {
15851
+ id: "tencent/Hy4-preview",
15852
+ name: "Hy4 preview",
15853
+ api: "openai-completions",
15854
+ provider: "huggingface",
15855
+ baseUrl: "https://router.huggingface.co/v1",
15856
+ compat: { "supportsDeveloperRole": false },
15857
+ reasoning: true,
15858
+ input: ["text"],
15859
+ cost: {
15860
+ input: 0.834,
15861
+ output: 2.501,
15862
+ cacheRead: 0,
15863
+ cacheWrite: 0,
15864
+ },
15865
+ contextWindow: 1000000,
15866
+ maxTokens: 64000,
15867
+ },
15667
15868
  "thinkingmachines/Inkling": {
15668
15869
  id: "thinkingmachines/Inkling",
15669
15870
  name: "Inkling",
@@ -16915,26 +17116,6 @@ export const MODELS = {
16915
17116
  },
16916
17117
  },
16917
17118
  "nvidia": {
16918
- "deepseek-ai/deepseek-v4-flash-0731": {
16919
- id: "deepseek-ai/deepseek-v4-flash-0731",
16920
- name: "DeepSeek V4 Flash 0731",
16921
- api: "openai-completions",
16922
- provider: "nvidia",
16923
- baseUrl: "https://integrate.api.nvidia.com/v1",
16924
- headers: { "NVCF-POLL-SECONDS": "3600" },
16925
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
16926
- reasoning: true,
16927
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
16928
- input: ["text"],
16929
- cost: {
16930
- input: 0,
16931
- output: 0,
16932
- cacheRead: 0,
16933
- cacheWrite: 0,
16934
- },
16935
- contextWindow: 1000000,
16936
- maxTokens: 384000,
16937
- },
16938
17119
  "google/gemma-3-12b-it": {
16939
17120
  id: "google/gemma-3-12b-it",
16940
17121
  name: "Gemma 3 12B IT",
@@ -17920,6 +18101,42 @@ export const MODELS = {
17920
18101
  contextWindow: 1050000,
17921
18102
  maxTokens: 128000,
17922
18103
  },
18104
+ "gpt-6-luna": {
18105
+ id: "gpt-6-luna",
18106
+ name: "GPT-6 Luna",
18107
+ api: "openai-responses",
18108
+ provider: "openai",
18109
+ baseUrl: "https://api.openai.com/v1",
18110
+ reasoning: true,
18111
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
18112
+ input: ["text", "image"],
18113
+ cost: {
18114
+ input: 0.1,
18115
+ output: 0.5,
18116
+ cacheRead: 0.01,
18117
+ cacheWrite: 0.125,
18118
+ },
18119
+ contextWindow: 1050000,
18120
+ maxTokens: 128000,
18121
+ },
18122
+ "gpt-6-sol": {
18123
+ id: "gpt-6-sol",
18124
+ name: "GPT-6 Sol",
18125
+ api: "openai-responses",
18126
+ provider: "openai",
18127
+ baseUrl: "https://api.openai.com/v1",
18128
+ reasoning: true,
18129
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
18130
+ input: ["text", "image"],
18131
+ cost: {
18132
+ input: 2,
18133
+ output: 10,
18134
+ cacheRead: 0.2,
18135
+ cacheWrite: 2.5,
18136
+ },
18137
+ contextWindow: 1050000,
18138
+ maxTokens: 128000,
18139
+ },
17923
18140
  "gpt-realtime-2.1": {
17924
18141
  id: "gpt-realtime-2.1",
17925
18142
  name: "GPT-Realtime-2.1",
@@ -18352,6 +18569,25 @@ export const MODELS = {
18352
18569
  contextWindow: 1000000,
18353
18570
  maxTokens: 128000,
18354
18571
  },
18572
+ "claude-opus-5-5": {
18573
+ id: "claude-opus-5-5",
18574
+ name: "Claude Opus 5.5",
18575
+ api: "anthropic-messages",
18576
+ provider: "opencode",
18577
+ baseUrl: "https://opencode.ai/zen",
18578
+ compat: { "forceAdaptiveThinking": true },
18579
+ reasoning: true,
18580
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
18581
+ input: ["text", "image"],
18582
+ cost: {
18583
+ input: 4,
18584
+ output: 20,
18585
+ cacheRead: 0.2,
18586
+ cacheWrite: 5,
18587
+ },
18588
+ contextWindow: 1000000,
18589
+ maxTokens: 128000,
18590
+ },
18355
18591
  "claude-sonnet-4": {
18356
18592
  id: "claude-sonnet-4",
18357
18593
  name: "Claude Sonnet 4",
@@ -19073,40 +19309,76 @@ export const MODELS = {
19073
19309
  contextWindow: 1050000,
19074
19310
  maxTokens: 128000,
19075
19311
  },
19076
- "grok-4.5": {
19077
- id: "grok-4.5",
19078
- name: "Grok 4.5",
19312
+ "gpt-6-luna": {
19313
+ id: "gpt-6-luna",
19314
+ name: "GPT-6 Luna",
19079
19315
  api: "openai-responses",
19080
19316
  provider: "opencode",
19081
19317
  baseUrl: "https://opencode.ai/zen/v1",
19082
19318
  reasoning: true,
19319
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
19083
19320
  input: ["text", "image"],
19084
19321
  cost: {
19085
- input: 2,
19086
- output: 6,
19087
- cacheRead: 0.3,
19088
- cacheWrite: 0,
19322
+ input: 0.1,
19323
+ output: 0.5,
19324
+ cacheRead: 0.01,
19325
+ cacheWrite: 0.125,
19089
19326
  },
19090
- contextWindow: 500000,
19091
- maxTokens: 500000,
19327
+ contextWindow: 1050000,
19328
+ maxTokens: 128000,
19092
19329
  },
19093
- "grok-4.6": {
19094
- id: "grok-4.6",
19095
- name: "Grok 4.6",
19330
+ "gpt-6-sol": {
19331
+ id: "gpt-6-sol",
19332
+ name: "GPT-6 Sol",
19096
19333
  api: "openai-responses",
19097
19334
  provider: "opencode",
19098
19335
  baseUrl: "https://opencode.ai/zen/v1",
19099
19336
  reasoning: true,
19100
- thinkingLevelMap: { "xhigh": "xhigh" },
19337
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
19101
19338
  input: ["text", "image"],
19102
19339
  cost: {
19103
19340
  input: 2,
19104
- output: 6,
19105
- cacheRead: 0.5,
19106
- cacheWrite: 0,
19341
+ output: 10,
19342
+ cacheRead: 0.2,
19343
+ cacheWrite: 2.5,
19107
19344
  },
19108
- contextWindow: 500000,
19109
- maxTokens: 500000,
19345
+ contextWindow: 1050000,
19346
+ maxTokens: 128000,
19347
+ },
19348
+ "grok-4.5": {
19349
+ id: "grok-4.5",
19350
+ name: "Grok 4.5",
19351
+ api: "openai-responses",
19352
+ provider: "opencode",
19353
+ baseUrl: "https://opencode.ai/zen/v1",
19354
+ reasoning: true,
19355
+ input: ["text", "image"],
19356
+ cost: {
19357
+ input: 2,
19358
+ output: 6,
19359
+ cacheRead: 0.3,
19360
+ cacheWrite: 0,
19361
+ },
19362
+ contextWindow: 500000,
19363
+ maxTokens: 500000,
19364
+ },
19365
+ "grok-4.6": {
19366
+ id: "grok-4.6",
19367
+ name: "Grok 4.6",
19368
+ api: "openai-responses",
19369
+ provider: "opencode",
19370
+ baseUrl: "https://opencode.ai/zen/v1",
19371
+ reasoning: true,
19372
+ thinkingLevelMap: { "xhigh": "xhigh" },
19373
+ input: ["text", "image"],
19374
+ cost: {
19375
+ input: 2,
19376
+ output: 6,
19377
+ cacheRead: 0.5,
19378
+ cacheWrite: 0,
19379
+ },
19380
+ contextWindow: 500000,
19381
+ maxTokens: 500000,
19110
19382
  },
19111
19383
  "grok-build-0.1": {
19112
19384
  id: "grok-build-0.1",
@@ -19212,9 +19484,9 @@ export const MODELS = {
19212
19484
  contextWindow: 262144,
19213
19485
  maxTokens: 32768,
19214
19486
  },
19215
- "mimo-v2.5-free": {
19216
- id: "mimo-v2.5-free",
19217
- name: "MiMo V2.5 Free",
19487
+ "mimo-v2.6-flash-free": {
19488
+ id: "mimo-v2.6-flash-free",
19489
+ name: "MiMo-V2.6-Flash Free",
19218
19490
  api: "openai-completions",
19219
19491
  provider: "opencode",
19220
19492
  baseUrl: "https://opencode.ai/zen/v1",
@@ -19625,6 +19897,24 @@ export const MODELS = {
19625
19897
  contextWindow: 500000,
19626
19898
  maxTokens: 500000,
19627
19899
  },
19900
+ "grok-4.7": {
19901
+ id: "grok-4.7",
19902
+ name: "Grok 4.7",
19903
+ api: "openai-responses",
19904
+ provider: "opencode-go",
19905
+ baseUrl: "https://opencode.ai/zen/go/v1",
19906
+ reasoning: true,
19907
+ thinkingLevelMap: { "xhigh": "xhigh" },
19908
+ input: ["text", "image"],
19909
+ cost: {
19910
+ input: 2,
19911
+ output: 6,
19912
+ cacheRead: 0.5,
19913
+ cacheWrite: 0,
19914
+ },
19915
+ contextWindow: 500000,
19916
+ maxTokens: 500000,
19917
+ },
19628
19918
  "hy3": {
19629
19919
  id: "hy3",
19630
19920
  name: "Hy3",
@@ -19763,6 +20053,40 @@ export const MODELS = {
19763
20053
  contextWindow: 1048576,
19764
20054
  maxTokens: 128000,
19765
20055
  },
20056
+ "mimo-v2.6-flash": {
20057
+ id: "mimo-v2.6-flash",
20058
+ name: "MiMo-V2.6-Flash",
20059
+ api: "openai-completions",
20060
+ provider: "opencode-go",
20061
+ baseUrl: "https://opencode.ai/zen/go/v1",
20062
+ reasoning: true,
20063
+ input: ["text", "image"],
20064
+ cost: {
20065
+ input: 0.14,
20066
+ output: 0.28,
20067
+ cacheRead: 0.0028,
20068
+ cacheWrite: 0,
20069
+ },
20070
+ contextWindow: 1048576,
20071
+ maxTokens: 131072,
20072
+ },
20073
+ "mimo-v2.6-pro": {
20074
+ id: "mimo-v2.6-pro",
20075
+ name: "MiMo-V2.6-Pro",
20076
+ api: "openai-completions",
20077
+ provider: "opencode-go",
20078
+ baseUrl: "https://opencode.ai/zen/go/v1",
20079
+ reasoning: true,
20080
+ input: ["text", "image"],
20081
+ cost: {
20082
+ input: 0.435,
20083
+ output: 0.87,
20084
+ cacheRead: 0.003625,
20085
+ cacheWrite: 0,
20086
+ },
20087
+ contextWindow: 1048576,
20088
+ maxTokens: 131072,
20089
+ },
19766
20090
  "minimax-m2.7": {
19767
20091
  id: "minimax-m2.7",
19768
20092
  name: "MiniMax-M2.7",
@@ -19775,7 +20099,7 @@ export const MODELS = {
19775
20099
  input: 0.3,
19776
20100
  output: 1.2,
19777
20101
  cacheRead: 0.06,
19778
- cacheWrite: 0,
20102
+ cacheWrite: 0.375,
19779
20103
  },
19780
20104
  contextWindow: 204800,
19781
20105
  maxTokens: 131072,
@@ -19941,7 +20265,7 @@ export const MODELS = {
19941
20265
  cacheRead: 0.19999999999999998,
19942
20266
  cacheWrite: 0,
19943
20267
  },
19944
- contextWindow: 131072,
20268
+ contextWindow: 1048576,
19945
20269
  maxTokens: 32768,
19946
20270
  },
19947
20271
  "aion-labs/aion-3.0": {
@@ -19959,7 +20283,7 @@ export const MODELS = {
19959
20283
  cacheRead: 0.75,
19960
20284
  cacheWrite: 0,
19961
20285
  },
19962
- contextWindow: 131072,
20286
+ contextWindow: 1048576,
19963
20287
  maxTokens: 32768,
19964
20288
  },
19965
20289
  "aion-labs/aion-3.0-mini": {
@@ -19977,7 +20301,7 @@ export const MODELS = {
19977
20301
  cacheRead: 0.18,
19978
20302
  cacheWrite: 0,
19979
20303
  },
19980
- contextWindow: 131072,
20304
+ contextWindow: 1048576,
19981
20305
  maxTokens: 32768,
19982
20306
  },
19983
20307
  "amazon/nova-2-lite-v1": {
@@ -20188,23 +20512,6 @@ export const MODELS = {
20188
20512
  contextWindow: 200000,
20189
20513
  maxTokens: 64000,
20190
20514
  },
20191
- "anthropic/claude-opus-4": {
20192
- id: "anthropic/claude-opus-4",
20193
- name: "Anthropic: Claude Opus 4",
20194
- api: "openai-completions",
20195
- provider: "openrouter",
20196
- baseUrl: "https://openrouter.ai/api/v1",
20197
- reasoning: true,
20198
- input: ["text", "image"],
20199
- cost: {
20200
- input: 15,
20201
- output: 75,
20202
- cacheRead: 1.5,
20203
- cacheWrite: 18.75,
20204
- },
20205
- contextWindow: 200000,
20206
- maxTokens: 32000,
20207
- },
20208
20515
  "anthropic/claude-opus-4.1": {
20209
20516
  id: "anthropic/claude-opus-4.1",
20210
20517
  name: "Anthropic: Claude Opus 4.1",
@@ -20399,6 +20706,42 @@ export const MODELS = {
20399
20706
  contextWindow: 1000000,
20400
20707
  maxTokens: 128000,
20401
20708
  },
20709
+ "anthropic/claude-opus-5.5": {
20710
+ id: "anthropic/claude-opus-5.5",
20711
+ name: "Anthropic: Claude Opus 5.5",
20712
+ api: "openai-completions",
20713
+ provider: "openrouter",
20714
+ baseUrl: "https://openrouter.ai/api/v1",
20715
+ reasoning: true,
20716
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
20717
+ input: ["text", "image"],
20718
+ cost: {
20719
+ input: 4,
20720
+ output: 20,
20721
+ cacheRead: 0.19999999999999998,
20722
+ cacheWrite: 5,
20723
+ },
20724
+ contextWindow: 1000000,
20725
+ maxTokens: 128000,
20726
+ },
20727
+ "anthropic/claude-opus-5.5:batch": {
20728
+ id: "anthropic/claude-opus-5.5:batch",
20729
+ name: "Anthropic: Claude Opus 5.5 (batch)",
20730
+ api: "openai-completions",
20731
+ provider: "openrouter",
20732
+ baseUrl: "https://openrouter.ai/api/v1",
20733
+ reasoning: true,
20734
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
20735
+ input: ["text", "image"],
20736
+ cost: {
20737
+ input: 2,
20738
+ output: 10,
20739
+ cacheRead: 0.09999999999999999,
20740
+ cacheWrite: 2.5,
20741
+ },
20742
+ contextWindow: 1000000,
20743
+ maxTokens: 128000,
20744
+ },
20402
20745
  "anthropic/claude-opus-5:batch": {
20403
20746
  id: "anthropic/claude-opus-5:batch",
20404
20747
  name: "Anthropic: Claude Opus 5 (batch)",
@@ -20431,7 +20774,7 @@ export const MODELS = {
20431
20774
  cacheRead: 0.3,
20432
20775
  cacheWrite: 3.75,
20433
20776
  },
20434
- contextWindow: 1000000,
20777
+ contextWindow: 200000,
20435
20778
  maxTokens: 64000,
20436
20779
  },
20437
20780
  "anthropic/claude-sonnet-4.5": {
@@ -20880,9 +21223,9 @@ export const MODELS = {
20880
21223
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "off": "none", "max": null, "ultra": null },
20881
21224
  input: ["text"],
20882
21225
  cost: {
20883
- input: 0.04312,
20884
- output: 0.08624,
20885
- cacheRead: 0.008624,
21226
+ input: 0.049,
21227
+ output: 0.098,
21228
+ cacheRead: 0.0098,
20886
21229
  cacheWrite: 0,
20887
21230
  },
20888
21231
  contextWindow: 1048576,
@@ -20900,51 +21243,13 @@ export const MODELS = {
20900
21243
  input: ["text"],
20901
21244
  cost: {
20902
21245
  input: 0.04,
20903
- output: 0.08,
21246
+ output: 0.64,
20904
21247
  cacheRead: 0.016,
20905
21248
  cacheWrite: 0,
20906
21249
  },
20907
21250
  contextWindow: 1310720,
20908
21251
  maxTokens: 943718,
20909
21252
  },
20910
- "deepseek/deepseek-v4-flash-0731:batch": {
20911
- id: "deepseek/deepseek-v4-flash-0731:batch",
20912
- name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
20913
- api: "openai-completions",
20914
- provider: "openrouter",
20915
- baseUrl: "https://openrouter.ai/api/v1",
20916
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20917
- reasoning: true,
20918
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20919
- input: ["text"],
20920
- cost: {
20921
- input: 0.11,
20922
- output: 0.33,
20923
- cacheRead: 0.0035,
20924
- cacheWrite: 0,
20925
- },
20926
- contextWindow: 1048576,
20927
- maxTokens: 943718,
20928
- },
20929
- "deepseek/deepseek-v4-flash-0731:free": {
20930
- id: "deepseek/deepseek-v4-flash-0731:free",
20931
- name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
20932
- api: "openai-completions",
20933
- provider: "openrouter",
20934
- baseUrl: "https://openrouter.ai/api/v1",
20935
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20936
- reasoning: true,
20937
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20938
- input: ["text"],
20939
- cost: {
20940
- input: 0,
20941
- output: 0,
20942
- cacheRead: 0,
20943
- cacheWrite: 0,
20944
- },
20945
- contextWindow: 1048576,
20946
- maxTokens: 393216,
20947
- },
20948
21253
  "deepseek/deepseek-v4-flash-vision-exp": {
20949
21254
  id: "deepseek/deepseek-v4-flash-vision-exp",
20950
21255
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -20956,28 +21261,9 @@ export const MODELS = {
20956
21261
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20957
21262
  input: ["text", "image"],
20958
21263
  cost: {
20959
- input: 0.21559999999999999,
20960
- output: 0.6468,
20961
- cacheRead: 0.00686,
20962
- cacheWrite: 0,
20963
- },
20964
- contextWindow: 1048576,
20965
- maxTokens: 262144,
20966
- },
20967
- "deepseek/deepseek-v4-flash-vision-exp:batch": {
20968
- id: "deepseek/deepseek-v4-flash-vision-exp:batch",
20969
- name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
20970
- api: "openai-completions",
20971
- provider: "openrouter",
20972
- baseUrl: "https://openrouter.ai/api/v1",
20973
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20974
- reasoning: true,
20975
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20976
- input: ["text", "image"],
20977
- cost: {
20978
- input: 0.11,
20979
- output: 0.33,
20980
- cacheRead: 0.0035,
21264
+ input: 0.22,
21265
+ output: 0.66,
21266
+ cacheRead: 0.007,
20981
21267
  cacheWrite: 0,
20982
21268
  },
20983
21269
  contextWindow: 1048576,
@@ -20994,9 +21280,9 @@ export const MODELS = {
20994
21280
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "off": "none", "max": null, "ultra": null },
20995
21281
  input: ["text"],
20996
21282
  cost: {
20997
- input: 0.422298,
20998
- output: 0.844596,
20999
- cacheRead: 0.0351915,
21283
+ input: 0.895578,
21284
+ output: 1.791156,
21285
+ cacheRead: 0.0746315,
21000
21286
  cacheWrite: 0,
21001
21287
  },
21002
21288
  contextWindow: 1048576,
@@ -21013,36 +21299,36 @@ export const MODELS = {
21013
21299
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
21014
21300
  input: ["text"],
21015
21301
  cost: {
21016
- input: 0.57816,
21017
- output: 1.73448,
21018
- cacheRead: 0.018396000000000003,
21302
+ input: 0.66,
21303
+ output: 1.9800000000000002,
21304
+ cacheRead: 0.022,
21019
21305
  cacheWrite: 0,
21020
21306
  },
21021
21307
  contextWindow: 1048576,
21022
- maxTokens: 393216,
21308
+ maxTokens: 384000,
21023
21309
  },
21024
- "deepseek/deepseek-v4-pro-0813:batch": {
21025
- id: "deepseek/deepseek-v4-pro-0813:batch",
21026
- name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
21310
+ "deepseek/deepseek-v4.1-flash": {
21311
+ id: "deepseek/deepseek-v4.1-flash",
21312
+ name: "DeepSeek: DeepSeek V4.1 Flash",
21027
21313
  api: "openai-completions",
21028
21314
  provider: "openrouter",
21029
21315
  baseUrl: "https://openrouter.ai/api/v1",
21030
21316
  compat: { "requiresReasoningContentOnAssistantMessages": true },
21031
21317
  reasoning: true,
21032
21318
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
21033
- input: ["text"],
21319
+ input: ["text", "image"],
21034
21320
  cost: {
21035
- input: 0.66,
21036
- output: 1.9800000000000002,
21037
- cacheRead: 0.022,
21321
+ input: 0.15,
21322
+ output: 0.6,
21323
+ cacheRead: 0.003,
21038
21324
  cacheWrite: 0,
21039
21325
  },
21040
21326
  contextWindow: 1048576,
21041
- maxTokens: 943718,
21327
+ maxTokens: 384000,
21042
21328
  },
21043
- "deepseek/deepseek-v4.1-flash": {
21044
- id: "deepseek/deepseek-v4.1-flash",
21045
- name: "DeepSeek: DeepSeek V4.1 Flash",
21329
+ "deepseek/deepseek-v4.1-flash:batch": {
21330
+ id: "deepseek/deepseek-v4.1-flash:batch",
21331
+ name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
21046
21332
  api: "openai-completions",
21047
21333
  provider: "openrouter",
21048
21334
  baseUrl: "https://openrouter.ai/api/v1",
@@ -21051,13 +21337,13 @@ export const MODELS = {
21051
21337
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
21052
21338
  input: ["text", "image"],
21053
21339
  cost: {
21054
- input: 0.15,
21055
- output: 0.6,
21056
- cacheRead: 0.003,
21340
+ input: 0.112,
21341
+ output: 0.33599999999999997,
21342
+ cacheRead: 0.00336,
21057
21343
  cacheWrite: 0,
21058
21344
  },
21059
21345
  contextWindow: 1048576,
21060
- maxTokens: 384000,
21346
+ maxTokens: 131072,
21061
21347
  },
21062
21348
  "dots-studio/dots-3-note-preview:free": {
21063
21349
  id: "dots-studio/dots-3-note-preview:free",
@@ -21798,23 +22084,6 @@ export const MODELS = {
21798
22084
  contextWindow: 262144,
21799
22085
  maxTokens: 32768,
21800
22086
  },
21801
- "kwaipilot/kat-coder-pro-v2": {
21802
- id: "kwaipilot/kat-coder-pro-v2",
21803
- name: "Kwaipilot: KAT-Coder-Pro V2",
21804
- api: "openai-completions",
21805
- provider: "openrouter",
21806
- baseUrl: "https://openrouter.ai/api/v1",
21807
- reasoning: false,
21808
- input: ["text"],
21809
- cost: {
21810
- input: 0.3,
21811
- output: 1.2,
21812
- cacheRead: 0.06,
21813
- cacheWrite: 0,
21814
- },
21815
- contextWindow: 262144,
21816
- maxTokens: 144000,
21817
- },
21818
22087
  "kwaipilot/kat-coder-pro-v2.5": {
21819
22088
  id: "kwaipilot/kat-coder-pro-v2.5",
21820
22089
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -21962,31 +22231,13 @@ export const MODELS = {
21962
22231
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
21963
22232
  input: ["text", "image"],
21964
22233
  cost: {
21965
- input: 0.35,
21966
- output: 1.5,
22234
+ input: 0.3,
22235
+ output: 1.2,
21967
22236
  cacheRead: 0.04,
21968
22237
  cacheWrite: 0,
21969
22238
  },
21970
22239
  contextWindow: 131072,
21971
- maxTokens: 117964,
21972
- },
21973
- "meta/muse-glimmer-30b:batch": {
21974
- id: "meta/muse-glimmer-30b:batch",
21975
- name: "Meta: Muse Glimmer 30B (batch)",
21976
- api: "openai-completions",
21977
- provider: "openrouter",
21978
- baseUrl: "https://openrouter.ai/api/v1",
21979
- reasoning: true,
21980
- thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
21981
- input: ["text", "image"],
21982
- cost: {
21983
- input: 0.175,
21984
- output: 0.75,
21985
- cacheRead: 0.02,
21986
- cacheWrite: 0,
21987
- },
21988
- contextWindow: 131072,
21989
- maxTokens: 117964,
22240
+ maxTokens: 16384,
21990
22241
  },
21991
22242
  "meta/muse-spark-1.1": {
21992
22243
  id: "meta/muse-spark-1.1",
@@ -22184,35 +22435,18 @@ export const MODELS = {
22184
22435
  contextWindow: 1048576,
22185
22436
  maxTokens: 512000,
22186
22437
  },
22187
- "minimax/minimax-m3:batch": {
22188
- id: "minimax/minimax-m3:batch",
22189
- name: "MiniMax: MiniMax M3 (batch)",
22438
+ "mistralai/codestral-2508": {
22439
+ id: "mistralai/codestral-2508",
22440
+ name: "Mistral: Codestral 2508",
22190
22441
  api: "openai-completions",
22191
22442
  provider: "openrouter",
22192
22443
  baseUrl: "https://openrouter.ai/api/v1",
22193
- reasoning: true,
22194
- input: ["text", "image"],
22444
+ reasoning: false,
22445
+ input: ["text"],
22195
22446
  cost: {
22196
22447
  input: 0.3,
22197
- output: 1.2,
22198
- cacheRead: 0.06,
22199
- cacheWrite: 0,
22200
- },
22201
- contextWindow: 524288,
22202
- maxTokens: 471859,
22203
- },
22204
- "mistralai/codestral-2508": {
22205
- id: "mistralai/codestral-2508",
22206
- name: "Mistral: Codestral 2508",
22207
- api: "openai-completions",
22208
- provider: "openrouter",
22209
- baseUrl: "https://openrouter.ai/api/v1",
22210
- reasoning: false,
22211
- input: ["text"],
22212
- cost: {
22213
- input: 0.3,
22214
- output: 0.8999999999999999,
22215
- cacheRead: 0.03,
22448
+ output: 0.8999999999999999,
22449
+ cacheRead: 0.03,
22216
22450
  cacheWrite: 0,
22217
22451
  },
22218
22452
  contextWindow: 256000,
@@ -22528,6 +22762,23 @@ export const MODELS = {
22528
22762
  contextWindow: 262144,
22529
22763
  maxTokens: 209715,
22530
22764
  },
22765
+ "mistralai/mistral-small-3.1-24b-instruct": {
22766
+ id: "mistralai/mistral-small-3.1-24b-instruct",
22767
+ name: "Mistral: Mistral Small 3.1 24B",
22768
+ api: "openai-completions",
22769
+ provider: "openrouter",
22770
+ baseUrl: "https://openrouter.ai/api/v1",
22771
+ reasoning: false,
22772
+ input: ["text", "image"],
22773
+ cost: {
22774
+ input: 0.351,
22775
+ output: 0.5549999999999999,
22776
+ cacheRead: 0,
22777
+ cacheWrite: 0,
22778
+ },
22779
+ contextWindow: 128000,
22780
+ maxTokens: 102400,
22781
+ },
22531
22782
  "mistralai/mistral-small-3.2-24b-instruct": {
22532
22783
  id: "mistralai/mistral-small-3.2-24b-instruct",
22533
22784
  name: "Mistral: Mistral Small 3.2 24B",
@@ -22677,7 +22928,7 @@ export const MODELS = {
22677
22928
  input: ["text", "image"],
22678
22929
  cost: {
22679
22930
  input: 0.7062,
22680
- output: 3.21,
22931
+ output: 3.3000000000000003,
22681
22932
  cacheRead: 0.18,
22682
22933
  cacheWrite: 0,
22683
22934
  },
@@ -22694,9 +22945,9 @@ export const MODELS = {
22694
22945
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
22695
22946
  input: ["text", "image"],
22696
22947
  cost: {
22697
- input: 1.7,
22698
- output: 8.5,
22699
- cacheRead: 0.16999999999999998,
22948
+ input: 3,
22949
+ output: 15,
22950
+ cacheRead: 0.3,
22700
22951
  cacheWrite: 0,
22701
22952
  },
22702
22953
  contextWindow: 1048576,
@@ -22712,13 +22963,13 @@ export const MODELS = {
22712
22963
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
22713
22964
  input: ["text", "image"],
22714
22965
  cost: {
22715
- input: 3,
22716
- output: 15,
22717
- cacheRead: 0.3,
22966
+ input: 2.2800000000000002,
22967
+ output: 11.399999999999999,
22968
+ cacheRead: 0.228,
22718
22969
  cacheWrite: 0,
22719
22970
  },
22720
22971
  contextWindow: 1048576,
22721
- maxTokens: 943718,
22972
+ maxTokens: 16384,
22722
22973
  },
22723
22974
  "nex-agi/nex-n2.5-mini:free": {
22724
22975
  id: "nex-agi/nex-n2.5-mini:free",
@@ -22738,6 +22989,24 @@ export const MODELS = {
22738
22989
  contextWindow: 262144,
22739
22990
  maxTokens: 235929,
22740
22991
  },
22992
+ "nex-agi/nex-n2.5-pro": {
22993
+ id: "nex-agi/nex-n2.5-pro",
22994
+ name: "Nex AGI: Nex-N2.5-Pro",
22995
+ api: "openai-completions",
22996
+ provider: "openrouter",
22997
+ baseUrl: "https://openrouter.ai/api/v1",
22998
+ reasoning: true,
22999
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
23000
+ input: ["text", "image"],
23001
+ cost: {
23002
+ input: 0.075,
23003
+ output: 0.25,
23004
+ cacheRead: 0.015,
23005
+ cacheWrite: 0,
23006
+ },
23007
+ contextWindow: 262144,
23008
+ maxTokens: 235929,
23009
+ },
22741
23010
  "nex-agi/nex-n2.5-pro:free": {
22742
23011
  id: "nex-agi/nex-n2.5-pro:free",
22743
23012
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -22765,9 +23034,9 @@ export const MODELS = {
22765
23034
  reasoning: true,
22766
23035
  input: ["text"],
22767
23036
  cost: {
22768
- input: 0.06,
22769
- output: 0.24,
22770
- cacheRead: 0,
23037
+ input: 0.049999999999999996,
23038
+ output: 0.19999999999999998,
23039
+ cacheRead: 0.03,
22771
23040
  cacheWrite: 0,
22772
23041
  },
22773
23042
  contextWindow: 262144,
@@ -24117,6 +24386,150 @@ export const MODELS = {
24117
24386
  contextWindow: 1050000,
24118
24387
  maxTokens: 128000,
24119
24388
  },
24389
+ "openai/gpt-6-luna": {
24390
+ id: "openai/gpt-6-luna",
24391
+ name: "OpenAI: GPT-6 Luna",
24392
+ api: "openai-completions",
24393
+ provider: "openrouter",
24394
+ baseUrl: "https://openrouter.ai/api/v1",
24395
+ reasoning: true,
24396
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24397
+ input: ["text", "image"],
24398
+ cost: {
24399
+ input: 0.09999999999999999,
24400
+ output: 0.5,
24401
+ cacheRead: 0.01,
24402
+ cacheWrite: 0.125,
24403
+ },
24404
+ contextWindow: 1050000,
24405
+ maxTokens: 128000,
24406
+ },
24407
+ "openai/gpt-6-luna-pro": {
24408
+ id: "openai/gpt-6-luna-pro",
24409
+ name: "OpenAI: GPT-6 Luna Pro",
24410
+ api: "openai-completions",
24411
+ provider: "openrouter",
24412
+ baseUrl: "https://openrouter.ai/api/v1",
24413
+ reasoning: true,
24414
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24415
+ input: ["text", "image"],
24416
+ cost: {
24417
+ input: 0.09999999999999999,
24418
+ output: 0.5,
24419
+ cacheRead: 0.01,
24420
+ cacheWrite: 0.125,
24421
+ },
24422
+ contextWindow: 1050000,
24423
+ maxTokens: 128000,
24424
+ },
24425
+ "openai/gpt-6-luna-pro:batch": {
24426
+ id: "openai/gpt-6-luna-pro:batch",
24427
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
24428
+ api: "openai-completions",
24429
+ provider: "openrouter",
24430
+ baseUrl: "https://openrouter.ai/api/v1",
24431
+ reasoning: true,
24432
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24433
+ input: ["text", "image"],
24434
+ cost: {
24435
+ input: 0.049999999999999996,
24436
+ output: 0.25,
24437
+ cacheRead: 0.005,
24438
+ cacheWrite: 0.0625,
24439
+ },
24440
+ contextWindow: 1050000,
24441
+ maxTokens: 128000,
24442
+ },
24443
+ "openai/gpt-6-luna:batch": {
24444
+ id: "openai/gpt-6-luna:batch",
24445
+ name: "OpenAI: GPT-6 Luna (batch)",
24446
+ api: "openai-completions",
24447
+ provider: "openrouter",
24448
+ baseUrl: "https://openrouter.ai/api/v1",
24449
+ reasoning: true,
24450
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24451
+ input: ["text", "image"],
24452
+ cost: {
24453
+ input: 0.049999999999999996,
24454
+ output: 0.25,
24455
+ cacheRead: 0.005,
24456
+ cacheWrite: 0.0625,
24457
+ },
24458
+ contextWindow: 1050000,
24459
+ maxTokens: 128000,
24460
+ },
24461
+ "openai/gpt-6-sol": {
24462
+ id: "openai/gpt-6-sol",
24463
+ name: "OpenAI: GPT-6 Sol",
24464
+ api: "openai-completions",
24465
+ provider: "openrouter",
24466
+ baseUrl: "https://openrouter.ai/api/v1",
24467
+ reasoning: true,
24468
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24469
+ input: ["text", "image"],
24470
+ cost: {
24471
+ input: 2,
24472
+ output: 10,
24473
+ cacheRead: 0.19999999999999998,
24474
+ cacheWrite: 2.5,
24475
+ },
24476
+ contextWindow: 1050000,
24477
+ maxTokens: 128000,
24478
+ },
24479
+ "openai/gpt-6-sol-pro": {
24480
+ id: "openai/gpt-6-sol-pro",
24481
+ name: "OpenAI: GPT-6 Sol Pro",
24482
+ api: "openai-completions",
24483
+ provider: "openrouter",
24484
+ baseUrl: "https://openrouter.ai/api/v1",
24485
+ reasoning: true,
24486
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24487
+ input: ["text", "image"],
24488
+ cost: {
24489
+ input: 2,
24490
+ output: 10,
24491
+ cacheRead: 0.19999999999999998,
24492
+ cacheWrite: 2.5,
24493
+ },
24494
+ contextWindow: 1050000,
24495
+ maxTokens: 128000,
24496
+ },
24497
+ "openai/gpt-6-sol-pro:batch": {
24498
+ id: "openai/gpt-6-sol-pro:batch",
24499
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
24500
+ api: "openai-completions",
24501
+ provider: "openrouter",
24502
+ baseUrl: "https://openrouter.ai/api/v1",
24503
+ reasoning: true,
24504
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24505
+ input: ["text", "image"],
24506
+ cost: {
24507
+ input: 1,
24508
+ output: 5,
24509
+ cacheRead: 0.09999999999999999,
24510
+ cacheWrite: 1.25,
24511
+ },
24512
+ contextWindow: 1050000,
24513
+ maxTokens: 128000,
24514
+ },
24515
+ "openai/gpt-6-sol:batch": {
24516
+ id: "openai/gpt-6-sol:batch",
24517
+ name: "OpenAI: GPT-6 Sol (batch)",
24518
+ api: "openai-completions",
24519
+ provider: "openrouter",
24520
+ baseUrl: "https://openrouter.ai/api/v1",
24521
+ reasoning: true,
24522
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
24523
+ input: ["text", "image"],
24524
+ cost: {
24525
+ input: 1,
24526
+ output: 5,
24527
+ cacheRead: 0.09999999999999999,
24528
+ cacheWrite: 1.25,
24529
+ },
24530
+ contextWindow: 1050000,
24531
+ maxTokens: 128000,
24532
+ },
24120
24533
  "openai/gpt-audio": {
24121
24534
  id: "openai/gpt-audio",
24122
24535
  name: "OpenAI: GPT Audio",
@@ -24186,9 +24599,9 @@ export const MODELS = {
24186
24599
  contextWindow: 131072,
24187
24600
  maxTokens: 65536,
24188
24601
  },
24189
- "openai/gpt-oss-120b:batch": {
24190
- id: "openai/gpt-oss-120b:batch",
24191
- name: "OpenAI: gpt-oss-120b (batch)",
24602
+ "openai/gpt-oss-20b": {
24603
+ id: "openai/gpt-oss-20b",
24604
+ name: "OpenAI: gpt-oss-20b",
24192
24605
  api: "openai-completions",
24193
24606
  provider: "openrouter",
24194
24607
  baseUrl: "https://openrouter.ai/api/v1",
@@ -24196,17 +24609,17 @@ export const MODELS = {
24196
24609
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
24197
24610
  input: ["text"],
24198
24611
  cost: {
24199
- input: 0.15,
24200
- output: 0.6,
24612
+ input: 0.018,
24613
+ output: 0.09,
24201
24614
  cacheRead: 0,
24202
24615
  cacheWrite: 0,
24203
24616
  },
24204
24617
  contextWindow: 131072,
24205
- maxTokens: 117964,
24618
+ maxTokens: 32768,
24206
24619
  },
24207
- "openai/gpt-oss-20b": {
24208
- id: "openai/gpt-oss-20b",
24209
- name: "OpenAI: gpt-oss-20b",
24620
+ "openai/gpt-oss-20b:batch": {
24621
+ id: "openai/gpt-oss-20b:batch",
24622
+ name: "OpenAI: gpt-oss-20b (batch)",
24210
24623
  api: "openai-completions",
24211
24624
  provider: "openrouter",
24212
24625
  baseUrl: "https://openrouter.ai/api/v1",
@@ -24214,9 +24627,9 @@ export const MODELS = {
24214
24627
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
24215
24628
  input: ["text"],
24216
24629
  cost: {
24217
- input: 0.03,
24218
- output: 0.13,
24219
- cacheRead: 0.03,
24630
+ input: 0.024,
24631
+ output: 0.112,
24632
+ cacheRead: 0,
24220
24633
  cacheWrite: 0,
24221
24634
  },
24222
24635
  contextWindow: 131072,
@@ -24930,7 +25343,7 @@ export const MODELS = {
24930
25343
  cacheWrite: 0,
24931
25344
  },
24932
25345
  contextWindow: 262144,
24933
- maxTokens: 32768,
25346
+ maxTokens: 235929,
24934
25347
  },
24935
25348
  "qwen/qwen3-vl-235b-a22b-instruct": {
24936
25349
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -24976,8 +25389,8 @@ export const MODELS = {
24976
25389
  reasoning: false,
24977
25390
  input: ["text", "image"],
24978
25391
  cost: {
24979
- input: 0.19999999999999998,
24980
- output: 0.7,
25392
+ input: 0.13,
25393
+ output: 0.52,
24981
25394
  cacheRead: 0,
24982
25395
  cacheWrite: 0,
24983
25396
  },
@@ -25100,13 +25513,13 @@ export const MODELS = {
25100
25513
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25101
25514
  input: ["text", "image"],
25102
25515
  cost: {
25103
- input: 0.1625,
25104
- output: 1.3,
25105
- cacheRead: 0,
25516
+ input: 0.3125,
25517
+ output: 1.25,
25518
+ cacheRead: 0.15625,
25106
25519
  cacheWrite: 0,
25107
25520
  },
25108
25521
  contextWindow: 262144,
25109
- maxTokens: 65536,
25522
+ maxTokens: 16384,
25110
25523
  },
25111
25524
  "qwen/qwen3.5-397b-a17b": {
25112
25525
  id: "qwen/qwen3.5-397b-a17b",
@@ -25142,25 +25555,7 @@ export const MODELS = {
25142
25555
  cacheWrite: 0,
25143
25556
  },
25144
25557
  contextWindow: 262144,
25145
- maxTokens: 235929,
25146
- },
25147
- "qwen/qwen3.5-9b:batch": {
25148
- id: "qwen/qwen3.5-9b:batch",
25149
- name: "Qwen: Qwen3.5-9B (batch)",
25150
- api: "openai-completions",
25151
- provider: "openrouter",
25152
- baseUrl: "https://openrouter.ai/api/v1",
25153
- reasoning: true,
25154
- thinkingLevelMap: { "xhigh": "high", "max": "max" },
25155
- input: ["text", "image"],
25156
- cost: {
25157
- input: 0.16999999999999998,
25158
- output: 0.25,
25159
- cacheRead: 0,
25160
- cacheWrite: 0,
25161
- },
25162
- contextWindow: 262144,
25163
- maxTokens: 235929,
25558
+ maxTokens: 32768,
25164
25559
  },
25165
25560
  "qwen/qwen3.5-flash-02-23": {
25166
25561
  id: "qwen/qwen3.5-flash-02-23",
@@ -25226,13 +25621,13 @@ export const MODELS = {
25226
25621
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25227
25622
  input: ["text", "image"],
25228
25623
  cost: {
25229
- input: 0.3,
25230
- output: 2,
25231
- cacheRead: 0.03,
25624
+ input: 0.32,
25625
+ output: 2.7,
25626
+ cacheRead: 0.15,
25232
25627
  cacheWrite: 0,
25233
25628
  },
25234
25629
  contextWindow: 262144,
25235
- maxTokens: 65536,
25630
+ maxTokens: 262140,
25236
25631
  },
25237
25632
  "qwen/qwen3.6-35b-a3b": {
25238
25633
  id: "qwen/qwen3.6-35b-a3b",
@@ -25244,8 +25639,8 @@ export const MODELS = {
25244
25639
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25245
25640
  input: ["text", "image"],
25246
25641
  cost: {
25247
- input: 0.09999999999999999,
25248
- output: 0.8999999999999999,
25642
+ input: 0.15,
25643
+ output: 1,
25249
25644
  cacheRead: 0.049999999999999996,
25250
25645
  cacheWrite: 0,
25251
25646
  },
@@ -25378,24 +25773,6 @@ export const MODELS = {
25378
25773
  contextWindow: 1048576,
25379
25774
  maxTokens: 131072,
25380
25775
  },
25381
- "qwen/qwen3.8-2.4t-a95b:batch": {
25382
- id: "qwen/qwen3.8-2.4t-a95b:batch",
25383
- name: "Qwen: Qwen3.8 2.4T A95B (batch)",
25384
- api: "openai-completions",
25385
- provider: "openrouter",
25386
- baseUrl: "https://openrouter.ai/api/v1",
25387
- reasoning: true,
25388
- thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": null, "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
25389
- input: ["text"],
25390
- cost: {
25391
- input: 2,
25392
- output: 6,
25393
- cacheRead: 0.25,
25394
- cacheWrite: 0,
25395
- },
25396
- contextWindow: 1010000,
25397
- maxTokens: 909000,
25398
- },
25399
25776
  "qwen/qwen3.8-27b": {
25400
25777
  id: "qwen/qwen3.8-27b",
25401
25778
  name: "Qwen: Qwen3.8 27B",
@@ -25406,9 +25783,9 @@ export const MODELS = {
25406
25783
  thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
25407
25784
  input: ["text", "image"],
25408
25785
  cost: {
25409
- input: 0.21400000000000002,
25410
- output: 2.5500000000000003,
25411
- cacheRead: 0.15,
25786
+ input: 0.42,
25787
+ output: 3,
25788
+ cacheRead: 0.08499999999999999,
25412
25789
  cacheWrite: 0,
25413
25790
  },
25414
25791
  contextWindow: 1000000,
@@ -25468,18 +25845,36 @@ export const MODELS = {
25468
25845
  contextWindow: 1000000,
25469
25846
  maxTokens: 131072,
25470
25847
  },
25471
- "rekaai/reka-edge": {
25472
- id: "rekaai/reka-edge",
25473
- name: "Reka Edge",
25848
+ "qwen/qwen3.8-omni-flash": {
25849
+ id: "qwen/qwen3.8-omni-flash",
25850
+ name: "Qwen: Qwen3.8 Omni Flash",
25474
25851
  api: "openai-completions",
25475
25852
  provider: "openrouter",
25476
25853
  baseUrl: "https://openrouter.ai/api/v1",
25477
- reasoning: false,
25854
+ reasoning: true,
25855
+ thinkingLevelMap: { "xhigh": "high", "max": "max" },
25478
25856
  input: ["text", "image"],
25479
25857
  cost: {
25480
- input: 0.09999999999999999,
25481
- output: 0.09999999999999999,
25482
- cacheRead: 0,
25858
+ input: 0.15,
25859
+ output: 0.47,
25860
+ cacheRead: 0.016,
25861
+ cacheWrite: 0,
25862
+ },
25863
+ contextWindow: 1000000,
25864
+ maxTokens: 131072,
25865
+ },
25866
+ "rekaai/reka-edge": {
25867
+ id: "rekaai/reka-edge",
25868
+ name: "Reka Edge",
25869
+ api: "openai-completions",
25870
+ provider: "openrouter",
25871
+ baseUrl: "https://openrouter.ai/api/v1",
25872
+ reasoning: false,
25873
+ input: ["text", "image"],
25874
+ cost: {
25875
+ input: 0.09999999999999999,
25876
+ output: 0.09999999999999999,
25877
+ cacheRead: 0,
25483
25878
  cacheWrite: 0,
25484
25879
  },
25485
25880
  contextWindow: 16384,
@@ -25637,9 +26032,9 @@ export const MODELS = {
25637
26032
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
25638
26033
  input: ["text"],
25639
26034
  cost: {
25640
- input: 0.13199999999999998,
25641
- output: 0.5279999999999999,
25642
- cacheRead: 0.032999999999999995,
26035
+ input: 0.0825,
26036
+ output: 0.33,
26037
+ cacheRead: 0.020625,
25643
26038
  cacheWrite: 0,
25644
26039
  },
25645
26040
  contextWindow: 262144,
@@ -25735,24 +26130,6 @@ export const MODELS = {
25735
26130
  contextWindow: 1048576,
25736
26131
  maxTokens: 262144,
25737
26132
  },
25738
- "thinkingmachines/inkling:batch": {
25739
- id: "thinkingmachines/inkling:batch",
25740
- name: "Thinking Machines: Inkling (batch)",
25741
- api: "openai-completions",
25742
- provider: "openrouter",
25743
- baseUrl: "https://openrouter.ai/api/v1",
25744
- reasoning: true,
25745
- thinkingLevelMap: { "off": "none", "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max", "ultra": null },
25746
- input: ["text", "image"],
25747
- cost: {
25748
- input: 1,
25749
- output: 4.05,
25750
- cacheRead: 0.16999999999999998,
25751
- cacheWrite: 0,
25752
- },
25753
- contextWindow: 524288,
25754
- maxTokens: 471859,
25755
- },
25756
26133
  "thinkingmachines/inkling:free": {
25757
26134
  id: "thinkingmachines/inkling:free",
25758
26135
  name: "Thinking Machines: Inkling (free)",
@@ -25913,6 +26290,24 @@ export const MODELS = {
25913
26290
  contextWindow: 500000,
25914
26291
  maxTokens: 450000,
25915
26292
  },
26293
+ "x-ai/grok-4.7": {
26294
+ id: "x-ai/grok-4.7",
26295
+ name: "SpaceXAI: Grok 4.7",
26296
+ api: "openai-completions",
26297
+ provider: "openrouter",
26298
+ baseUrl: "https://openrouter.ai/api/v1",
26299
+ reasoning: true,
26300
+ thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "max": null, "ultra": null },
26301
+ input: ["text", "image"],
26302
+ cost: {
26303
+ input: 1.5999999999999999,
26304
+ output: 4.8,
26305
+ cacheRead: 0.39999999999999997,
26306
+ cacheWrite: 0,
26307
+ },
26308
+ contextWindow: 500000,
26309
+ maxTokens: 450000,
26310
+ },
25916
26311
  "x-ai/grok-build-0.1": {
25917
26312
  id: "x-ai/grok-build-0.1",
25918
26313
  name: "SpaceXAI: Grok Build 0.1",
@@ -25965,6 +26360,57 @@ export const MODELS = {
25965
26360
  contextWindow: 1050000,
25966
26361
  maxTokens: 131072,
25967
26362
  },
26363
+ "xiaomi/mimo-v2.6-flash": {
26364
+ id: "xiaomi/mimo-v2.6-flash",
26365
+ name: "Xiaomi: MiMo-V2.6-Flash",
26366
+ api: "openai-completions",
26367
+ provider: "openrouter",
26368
+ baseUrl: "https://openrouter.ai/api/v1",
26369
+ reasoning: true,
26370
+ input: ["text", "image"],
26371
+ cost: {
26372
+ input: 0.14,
26373
+ output: 0.28,
26374
+ cacheRead: 0.0028,
26375
+ cacheWrite: 0,
26376
+ },
26377
+ contextWindow: 1048576,
26378
+ maxTokens: 131072,
26379
+ },
26380
+ "xiaomi/mimo-v2.6-pro": {
26381
+ id: "xiaomi/mimo-v2.6-pro",
26382
+ name: "Xiaomi: MiMo-V2.6-Pro",
26383
+ api: "openai-completions",
26384
+ provider: "openrouter",
26385
+ baseUrl: "https://openrouter.ai/api/v1",
26386
+ reasoning: true,
26387
+ input: ["text", "image"],
26388
+ cost: {
26389
+ input: 0.435,
26390
+ output: 0.87,
26391
+ cacheRead: 0.0036,
26392
+ cacheWrite: 0,
26393
+ },
26394
+ contextWindow: 1048576,
26395
+ maxTokens: 131072,
26396
+ },
26397
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
26398
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
26399
+ name: "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
26400
+ api: "openai-completions",
26401
+ provider: "openrouter",
26402
+ baseUrl: "https://openrouter.ai/api/v1",
26403
+ reasoning: true,
26404
+ input: ["text", "image"],
26405
+ cost: {
26406
+ input: 4.35,
26407
+ output: 8.7,
26408
+ cacheRead: 0.036,
26409
+ cacheWrite: 0,
26410
+ },
26411
+ contextWindow: 1048576,
26412
+ maxTokens: 131072,
26413
+ },
25968
26414
  "z-ai/glm-4.5": {
25969
26415
  id: "z-ai/glm-4.5",
25970
26416
  name: "Z.ai: GLM 4.5",
@@ -26025,13 +26471,13 @@ export const MODELS = {
26025
26471
  reasoning: true,
26026
26472
  input: ["text"],
26027
26473
  cost: {
26028
- input: 0.5,
26029
- output: 2,
26030
- cacheRead: 0.09999999999999999,
26474
+ input: 0.43,
26475
+ output: 1.75,
26476
+ cacheRead: 0.08,
26031
26477
  cacheWrite: 0,
26032
26478
  },
26033
26479
  contextWindow: 204800,
26034
- maxTokens: 131072,
26480
+ maxTokens: 16384,
26035
26481
  },
26036
26482
  "z-ai/glm-4.6v": {
26037
26483
  id: "z-ai/glm-4.6v",
@@ -26145,32 +26591,14 @@ export const MODELS = {
26145
26591
  thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
26146
26592
  input: ["text"],
26147
26593
  cost: {
26148
- input: 0.5544,
26149
- output: 1.7424,
26150
- cacheRead: 0.10296000000000001,
26594
+ input: 0.6496,
26595
+ output: 2.0416,
26596
+ cacheRead: 0.12064,
26151
26597
  cacheWrite: 0,
26152
26598
  },
26153
26599
  contextWindow: 1048576,
26154
26600
  maxTokens: 131072,
26155
26601
  },
26156
- "z-ai/glm-5.2:batch": {
26157
- id: "z-ai/glm-5.2:batch",
26158
- name: "Z.ai: GLM 5.2 (batch)",
26159
- api: "openai-completions",
26160
- provider: "openrouter",
26161
- baseUrl: "https://openrouter.ai/api/v1",
26162
- reasoning: true,
26163
- thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
26164
- input: ["text"],
26165
- cost: {
26166
- input: 0.7,
26167
- output: 2.2,
26168
- cacheRead: 0.07,
26169
- cacheWrite: 0,
26170
- },
26171
- contextWindow: 1048576,
26172
- maxTokens: 943718,
26173
- },
26174
26602
  "z-ai/glm-5.3": {
26175
26603
  id: "z-ai/glm-5.3",
26176
26604
  name: "Z.ai: GLM 5.3",
@@ -26181,9 +26609,9 @@ export const MODELS = {
26181
26609
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26182
26610
  input: ["text"],
26183
26611
  cost: {
26184
- input: 0.9099999999999999,
26185
- output: 2.8600000000000003,
26186
- cacheRead: 0.16899999999999998,
26612
+ input: 0.6537999999999999,
26613
+ output: 2.0547999999999997,
26614
+ cacheRead: 0.12142000000000001,
26187
26615
  cacheWrite: 0,
26188
26616
  },
26189
26617
  contextWindow: 1310720,
@@ -26199,13 +26627,13 @@ export const MODELS = {
26199
26627
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26200
26628
  input: ["text", "image"],
26201
26629
  cost: {
26202
- input: 0.09,
26203
- output: 0.3,
26204
- cacheRead: 0.018,
26630
+ input: 0.15,
26631
+ output: 0.5,
26632
+ cacheRead: 0.049999999999999996,
26205
26633
  cacheWrite: 0,
26206
26634
  },
26207
26635
  contextWindow: 1310720,
26208
- maxTokens: 131072,
26636
+ maxTokens: 943718,
26209
26637
  },
26210
26638
  "z-ai/glm-5.3-flash:batch": {
26211
26639
  id: "z-ai/glm-5.3-flash:batch",
@@ -26217,13 +26645,13 @@ export const MODELS = {
26217
26645
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26218
26646
  input: ["text", "image"],
26219
26647
  cost: {
26220
- input: 0.075,
26221
- output: 0.25,
26222
- cacheRead: 0.015,
26648
+ input: 0.06,
26649
+ output: 0.19999999999999998,
26650
+ cacheRead: 0.012,
26223
26651
  cacheWrite: 0,
26224
26652
  },
26225
26653
  contextWindow: 1048576,
26226
- maxTokens: 943718,
26654
+ maxTokens: 131072,
26227
26655
  },
26228
26656
  "z-ai/glm-5.3-flashx": {
26229
26657
  id: "z-ai/glm-5.3-flashx",
@@ -26253,13 +26681,13 @@ export const MODELS = {
26253
26681
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26254
26682
  input: ["text"],
26255
26683
  cost: {
26256
- input: 0.7,
26257
- output: 2.2,
26258
- cacheRead: 0.13,
26684
+ input: 0.72,
26685
+ output: 2.4,
26686
+ cacheRead: 0.12,
26259
26687
  cacheWrite: 0,
26260
26688
  },
26261
26689
  contextWindow: 1048576,
26262
- maxTokens: 943718,
26690
+ maxTokens: 131072,
26263
26691
  },
26264
26692
  "z-ai/glm-5v-turbo": {
26265
26693
  id: "z-ai/glm-5v-turbo",
@@ -26320,13 +26748,13 @@ export const MODELS = {
26320
26748
  provider: "openrouter",
26321
26749
  baseUrl: "https://openrouter.ai/api/v1",
26322
26750
  reasoning: true,
26323
- thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
26751
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
26324
26752
  input: ["text", "image"],
26325
26753
  cost: {
26326
- input: 5,
26327
- output: 25,
26328
- cacheRead: 0.5,
26329
- cacheWrite: 6.25,
26754
+ input: 4,
26755
+ output: 20,
26756
+ cacheRead: 0.19999999999999998,
26757
+ cacheWrite: 5,
26330
26758
  },
26331
26759
  contextWindow: 1000000,
26332
26760
  maxTokens: 128000,
@@ -26359,9 +26787,9 @@ export const MODELS = {
26359
26787
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26360
26788
  input: ["text", "image"],
26361
26789
  cost: {
26362
- input: 0.13,
26363
- output: 0.52,
26364
- cacheRead: 0.0026000000000000003,
26790
+ input: 0.12,
26791
+ output: 0.48,
26792
+ cacheRead: 0.0036,
26365
26793
  cacheWrite: 0,
26366
26794
  },
26367
26795
  contextWindow: 1048576,
@@ -26377,9 +26805,9 @@ export const MODELS = {
26377
26805
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26378
26806
  input: ["text"],
26379
26807
  cost: {
26380
- input: 0.57816,
26381
- output: 1.73448,
26382
- cacheRead: 0.018396000000000003,
26808
+ input: 0.39996,
26809
+ output: 1.19988,
26810
+ cacheRead: 0.012726,
26383
26811
  cacheWrite: 0,
26384
26812
  },
26385
26813
  contextWindow: 1048576,
@@ -26396,9 +26824,9 @@ export const MODELS = {
26396
26824
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
26397
26825
  input: ["text"],
26398
26826
  cost: {
26399
- input: 0.04,
26400
- output: 0.08,
26401
- cacheRead: 0.016,
26827
+ input: 0.03,
26828
+ output: 0.7999999999999999,
26829
+ cacheRead: 0.008,
26402
26830
  cacheWrite: 0,
26403
26831
  },
26404
26832
  contextWindow: 1310720,
@@ -26450,9 +26878,9 @@ export const MODELS = {
26450
26878
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26451
26879
  input: ["text", "image"],
26452
26880
  cost: {
26453
- input: 1.7,
26454
- output: 8.5,
26455
- cacheRead: 0.16999999999999998,
26881
+ input: 1.4989,
26882
+ output: 10.758,
26883
+ cacheRead: 0.3,
26456
26884
  cacheWrite: 0,
26457
26885
  },
26458
26886
  contextWindow: 1048576,
@@ -26486,10 +26914,10 @@ export const MODELS = {
26486
26914
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
26487
26915
  input: ["text", "image"],
26488
26916
  cost: {
26489
- input: 0.19999999999999998,
26490
- output: 1.2,
26491
- cacheRead: 0.02,
26492
- cacheWrite: 0.25,
26917
+ input: 0.09999999999999999,
26918
+ output: 0.5,
26919
+ cacheRead: 0.01,
26920
+ cacheWrite: 0.125,
26493
26921
  },
26494
26922
  contextWindow: 1050000,
26495
26923
  maxTokens: 128000,
@@ -26558,9 +26986,9 @@ export const MODELS = {
26558
26986
  thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "max": null, "ultra": null },
26559
26987
  input: ["text", "image"],
26560
26988
  cost: {
26561
- input: 2,
26562
- output: 6,
26563
- cacheRead: 0.5,
26989
+ input: 1.5999999999999999,
26990
+ output: 4.8,
26991
+ cacheRead: 0.39999999999999997,
26564
26992
  cacheWrite: 0,
26565
26993
  },
26566
26994
  contextWindow: 500000,
@@ -26582,7 +27010,7 @@ export const MODELS = {
26582
27010
  cacheWrite: 0,
26583
27011
  },
26584
27012
  contextWindow: 1310720,
26585
- maxTokens: 131072,
27013
+ maxTokens: 943718,
26586
27014
  },
26587
27015
  "~z-ai/glm-latest": {
26588
27016
  id: "~z-ai/glm-latest",
@@ -26594,9 +27022,9 @@ export const MODELS = {
26594
27022
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26595
27023
  input: ["text"],
26596
27024
  cost: {
26597
- input: 0.8917999999999999,
26598
- output: 2.8028,
26599
- cacheRead: 0.16562,
27025
+ input: 0.6537999999999999,
27026
+ output: 2.0547999999999997,
27027
+ cacheRead: 0.12142000000000001,
26600
27028
  cacheWrite: 0,
26601
27029
  },
26602
27030
  contextWindow: 1310720,
@@ -27858,6 +28286,44 @@ export const MODELS = {
27858
28286
  contextWindow: 1000000,
27859
28287
  maxTokens: 128000,
27860
28288
  },
28289
+ "anthropic/claude-opus-5.5": {
28290
+ id: "anthropic/claude-opus-5.5",
28291
+ name: "Claude Opus 5.5",
28292
+ api: "anthropic-messages",
28293
+ provider: "vercel-ai-gateway",
28294
+ baseUrl: "https://ai-gateway.vercel.sh",
28295
+ compat: { "forceAdaptiveThinking": true },
28296
+ reasoning: true,
28297
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
28298
+ input: ["text", "image"],
28299
+ cost: {
28300
+ input: 4,
28301
+ output: 20,
28302
+ cacheRead: 0.19999999999999998,
28303
+ cacheWrite: 5,
28304
+ },
28305
+ contextWindow: 1000000,
28306
+ maxTokens: 128000,
28307
+ },
28308
+ "anthropic/claude-opus-5.5-fast": {
28309
+ id: "anthropic/claude-opus-5.5-fast",
28310
+ name: "Claude Opus 5.5 (Fast)",
28311
+ api: "anthropic-messages",
28312
+ provider: "vercel-ai-gateway",
28313
+ baseUrl: "https://ai-gateway.vercel.sh",
28314
+ compat: { "forceAdaptiveThinking": true },
28315
+ reasoning: true,
28316
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
28317
+ input: ["text", "image"],
28318
+ cost: {
28319
+ input: 8,
28320
+ output: 40,
28321
+ cacheRead: 0.39999999999999997,
28322
+ cacheWrite: 10,
28323
+ },
28324
+ contextWindow: 1000000,
28325
+ maxTokens: 128000,
28326
+ },
27861
28327
  "anthropic/claude-sonnet-4": {
27862
28328
  id: "anthropic/claude-sonnet-4",
27863
28329
  name: "Claude Sonnet 4",
@@ -28197,7 +28663,7 @@ export const MODELS = {
28197
28663
  cost: {
28198
28664
  input: 0.3,
28199
28665
  output: 1.2,
28200
- cacheRead: 0.03,
28666
+ cacheRead: 0.007,
28201
28667
  cacheWrite: 0,
28202
28668
  },
28203
28669
  contextWindow: 1048576,
@@ -29070,6 +29536,23 @@ export const MODELS = {
29070
29536
  contextWindow: 262144,
29071
29537
  maxTokens: 4000,
29072
29538
  },
29539
+ "mixedbread/toast-1": {
29540
+ id: "mixedbread/toast-1",
29541
+ name: "Toast 1",
29542
+ api: "anthropic-messages",
29543
+ provider: "vercel-ai-gateway",
29544
+ baseUrl: "https://ai-gateway.vercel.sh",
29545
+ reasoning: false,
29546
+ input: ["text"],
29547
+ cost: {
29548
+ input: 0.3,
29549
+ output: 0.72,
29550
+ cacheRead: 0.036,
29551
+ cacheWrite: 0,
29552
+ },
29553
+ contextWindow: 131000,
29554
+ maxTokens: 4000,
29555
+ },
29073
29556
  "moonshotai/kimi-k2": {
29074
29557
  id: "moonshotai/kimi-k2",
29075
29558
  name: "Kimi K2 Instruct",
@@ -30128,53 +30611,121 @@ export const MODELS = {
30128
30611
  contextWindow: 1050000,
30129
30612
  maxTokens: 128000,
30130
30613
  },
30131
- "openai/gpt-oss-120b": {
30132
- id: "openai/gpt-oss-120b",
30133
- name: "GPT OSS 120B",
30614
+ "openai/gpt-6-luna": {
30615
+ id: "openai/gpt-6-luna",
30616
+ name: "GPT-6 Luna",
30134
30617
  api: "anthropic-messages",
30135
30618
  provider: "vercel-ai-gateway",
30136
30619
  baseUrl: "https://ai-gateway.vercel.sh",
30137
30620
  reasoning: true,
30138
- input: ["text"],
30621
+ input: ["text", "image"],
30139
30622
  cost: {
30140
30623
  input: 0.09999999999999999,
30141
30624
  output: 0.5,
30142
- cacheRead: 0,
30143
- cacheWrite: 0,
30625
+ cacheRead: 0.01,
30626
+ cacheWrite: 0.125,
30144
30627
  },
30145
- contextWindow: 131072,
30146
- maxTokens: 131072,
30628
+ contextWindow: 1050000,
30629
+ maxTokens: 128000,
30147
30630
  },
30148
- "openai/gpt-oss-20b": {
30149
- id: "openai/gpt-oss-20b",
30150
- name: "GPT OSS 20B",
30631
+ "openai/gpt-6-luna-fast": {
30632
+ id: "openai/gpt-6-luna-fast",
30633
+ name: "GPT-6 Luna (Fast)",
30151
30634
  api: "anthropic-messages",
30152
30635
  provider: "vercel-ai-gateway",
30153
30636
  baseUrl: "https://ai-gateway.vercel.sh",
30154
30637
  reasoning: true,
30155
- input: ["text"],
30638
+ input: ["text", "image"],
30156
30639
  cost: {
30157
- input: 0.03,
30158
- output: 0.14,
30159
- cacheRead: 0,
30160
- cacheWrite: 0,
30640
+ input: 0.19999999999999998,
30641
+ output: 1,
30642
+ cacheRead: 0.02,
30643
+ cacheWrite: 0.25,
30161
30644
  },
30162
- contextWindow: 131072,
30163
- maxTokens: 8192,
30645
+ contextWindow: 1050000,
30646
+ maxTokens: 128000,
30164
30647
  },
30165
- "openai/gpt-oss-safeguard-120b": {
30166
- id: "openai/gpt-oss-safeguard-120b",
30167
- name: "GPT OSS Safeguard 120B",
30648
+ "openai/gpt-6-sol": {
30649
+ id: "openai/gpt-6-sol",
30650
+ name: "GPT-6 Sol",
30168
30651
  api: "anthropic-messages",
30169
30652
  provider: "vercel-ai-gateway",
30170
30653
  baseUrl: "https://ai-gateway.vercel.sh",
30171
30654
  reasoning: true,
30172
- input: ["text"],
30655
+ input: ["text", "image"],
30173
30656
  cost: {
30174
- input: 0.15,
30175
- output: 0.6,
30176
- cacheRead: 0,
30177
- cacheWrite: 0,
30657
+ input: 2,
30658
+ output: 10,
30659
+ cacheRead: 0.19999999999999998,
30660
+ cacheWrite: 2.5,
30661
+ },
30662
+ contextWindow: 1050000,
30663
+ maxTokens: 128000,
30664
+ },
30665
+ "openai/gpt-6-sol-fast": {
30666
+ id: "openai/gpt-6-sol-fast",
30667
+ name: "GPT-6 Sol (Fast)",
30668
+ api: "anthropic-messages",
30669
+ provider: "vercel-ai-gateway",
30670
+ baseUrl: "https://ai-gateway.vercel.sh",
30671
+ reasoning: true,
30672
+ input: ["text", "image"],
30673
+ cost: {
30674
+ input: 4,
30675
+ output: 20,
30676
+ cacheRead: 0.39999999999999997,
30677
+ cacheWrite: 5,
30678
+ },
30679
+ contextWindow: 1050000,
30680
+ maxTokens: 128000,
30681
+ },
30682
+ "openai/gpt-oss-120b": {
30683
+ id: "openai/gpt-oss-120b",
30684
+ name: "GPT OSS 120B",
30685
+ api: "anthropic-messages",
30686
+ provider: "vercel-ai-gateway",
30687
+ baseUrl: "https://ai-gateway.vercel.sh",
30688
+ reasoning: true,
30689
+ input: ["text"],
30690
+ cost: {
30691
+ input: 0.09999999999999999,
30692
+ output: 0.5,
30693
+ cacheRead: 0,
30694
+ cacheWrite: 0,
30695
+ },
30696
+ contextWindow: 131072,
30697
+ maxTokens: 131072,
30698
+ },
30699
+ "openai/gpt-oss-20b": {
30700
+ id: "openai/gpt-oss-20b",
30701
+ name: "GPT OSS 20B",
30702
+ api: "anthropic-messages",
30703
+ provider: "vercel-ai-gateway",
30704
+ baseUrl: "https://ai-gateway.vercel.sh",
30705
+ reasoning: true,
30706
+ input: ["text"],
30707
+ cost: {
30708
+ input: 0.03,
30709
+ output: 0.14,
30710
+ cacheRead: 0,
30711
+ cacheWrite: 0,
30712
+ },
30713
+ contextWindow: 131072,
30714
+ maxTokens: 8192,
30715
+ },
30716
+ "openai/gpt-oss-safeguard-120b": {
30717
+ id: "openai/gpt-oss-safeguard-120b",
30718
+ name: "GPT OSS Safeguard 120B",
30719
+ api: "anthropic-messages",
30720
+ provider: "vercel-ai-gateway",
30721
+ baseUrl: "https://ai-gateway.vercel.sh",
30722
+ reasoning: true,
30723
+ input: ["text"],
30724
+ cost: {
30725
+ input: 0.15,
30726
+ output: 0.6,
30727
+ cacheRead: 0,
30728
+ cacheWrite: 0,
30178
30729
  },
30179
30730
  contextWindow: 128000,
30180
30731
  maxTokens: 16000,
@@ -30349,6 +30900,40 @@ export const MODELS = {
30349
30900
  contextWindow: 256000,
30350
30901
  maxTokens: 32768,
30351
30902
  },
30903
+ "quiverai/arrow-2": {
30904
+ id: "quiverai/arrow-2",
30905
+ name: "Arrow 2",
30906
+ api: "anthropic-messages",
30907
+ provider: "vercel-ai-gateway",
30908
+ baseUrl: "https://ai-gateway.vercel.sh",
30909
+ reasoning: true,
30910
+ input: ["text", "image"],
30911
+ cost: {
30912
+ input: 4,
30913
+ output: 20,
30914
+ cacheRead: 0.39999999999999997,
30915
+ cacheWrite: 5,
30916
+ },
30917
+ contextWindow: 131072,
30918
+ maxTokens: 131072,
30919
+ },
30920
+ "quiverai/arrow-2-telos": {
30921
+ id: "quiverai/arrow-2-telos",
30922
+ name: "Arrow 2 Telos",
30923
+ api: "anthropic-messages",
30924
+ provider: "vercel-ai-gateway",
30925
+ baseUrl: "https://ai-gateway.vercel.sh",
30926
+ reasoning: true,
30927
+ input: ["text", "image"],
30928
+ cost: {
30929
+ input: 6,
30930
+ output: 30,
30931
+ cacheRead: 0.6,
30932
+ cacheWrite: 7.5,
30933
+ },
30934
+ contextWindow: 131072,
30935
+ maxTokens: 131072,
30936
+ },
30352
30937
  "sakana/fugu-max": {
30353
30938
  id: "sakana/fugu-max",
30354
30939
  name: "Fugu Max",
@@ -30606,6 +31191,24 @@ export const MODELS = {
30606
31191
  contextWindow: 500000,
30607
31192
  maxTokens: 500000,
30608
31193
  },
31194
+ "spacexai/grok-4.7": {
31195
+ id: "spacexai/grok-4.7",
31196
+ name: "Grok 4.7",
31197
+ api: "anthropic-messages",
31198
+ provider: "vercel-ai-gateway",
31199
+ baseUrl: "https://ai-gateway.vercel.sh",
31200
+ reasoning: true,
31201
+ thinkingLevelMap: { "xhigh": "xhigh" },
31202
+ input: ["text", "image"],
31203
+ cost: {
31204
+ input: 1.2,
31205
+ output: 3.5999999999999996,
31206
+ cacheRead: 0.3,
31207
+ cacheWrite: 0,
31208
+ },
31209
+ contextWindow: 500000,
31210
+ maxTokens: 500000,
31211
+ },
30609
31212
  "spacexai/grok-build-0.1": {
30610
31213
  id: "spacexai/grok-build-0.1",
30611
31214
  name: "Grok Build 0.1",
@@ -30759,6 +31362,57 @@ export const MODELS = {
30759
31362
  contextWindow: 1050000,
30760
31363
  maxTokens: 131000,
30761
31364
  },
31365
+ "xiaomi/mimo-v2.6-flash": {
31366
+ id: "xiaomi/mimo-v2.6-flash",
31367
+ name: "MiMo V2.6 Flash",
31368
+ api: "anthropic-messages",
31369
+ provider: "vercel-ai-gateway",
31370
+ baseUrl: "https://ai-gateway.vercel.sh",
31371
+ reasoning: true,
31372
+ input: ["text", "image"],
31373
+ cost: {
31374
+ input: 0.14,
31375
+ output: 0.28,
31376
+ cacheRead: 0.0028,
31377
+ cacheWrite: 0,
31378
+ },
31379
+ contextWindow: 1048576,
31380
+ maxTokens: 131072,
31381
+ },
31382
+ "xiaomi/mimo-v2.6-pro": {
31383
+ id: "xiaomi/mimo-v2.6-pro",
31384
+ name: "MiMo V2.6 Pro",
31385
+ api: "anthropic-messages",
31386
+ provider: "vercel-ai-gateway",
31387
+ baseUrl: "https://ai-gateway.vercel.sh",
31388
+ reasoning: true,
31389
+ input: ["text", "image"],
31390
+ cost: {
31391
+ input: 0.435,
31392
+ output: 0.87,
31393
+ cacheRead: 0.0036,
31394
+ cacheWrite: 0,
31395
+ },
31396
+ contextWindow: 1048576,
31397
+ maxTokens: 131072,
31398
+ },
31399
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
31400
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
31401
+ name: "MiMo V2.6 Pro UltraSpeed",
31402
+ api: "anthropic-messages",
31403
+ provider: "vercel-ai-gateway",
31404
+ baseUrl: "https://ai-gateway.vercel.sh",
31405
+ reasoning: true,
31406
+ input: ["text", "image"],
31407
+ cost: {
31408
+ input: 4.35,
31409
+ output: 8.7,
31410
+ cacheRead: 0.036,
31411
+ cacheWrite: 0,
31412
+ },
31413
+ contextWindow: 1048576,
31414
+ maxTokens: 131072,
31415
+ },
30762
31416
  "zai/glm-4.5": {
30763
31417
  id: "zai/glm-4.5",
30764
31418
  name: "GLM 4.5",
@@ -31691,6 +32345,24 @@ export const MODELS = {
31691
32345
  contextWindow: 500000,
31692
32346
  maxTokens: 500000,
31693
32347
  },
32348
+ "grok-4.7": {
32349
+ id: "grok-4.7",
32350
+ name: "Grok 4.7",
32351
+ api: "openai-completions",
32352
+ provider: "xai",
32353
+ baseUrl: "https://api.x.ai/v1",
32354
+ reasoning: true,
32355
+ thinkingLevelMap: { "xhigh": "xhigh" },
32356
+ input: ["text", "image"],
32357
+ cost: {
32358
+ input: 2,
32359
+ output: 6,
32360
+ cacheRead: 0.5,
32361
+ cacheWrite: 0,
32362
+ },
32363
+ contextWindow: 500000,
32364
+ maxTokens: 500000,
32365
+ },
31694
32366
  "grok-build-0.1": {
31695
32367
  id: "grok-build-0.1",
31696
32368
  name: "Grok Build 0.1",
@@ -31835,6 +32507,60 @@ export const MODELS = {
31835
32507
  contextWindow: 1048576,
31836
32508
  maxTokens: 131072,
31837
32509
  },
32510
+ "mimo-v2.6-flash": {
32511
+ id: "mimo-v2.6-flash",
32512
+ name: "MiMo-V2.6-Flash",
32513
+ api: "openai-completions",
32514
+ provider: "xiaomi",
32515
+ baseUrl: "https://api.xiaomimimo.com/v1",
32516
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32517
+ reasoning: true,
32518
+ input: ["text", "image"],
32519
+ cost: {
32520
+ input: 0.14,
32521
+ output: 0.28,
32522
+ cacheRead: 0.0028,
32523
+ cacheWrite: 0,
32524
+ },
32525
+ contextWindow: 1048576,
32526
+ maxTokens: 131072,
32527
+ },
32528
+ "mimo-v2.6-pro": {
32529
+ id: "mimo-v2.6-pro",
32530
+ name: "MiMo-V2.6-Pro",
32531
+ api: "openai-completions",
32532
+ provider: "xiaomi",
32533
+ baseUrl: "https://api.xiaomimimo.com/v1",
32534
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32535
+ reasoning: true,
32536
+ input: ["text", "image"],
32537
+ cost: {
32538
+ input: 0.435,
32539
+ output: 0.87,
32540
+ cacheRead: 0.0036,
32541
+ cacheWrite: 0,
32542
+ },
32543
+ contextWindow: 1048576,
32544
+ maxTokens: 131072,
32545
+ },
32546
+ "mimo-v2.6-pro-ultraspeed": {
32547
+ id: "mimo-v2.6-pro-ultraspeed",
32548
+ name: "MiMo-V2.6-Pro-UltraSpeed",
32549
+ api: "openai-completions",
32550
+ provider: "xiaomi",
32551
+ baseUrl: "https://api.xiaomimimo.com/v1",
32552
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32553
+ reasoning: true,
32554
+ input: ["text", "image"],
32555
+ cost: {
32556
+ input: 4.35,
32557
+ output: 8.7,
32558
+ cacheRead: 0.036,
32559
+ cacheWrite: 0,
32560
+ },
32561
+ contextWindow: 1048576,
32562
+ maxTokens: 131072,
32563
+ },
31838
32564
  },
31839
32565
  "xiaomi-token-plan-ams": {
31840
32566
  "mimo-v2-omni": {
@@ -31927,6 +32653,60 @@ export const MODELS = {
31927
32653
  contextWindow: 1048576,
31928
32654
  maxTokens: 131072,
31929
32655
  },
32656
+ "mimo-v2.6-flash": {
32657
+ id: "mimo-v2.6-flash",
32658
+ name: "MiMo-V2.6-Flash",
32659
+ api: "openai-completions",
32660
+ provider: "xiaomi-token-plan-ams",
32661
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
32662
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32663
+ reasoning: true,
32664
+ input: ["text", "image"],
32665
+ cost: {
32666
+ input: 0.14,
32667
+ output: 0.28,
32668
+ cacheRead: 0.0028,
32669
+ cacheWrite: 0,
32670
+ },
32671
+ contextWindow: 1048576,
32672
+ maxTokens: 131072,
32673
+ },
32674
+ "mimo-v2.6-pro": {
32675
+ id: "mimo-v2.6-pro",
32676
+ name: "MiMo-V2.6-Pro",
32677
+ api: "openai-completions",
32678
+ provider: "xiaomi-token-plan-ams",
32679
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
32680
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32681
+ reasoning: true,
32682
+ input: ["text", "image"],
32683
+ cost: {
32684
+ input: 0.435,
32685
+ output: 0.87,
32686
+ cacheRead: 0.0036,
32687
+ cacheWrite: 0,
32688
+ },
32689
+ contextWindow: 1048576,
32690
+ maxTokens: 131072,
32691
+ },
32692
+ "mimo-v2.6-pro-ultraspeed": {
32693
+ id: "mimo-v2.6-pro-ultraspeed",
32694
+ name: "MiMo-V2.6-Pro-UltraSpeed",
32695
+ api: "openai-completions",
32696
+ provider: "xiaomi-token-plan-ams",
32697
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
32698
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32699
+ reasoning: true,
32700
+ input: ["text", "image"],
32701
+ cost: {
32702
+ input: 4.35,
32703
+ output: 8.7,
32704
+ cacheRead: 0.036,
32705
+ cacheWrite: 0,
32706
+ },
32707
+ contextWindow: 1048576,
32708
+ maxTokens: 131072,
32709
+ },
31930
32710
  },
31931
32711
  "xiaomi-token-plan-cn": {
31932
32712
  "mimo-v2-omni": {
@@ -32019,6 +32799,60 @@ export const MODELS = {
32019
32799
  contextWindow: 1048576,
32020
32800
  maxTokens: 131072,
32021
32801
  },
32802
+ "mimo-v2.6-flash": {
32803
+ id: "mimo-v2.6-flash",
32804
+ name: "MiMo-V2.6-Flash",
32805
+ api: "openai-completions",
32806
+ provider: "xiaomi-token-plan-cn",
32807
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
32808
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32809
+ reasoning: true,
32810
+ input: ["text", "image"],
32811
+ cost: {
32812
+ input: 0.14,
32813
+ output: 0.28,
32814
+ cacheRead: 0.0028,
32815
+ cacheWrite: 0,
32816
+ },
32817
+ contextWindow: 1048576,
32818
+ maxTokens: 131072,
32819
+ },
32820
+ "mimo-v2.6-pro": {
32821
+ id: "mimo-v2.6-pro",
32822
+ name: "MiMo-V2.6-Pro",
32823
+ api: "openai-completions",
32824
+ provider: "xiaomi-token-plan-cn",
32825
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
32826
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32827
+ reasoning: true,
32828
+ input: ["text", "image"],
32829
+ cost: {
32830
+ input: 0.435,
32831
+ output: 0.87,
32832
+ cacheRead: 0.0036,
32833
+ cacheWrite: 0,
32834
+ },
32835
+ contextWindow: 1048576,
32836
+ maxTokens: 131072,
32837
+ },
32838
+ "mimo-v2.6-pro-ultraspeed": {
32839
+ id: "mimo-v2.6-pro-ultraspeed",
32840
+ name: "MiMo-V2.6-Pro-UltraSpeed",
32841
+ api: "openai-completions",
32842
+ provider: "xiaomi-token-plan-cn",
32843
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
32844
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32845
+ reasoning: true,
32846
+ input: ["text", "image"],
32847
+ cost: {
32848
+ input: 4.35,
32849
+ output: 8.7,
32850
+ cacheRead: 0.036,
32851
+ cacheWrite: 0,
32852
+ },
32853
+ contextWindow: 1048576,
32854
+ maxTokens: 131072,
32855
+ },
32022
32856
  },
32023
32857
  "xiaomi-token-plan-sgp": {
32024
32858
  "mimo-v2-omni": {
@@ -32111,6 +32945,60 @@ export const MODELS = {
32111
32945
  contextWindow: 1048576,
32112
32946
  maxTokens: 131072,
32113
32947
  },
32948
+ "mimo-v2.6-flash": {
32949
+ id: "mimo-v2.6-flash",
32950
+ name: "MiMo-V2.6-Flash",
32951
+ api: "openai-completions",
32952
+ provider: "xiaomi-token-plan-sgp",
32953
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
32954
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32955
+ reasoning: true,
32956
+ input: ["text", "image"],
32957
+ cost: {
32958
+ input: 0.14,
32959
+ output: 0.28,
32960
+ cacheRead: 0.0028,
32961
+ cacheWrite: 0,
32962
+ },
32963
+ contextWindow: 1048576,
32964
+ maxTokens: 131072,
32965
+ },
32966
+ "mimo-v2.6-pro": {
32967
+ id: "mimo-v2.6-pro",
32968
+ name: "MiMo-V2.6-Pro",
32969
+ api: "openai-completions",
32970
+ provider: "xiaomi-token-plan-sgp",
32971
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
32972
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32973
+ reasoning: true,
32974
+ input: ["text", "image"],
32975
+ cost: {
32976
+ input: 0.435,
32977
+ output: 0.87,
32978
+ cacheRead: 0.0036,
32979
+ cacheWrite: 0,
32980
+ },
32981
+ contextWindow: 1048576,
32982
+ maxTokens: 131072,
32983
+ },
32984
+ "mimo-v2.6-pro-ultraspeed": {
32985
+ id: "mimo-v2.6-pro-ultraspeed",
32986
+ name: "MiMo-V2.6-Pro-UltraSpeed",
32987
+ api: "openai-completions",
32988
+ provider: "xiaomi-token-plan-sgp",
32989
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
32990
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
32991
+ reasoning: true,
32992
+ input: ["text", "image"],
32993
+ cost: {
32994
+ input: 4.35,
32995
+ output: 8.7,
32996
+ cacheRead: 0.036,
32997
+ cacheWrite: 0,
32998
+ },
32999
+ contextWindow: 1048576,
33000
+ maxTokens: 131072,
33001
+ },
32114
33002
  },
32115
33003
  "zai": {
32116
33004
  "glm-4.7": {