omk-ai 1.0.0 → 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 (52) hide show
  1. package/CHANGELOG.md +29 -1
  2. package/README.md +2 -0
  3. package/dist/env-api-keys.d.ts.map +1 -1
  4. package/dist/env-api-keys.js +1 -0
  5. package/dist/env-api-keys.js.map +1 -1
  6. package/dist/models.d.ts.map +1 -1
  7. package/dist/models.generated.d.ts +2490 -369
  8. package/dist/models.generated.d.ts.map +1 -1
  9. package/dist/models.generated.js +1922 -444
  10. package/dist/models.generated.js.map +1 -1
  11. package/dist/models.js +4 -1
  12. package/dist/models.js.map +1 -1
  13. package/dist/provider-response-types.d.ts +15 -0
  14. package/dist/provider-response-types.d.ts.map +1 -0
  15. package/dist/provider-response-types.js +2 -0
  16. package/dist/provider-response-types.js.map +1 -0
  17. package/dist/providers/anthropic.d.ts.map +1 -1
  18. package/dist/providers/anthropic.js +2 -23
  19. package/dist/providers/anthropic.js.map +1 -1
  20. package/dist/providers/bedrock-thinking.d.ts.map +1 -1
  21. package/dist/providers/bedrock-thinking.js +2 -2
  22. package/dist/providers/bedrock-thinking.js.map +1 -1
  23. package/dist/providers/google-shared.d.ts.map +1 -1
  24. package/dist/providers/google-shared.js +13 -6
  25. package/dist/providers/google-shared.js.map +1 -1
  26. package/dist/providers/grok-thinking.d.ts.map +1 -1
  27. package/dist/providers/grok-thinking.js +10 -0
  28. package/dist/providers/grok-thinking.js.map +1 -1
  29. package/dist/providers/openai-completions-compat.d.ts.map +1 -1
  30. package/dist/providers/openai-completions-compat.js +2 -0
  31. package/dist/providers/openai-completions-compat.js.map +1 -1
  32. package/dist/providers/openai-completions.d.ts.map +1 -1
  33. package/dist/providers/openai-completions.js +22 -29
  34. package/dist/providers/openai-completions.js.map +1 -1
  35. package/dist/providers/openai-responses-shared.d.ts.map +1 -1
  36. package/dist/providers/openai-responses-shared.js +10 -23
  37. package/dist/providers/openai-responses-shared.js.map +1 -1
  38. package/dist/providers/provider-stop-reasons.d.ts +9 -0
  39. package/dist/providers/provider-stop-reasons.d.ts.map +1 -0
  40. package/dist/providers/provider-stop-reasons.js +63 -0
  41. package/dist/providers/provider-stop-reasons.js.map +1 -0
  42. package/dist/types.d.ts +13 -15
  43. package/dist/types.d.ts.map +1 -1
  44. package/dist/types.js.map +1 -1
  45. package/dist/utils/claude-code-identity.d.ts +4 -4
  46. package/dist/utils/claude-code-identity.d.ts.map +1 -1
  47. package/dist/utils/claude-code-identity.js +1 -1
  48. package/dist/utils/claude-code-identity.js.map +1 -1
  49. package/dist/utils/validation.d.ts.map +1 -1
  50. package/dist/utils/validation.js +9 -21
  51. package/dist/utils/validation.js.map +1 -1
  52. 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",
@@ -18480,6 +18716,25 @@ export const MODELS = {
18480
18716
  contextWindow: 1000000,
18481
18717
  maxTokens: 384000,
18482
18718
  },
18719
+ "deepseek-v4.1-flash": {
18720
+ id: "deepseek-v4.1-flash",
18721
+ name: "DeepSeek V4.1 Flash",
18722
+ api: "openai-completions",
18723
+ provider: "opencode",
18724
+ baseUrl: "https://opencode.ai/zen/v1",
18725
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "supportsReasoningEffort": true, "maxTokensField": "max_tokens" },
18726
+ reasoning: true,
18727
+ thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
18728
+ input: ["text", "image"],
18729
+ cost: {
18730
+ input: 0.3,
18731
+ output: 1.2,
18732
+ cacheRead: 0.006,
18733
+ cacheWrite: 0,
18734
+ },
18735
+ contextWindow: 1000000,
18736
+ maxTokens: 384000,
18737
+ },
18483
18738
  "gemini-3-flash": {
18484
18739
  id: "gemini-3-flash",
18485
18740
  name: "Gemini 3 Flash",
@@ -19002,7 +19257,7 @@ export const MODELS = {
19002
19257
  },
19003
19258
  "gpt-5.6-sol": {
19004
19259
  id: "gpt-5.6-sol",
19005
- name: "GPT-5.6 Sol (50% Off)",
19260
+ name: "GPT-5.6 Sol",
19006
19261
  api: "openai-responses",
19007
19262
  provider: "opencode",
19008
19263
  baseUrl: "https://opencode.ai/zen/v1",
@@ -19010,13 +19265,13 @@ export const MODELS = {
19010
19265
  thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
19011
19266
  input: ["text", "image"],
19012
19267
  cost: {
19013
- input: 2,
19014
- output: 10,
19015
- cacheRead: 0.2,
19016
- cacheWrite: 2.5,
19017
- },
19018
- contextWindow: 1000000,
19019
- maxTokens: 128000,
19268
+ input: 4,
19269
+ output: 20,
19270
+ cacheRead: 0.4,
19271
+ cacheWrite: 5,
19272
+ },
19273
+ contextWindow: 1000000,
19274
+ maxTokens: 128000,
19020
19275
  },
19021
19276
  "gpt-5.6-terra": {
19022
19277
  id: "gpt-5.6-terra",
@@ -19054,6 +19309,42 @@ export const MODELS = {
19054
19309
  contextWindow: 1050000,
19055
19310
  maxTokens: 128000,
19056
19311
  },
19312
+ "gpt-6-luna": {
19313
+ id: "gpt-6-luna",
19314
+ name: "GPT-6 Luna",
19315
+ api: "openai-responses",
19316
+ provider: "opencode",
19317
+ baseUrl: "https://opencode.ai/zen/v1",
19318
+ reasoning: true,
19319
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
19320
+ input: ["text", "image"],
19321
+ cost: {
19322
+ input: 0.1,
19323
+ output: 0.5,
19324
+ cacheRead: 0.01,
19325
+ cacheWrite: 0.125,
19326
+ },
19327
+ contextWindow: 1050000,
19328
+ maxTokens: 128000,
19329
+ },
19330
+ "gpt-6-sol": {
19331
+ id: "gpt-6-sol",
19332
+ name: "GPT-6 Sol",
19333
+ api: "openai-responses",
19334
+ provider: "opencode",
19335
+ baseUrl: "https://opencode.ai/zen/v1",
19336
+ reasoning: true,
19337
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
19338
+ input: ["text", "image"],
19339
+ cost: {
19340
+ input: 2,
19341
+ output: 10,
19342
+ cacheRead: 0.2,
19343
+ cacheWrite: 2.5,
19344
+ },
19345
+ contextWindow: 1050000,
19346
+ maxTokens: 128000,
19347
+ },
19057
19348
  "grok-4.5": {
19058
19349
  id: "grok-4.5",
19059
19350
  name: "Grok 4.5",
@@ -19193,9 +19484,9 @@ export const MODELS = {
19193
19484
  contextWindow: 262144,
19194
19485
  maxTokens: 32768,
19195
19486
  },
19196
- "mimo-v2.5-free": {
19197
- id: "mimo-v2.5-free",
19198
- 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",
19199
19490
  api: "openai-completions",
19200
19491
  provider: "opencode",
19201
19492
  baseUrl: "https://opencode.ai/zen/v1",
@@ -19403,6 +19694,24 @@ export const MODELS = {
19403
19694
  contextWindow: 262144,
19404
19695
  maxTokens: 65536,
19405
19696
  },
19697
+ "qwen3.8-flash": {
19698
+ id: "qwen3.8-flash",
19699
+ name: "Qwen3.8 Flash",
19700
+ api: "anthropic-messages",
19701
+ provider: "opencode",
19702
+ baseUrl: "https://opencode.ai/zen",
19703
+ reasoning: true,
19704
+ thinkingLevelMap: { "xhigh": "high", "max": "max" },
19705
+ input: ["text", "image"],
19706
+ cost: {
19707
+ input: 0.15,
19708
+ output: 0.47,
19709
+ cacheRead: 0.016,
19710
+ cacheWrite: 0.2,
19711
+ },
19712
+ contextWindow: 1000000,
19713
+ maxTokens: 131072,
19714
+ },
19406
19715
  },
19407
19716
  "opencode-go": {
19408
19717
  "deepseek-v4-flash": {
@@ -19588,6 +19897,24 @@ export const MODELS = {
19588
19897
  contextWindow: 500000,
19589
19898
  maxTokens: 500000,
19590
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
+ },
19591
19918
  "hy3": {
19592
19919
  id: "hy3",
19593
19920
  name: "Hy3",
@@ -19726,6 +20053,40 @@ export const MODELS = {
19726
20053
  contextWindow: 1048576,
19727
20054
  maxTokens: 128000,
19728
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
+ },
19729
20090
  "minimax-m2.7": {
19730
20091
  id: "minimax-m2.7",
19731
20092
  name: "MiniMax-M2.7",
@@ -19738,7 +20099,7 @@ export const MODELS = {
19738
20099
  input: 0.3,
19739
20100
  output: 1.2,
19740
20101
  cacheRead: 0.06,
19741
- cacheWrite: 0,
20102
+ cacheWrite: 0.375,
19742
20103
  },
19743
20104
  contextWindow: 204800,
19744
20105
  maxTokens: 131072,
@@ -19904,7 +20265,7 @@ export const MODELS = {
19904
20265
  cacheRead: 0.19999999999999998,
19905
20266
  cacheWrite: 0,
19906
20267
  },
19907
- contextWindow: 131072,
20268
+ contextWindow: 1048576,
19908
20269
  maxTokens: 32768,
19909
20270
  },
19910
20271
  "aion-labs/aion-3.0": {
@@ -19922,7 +20283,7 @@ export const MODELS = {
19922
20283
  cacheRead: 0.75,
19923
20284
  cacheWrite: 0,
19924
20285
  },
19925
- contextWindow: 131072,
20286
+ contextWindow: 1048576,
19926
20287
  maxTokens: 32768,
19927
20288
  },
19928
20289
  "aion-labs/aion-3.0-mini": {
@@ -19940,7 +20301,7 @@ export const MODELS = {
19940
20301
  cacheRead: 0.18,
19941
20302
  cacheWrite: 0,
19942
20303
  },
19943
- contextWindow: 131072,
20304
+ contextWindow: 1048576,
19944
20305
  maxTokens: 32768,
19945
20306
  },
19946
20307
  "amazon/nova-2-lite-v1": {
@@ -20151,23 +20512,6 @@ export const MODELS = {
20151
20512
  contextWindow: 200000,
20152
20513
  maxTokens: 64000,
20153
20514
  },
20154
- "anthropic/claude-opus-4": {
20155
- id: "anthropic/claude-opus-4",
20156
- name: "Anthropic: Claude Opus 4",
20157
- api: "openai-completions",
20158
- provider: "openrouter",
20159
- baseUrl: "https://openrouter.ai/api/v1",
20160
- reasoning: true,
20161
- input: ["text", "image"],
20162
- cost: {
20163
- input: 15,
20164
- output: 75,
20165
- cacheRead: 1.5,
20166
- cacheWrite: 18.75,
20167
- },
20168
- contextWindow: 200000,
20169
- maxTokens: 32000,
20170
- },
20171
20515
  "anthropic/claude-opus-4.1": {
20172
20516
  id: "anthropic/claude-opus-4.1",
20173
20517
  name: "Anthropic: Claude Opus 4.1",
@@ -20362,6 +20706,42 @@ export const MODELS = {
20362
20706
  contextWindow: 1000000,
20363
20707
  maxTokens: 128000,
20364
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
+ },
20365
20745
  "anthropic/claude-opus-5:batch": {
20366
20746
  id: "anthropic/claude-opus-5:batch",
20367
20747
  name: "Anthropic: Claude Opus 5 (batch)",
@@ -20394,7 +20774,7 @@ export const MODELS = {
20394
20774
  cacheRead: 0.3,
20395
20775
  cacheWrite: 3.75,
20396
20776
  },
20397
- contextWindow: 1000000,
20777
+ contextWindow: 200000,
20398
20778
  maxTokens: 64000,
20399
20779
  },
20400
20780
  "anthropic/claude-sonnet-4.5": {
@@ -20843,9 +21223,9 @@ export const MODELS = {
20843
21223
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "off": "none", "max": null, "ultra": null },
20844
21224
  input: ["text"],
20845
21225
  cost: {
20846
- input: 0.088606,
20847
- output: 0.177212,
20848
- cacheRead: 0.017721200000000003,
21226
+ input: 0.049,
21227
+ output: 0.098,
21228
+ cacheRead: 0.0098,
20849
21229
  cacheWrite: 0,
20850
21230
  },
20851
21231
  contextWindow: 1048576,
@@ -20862,52 +21242,14 @@ export const MODELS = {
20862
21242
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20863
21243
  input: ["text"],
20864
21244
  cost: {
20865
- input: 0.06,
20866
- output: 0.12,
20867
- cacheRead: 0.012,
21245
+ input: 0.04,
21246
+ output: 0.64,
21247
+ cacheRead: 0.016,
20868
21248
  cacheWrite: 0,
20869
21249
  },
20870
21250
  contextWindow: 1310720,
20871
21251
  maxTokens: 943718,
20872
21252
  },
20873
- "deepseek/deepseek-v4-flash-0731:batch": {
20874
- id: "deepseek/deepseek-v4-flash-0731:batch",
20875
- name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
20876
- api: "openai-completions",
20877
- provider: "openrouter",
20878
- baseUrl: "https://openrouter.ai/api/v1",
20879
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20880
- reasoning: true,
20881
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20882
- input: ["text"],
20883
- cost: {
20884
- input: 0.11,
20885
- output: 0.33,
20886
- cacheRead: 0.0035,
20887
- cacheWrite: 0,
20888
- },
20889
- contextWindow: 1048576,
20890
- maxTokens: 943718,
20891
- },
20892
- "deepseek/deepseek-v4-flash-0731:free": {
20893
- id: "deepseek/deepseek-v4-flash-0731:free",
20894
- name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
20895
- api: "openai-completions",
20896
- provider: "openrouter",
20897
- baseUrl: "https://openrouter.ai/api/v1",
20898
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20899
- reasoning: true,
20900
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20901
- input: ["text"],
20902
- cost: {
20903
- input: 0,
20904
- output: 0,
20905
- cacheRead: 0,
20906
- cacheWrite: 0,
20907
- },
20908
- contextWindow: 1048576,
20909
- maxTokens: 393216,
20910
- },
20911
21253
  "deepseek/deepseek-v4-flash-vision-exp": {
20912
21254
  id: "deepseek/deepseek-v4-flash-vision-exp",
20913
21255
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -20919,28 +21261,9 @@ export const MODELS = {
20919
21261
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20920
21262
  input: ["text", "image"],
20921
21263
  cost: {
20922
- input: 0.21559999999999999,
20923
- output: 0.6468,
20924
- cacheRead: 0.00686,
20925
- cacheWrite: 0,
20926
- },
20927
- contextWindow: 1048576,
20928
- maxTokens: 262144,
20929
- },
20930
- "deepseek/deepseek-v4-flash-vision-exp:batch": {
20931
- id: "deepseek/deepseek-v4-flash-vision-exp:batch",
20932
- name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
20933
- api: "openai-completions",
20934
- provider: "openrouter",
20935
- baseUrl: "https://openrouter.ai/api/v1",
20936
- compat: { "requiresReasoningContentOnAssistantMessages": true },
20937
- reasoning: true,
20938
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20939
- input: ["text", "image"],
20940
- cost: {
20941
- input: 0.11,
20942
- output: 0.33,
20943
- cacheRead: 0.0035,
21264
+ input: 0.22,
21265
+ output: 0.66,
21266
+ cacheRead: 0.007,
20944
21267
  cacheWrite: 0,
20945
21268
  },
20946
21269
  contextWindow: 1048576,
@@ -20957,13 +21280,13 @@ export const MODELS = {
20957
21280
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "off": "none", "max": null, "ultra": null },
20958
21281
  input: ["text"],
20959
21282
  cost: {
20960
- input: 1.5999999999999999,
20961
- output: 3.1999999999999997,
20962
- cacheRead: 0.135,
21283
+ input: 0.895578,
21284
+ output: 1.791156,
21285
+ cacheRead: 0.0746315,
20963
21286
  cacheWrite: 0,
20964
21287
  },
20965
21288
  contextWindow: 1048576,
20966
- maxTokens: 393216,
21289
+ maxTokens: 384000,
20967
21290
  },
20968
21291
  "deepseek/deepseek-v4-pro-0813": {
20969
21292
  id: "deepseek/deepseek-v4-pro-0813",
@@ -20976,36 +21299,36 @@ export const MODELS = {
20976
21299
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20977
21300
  input: ["text"],
20978
21301
  cost: {
20979
- input: 1.32,
20980
- output: 3.9600000000000004,
20981
- cacheRead: 0.044,
21302
+ input: 0.66,
21303
+ output: 1.9800000000000002,
21304
+ cacheRead: 0.022,
20982
21305
  cacheWrite: 0,
20983
21306
  },
20984
21307
  contextWindow: 1048576,
20985
21308
  maxTokens: 384000,
20986
21309
  },
20987
- "deepseek/deepseek-v4-pro-0813:batch": {
20988
- id: "deepseek/deepseek-v4-pro-0813:batch",
20989
- 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",
20990
21313
  api: "openai-completions",
20991
21314
  provider: "openrouter",
20992
21315
  baseUrl: "https://openrouter.ai/api/v1",
20993
21316
  compat: { "requiresReasoningContentOnAssistantMessages": true },
20994
21317
  reasoning: true,
20995
21318
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
20996
- input: ["text"],
21319
+ input: ["text", "image"],
20997
21320
  cost: {
20998
- input: 0.66,
20999
- output: 1.9800000000000002,
21000
- cacheRead: 0.022,
21321
+ input: 0.15,
21322
+ output: 0.6,
21323
+ cacheRead: 0.003,
21001
21324
  cacheWrite: 0,
21002
21325
  },
21003
21326
  contextWindow: 1048576,
21004
- maxTokens: 943718,
21327
+ maxTokens: 384000,
21005
21328
  },
21006
- "deepseek/deepseek-v4.1-flash": {
21007
- id: "deepseek/deepseek-v4.1-flash",
21008
- 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)",
21009
21332
  api: "openai-completions",
21010
21333
  provider: "openrouter",
21011
21334
  baseUrl: "https://openrouter.ai/api/v1",
@@ -21014,13 +21337,13 @@ export const MODELS = {
21014
21337
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
21015
21338
  input: ["text", "image"],
21016
21339
  cost: {
21017
- input: 0.3,
21018
- output: 1.2,
21019
- cacheRead: 0.006,
21340
+ input: 0.112,
21341
+ output: 0.33599999999999997,
21342
+ cacheRead: 0.00336,
21020
21343
  cacheWrite: 0,
21021
21344
  },
21022
21345
  contextWindow: 1048576,
21023
- maxTokens: 384000,
21346
+ maxTokens: 131072,
21024
21347
  },
21025
21348
  "dots-studio/dots-3-note-preview:free": {
21026
21349
  id: "dots-studio/dots-3-note-preview:free",
@@ -21761,23 +22084,6 @@ export const MODELS = {
21761
22084
  contextWindow: 262144,
21762
22085
  maxTokens: 32768,
21763
22086
  },
21764
- "kwaipilot/kat-coder-pro-v2": {
21765
- id: "kwaipilot/kat-coder-pro-v2",
21766
- name: "Kwaipilot: KAT-Coder-Pro V2",
21767
- api: "openai-completions",
21768
- provider: "openrouter",
21769
- baseUrl: "https://openrouter.ai/api/v1",
21770
- reasoning: false,
21771
- input: ["text"],
21772
- cost: {
21773
- input: 0.3,
21774
- output: 1.2,
21775
- cacheRead: 0.06,
21776
- cacheWrite: 0,
21777
- },
21778
- contextWindow: 262144,
21779
- maxTokens: 144000,
21780
- },
21781
22087
  "kwaipilot/kat-coder-pro-v2.5": {
21782
22088
  id: "kwaipilot/kat-coder-pro-v2.5",
21783
22089
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -21926,34 +22232,16 @@ export const MODELS = {
21926
22232
  input: ["text", "image"],
21927
22233
  cost: {
21928
22234
  input: 0.3,
21929
- output: 1.1,
22235
+ output: 1.2,
21930
22236
  cacheRead: 0.04,
21931
22237
  cacheWrite: 0,
21932
22238
  },
21933
22239
  contextWindow: 131072,
21934
- maxTokens: 117964,
22240
+ maxTokens: 16384,
21935
22241
  },
21936
- "meta/muse-glimmer-30b:batch": {
21937
- id: "meta/muse-glimmer-30b:batch",
21938
- name: "Meta: Muse Glimmer 30B (batch)",
21939
- api: "openai-completions",
21940
- provider: "openrouter",
21941
- baseUrl: "https://openrouter.ai/api/v1",
21942
- reasoning: true,
21943
- thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
21944
- input: ["text", "image"],
21945
- cost: {
21946
- input: 0.175,
21947
- output: 0.75,
21948
- cacheRead: 0.02,
21949
- cacheWrite: 0,
21950
- },
21951
- contextWindow: 131072,
21952
- maxTokens: 117964,
21953
- },
21954
- "meta/muse-spark-1.1": {
21955
- id: "meta/muse-spark-1.1",
21956
- name: "Meta: Muse Spark 1.1",
22242
+ "meta/muse-spark-1.1": {
22243
+ id: "meta/muse-spark-1.1",
22244
+ name: "Meta: Muse Spark 1.1",
21957
22245
  api: "openai-completions",
21958
22246
  provider: "openrouter",
21959
22247
  baseUrl: "https://openrouter.ai/api/v1",
@@ -22147,23 +22435,6 @@ export const MODELS = {
22147
22435
  contextWindow: 1048576,
22148
22436
  maxTokens: 512000,
22149
22437
  },
22150
- "minimax/minimax-m3:batch": {
22151
- id: "minimax/minimax-m3:batch",
22152
- name: "MiniMax: MiniMax M3 (batch)",
22153
- api: "openai-completions",
22154
- provider: "openrouter",
22155
- baseUrl: "https://openrouter.ai/api/v1",
22156
- reasoning: true,
22157
- input: ["text", "image"],
22158
- cost: {
22159
- input: 0.3,
22160
- output: 1.2,
22161
- cacheRead: 0.06,
22162
- cacheWrite: 0,
22163
- },
22164
- contextWindow: 524288,
22165
- maxTokens: 471859,
22166
- },
22167
22438
  "mistralai/codestral-2508": {
22168
22439
  id: "mistralai/codestral-2508",
22169
22440
  name: "Mistral: Codestral 2508",
@@ -22491,6 +22762,23 @@ export const MODELS = {
22491
22762
  contextWindow: 262144,
22492
22763
  maxTokens: 209715,
22493
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
+ },
22494
22782
  "mistralai/mistral-small-3.2-24b-instruct": {
22495
22783
  id: "mistralai/mistral-small-3.2-24b-instruct",
22496
22784
  name: "Mistral: Mistral Small 3.2 24B",
@@ -22640,7 +22928,7 @@ export const MODELS = {
22640
22928
  input: ["text", "image"],
22641
22929
  cost: {
22642
22930
  input: 0.7062,
22643
- output: 3.21,
22931
+ output: 3.3000000000000003,
22644
22932
  cacheRead: 0.18,
22645
22933
  cacheWrite: 0,
22646
22934
  },
@@ -22657,9 +22945,9 @@ export const MODELS = {
22657
22945
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
22658
22946
  input: ["text", "image"],
22659
22947
  cost: {
22660
- input: 2,
22661
- output: 11.2,
22662
- cacheRead: 0.232,
22948
+ input: 3,
22949
+ output: 15,
22950
+ cacheRead: 0.3,
22663
22951
  cacheWrite: 0,
22664
22952
  },
22665
22953
  contextWindow: 1048576,
@@ -22675,13 +22963,13 @@ export const MODELS = {
22675
22963
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
22676
22964
  input: ["text", "image"],
22677
22965
  cost: {
22678
- input: 3,
22679
- output: 15,
22680
- cacheRead: 0.3,
22966
+ input: 2.2800000000000002,
22967
+ output: 11.399999999999999,
22968
+ cacheRead: 0.228,
22681
22969
  cacheWrite: 0,
22682
22970
  },
22683
22971
  contextWindow: 1048576,
22684
- maxTokens: 943718,
22972
+ maxTokens: 16384,
22685
22973
  },
22686
22974
  "nex-agi/nex-n2.5-mini:free": {
22687
22975
  id: "nex-agi/nex-n2.5-mini:free",
@@ -22701,6 +22989,24 @@ export const MODELS = {
22701
22989
  contextWindow: 262144,
22702
22990
  maxTokens: 235929,
22703
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
+ },
22704
23010
  "nex-agi/nex-n2.5-pro:free": {
22705
23011
  id: "nex-agi/nex-n2.5-pro:free",
22706
23012
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -22728,9 +23034,9 @@ export const MODELS = {
22728
23034
  reasoning: true,
22729
23035
  input: ["text"],
22730
23036
  cost: {
22731
- input: 0.06,
22732
- output: 0.24,
22733
- cacheRead: 0,
23037
+ input: 0.049999999999999996,
23038
+ output: 0.19999999999999998,
23039
+ cacheRead: 0.03,
22734
23040
  cacheWrite: 0,
22735
23041
  },
22736
23042
  contextWindow: 262144,
@@ -22799,13 +23105,13 @@ export const MODELS = {
22799
23105
  thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
22800
23106
  input: ["text"],
22801
23107
  cost: {
22802
- input: 0.625,
22803
- output: 3.125,
22804
- cacheRead: 0.1875,
23108
+ input: 0.6,
23109
+ output: 2.4,
23110
+ cacheRead: 0.12,
22805
23111
  cacheWrite: 0,
22806
23112
  },
22807
23113
  contextWindow: 262144,
22808
- maxTokens: 32768,
23114
+ maxTokens: 182520,
22809
23115
  },
22810
23116
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
22811
23117
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -22834,13 +23140,13 @@ export const MODELS = {
22834
23140
  reasoning: true,
22835
23141
  input: ["text"],
22836
23142
  cost: {
22837
- input: 0.08,
23143
+ input: 0.07,
22838
23144
  output: 0.19999999999999998,
22839
23145
  cacheRead: 0.04,
22840
23146
  cacheWrite: 0,
22841
23147
  },
22842
23148
  contextWindow: 262144,
22843
- maxTokens: 131072,
23149
+ maxTokens: 235929,
22844
23150
  },
22845
23151
  "nvidia/nemotron-3.5-lightning:free": {
22846
23152
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -24080,6 +24386,150 @@ export const MODELS = {
24080
24386
  contextWindow: 1050000,
24081
24387
  maxTokens: 128000,
24082
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
+ },
24083
24533
  "openai/gpt-audio": {
24084
24534
  id: "openai/gpt-audio",
24085
24535
  name: "OpenAI: GPT Audio",
@@ -24149,9 +24599,9 @@ export const MODELS = {
24149
24599
  contextWindow: 131072,
24150
24600
  maxTokens: 65536,
24151
24601
  },
24152
- "openai/gpt-oss-120b:batch": {
24153
- id: "openai/gpt-oss-120b:batch",
24154
- name: "OpenAI: gpt-oss-120b (batch)",
24602
+ "openai/gpt-oss-20b": {
24603
+ id: "openai/gpt-oss-20b",
24604
+ name: "OpenAI: gpt-oss-20b",
24155
24605
  api: "openai-completions",
24156
24606
  provider: "openrouter",
24157
24607
  baseUrl: "https://openrouter.ai/api/v1",
@@ -24159,17 +24609,17 @@ export const MODELS = {
24159
24609
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
24160
24610
  input: ["text"],
24161
24611
  cost: {
24162
- input: 0.15,
24163
- output: 0.6,
24612
+ input: 0.018,
24613
+ output: 0.09,
24164
24614
  cacheRead: 0,
24165
24615
  cacheWrite: 0,
24166
24616
  },
24167
24617
  contextWindow: 131072,
24168
- maxTokens: 117964,
24618
+ maxTokens: 32768,
24169
24619
  },
24170
- "openai/gpt-oss-20b": {
24171
- id: "openai/gpt-oss-20b",
24172
- 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)",
24173
24623
  api: "openai-completions",
24174
24624
  provider: "openrouter",
24175
24625
  baseUrl: "https://openrouter.ai/api/v1",
@@ -24177,9 +24627,9 @@ export const MODELS = {
24177
24627
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
24178
24628
  input: ["text"],
24179
24629
  cost: {
24180
- input: 0.03,
24181
- output: 0.13,
24182
- cacheRead: 0.03,
24630
+ input: 0.024,
24631
+ output: 0.112,
24632
+ cacheRead: 0,
24183
24633
  cacheWrite: 0,
24184
24634
  },
24185
24635
  contextWindow: 131072,
@@ -24494,6 +24944,24 @@ export const MODELS = {
24494
24944
  contextWindow: 262144,
24495
24945
  maxTokens: 32768,
24496
24946
  },
24947
+ "prism-ml/ternary-bonsai-2-27b": {
24948
+ id: "prism-ml/ternary-bonsai-2-27b",
24949
+ name: "PrismML: Ternary Bonsai 2 27B",
24950
+ api: "openai-completions",
24951
+ provider: "openrouter",
24952
+ baseUrl: "https://openrouter.ai/api/v1",
24953
+ reasoning: true,
24954
+ thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": "xhigh", "max": null, "ultra": null },
24955
+ input: ["text", "image"],
24956
+ cost: {
24957
+ input: 0.075,
24958
+ output: 0.5,
24959
+ cacheRead: 0,
24960
+ cacheWrite: 0,
24961
+ },
24962
+ contextWindow: 262144,
24963
+ maxTokens: 32768,
24964
+ },
24497
24965
  "qwen/qwen-2.5-72b-instruct": {
24498
24966
  id: "qwen/qwen-2.5-72b-instruct",
24499
24967
  name: "Qwen2.5 72B Instruct",
@@ -24875,7 +25343,7 @@ export const MODELS = {
24875
25343
  cacheWrite: 0,
24876
25344
  },
24877
25345
  contextWindow: 262144,
24878
- maxTokens: 32768,
25346
+ maxTokens: 235929,
24879
25347
  },
24880
25348
  "qwen/qwen3-vl-235b-a22b-instruct": {
24881
25349
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -25045,13 +25513,13 @@ export const MODELS = {
25045
25513
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25046
25514
  input: ["text", "image"],
25047
25515
  cost: {
25048
- input: 0.1625,
25049
- output: 1.3,
25050
- cacheRead: 0,
25516
+ input: 0.3125,
25517
+ output: 1.25,
25518
+ cacheRead: 0.15625,
25051
25519
  cacheWrite: 0,
25052
25520
  },
25053
25521
  contextWindow: 262144,
25054
- maxTokens: 65536,
25522
+ maxTokens: 16384,
25055
25523
  },
25056
25524
  "qwen/qwen3.5-397b-a17b": {
25057
25525
  id: "qwen/qwen3.5-397b-a17b",
@@ -25087,25 +25555,7 @@ export const MODELS = {
25087
25555
  cacheWrite: 0,
25088
25556
  },
25089
25557
  contextWindow: 262144,
25090
- maxTokens: 235929,
25091
- },
25092
- "qwen/qwen3.5-9b:batch": {
25093
- id: "qwen/qwen3.5-9b:batch",
25094
- name: "Qwen: Qwen3.5-9B (batch)",
25095
- api: "openai-completions",
25096
- provider: "openrouter",
25097
- baseUrl: "https://openrouter.ai/api/v1",
25098
- reasoning: true,
25099
- thinkingLevelMap: { "xhigh": "high", "max": "max" },
25100
- input: ["text", "image"],
25101
- cost: {
25102
- input: 0.16999999999999998,
25103
- output: 0.25,
25104
- cacheRead: 0,
25105
- cacheWrite: 0,
25106
- },
25107
- contextWindow: 262144,
25108
- maxTokens: 235929,
25558
+ maxTokens: 32768,
25109
25559
  },
25110
25560
  "qwen/qwen3.5-flash-02-23": {
25111
25561
  id: "qwen/qwen3.5-flash-02-23",
@@ -25171,13 +25621,13 @@ export const MODELS = {
25171
25621
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25172
25622
  input: ["text", "image"],
25173
25623
  cost: {
25174
- input: 0.3,
25175
- output: 2,
25176
- cacheRead: 0.03,
25624
+ input: 0.32,
25625
+ output: 2.7,
25626
+ cacheRead: 0.15,
25177
25627
  cacheWrite: 0,
25178
25628
  },
25179
25629
  contextWindow: 262144,
25180
- maxTokens: 65536,
25630
+ maxTokens: 262140,
25181
25631
  },
25182
25632
  "qwen/qwen3.6-35b-a3b": {
25183
25633
  id: "qwen/qwen3.6-35b-a3b",
@@ -25189,8 +25639,8 @@ export const MODELS = {
25189
25639
  thinkingLevelMap: { "xhigh": "high", "max": "max" },
25190
25640
  input: ["text", "image"],
25191
25641
  cost: {
25192
- input: 0.09999999999999999,
25193
- output: 0.8999999999999999,
25642
+ input: 0.15,
25643
+ output: 1,
25194
25644
  cacheRead: 0.049999999999999996,
25195
25645
  cacheWrite: 0,
25196
25646
  },
@@ -25323,24 +25773,6 @@ export const MODELS = {
25323
25773
  contextWindow: 1048576,
25324
25774
  maxTokens: 131072,
25325
25775
  },
25326
- "qwen/qwen3.8-2.4t-a95b:batch": {
25327
- id: "qwen/qwen3.8-2.4t-a95b:batch",
25328
- name: "Qwen: Qwen3.8 2.4T A95B (batch)",
25329
- api: "openai-completions",
25330
- provider: "openrouter",
25331
- baseUrl: "https://openrouter.ai/api/v1",
25332
- reasoning: true,
25333
- thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": null, "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
25334
- input: ["text"],
25335
- cost: {
25336
- input: 2,
25337
- output: 6,
25338
- cacheRead: 0.25,
25339
- cacheWrite: 0,
25340
- },
25341
- contextWindow: 1010000,
25342
- maxTokens: 909000,
25343
- },
25344
25776
  "qwen/qwen3.8-27b": {
25345
25777
  id: "qwen/qwen3.8-27b",
25346
25778
  name: "Qwen: Qwen3.8 27B",
@@ -25351,9 +25783,9 @@ export const MODELS = {
25351
25783
  thinkingLevelMap: { "xhigh": "xhigh", "max": null, "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": null, "ultra": null },
25352
25784
  input: ["text", "image"],
25353
25785
  cost: {
25354
- input: 0.21400000000000002,
25355
- output: 2.5500000000000003,
25356
- cacheRead: 0.15,
25786
+ input: 0.42,
25787
+ output: 3,
25788
+ cacheRead: 0.08499999999999999,
25357
25789
  cacheWrite: 0,
25358
25790
  },
25359
25791
  contextWindow: 1000000,
@@ -25413,6 +25845,24 @@ export const MODELS = {
25413
25845
  contextWindow: 1000000,
25414
25846
  maxTokens: 131072,
25415
25847
  },
25848
+ "qwen/qwen3.8-omni-flash": {
25849
+ id: "qwen/qwen3.8-omni-flash",
25850
+ name: "Qwen: Qwen3.8 Omni Flash",
25851
+ api: "openai-completions",
25852
+ provider: "openrouter",
25853
+ baseUrl: "https://openrouter.ai/api/v1",
25854
+ reasoning: true,
25855
+ thinkingLevelMap: { "xhigh": "high", "max": "max" },
25856
+ input: ["text", "image"],
25857
+ cost: {
25858
+ input: 0.15,
25859
+ output: 0.47,
25860
+ cacheRead: 0.016,
25861
+ cacheWrite: 0,
25862
+ },
25863
+ contextWindow: 1000000,
25864
+ maxTokens: 131072,
25865
+ },
25416
25866
  "rekaai/reka-edge": {
25417
25867
  id: "rekaai/reka-edge",
25418
25868
  name: "Reka Edge",
@@ -25582,9 +26032,9 @@ export const MODELS = {
25582
26032
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
25583
26033
  input: ["text"],
25584
26034
  cost: {
25585
- input: 0.13199999999999998,
25586
- output: 0.5279999999999999,
25587
- cacheRead: 0.032999999999999995,
26035
+ input: 0.0825,
26036
+ output: 0.33,
26037
+ cacheRead: 0.020625,
25588
26038
  cacheWrite: 0,
25589
26039
  },
25590
26040
  contextWindow: 262144,
@@ -25680,24 +26130,6 @@ export const MODELS = {
25680
26130
  contextWindow: 1048576,
25681
26131
  maxTokens: 262144,
25682
26132
  },
25683
- "thinkingmachines/inkling:batch": {
25684
- id: "thinkingmachines/inkling:batch",
25685
- name: "Thinking Machines: Inkling (batch)",
25686
- api: "openai-completions",
25687
- provider: "openrouter",
25688
- baseUrl: "https://openrouter.ai/api/v1",
25689
- reasoning: true,
25690
- thinkingLevelMap: { "off": "none", "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max", "ultra": null },
25691
- input: ["text", "image"],
25692
- cost: {
25693
- input: 1,
25694
- output: 4.05,
25695
- cacheRead: 0.16999999999999998,
25696
- cacheWrite: 0,
25697
- },
25698
- contextWindow: 524288,
25699
- maxTokens: 471859,
25700
- },
25701
26133
  "thinkingmachines/inkling:free": {
25702
26134
  id: "thinkingmachines/inkling:free",
25703
26135
  name: "Thinking Machines: Inkling (free)",
@@ -25740,6 +26172,7 @@ export const MODELS = {
25740
26172
  provider: "openrouter",
25741
26173
  baseUrl: "https://openrouter.ai/api/v1",
25742
26174
  reasoning: true,
26175
+ thinkingLevelMap: { "off": "none", "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
25743
26176
  input: ["text"],
25744
26177
  cost: {
25745
26178
  input: 0.15,
@@ -25757,6 +26190,7 @@ export const MODELS = {
25757
26190
  provider: "openrouter",
25758
26191
  baseUrl: "https://openrouter.ai/api/v1",
25759
26192
  reasoning: true,
26193
+ thinkingLevelMap: { "off": "none", "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
25760
26194
  input: ["text"],
25761
26195
  cost: {
25762
26196
  input: 0.09,
@@ -25856,6 +26290,24 @@ export const MODELS = {
25856
26290
  contextWindow: 500000,
25857
26291
  maxTokens: 450000,
25858
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
+ },
25859
26311
  "x-ai/grok-build-0.1": {
25860
26312
  id: "x-ai/grok-build-0.1",
25861
26313
  name: "SpaceXAI: Grok Build 0.1",
@@ -25908,6 +26360,57 @@ export const MODELS = {
25908
26360
  contextWindow: 1050000,
25909
26361
  maxTokens: 131072,
25910
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
+ },
25911
26414
  "z-ai/glm-4.5": {
25912
26415
  id: "z-ai/glm-4.5",
25913
26416
  name: "Z.ai: GLM 4.5",
@@ -26088,31 +26591,13 @@ export const MODELS = {
26088
26591
  thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
26089
26592
  input: ["text"],
26090
26593
  cost: {
26091
- input: 0.4875,
26092
- output: 1.56,
26093
- cacheRead: 0.091,
26094
- cacheWrite: 0,
26095
- },
26096
- contextWindow: 1048576,
26097
- maxTokens: 163840,
26098
- },
26099
- "z-ai/glm-5.2:batch": {
26100
- id: "z-ai/glm-5.2:batch",
26101
- name: "Z.ai: GLM 5.2 (batch)",
26102
- api: "openai-completions",
26103
- provider: "openrouter",
26104
- baseUrl: "https://openrouter.ai/api/v1",
26105
- reasoning: true,
26106
- thinkingLevelMap: { "off": "none", "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null, "ultra": null },
26107
- input: ["text"],
26108
- cost: {
26109
- input: 0.7,
26110
- output: 2.2,
26111
- cacheRead: 0.07,
26594
+ input: 0.6496,
26595
+ output: 2.0416,
26596
+ cacheRead: 0.12064,
26112
26597
  cacheWrite: 0,
26113
26598
  },
26114
26599
  contextWindow: 1048576,
26115
- maxTokens: 943718,
26600
+ maxTokens: 131072,
26116
26601
  },
26117
26602
  "z-ai/glm-5.3": {
26118
26603
  id: "z-ai/glm-5.3",
@@ -26124,13 +26609,13 @@ export const MODELS = {
26124
26609
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26125
26610
  input: ["text"],
26126
26611
  cost: {
26127
- input: 1.4,
26128
- output: 4.4,
26129
- cacheRead: 0.26,
26612
+ input: 0.6537999999999999,
26613
+ output: 2.0547999999999997,
26614
+ cacheRead: 0.12142000000000001,
26130
26615
  cacheWrite: 0,
26131
26616
  },
26132
26617
  contextWindow: 1310720,
26133
- maxTokens: 943717,
26618
+ maxTokens: 131072,
26134
26619
  },
26135
26620
  "z-ai/glm-5.3-flash": {
26136
26621
  id: "z-ai/glm-5.3-flash",
@@ -26142,13 +26627,13 @@ export const MODELS = {
26142
26627
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26143
26628
  input: ["text", "image"],
26144
26629
  cost: {
26145
- input: 0.09,
26146
- output: 0.3,
26147
- cacheRead: 0.018,
26630
+ input: 0.15,
26631
+ output: 0.5,
26632
+ cacheRead: 0.049999999999999996,
26148
26633
  cacheWrite: 0,
26149
26634
  },
26150
26635
  contextWindow: 1310720,
26151
- maxTokens: 131072,
26636
+ maxTokens: 943718,
26152
26637
  },
26153
26638
  "z-ai/glm-5.3-flash:batch": {
26154
26639
  id: "z-ai/glm-5.3-flash:batch",
@@ -26160,13 +26645,31 @@ export const MODELS = {
26160
26645
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26161
26646
  input: ["text", "image"],
26162
26647
  cost: {
26163
- input: 0.075,
26164
- output: 0.25,
26165
- cacheRead: 0.015,
26648
+ input: 0.06,
26649
+ output: 0.19999999999999998,
26650
+ cacheRead: 0.012,
26166
26651
  cacheWrite: 0,
26167
26652
  },
26168
26653
  contextWindow: 1048576,
26169
- maxTokens: 943718,
26654
+ maxTokens: 131072,
26655
+ },
26656
+ "z-ai/glm-5.3-flashx": {
26657
+ id: "z-ai/glm-5.3-flashx",
26658
+ name: "Z.ai: GLM 5.3 FlashX",
26659
+ api: "openai-completions",
26660
+ provider: "openrouter",
26661
+ baseUrl: "https://openrouter.ai/api/v1",
26662
+ reasoning: true,
26663
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26664
+ input: ["text", "image"],
26665
+ cost: {
26666
+ input: 0.37,
26667
+ output: 1.25,
26668
+ cacheRead: 0.075,
26669
+ cacheWrite: 0,
26670
+ },
26671
+ contextWindow: 1048576,
26672
+ maxTokens: 131072,
26170
26673
  },
26171
26674
  "z-ai/glm-5.3:batch": {
26172
26675
  id: "z-ai/glm-5.3:batch",
@@ -26178,13 +26681,13 @@ export const MODELS = {
26178
26681
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26179
26682
  input: ["text"],
26180
26683
  cost: {
26181
- input: 0.7,
26182
- output: 2.2,
26183
- cacheRead: 0.13,
26684
+ input: 0.72,
26685
+ output: 2.4,
26686
+ cacheRead: 0.12,
26184
26687
  cacheWrite: 0,
26185
26688
  },
26186
26689
  contextWindow: 1048576,
26187
- maxTokens: 943718,
26690
+ maxTokens: 131072,
26188
26691
  },
26189
26692
  "z-ai/glm-5v-turbo": {
26190
26693
  id: "z-ai/glm-5v-turbo",
@@ -26245,13 +26748,13 @@ export const MODELS = {
26245
26748
  provider: "openrouter",
26246
26749
  baseUrl: "https://openrouter.ai/api/v1",
26247
26750
  reasoning: true,
26248
- 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 },
26249
26752
  input: ["text", "image"],
26250
26753
  cost: {
26251
- input: 5,
26252
- output: 25,
26253
- cacheRead: 0.5,
26254
- cacheWrite: 6.25,
26754
+ input: 4,
26755
+ output: 20,
26756
+ cacheRead: 0.19999999999999998,
26757
+ cacheWrite: 5,
26255
26758
  },
26256
26759
  contextWindow: 1000000,
26257
26760
  maxTokens: 128000,
@@ -26284,9 +26787,9 @@ export const MODELS = {
26284
26787
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26285
26788
  input: ["text", "image"],
26286
26789
  cost: {
26287
- input: 0.135,
26288
- output: 0.54,
26289
- cacheRead: 0.00405,
26790
+ input: 0.12,
26791
+ output: 0.48,
26792
+ cacheRead: 0.0036,
26290
26793
  cacheWrite: 0,
26291
26794
  },
26292
26795
  contextWindow: 1048576,
@@ -26302,13 +26805,13 @@ export const MODELS = {
26302
26805
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26303
26806
  input: ["text"],
26304
26807
  cost: {
26305
- input: 0.7,
26306
- output: 2.96,
26307
- cacheRead: 0.032999999999999995,
26808
+ input: 0.39996,
26809
+ output: 1.19988,
26810
+ cacheRead: 0.012726,
26308
26811
  cacheWrite: 0,
26309
26812
  },
26310
26813
  contextWindow: 1048576,
26311
- maxTokens: 384000,
26814
+ maxTokens: 393216,
26312
26815
  },
26313
26816
  "~deepseek/deepseek-v4-flash-latest": {
26314
26817
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -26321,9 +26824,9 @@ export const MODELS = {
26321
26824
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "off": "none", "max": "max", "ultra": null },
26322
26825
  input: ["text"],
26323
26826
  cost: {
26324
- input: 0.055799999999999995,
26325
- output: 0.1767,
26326
- cacheRead: 0.008799999999999999,
26827
+ input: 0.03,
26828
+ output: 0.7999999999999999,
26829
+ cacheRead: 0.008,
26327
26830
  cacheWrite: 0,
26328
26831
  },
26329
26832
  contextWindow: 1310720,
@@ -26375,9 +26878,9 @@ export const MODELS = {
26375
26878
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26376
26879
  input: ["text", "image"],
26377
26880
  cost: {
26378
- input: 2,
26379
- output: 11.2,
26380
- cacheRead: 0.232,
26881
+ input: 1.4989,
26882
+ output: 10.758,
26883
+ cacheRead: 0.3,
26381
26884
  cacheWrite: 0,
26382
26885
  },
26383
26886
  contextWindow: 1048576,
@@ -26411,10 +26914,10 @@ export const MODELS = {
26411
26914
  thinkingLevelMap: { "off": "none", "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
26412
26915
  input: ["text", "image"],
26413
26916
  cost: {
26414
- input: 0.19999999999999998,
26415
- output: 1.2,
26416
- cacheRead: 0.02,
26417
- cacheWrite: 0.25,
26917
+ input: 0.09999999999999999,
26918
+ output: 0.5,
26919
+ cacheRead: 0.01,
26920
+ cacheWrite: 0.125,
26418
26921
  },
26419
26922
  contextWindow: 1050000,
26420
26923
  maxTokens: 128000,
@@ -26483,9 +26986,9 @@ export const MODELS = {
26483
26986
  thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "max": null, "ultra": null },
26484
26987
  input: ["text", "image"],
26485
26988
  cost: {
26486
- input: 2,
26487
- output: 6,
26488
- cacheRead: 0.5,
26989
+ input: 1.5999999999999999,
26990
+ output: 4.8,
26991
+ cacheRead: 0.39999999999999997,
26489
26992
  cacheWrite: 0,
26490
26993
  },
26491
26994
  contextWindow: 500000,
@@ -26507,7 +27010,7 @@ export const MODELS = {
26507
27010
  cacheWrite: 0,
26508
27011
  },
26509
27012
  contextWindow: 1310720,
26510
- maxTokens: 131072,
27013
+ maxTokens: 943718,
26511
27014
  },
26512
27015
  "~z-ai/glm-latest": {
26513
27016
  id: "~z-ai/glm-latest",
@@ -26519,13 +27022,13 @@ export const MODELS = {
26519
27022
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
26520
27023
  input: ["text"],
26521
27024
  cost: {
26522
- input: 0.8775,
26523
- output: 2.9699999999999998,
26524
- cacheRead: 0.1755,
27025
+ input: 0.6537999999999999,
27026
+ output: 2.0547999999999997,
27027
+ cacheRead: 0.12142000000000001,
26525
27028
  cacheWrite: 0,
26526
27029
  },
26527
27030
  contextWindow: 1310720,
26528
- maxTokens: 235929,
27031
+ maxTokens: 131072,
26529
27032
  },
26530
27033
  },
26531
27034
  "together": {
@@ -27783,6 +28286,44 @@ export const MODELS = {
27783
28286
  contextWindow: 1000000,
27784
28287
  maxTokens: 128000,
27785
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
+ },
27786
28327
  "anthropic/claude-sonnet-4": {
27787
28328
  id: "anthropic/claude-sonnet-4",
27788
28329
  name: "Claude Sonnet 4",
@@ -28122,7 +28663,7 @@ export const MODELS = {
28122
28663
  cost: {
28123
28664
  input: 0.3,
28124
28665
  output: 1.2,
28125
- cacheRead: 0.03,
28666
+ cacheRead: 0.007,
28126
28667
  cacheWrite: 0,
28127
28668
  },
28128
28669
  contextWindow: 1048576,
@@ -28995,6 +29536,23 @@ export const MODELS = {
28995
29536
  contextWindow: 262144,
28996
29537
  maxTokens: 4000,
28997
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
+ },
28998
29556
  "moonshotai/kimi-k2": {
28999
29557
  id: "moonshotai/kimi-k2",
29000
29558
  name: "Kimi K2 Instruct",
@@ -29957,11 +30515,11 @@ export const MODELS = {
29957
30515
  thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
29958
30516
  input: ["text", "image"],
29959
30517
  cost: {
29960
- input: 2,
29961
- output: 10,
29962
- cacheRead: 0.19999999999999998,
29963
- cacheWrite: 2.5,
29964
- },
30518
+ input: 4,
30519
+ output: 20,
30520
+ cacheRead: 0.39999999999999997,
30521
+ cacheWrite: 5,
30522
+ },
29965
30523
  contextWindow: 1000000,
29966
30524
  maxTokens: 128000,
29967
30525
  },
@@ -29975,10 +30533,10 @@ export const MODELS = {
29975
30533
  thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
29976
30534
  input: ["text", "image"],
29977
30535
  cost: {
29978
- input: 4,
29979
- output: 20,
29980
- cacheRead: 0.39999999999999997,
29981
- cacheWrite: 5,
30536
+ input: 8,
30537
+ output: 40,
30538
+ cacheRead: 0.7999999999999999,
30539
+ cacheWrite: 10,
29982
30540
  },
29983
30541
  contextWindow: 1000000,
29984
30542
  maxTokens: 128000,
@@ -30053,6 +30611,74 @@ export const MODELS = {
30053
30611
  contextWindow: 1050000,
30054
30612
  maxTokens: 128000,
30055
30613
  },
30614
+ "openai/gpt-6-luna": {
30615
+ id: "openai/gpt-6-luna",
30616
+ name: "GPT-6 Luna",
30617
+ api: "anthropic-messages",
30618
+ provider: "vercel-ai-gateway",
30619
+ baseUrl: "https://ai-gateway.vercel.sh",
30620
+ reasoning: true,
30621
+ input: ["text", "image"],
30622
+ cost: {
30623
+ input: 0.09999999999999999,
30624
+ output: 0.5,
30625
+ cacheRead: 0.01,
30626
+ cacheWrite: 0.125,
30627
+ },
30628
+ contextWindow: 1050000,
30629
+ maxTokens: 128000,
30630
+ },
30631
+ "openai/gpt-6-luna-fast": {
30632
+ id: "openai/gpt-6-luna-fast",
30633
+ name: "GPT-6 Luna (Fast)",
30634
+ api: "anthropic-messages",
30635
+ provider: "vercel-ai-gateway",
30636
+ baseUrl: "https://ai-gateway.vercel.sh",
30637
+ reasoning: true,
30638
+ input: ["text", "image"],
30639
+ cost: {
30640
+ input: 0.19999999999999998,
30641
+ output: 1,
30642
+ cacheRead: 0.02,
30643
+ cacheWrite: 0.25,
30644
+ },
30645
+ contextWindow: 1050000,
30646
+ maxTokens: 128000,
30647
+ },
30648
+ "openai/gpt-6-sol": {
30649
+ id: "openai/gpt-6-sol",
30650
+ name: "GPT-6 Sol",
30651
+ api: "anthropic-messages",
30652
+ provider: "vercel-ai-gateway",
30653
+ baseUrl: "https://ai-gateway.vercel.sh",
30654
+ reasoning: true,
30655
+ input: ["text", "image"],
30656
+ cost: {
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
+ },
30056
30682
  "openai/gpt-oss-120b": {
30057
30683
  id: "openai/gpt-oss-120b",
30058
30684
  name: "GPT OSS 120B",
@@ -30274,6 +30900,40 @@ export const MODELS = {
30274
30900
  contextWindow: 256000,
30275
30901
  maxTokens: 32768,
30276
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
+ },
30277
30937
  "sakana/fugu-max": {
30278
30938
  id: "sakana/fugu-max",
30279
30939
  name: "Fugu Max",
@@ -30531,6 +31191,24 @@ export const MODELS = {
30531
31191
  contextWindow: 500000,
30532
31192
  maxTokens: 500000,
30533
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
+ },
30534
31212
  "spacexai/grok-build-0.1": {
30535
31213
  id: "spacexai/grok-build-0.1",
30536
31214
  name: "Grok Build 0.1",
@@ -30684,6 +31362,57 @@ export const MODELS = {
30684
31362
  contextWindow: 1050000,
30685
31363
  maxTokens: 131000,
30686
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
+ },
30687
31416
  "zai/glm-4.5": {
30688
31417
  id: "zai/glm-4.5",
30689
31418
  name: "GLM 4.5",
@@ -30980,110 +31709,625 @@ export const MODELS = {
30980
31709
  maxTokens: 128000,
30981
31710
  },
30982
31711
  },
30983
- "xai": {
30984
- "grok-3": {
30985
- id: "grok-3",
30986
- name: "Grok 3",
31712
+ "workbuddy": {
31713
+ "auto": {
31714
+ id: "auto",
31715
+ name: "Auto (WorkBuddy)",
30987
31716
  api: "openai-completions",
30988
- provider: "xai",
30989
- baseUrl: "https://api.x.ai/v1",
31717
+ provider: "workbuddy",
31718
+ baseUrl: "https://www.workbuddy.ai/v2",
31719
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
30990
31720
  reasoning: false,
30991
- input: ["text"],
31721
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": null, "xhigh": null, "max": null, "ultra": null },
31722
+ input: ["text", "image"],
30992
31723
  cost: {
30993
- input: 3,
30994
- output: 15,
30995
- cacheRead: 0.75,
31724
+ input: 0,
31725
+ output: 0,
31726
+ cacheRead: 0,
30996
31727
  cacheWrite: 0,
30997
31728
  },
30998
- contextWindow: 131072,
30999
- maxTokens: 8192,
31729
+ contextWindow: 168000,
31730
+ maxTokens: 32000,
31000
31731
  },
31001
- "grok-3-fast": {
31002
- id: "grok-3-fast",
31003
- name: "Grok 3 Fast",
31732
+ "claude-opus-4.6": {
31733
+ id: "claude-opus-4.6",
31734
+ name: "Claude Opus 4.6 (WorkBuddy)",
31004
31735
  api: "openai-completions",
31005
- provider: "xai",
31006
- baseUrl: "https://api.x.ai/v1",
31007
- reasoning: false,
31008
- input: ["text"],
31736
+ provider: "workbuddy",
31737
+ baseUrl: "https://www.workbuddy.ai/v2",
31738
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31739
+ reasoning: true,
31740
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max", "ultra": null },
31741
+ input: ["text", "image"],
31009
31742
  cost: {
31010
- input: 5,
31011
- output: 25,
31012
- cacheRead: 1.25,
31743
+ input: 0,
31744
+ output: 0,
31745
+ cacheRead: 0,
31013
31746
  cacheWrite: 0,
31014
31747
  },
31015
- contextWindow: 131072,
31016
- maxTokens: 8192,
31748
+ contextWindow: 1000000,
31749
+ maxTokens: 128000,
31017
31750
  },
31018
- "grok-4.20-0309-non-reasoning": {
31019
- id: "grok-4.20-0309-non-reasoning",
31020
- name: "Grok 4.20 (Non-Reasoning)",
31751
+ "claude-opus-5": {
31752
+ id: "claude-opus-5",
31753
+ name: "Claude Opus 5 (WorkBuddy)",
31021
31754
  api: "openai-completions",
31022
- provider: "xai",
31023
- baseUrl: "https://api.x.ai/v1",
31024
- reasoning: false,
31755
+ provider: "workbuddy",
31756
+ baseUrl: "https://www.workbuddy.ai/v2",
31757
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31758
+ reasoning: true,
31759
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
31025
31760
  input: ["text", "image"],
31026
31761
  cost: {
31027
- input: 1.25,
31028
- output: 2.5,
31029
- cacheRead: 0.2,
31762
+ input: 0,
31763
+ output: 0,
31764
+ cacheRead: 0,
31030
31765
  cacheWrite: 0,
31031
31766
  },
31032
31767
  contextWindow: 1000000,
31033
- maxTokens: 30000,
31768
+ maxTokens: 128000,
31034
31769
  },
31035
- "grok-4.20-0309-reasoning": {
31036
- id: "grok-4.20-0309-reasoning",
31037
- name: "Grok 4.20 (Reasoning)",
31770
+ "claude-sonnet-4.6": {
31771
+ id: "claude-sonnet-4.6",
31772
+ name: "Claude Sonnet 4.6 (WorkBuddy)",
31038
31773
  api: "openai-completions",
31039
- provider: "xai",
31040
- baseUrl: "https://api.x.ai/v1",
31774
+ provider: "workbuddy",
31775
+ baseUrl: "https://www.workbuddy.ai/v2",
31776
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31041
31777
  reasoning: true,
31778
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max", "ultra": null },
31042
31779
  input: ["text", "image"],
31043
31780
  cost: {
31044
- input: 1.25,
31045
- output: 2.5,
31046
- cacheRead: 0.2,
31781
+ input: 0,
31782
+ output: 0,
31783
+ cacheRead: 0,
31047
31784
  cacheWrite: 0,
31048
31785
  },
31049
31786
  contextWindow: 1000000,
31050
- maxTokens: 30000,
31787
+ maxTokens: 128000,
31051
31788
  },
31052
- "grok-4.3": {
31053
- id: "grok-4.3",
31054
- name: "Grok 4.3",
31789
+ "deepseek-v3-0324": {
31790
+ id: "deepseek-v3-0324",
31791
+ name: "DeepSeek-V3 0324 (WorkBuddy)",
31055
31792
  api: "openai-completions",
31056
- provider: "xai",
31057
- baseUrl: "https://api.x.ai/v1",
31058
- reasoning: true,
31059
- input: ["text", "image"],
31793
+ provider: "workbuddy",
31794
+ baseUrl: "https://www.workbuddy.ai/v2",
31795
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31796
+ reasoning: false,
31797
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": null, "xhigh": null, "max": null, "ultra": null },
31798
+ input: ["text"],
31060
31799
  cost: {
31061
- input: 1.25,
31062
- output: 2.5,
31063
- cacheRead: 0.2,
31800
+ input: 0,
31801
+ output: 0,
31802
+ cacheRead: 0,
31064
31803
  cacheWrite: 0,
31065
31804
  },
31066
- contextWindow: 1000000,
31067
- maxTokens: 30000,
31805
+ contextWindow: 128000,
31806
+ maxTokens: 8192,
31068
31807
  },
31069
- "grok-4.5": {
31070
- id: "grok-4.5",
31071
- name: "Grok 4.5",
31808
+ "deepseek-v4.1-flash": {
31809
+ id: "deepseek-v4.1-flash",
31810
+ name: "DeepSeek V4.1 Flash (WorkBuddy)",
31072
31811
  api: "openai-completions",
31073
- provider: "xai",
31074
- baseUrl: "https://api.x.ai/v1",
31812
+ provider: "workbuddy",
31813
+ baseUrl: "https://www.workbuddy.ai/v2",
31814
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31075
31815
  reasoning: true,
31816
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
31076
31817
  input: ["text", "image"],
31077
31818
  cost: {
31078
- input: 2,
31079
- output: 6,
31080
- cacheRead: 0.3,
31819
+ input: 0,
31820
+ output: 0,
31821
+ cacheRead: 0,
31081
31822
  cacheWrite: 0,
31082
31823
  },
31083
- contextWindow: 500000,
31084
- maxTokens: 500000,
31824
+ contextWindow: 1000000,
31825
+ maxTokens: 384000,
31085
31826
  },
31086
- "grok-4.6": {
31827
+ "gemini-3.1-pro": {
31828
+ id: "gemini-3.1-pro",
31829
+ name: "Gemini-3.1-Pro (WorkBuddy)",
31830
+ api: "openai-completions",
31831
+ provider: "workbuddy",
31832
+ baseUrl: "https://www.workbuddy.ai/v2",
31833
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true, "supportsReasoningEffort": false },
31834
+ reasoning: true,
31835
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": null, "xhigh": null, "max": null, "ultra": null },
31836
+ input: ["text", "image"],
31837
+ cost: {
31838
+ input: 0,
31839
+ output: 0,
31840
+ cacheRead: 0,
31841
+ cacheWrite: 0,
31842
+ },
31843
+ contextWindow: 400000,
31844
+ maxTokens: 64000,
31845
+ },
31846
+ "gemini-3.5-flash": {
31847
+ id: "gemini-3.5-flash",
31848
+ name: "Gemini-3.5-Flash (WorkBuddy)",
31849
+ api: "openai-completions",
31850
+ provider: "workbuddy",
31851
+ baseUrl: "https://www.workbuddy.ai/v2",
31852
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31853
+ reasoning: true,
31854
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
31855
+ input: ["text", "image"],
31856
+ cost: {
31857
+ input: 0,
31858
+ output: 0,
31859
+ cacheRead: 0,
31860
+ cacheWrite: 0,
31861
+ },
31862
+ contextWindow: 1000000,
31863
+ maxTokens: 65536,
31864
+ },
31865
+ "gemini-3.8-flash": {
31866
+ id: "gemini-3.8-flash",
31867
+ name: "Gemini-3.8-Flash (WorkBuddy)",
31868
+ api: "openai-completions",
31869
+ provider: "workbuddy",
31870
+ baseUrl: "https://www.workbuddy.ai/v2",
31871
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31872
+ reasoning: true,
31873
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null, "ultra": null },
31874
+ input: ["text", "image"],
31875
+ cost: {
31876
+ input: 0,
31877
+ output: 0,
31878
+ cacheRead: 0,
31879
+ cacheWrite: 0,
31880
+ },
31881
+ contextWindow: 1048576,
31882
+ maxTokens: 65536,
31883
+ },
31884
+ "glm-5.1": {
31885
+ id: "glm-5.1",
31886
+ name: "GLM-5.1 (WorkBuddy)",
31887
+ api: "openai-completions",
31888
+ provider: "workbuddy",
31889
+ baseUrl: "https://www.workbuddy.ai/v2",
31890
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31891
+ reasoning: true,
31892
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
31893
+ input: ["text"],
31894
+ cost: {
31895
+ input: 0,
31896
+ output: 0,
31897
+ cacheRead: 0,
31898
+ cacheWrite: 0,
31899
+ },
31900
+ contextWindow: 200000,
31901
+ maxTokens: 48000,
31902
+ },
31903
+ "glm-5.2": {
31904
+ id: "glm-5.2",
31905
+ name: "GLM-5.2 (WorkBuddy)",
31906
+ api: "openai-completions",
31907
+ provider: "workbuddy",
31908
+ baseUrl: "https://www.workbuddy.ai/v2",
31909
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31910
+ reasoning: true,
31911
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": "xhigh", "ultra": null },
31912
+ input: ["text", "image"],
31913
+ cost: {
31914
+ input: 0,
31915
+ output: 0,
31916
+ cacheRead: 0,
31917
+ cacheWrite: 0,
31918
+ },
31919
+ contextWindow: 1000000,
31920
+ maxTokens: 48000,
31921
+ },
31922
+ "glm-5.3": {
31923
+ id: "glm-5.3",
31924
+ name: "GLM-5.3 (WorkBuddy)",
31925
+ api: "openai-completions",
31926
+ provider: "workbuddy",
31927
+ baseUrl: "https://www.workbuddy.ai/v2",
31928
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31929
+ reasoning: true,
31930
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max", "ultra": null },
31931
+ input: ["text", "image"],
31932
+ cost: {
31933
+ input: 0,
31934
+ output: 0,
31935
+ cacheRead: 0,
31936
+ cacheWrite: 0,
31937
+ },
31938
+ contextWindow: 1000000,
31939
+ maxTokens: 48000,
31940
+ },
31941
+ "glm-5v-turbo": {
31942
+ id: "glm-5v-turbo",
31943
+ name: "GLM-5v-Turbo (WorkBuddy)",
31944
+ api: "openai-completions",
31945
+ provider: "workbuddy",
31946
+ baseUrl: "https://www.workbuddy.ai/v2",
31947
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31948
+ reasoning: true,
31949
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
31950
+ input: ["text", "image"],
31951
+ cost: {
31952
+ input: 0,
31953
+ output: 0,
31954
+ cacheRead: 0,
31955
+ cacheWrite: 0,
31956
+ },
31957
+ contextWindow: 200000,
31958
+ maxTokens: 38000,
31959
+ },
31960
+ "gpt-5.3-codex": {
31961
+ id: "gpt-5.3-codex",
31962
+ name: "GPT-5.3-Codex (WorkBuddy)",
31963
+ api: "openai-completions",
31964
+ provider: "workbuddy",
31965
+ baseUrl: "https://www.workbuddy.ai/v2",
31966
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31967
+ reasoning: true,
31968
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
31969
+ input: ["text", "image"],
31970
+ cost: {
31971
+ input: 0,
31972
+ output: 0,
31973
+ cacheRead: 0,
31974
+ cacheWrite: 0,
31975
+ },
31976
+ contextWindow: 272000,
31977
+ maxTokens: 128000,
31978
+ },
31979
+ "gpt-5.4": {
31980
+ id: "gpt-5.4",
31981
+ name: "GPT-5.4 (WorkBuddy)",
31982
+ api: "openai-completions",
31983
+ provider: "workbuddy",
31984
+ baseUrl: "https://www.workbuddy.ai/v2",
31985
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
31986
+ reasoning: true,
31987
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
31988
+ input: ["text", "image"],
31989
+ cost: {
31990
+ input: 0,
31991
+ output: 0,
31992
+ cacheRead: 0,
31993
+ cacheWrite: 0,
31994
+ },
31995
+ contextWindow: 272000,
31996
+ maxTokens: 128000,
31997
+ },
31998
+ "gpt-5.5": {
31999
+ id: "gpt-5.5",
32000
+ name: "GPT-5.5 (WorkBuddy)",
32001
+ api: "openai-completions",
32002
+ provider: "workbuddy",
32003
+ baseUrl: "https://www.workbuddy.ai/v2",
32004
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32005
+ reasoning: true,
32006
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
32007
+ input: ["text", "image"],
32008
+ cost: {
32009
+ input: 0,
32010
+ output: 0,
32011
+ cacheRead: 0,
32012
+ cacheWrite: 0,
32013
+ },
32014
+ contextWindow: 1000000,
32015
+ maxTokens: 72000,
32016
+ },
32017
+ "gpt-5.6-luna": {
32018
+ id: "gpt-5.6-luna",
32019
+ name: "GPT-5.6-Luna (WorkBuddy)",
32020
+ api: "openai-completions",
32021
+ provider: "workbuddy",
32022
+ baseUrl: "https://www.workbuddy.ai/v2",
32023
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32024
+ reasoning: true,
32025
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "xhigh", "ultra": null },
32026
+ input: ["text", "image"],
32027
+ cost: {
32028
+ input: 0,
32029
+ output: 0,
32030
+ cacheRead: 0,
32031
+ cacheWrite: 0,
32032
+ },
32033
+ contextWindow: 1000000,
32034
+ maxTokens: 128000,
32035
+ },
32036
+ "gpt-5.6-sol": {
32037
+ id: "gpt-5.6-sol",
32038
+ name: "GPT-5.6-Sol (WorkBuddy)",
32039
+ api: "openai-completions",
32040
+ provider: "workbuddy",
32041
+ baseUrl: "https://www.workbuddy.ai/v2",
32042
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32043
+ reasoning: true,
32044
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "xhigh", "ultra": null },
32045
+ input: ["text", "image"],
32046
+ cost: {
32047
+ input: 0,
32048
+ output: 0,
32049
+ cacheRead: 0,
32050
+ cacheWrite: 0,
32051
+ },
32052
+ contextWindow: 1000000,
32053
+ maxTokens: 128000,
32054
+ },
32055
+ "gpt-5.6-terra": {
32056
+ id: "gpt-5.6-terra",
32057
+ name: "GPT-5.6-Terra (WorkBuddy)",
32058
+ api: "openai-completions",
32059
+ provider: "workbuddy",
32060
+ baseUrl: "https://www.workbuddy.ai/v2",
32061
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32062
+ reasoning: true,
32063
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "xhigh", "ultra": null },
32064
+ input: ["text", "image"],
32065
+ cost: {
32066
+ input: 0,
32067
+ output: 0,
32068
+ cacheRead: 0,
32069
+ cacheWrite: 0,
32070
+ },
32071
+ contextWindow: 1000000,
32072
+ maxTokens: 128000,
32073
+ },
32074
+ "gpt-6-astra": {
32075
+ id: "gpt-6-astra",
32076
+ name: "GPT-6 Astra (WorkBuddy)",
32077
+ api: "openai-completions",
32078
+ provider: "workbuddy",
32079
+ baseUrl: "https://www.workbuddy.ai/v2",
32080
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32081
+ reasoning: true,
32082
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max", "ultra": null },
32083
+ input: ["text", "image"],
32084
+ cost: {
32085
+ input: 0,
32086
+ output: 0,
32087
+ cacheRead: 0,
32088
+ cacheWrite: 0,
32089
+ },
32090
+ contextWindow: 1050000,
32091
+ maxTokens: 128000,
32092
+ },
32093
+ "grok-4.6": {
32094
+ id: "grok-4.6",
32095
+ name: "Grok 4.6 (WorkBuddy)",
32096
+ api: "openai-completions",
32097
+ provider: "workbuddy",
32098
+ baseUrl: "https://www.workbuddy.ai/v2",
32099
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32100
+ reasoning: true,
32101
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "xhigh", "ultra": null },
32102
+ input: ["text", "image"],
32103
+ cost: {
32104
+ input: 0,
32105
+ output: 0,
32106
+ cacheRead: 0,
32107
+ cacheWrite: 0,
32108
+ },
32109
+ contextWindow: 500000,
32110
+ maxTokens: 500000,
32111
+ },
32112
+ "hy3": {
32113
+ id: "hy3",
32114
+ name: "Hy3 (WorkBuddy)",
32115
+ api: "openai-completions",
32116
+ provider: "workbuddy",
32117
+ baseUrl: "https://www.workbuddy.ai/v2",
32118
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32119
+ reasoning: true,
32120
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
32121
+ input: ["text", "image"],
32122
+ cost: {
32123
+ input: 0,
32124
+ output: 0,
32125
+ cacheRead: 0,
32126
+ cacheWrite: 0,
32127
+ },
32128
+ contextWindow: 192000,
32129
+ maxTokens: 64000,
32130
+ },
32131
+ "hy4-preview": {
32132
+ id: "hy4-preview",
32133
+ name: "Hunyuan hy4 Preview (WorkBuddy)",
32134
+ api: "openai-completions",
32135
+ provider: "workbuddy",
32136
+ baseUrl: "https://www.workbuddy.ai/v2",
32137
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32138
+ reasoning: true,
32139
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
32140
+ input: ["text"],
32141
+ cost: {
32142
+ input: 0,
32143
+ output: 0,
32144
+ cacheRead: 0,
32145
+ cacheWrite: 0,
32146
+ },
32147
+ contextWindow: 1048576,
32148
+ maxTokens: 64000,
32149
+ },
32150
+ "kimi-k2.5": {
32151
+ id: "kimi-k2.5",
32152
+ name: "Kimi-K2.5 (WorkBuddy)",
32153
+ api: "openai-completions",
32154
+ provider: "workbuddy",
32155
+ baseUrl: "https://www.workbuddy.ai/v2",
32156
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32157
+ reasoning: true,
32158
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null, "ultra": null },
32159
+ input: ["text", "image"],
32160
+ cost: {
32161
+ input: 0,
32162
+ output: 0,
32163
+ cacheRead: 0,
32164
+ cacheWrite: 0,
32165
+ },
32166
+ contextWindow: 164000,
32167
+ maxTokens: 32000,
32168
+ },
32169
+ "kimi-k2.6": {
32170
+ id: "kimi-k2.6",
32171
+ name: "Kimi-K2.6 (WorkBuddy)",
32172
+ api: "openai-completions",
32173
+ provider: "workbuddy",
32174
+ baseUrl: "https://www.workbuddy.ai/v2",
32175
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32176
+ reasoning: true,
32177
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
32178
+ input: ["text", "image"],
32179
+ cost: {
32180
+ input: 0,
32181
+ output: 0,
32182
+ cacheRead: 0,
32183
+ cacheWrite: 0,
32184
+ },
32185
+ contextWindow: 256000,
32186
+ maxTokens: 32000,
32187
+ },
32188
+ "kimi-k3": {
32189
+ id: "kimi-k3",
32190
+ name: "Kimi-K3 (WorkBuddy)",
32191
+ api: "openai-completions",
32192
+ provider: "workbuddy",
32193
+ baseUrl: "https://www.workbuddy.ai/v2",
32194
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32195
+ reasoning: true,
32196
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
32197
+ input: ["text", "image"],
32198
+ cost: {
32199
+ input: 0,
32200
+ output: 0,
32201
+ cacheRead: 0,
32202
+ cacheWrite: 0,
32203
+ },
32204
+ contextWindow: 1000000,
32205
+ maxTokens: 32000,
32206
+ },
32207
+ "minimax-m3": {
32208
+ id: "minimax-m3",
32209
+ name: "MiniMax-M3 (WorkBuddy)",
32210
+ api: "openai-completions",
32211
+ provider: "workbuddy",
32212
+ baseUrl: "https://www.workbuddy.ai/v2",
32213
+ compat: { "supportsDeveloperRole": false, "maxTokensField": "max_tokens", "supportsUsageInStreaming": true, "requiresSystemMessageFirst": true },
32214
+ reasoning: true,
32215
+ thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": "medium", "high": null, "xhigh": null, "max": null, "ultra": null },
32216
+ input: ["text", "image"],
32217
+ cost: {
32218
+ input: 0,
32219
+ output: 0,
32220
+ cacheRead: 0,
32221
+ cacheWrite: 0,
32222
+ },
32223
+ contextWindow: 512000,
32224
+ maxTokens: 128000,
32225
+ },
32226
+ },
32227
+ "xai": {
32228
+ "grok-3": {
32229
+ id: "grok-3",
32230
+ name: "Grok 3",
32231
+ api: "openai-completions",
32232
+ provider: "xai",
32233
+ baseUrl: "https://api.x.ai/v1",
32234
+ reasoning: false,
32235
+ input: ["text"],
32236
+ cost: {
32237
+ input: 3,
32238
+ output: 15,
32239
+ cacheRead: 0.75,
32240
+ cacheWrite: 0,
32241
+ },
32242
+ contextWindow: 131072,
32243
+ maxTokens: 8192,
32244
+ },
32245
+ "grok-3-fast": {
32246
+ id: "grok-3-fast",
32247
+ name: "Grok 3 Fast",
32248
+ api: "openai-completions",
32249
+ provider: "xai",
32250
+ baseUrl: "https://api.x.ai/v1",
32251
+ reasoning: false,
32252
+ input: ["text"],
32253
+ cost: {
32254
+ input: 5,
32255
+ output: 25,
32256
+ cacheRead: 1.25,
32257
+ cacheWrite: 0,
32258
+ },
32259
+ contextWindow: 131072,
32260
+ maxTokens: 8192,
32261
+ },
32262
+ "grok-4.20-0309-non-reasoning": {
32263
+ id: "grok-4.20-0309-non-reasoning",
32264
+ name: "Grok 4.20 (Non-Reasoning)",
32265
+ api: "openai-completions",
32266
+ provider: "xai",
32267
+ baseUrl: "https://api.x.ai/v1",
32268
+ reasoning: false,
32269
+ input: ["text", "image"],
32270
+ cost: {
32271
+ input: 1.25,
32272
+ output: 2.5,
32273
+ cacheRead: 0.2,
32274
+ cacheWrite: 0,
32275
+ },
32276
+ contextWindow: 1000000,
32277
+ maxTokens: 30000,
32278
+ },
32279
+ "grok-4.20-0309-reasoning": {
32280
+ id: "grok-4.20-0309-reasoning",
32281
+ name: "Grok 4.20 (Reasoning)",
32282
+ api: "openai-completions",
32283
+ provider: "xai",
32284
+ baseUrl: "https://api.x.ai/v1",
32285
+ reasoning: true,
32286
+ input: ["text", "image"],
32287
+ cost: {
32288
+ input: 1.25,
32289
+ output: 2.5,
32290
+ cacheRead: 0.2,
32291
+ cacheWrite: 0,
32292
+ },
32293
+ contextWindow: 1000000,
32294
+ maxTokens: 30000,
32295
+ },
32296
+ "grok-4.3": {
32297
+ id: "grok-4.3",
32298
+ name: "Grok 4.3",
32299
+ api: "openai-completions",
32300
+ provider: "xai",
32301
+ baseUrl: "https://api.x.ai/v1",
32302
+ reasoning: true,
32303
+ input: ["text", "image"],
32304
+ cost: {
32305
+ input: 1.25,
32306
+ output: 2.5,
32307
+ cacheRead: 0.2,
32308
+ cacheWrite: 0,
32309
+ },
32310
+ contextWindow: 1000000,
32311
+ maxTokens: 30000,
32312
+ },
32313
+ "grok-4.5": {
32314
+ id: "grok-4.5",
32315
+ name: "Grok 4.5",
32316
+ api: "openai-completions",
32317
+ provider: "xai",
32318
+ baseUrl: "https://api.x.ai/v1",
32319
+ reasoning: true,
32320
+ input: ["text", "image"],
32321
+ cost: {
32322
+ input: 2,
32323
+ output: 6,
32324
+ cacheRead: 0.3,
32325
+ cacheWrite: 0,
32326
+ },
32327
+ contextWindow: 500000,
32328
+ maxTokens: 500000,
32329
+ },
32330
+ "grok-4.6": {
31087
32331
  id: "grok-4.6",
31088
32332
  name: "Grok 4.6",
31089
32333
  api: "openai-completions",
@@ -31101,6 +32345,24 @@ export const MODELS = {
31101
32345
  contextWindow: 500000,
31102
32346
  maxTokens: 500000,
31103
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
+ },
31104
32366
  "grok-build-0.1": {
31105
32367
  id: "grok-build-0.1",
31106
32368
  name: "Grok Build 0.1",
@@ -31245,6 +32507,60 @@ export const MODELS = {
31245
32507
  contextWindow: 1048576,
31246
32508
  maxTokens: 131072,
31247
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
+ },
31248
32564
  },
31249
32565
  "xiaomi-token-plan-ams": {
31250
32566
  "mimo-v2-omni": {
@@ -31337,6 +32653,60 @@ export const MODELS = {
31337
32653
  contextWindow: 1048576,
31338
32654
  maxTokens: 131072,
31339
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
+ },
31340
32710
  },
31341
32711
  "xiaomi-token-plan-cn": {
31342
32712
  "mimo-v2-omni": {
@@ -31429,6 +32799,60 @@ export const MODELS = {
31429
32799
  contextWindow: 1048576,
31430
32800
  maxTokens: 131072,
31431
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
+ },
31432
32856
  },
31433
32857
  "xiaomi-token-plan-sgp": {
31434
32858
  "mimo-v2-omni": {
@@ -31521,6 +32945,60 @@ export const MODELS = {
31521
32945
  contextWindow: 1048576,
31522
32946
  maxTokens: 131072,
31523
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
+ },
31524
33002
  },
31525
33003
  "zai": {
31526
33004
  "glm-4.7": {