@draht/ai 2026.3.14 → 2026.3.25

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 (82) hide show
  1. package/README.md +28 -0
  2. package/dist/cli.js +0 -0
  3. package/dist/index.d.ts +10 -8
  4. package/dist/index.d.ts.map +1 -1
  5. package/dist/index.js +0 -8
  6. package/dist/index.js.map +1 -1
  7. package/dist/models.d.ts +1 -1
  8. package/dist/models.d.ts.map +1 -1
  9. package/dist/models.generated.d.ts +593 -175
  10. package/dist/models.generated.d.ts.map +1 -1
  11. package/dist/models.generated.js +781 -371
  12. package/dist/models.generated.js.map +1 -1
  13. package/dist/models.js +3 -3
  14. package/dist/models.js.map +1 -1
  15. package/dist/providers/amazon-bedrock.d.ts +5 -0
  16. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  17. package/dist/providers/amazon-bedrock.js +32 -9
  18. package/dist/providers/amazon-bedrock.js.map +1 -1
  19. package/dist/providers/anthropic.d.ts +7 -0
  20. package/dist/providers/anthropic.d.ts.map +1 -1
  21. package/dist/providers/anthropic.js +42 -25
  22. package/dist/providers/anthropic.js.map +1 -1
  23. package/dist/providers/azure-openai-responses.d.ts.map +1 -1
  24. package/dist/providers/azure-openai-responses.js +1 -12
  25. package/dist/providers/azure-openai-responses.js.map +1 -1
  26. package/dist/providers/google-gemini-cli.d.ts.map +1 -1
  27. package/dist/providers/google-gemini-cli.js +19 -0
  28. package/dist/providers/google-gemini-cli.js.map +1 -1
  29. package/dist/providers/google-shared.d.ts.map +1 -1
  30. package/dist/providers/google-shared.js +20 -8
  31. package/dist/providers/google-shared.js.map +1 -1
  32. package/dist/providers/google-vertex.d.ts.map +1 -1
  33. package/dist/providers/google-vertex.js +28 -1
  34. package/dist/providers/google-vertex.js.map +1 -1
  35. package/dist/providers/google.d.ts.map +1 -1
  36. package/dist/providers/google.js +19 -0
  37. package/dist/providers/google.js.map +1 -1
  38. package/dist/providers/mistral.d.ts.map +1 -1
  39. package/dist/providers/mistral.js +3 -0
  40. package/dist/providers/mistral.js.map +1 -1
  41. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  42. package/dist/providers/openai-codex-responses.js +72 -35
  43. package/dist/providers/openai-codex-responses.js.map +1 -1
  44. package/dist/providers/openai-completions.d.ts.map +1 -1
  45. package/dist/providers/openai-completions.js +53 -16
  46. package/dist/providers/openai-completions.js.map +1 -1
  47. package/dist/providers/openai-responses-shared.d.ts.map +1 -1
  48. package/dist/providers/openai-responses-shared.js +43 -39
  49. package/dist/providers/openai-responses-shared.js.map +1 -1
  50. package/dist/providers/openai-responses.d.ts.map +1 -1
  51. package/dist/providers/openai-responses.js +2 -13
  52. package/dist/providers/openai-responses.js.map +1 -1
  53. package/dist/providers/register-builtins.d.ts +28 -1
  54. package/dist/providers/register-builtins.d.ts.map +1 -1
  55. package/dist/providers/register-builtins.js +170 -47
  56. package/dist/providers/register-builtins.js.map +1 -1
  57. package/dist/types.d.ts +11 -2
  58. package/dist/types.d.ts.map +1 -1
  59. package/dist/types.js.map +1 -1
  60. package/dist/utils/oauth/anthropic.d.ts +14 -6
  61. package/dist/utils/oauth/anthropic.d.ts.map +1 -1
  62. package/dist/utils/oauth/anthropic.js +288 -57
  63. package/dist/utils/oauth/anthropic.js.map +1 -1
  64. package/dist/utils/oauth/google-antigravity.d.ts.map +1 -1
  65. package/dist/utils/oauth/google-antigravity.js +22 -19
  66. package/dist/utils/oauth/google-antigravity.js.map +1 -1
  67. package/dist/utils/oauth/google-gemini-cli.d.ts.map +1 -1
  68. package/dist/utils/oauth/google-gemini-cli.js +22 -19
  69. package/dist/utils/oauth/google-gemini-cli.js.map +1 -1
  70. package/dist/utils/oauth/oauth-page.d.ts +3 -0
  71. package/dist/utils/oauth/oauth-page.d.ts.map +1 -0
  72. package/dist/utils/oauth/oauth-page.js +105 -0
  73. package/dist/utils/oauth/oauth-page.js.map +1 -0
  74. package/dist/utils/oauth/openai-codex.d.ts.map +1 -1
  75. package/dist/utils/oauth/openai-codex.js +24 -31
  76. package/dist/utils/oauth/openai-codex.js.map +1 -1
  77. package/dist/utils/validation.d.ts.map +1 -1
  78. package/dist/utils/validation.js +17 -9
  79. package/dist/utils/validation.js.map +1 -1
  80. package/package.json +39 -5
  81. package/bedrock-provider.d.ts +0 -1
  82. package/bedrock-provider.js +0 -1
@@ -254,7 +254,7 @@ export const MODELS = {
254
254
  cacheRead: 0.5,
255
255
  cacheWrite: 6.25,
256
256
  },
257
- contextWindow: 200000,
257
+ contextWindow: 1000000,
258
258
  maxTokens: 128000,
259
259
  },
260
260
  "anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -305,7 +305,7 @@ export const MODELS = {
305
305
  cacheRead: 0.3,
306
306
  cacheWrite: 3.75,
307
307
  },
308
- contextWindow: 200000,
308
+ contextWindow: 1000000,
309
309
  maxTokens: 64000,
310
310
  },
311
311
  "deepseek.r1-v1:0": {
@@ -407,7 +407,7 @@ export const MODELS = {
407
407
  cacheRead: 0.5,
408
408
  cacheWrite: 6.25,
409
409
  },
410
- contextWindow: 200000,
410
+ contextWindow: 1000000,
411
411
  maxTokens: 128000,
412
412
  },
413
413
  "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -458,7 +458,7 @@ export const MODELS = {
458
458
  cacheRead: 0.3,
459
459
  cacheWrite: 3.75,
460
460
  },
461
- contextWindow: 200000,
461
+ contextWindow: 1000000,
462
462
  maxTokens: 64000,
463
463
  },
464
464
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -509,7 +509,7 @@ export const MODELS = {
509
509
  cacheRead: 0.5,
510
510
  cacheWrite: 6.25,
511
511
  },
512
- contextWindow: 200000,
512
+ contextWindow: 1000000,
513
513
  maxTokens: 128000,
514
514
  },
515
515
  "global.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -560,7 +560,7 @@ export const MODELS = {
560
560
  cacheRead: 0.3,
561
561
  cacheWrite: 3.75,
562
562
  },
563
- contextWindow: 200000,
563
+ contextWindow: 1000000,
564
564
  maxTokens: 64000,
565
565
  },
566
566
  "google.gemma-3-27b-it": {
@@ -801,6 +801,23 @@ export const MODELS = {
801
801
  contextWindow: 204800,
802
802
  maxTokens: 131072,
803
803
  },
804
+ "minimax.minimax-m2.5": {
805
+ id: "minimax.minimax-m2.5",
806
+ name: "MiniMax M2.5",
807
+ api: "bedrock-converse-stream",
808
+ provider: "amazon-bedrock",
809
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
810
+ reasoning: true,
811
+ input: ["text"],
812
+ cost: {
813
+ input: 0.3,
814
+ output: 1.2,
815
+ cacheRead: 0,
816
+ cacheWrite: 0,
817
+ },
818
+ contextWindow: 1000000,
819
+ maxTokens: 131072,
820
+ },
804
821
  "mistral.devstral-2-123b": {
805
822
  id: "mistral.devstral-2-123b",
806
823
  name: "Devstral 2 123B",
@@ -1291,7 +1308,7 @@ export const MODELS = {
1291
1308
  cacheRead: 0.5,
1292
1309
  cacheWrite: 6.25,
1293
1310
  },
1294
- contextWindow: 200000,
1311
+ contextWindow: 1000000,
1295
1312
  maxTokens: 128000,
1296
1313
  },
1297
1314
  "us.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -1342,7 +1359,7 @@ export const MODELS = {
1342
1359
  cacheRead: 0.3,
1343
1360
  cacheWrite: 3.75,
1344
1361
  },
1345
- contextWindow: 200000,
1362
+ contextWindow: 1000000,
1346
1363
  maxTokens: 64000,
1347
1364
  },
1348
1365
  "writer.palmyra-x4-v1:0": {
@@ -1413,6 +1430,23 @@ export const MODELS = {
1413
1430
  contextWindow: 200000,
1414
1431
  maxTokens: 131072,
1415
1432
  },
1433
+ "zai.glm-5": {
1434
+ id: "zai.glm-5",
1435
+ name: "GLM-5",
1436
+ api: "bedrock-converse-stream",
1437
+ provider: "amazon-bedrock",
1438
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1439
+ reasoning: true,
1440
+ input: ["text"],
1441
+ cost: {
1442
+ input: 1,
1443
+ output: 3.2,
1444
+ cacheRead: 0,
1445
+ cacheWrite: 0,
1446
+ },
1447
+ contextWindow: 200000,
1448
+ maxTokens: 131072,
1449
+ },
1416
1450
  },
1417
1451
  "anthropic": {
1418
1452
  "claude-3-5-haiku-20241022": {
@@ -1718,7 +1752,7 @@ export const MODELS = {
1718
1752
  cacheRead: 0.5,
1719
1753
  cacheWrite: 6.25,
1720
1754
  },
1721
- contextWindow: 200000,
1755
+ contextWindow: 1000000,
1722
1756
  maxTokens: 128000,
1723
1757
  },
1724
1758
  "claude-sonnet-4-0": {
@@ -2301,6 +2335,40 @@ export const MODELS = {
2301
2335
  contextWindow: 272000,
2302
2336
  maxTokens: 128000,
2303
2337
  },
2338
+ "gpt-5.4-mini": {
2339
+ id: "gpt-5.4-mini",
2340
+ name: "GPT-5.4 mini",
2341
+ api: "azure-openai-responses",
2342
+ provider: "azure-openai-responses",
2343
+ baseUrl: "",
2344
+ reasoning: true,
2345
+ input: ["text", "image"],
2346
+ cost: {
2347
+ input: 0.75,
2348
+ output: 4.5,
2349
+ cacheRead: 0.075,
2350
+ cacheWrite: 0,
2351
+ },
2352
+ contextWindow: 400000,
2353
+ maxTokens: 128000,
2354
+ },
2355
+ "gpt-5.4-nano": {
2356
+ id: "gpt-5.4-nano",
2357
+ name: "GPT-5.4 nano",
2358
+ api: "azure-openai-responses",
2359
+ provider: "azure-openai-responses",
2360
+ baseUrl: "",
2361
+ reasoning: true,
2362
+ input: ["text", "image"],
2363
+ cost: {
2364
+ input: 0.2,
2365
+ output: 1.25,
2366
+ cacheRead: 0.02,
2367
+ cacheWrite: 0,
2368
+ },
2369
+ contextWindow: 400000,
2370
+ maxTokens: 128000,
2371
+ },
2304
2372
  "gpt-5.4-pro": {
2305
2373
  id: "gpt-5.4-pro",
2306
2374
  name: "GPT-5.4 Pro",
@@ -2541,7 +2609,7 @@ export const MODELS = {
2541
2609
  cacheRead: 0,
2542
2610
  cacheWrite: 0,
2543
2611
  },
2544
- contextWindow: 128000,
2612
+ contextWindow: 144000,
2545
2613
  maxTokens: 32000,
2546
2614
  },
2547
2615
  "claude-opus-4.5": {
@@ -2559,7 +2627,7 @@ export const MODELS = {
2559
2627
  cacheRead: 0,
2560
2628
  cacheWrite: 0,
2561
2629
  },
2562
- contextWindow: 128000,
2630
+ contextWindow: 160000,
2563
2631
  maxTokens: 32000,
2564
2632
  },
2565
2633
  "claude-opus-4.6": {
@@ -2577,7 +2645,7 @@ export const MODELS = {
2577
2645
  cacheRead: 0,
2578
2646
  cacheWrite: 0,
2579
2647
  },
2580
- contextWindow: 128000,
2648
+ contextWindow: 1000000,
2581
2649
  maxTokens: 64000,
2582
2650
  },
2583
2651
  "claude-sonnet-4": {
@@ -2595,7 +2663,7 @@ export const MODELS = {
2595
2663
  cacheRead: 0,
2596
2664
  cacheWrite: 0,
2597
2665
  },
2598
- contextWindow: 128000,
2666
+ contextWindow: 216000,
2599
2667
  maxTokens: 16000,
2600
2668
  },
2601
2669
  "claude-sonnet-4.5": {
@@ -2613,7 +2681,7 @@ export const MODELS = {
2613
2681
  cacheRead: 0,
2614
2682
  cacheWrite: 0,
2615
2683
  },
2616
- contextWindow: 128000,
2684
+ contextWindow: 144000,
2617
2685
  maxTokens: 32000,
2618
2686
  },
2619
2687
  "claude-sonnet-4.6": {
@@ -2631,7 +2699,7 @@ export const MODELS = {
2631
2699
  cacheRead: 0,
2632
2700
  cacheWrite: 0,
2633
2701
  },
2634
- contextWindow: 128000,
2702
+ contextWindow: 1000000,
2635
2703
  maxTokens: 32000,
2636
2704
  },
2637
2705
  "gemini-2.5-pro": {
@@ -2726,7 +2794,7 @@ export const MODELS = {
2726
2794
  cacheRead: 0,
2727
2795
  cacheWrite: 0,
2728
2796
  },
2729
- contextWindow: 64000,
2797
+ contextWindow: 128000,
2730
2798
  maxTokens: 16384,
2731
2799
  },
2732
2800
  "gpt-4o": {
@@ -2745,8 +2813,8 @@ export const MODELS = {
2745
2813
  cacheRead: 0,
2746
2814
  cacheWrite: 0,
2747
2815
  },
2748
- contextWindow: 64000,
2749
- maxTokens: 16384,
2816
+ contextWindow: 128000,
2817
+ maxTokens: 4096,
2750
2818
  },
2751
2819
  "gpt-5": {
2752
2820
  id: "gpt-5",
@@ -2781,7 +2849,7 @@ export const MODELS = {
2781
2849
  cacheRead: 0,
2782
2850
  cacheWrite: 0,
2783
2851
  },
2784
- contextWindow: 128000,
2852
+ contextWindow: 264000,
2785
2853
  maxTokens: 64000,
2786
2854
  },
2787
2855
  "gpt-5.1": {
@@ -2799,7 +2867,7 @@ export const MODELS = {
2799
2867
  cacheRead: 0,
2800
2868
  cacheWrite: 0,
2801
2869
  },
2802
- contextWindow: 128000,
2870
+ contextWindow: 264000,
2803
2871
  maxTokens: 64000,
2804
2872
  },
2805
2873
  "gpt-5.1-codex": {
@@ -2817,7 +2885,7 @@ export const MODELS = {
2817
2885
  cacheRead: 0,
2818
2886
  cacheWrite: 0,
2819
2887
  },
2820
- contextWindow: 128000,
2888
+ contextWindow: 400000,
2821
2889
  maxTokens: 128000,
2822
2890
  },
2823
2891
  "gpt-5.1-codex-max": {
@@ -2835,7 +2903,7 @@ export const MODELS = {
2835
2903
  cacheRead: 0,
2836
2904
  cacheWrite: 0,
2837
2905
  },
2838
- contextWindow: 128000,
2906
+ contextWindow: 400000,
2839
2907
  maxTokens: 128000,
2840
2908
  },
2841
2909
  "gpt-5.1-codex-mini": {
@@ -2853,7 +2921,7 @@ export const MODELS = {
2853
2921
  cacheRead: 0,
2854
2922
  cacheWrite: 0,
2855
2923
  },
2856
- contextWindow: 128000,
2924
+ contextWindow: 400000,
2857
2925
  maxTokens: 128000,
2858
2926
  },
2859
2927
  "gpt-5.2": {
@@ -2928,6 +2996,24 @@ export const MODELS = {
2928
2996
  contextWindow: 400000,
2929
2997
  maxTokens: 128000,
2930
2998
  },
2999
+ "gpt-5.4-mini": {
3000
+ id: "gpt-5.4-mini",
3001
+ name: "GPT-5.4 mini",
3002
+ api: "openai-responses",
3003
+ provider: "github-copilot",
3004
+ baseUrl: "https://api.individual.githubcopilot.com",
3005
+ 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" },
3006
+ reasoning: true,
3007
+ input: ["text", "image"],
3008
+ cost: {
3009
+ input: 0,
3010
+ output: 0,
3011
+ cacheRead: 0,
3012
+ cacheWrite: 0,
3013
+ },
3014
+ contextWindow: 400000,
3015
+ maxTokens: 128000,
3016
+ },
2931
3017
  "grok-code-fast-1": {
2932
3018
  id: "grok-code-fast-1",
2933
3019
  name: "Grok Code Fast 1",
@@ -4457,8 +4543,8 @@ export const MODELS = {
4457
4543
  cacheRead: 0,
4458
4544
  cacheWrite: 0,
4459
4545
  },
4460
- contextWindow: 196608,
4461
- maxTokens: 128000,
4546
+ contextWindow: 204800,
4547
+ maxTokens: 131072,
4462
4548
  },
4463
4549
  "MiniMax-M2.1": {
4464
4550
  id: "MiniMax-M2.1",
@@ -4477,6 +4563,23 @@ export const MODELS = {
4477
4563
  contextWindow: 204800,
4478
4564
  maxTokens: 131072,
4479
4565
  },
4566
+ "MiniMax-M2.1-highspeed": {
4567
+ id: "MiniMax-M2.1-highspeed",
4568
+ name: "MiniMax-M2.1-highspeed",
4569
+ api: "anthropic-messages",
4570
+ provider: "minimax",
4571
+ baseUrl: "https://api.minimax.io/anthropic",
4572
+ reasoning: true,
4573
+ input: ["text"],
4574
+ cost: {
4575
+ input: 0.6,
4576
+ output: 2.4,
4577
+ cacheRead: 0,
4578
+ cacheWrite: 0,
4579
+ },
4580
+ contextWindow: 204800,
4581
+ maxTokens: 131072,
4582
+ },
4480
4583
  "MiniMax-M2.5": {
4481
4584
  id: "MiniMax-M2.5",
4482
4585
  name: "MiniMax-M2.5",
@@ -4511,6 +4614,40 @@ export const MODELS = {
4511
4614
  contextWindow: 204800,
4512
4615
  maxTokens: 131072,
4513
4616
  },
4617
+ "MiniMax-M2.7": {
4618
+ id: "MiniMax-M2.7",
4619
+ name: "MiniMax-M2.7",
4620
+ api: "anthropic-messages",
4621
+ provider: "minimax",
4622
+ baseUrl: "https://api.minimax.io/anthropic",
4623
+ reasoning: true,
4624
+ input: ["text"],
4625
+ cost: {
4626
+ input: 0.3,
4627
+ output: 1.2,
4628
+ cacheRead: 0.06,
4629
+ cacheWrite: 0.375,
4630
+ },
4631
+ contextWindow: 204800,
4632
+ maxTokens: 131072,
4633
+ },
4634
+ "MiniMax-M2.7-highspeed": {
4635
+ id: "MiniMax-M2.7-highspeed",
4636
+ name: "MiniMax-M2.7-highspeed",
4637
+ api: "anthropic-messages",
4638
+ provider: "minimax",
4639
+ baseUrl: "https://api.minimax.io/anthropic",
4640
+ reasoning: true,
4641
+ input: ["text"],
4642
+ cost: {
4643
+ input: 0.6,
4644
+ output: 2.4,
4645
+ cacheRead: 0.06,
4646
+ cacheWrite: 0.375,
4647
+ },
4648
+ contextWindow: 204800,
4649
+ maxTokens: 131072,
4650
+ },
4514
4651
  },
4515
4652
  "minimax-cn": {
4516
4653
  "MiniMax-M2": {
@@ -4527,8 +4664,8 @@ export const MODELS = {
4527
4664
  cacheRead: 0,
4528
4665
  cacheWrite: 0,
4529
4666
  },
4530
- contextWindow: 196608,
4531
- maxTokens: 128000,
4667
+ contextWindow: 204800,
4668
+ maxTokens: 131072,
4532
4669
  },
4533
4670
  "MiniMax-M2.1": {
4534
4671
  id: "MiniMax-M2.1",
@@ -4547,6 +4684,23 @@ export const MODELS = {
4547
4684
  contextWindow: 204800,
4548
4685
  maxTokens: 131072,
4549
4686
  },
4687
+ "MiniMax-M2.1-highspeed": {
4688
+ id: "MiniMax-M2.1-highspeed",
4689
+ name: "MiniMax-M2.1-highspeed",
4690
+ api: "anthropic-messages",
4691
+ provider: "minimax-cn",
4692
+ baseUrl: "https://api.minimaxi.com/anthropic",
4693
+ reasoning: true,
4694
+ input: ["text"],
4695
+ cost: {
4696
+ input: 0.6,
4697
+ output: 2.4,
4698
+ cacheRead: 0,
4699
+ cacheWrite: 0,
4700
+ },
4701
+ contextWindow: 204800,
4702
+ maxTokens: 131072,
4703
+ },
4550
4704
  "MiniMax-M2.5": {
4551
4705
  id: "MiniMax-M2.5",
4552
4706
  name: "MiniMax-M2.5",
@@ -4581,6 +4735,40 @@ export const MODELS = {
4581
4735
  contextWindow: 204800,
4582
4736
  maxTokens: 131072,
4583
4737
  },
4738
+ "MiniMax-M2.7": {
4739
+ id: "MiniMax-M2.7",
4740
+ name: "MiniMax-M2.7",
4741
+ api: "anthropic-messages",
4742
+ provider: "minimax-cn",
4743
+ baseUrl: "https://api.minimaxi.com/anthropic",
4744
+ reasoning: true,
4745
+ input: ["text"],
4746
+ cost: {
4747
+ input: 0.3,
4748
+ output: 1.2,
4749
+ cacheRead: 0.06,
4750
+ cacheWrite: 0.375,
4751
+ },
4752
+ contextWindow: 204800,
4753
+ maxTokens: 131072,
4754
+ },
4755
+ "MiniMax-M2.7-highspeed": {
4756
+ id: "MiniMax-M2.7-highspeed",
4757
+ name: "MiniMax-M2.7-highspeed",
4758
+ api: "anthropic-messages",
4759
+ provider: "minimax-cn",
4760
+ baseUrl: "https://api.minimaxi.com/anthropic",
4761
+ reasoning: true,
4762
+ input: ["text"],
4763
+ cost: {
4764
+ input: 0.6,
4765
+ output: 2.4,
4766
+ cacheRead: 0.06,
4767
+ cacheWrite: 0.375,
4768
+ },
4769
+ contextWindow: 204800,
4770
+ maxTokens: 131072,
4771
+ },
4584
4772
  },
4585
4773
  "mistral": {
4586
4774
  "codestral-latest": {
@@ -5503,6 +5691,40 @@ export const MODELS = {
5503
5691
  contextWindow: 272000,
5504
5692
  maxTokens: 128000,
5505
5693
  },
5694
+ "gpt-5.4-mini": {
5695
+ id: "gpt-5.4-mini",
5696
+ name: "GPT-5.4 mini",
5697
+ api: "openai-responses",
5698
+ provider: "openai",
5699
+ baseUrl: "https://api.openai.com/v1",
5700
+ reasoning: true,
5701
+ input: ["text", "image"],
5702
+ cost: {
5703
+ input: 0.75,
5704
+ output: 4.5,
5705
+ cacheRead: 0.075,
5706
+ cacheWrite: 0,
5707
+ },
5708
+ contextWindow: 400000,
5709
+ maxTokens: 128000,
5710
+ },
5711
+ "gpt-5.4-nano": {
5712
+ id: "gpt-5.4-nano",
5713
+ name: "GPT-5.4 nano",
5714
+ api: "openai-responses",
5715
+ provider: "openai",
5716
+ baseUrl: "https://api.openai.com/v1",
5717
+ reasoning: true,
5718
+ input: ["text", "image"],
5719
+ cost: {
5720
+ input: 0.2,
5721
+ output: 1.25,
5722
+ cacheRead: 0.02,
5723
+ cacheWrite: 0,
5724
+ },
5725
+ contextWindow: 400000,
5726
+ maxTokens: 128000,
5727
+ },
5506
5728
  "gpt-5.4-pro": {
5507
5729
  id: "gpt-5.4-pro",
5508
5730
  name: "GPT-5.4 Pro",
@@ -5794,6 +6016,23 @@ export const MODELS = {
5794
6016
  contextWindow: 272000,
5795
6017
  maxTokens: 128000,
5796
6018
  },
6019
+ "gpt-5.4-mini": {
6020
+ id: "gpt-5.4-mini",
6021
+ name: "GPT-5.4 Mini",
6022
+ api: "openai-codex-responses",
6023
+ provider: "openai-codex",
6024
+ baseUrl: "https://chatgpt.com/backend-api",
6025
+ reasoning: true,
6026
+ input: ["text", "image"],
6027
+ cost: {
6028
+ input: 0.75,
6029
+ output: 4.5,
6030
+ cacheRead: 0.075,
6031
+ cacheWrite: 0,
6032
+ },
6033
+ contextWindow: 272000,
6034
+ maxTokens: 128000,
6035
+ },
5797
6036
  },
5798
6037
  "opencode": {
5799
6038
  "big-pickle": {
@@ -5895,7 +6134,7 @@ export const MODELS = {
5895
6134
  cacheRead: 0.5,
5896
6135
  cacheWrite: 6.25,
5897
6136
  },
5898
- contextWindow: 200000,
6137
+ contextWindow: 1000000,
5899
6138
  maxTokens: 128000,
5900
6139
  },
5901
6140
  "claude-sonnet-4": {
@@ -5966,9 +6205,9 @@ export const MODELS = {
5966
6205
  contextWindow: 1048576,
5967
6206
  maxTokens: 65536,
5968
6207
  },
5969
- "gemini-3-pro": {
5970
- id: "gemini-3-pro",
5971
- name: "Gemini 3 Pro",
6208
+ "gemini-3.1-pro": {
6209
+ id: "gemini-3.1-pro",
6210
+ name: "Gemini 3.1 Pro Preview",
5972
6211
  api: "google-generative-ai",
5973
6212
  provider: "opencode",
5974
6213
  baseUrl: "https://opencode.ai/zen/v1",
@@ -5983,57 +6222,6 @@ export const MODELS = {
5983
6222
  contextWindow: 1048576,
5984
6223
  maxTokens: 65536,
5985
6224
  },
5986
- "gemini-3.1-pro": {
5987
- id: "gemini-3.1-pro",
5988
- name: "Gemini 3.1 Pro Preview",
5989
- api: "google-generative-ai",
5990
- provider: "opencode",
5991
- baseUrl: "https://opencode.ai/zen/v1",
5992
- reasoning: true,
5993
- input: ["text", "image"],
5994
- cost: {
5995
- input: 2,
5996
- output: 12,
5997
- cacheRead: 0.2,
5998
- cacheWrite: 0,
5999
- },
6000
- contextWindow: 1048576,
6001
- maxTokens: 65536,
6002
- },
6003
- "glm-4.6": {
6004
- id: "glm-4.6",
6005
- name: "GLM-4.6",
6006
- api: "openai-completions",
6007
- provider: "opencode",
6008
- baseUrl: "https://opencode.ai/zen/v1",
6009
- reasoning: true,
6010
- input: ["text"],
6011
- cost: {
6012
- input: 0.6,
6013
- output: 2.2,
6014
- cacheRead: 0.1,
6015
- cacheWrite: 0,
6016
- },
6017
- contextWindow: 204800,
6018
- maxTokens: 131072,
6019
- },
6020
- "glm-4.7": {
6021
- id: "glm-4.7",
6022
- name: "GLM-4.7",
6023
- api: "openai-completions",
6024
- provider: "opencode",
6025
- baseUrl: "https://opencode.ai/zen/v1",
6026
- reasoning: true,
6027
- input: ["text"],
6028
- cost: {
6029
- input: 0.6,
6030
- output: 2.2,
6031
- cacheRead: 0.1,
6032
- cacheWrite: 0,
6033
- },
6034
- contextWindow: 204800,
6035
- maxTokens: 131072,
6036
- },
6037
6225
  "glm-5": {
6038
6226
  id: "glm-5",
6039
6227
  name: "GLM-5",
@@ -6238,6 +6426,40 @@ export const MODELS = {
6238
6426
  contextWindow: 272000,
6239
6427
  maxTokens: 128000,
6240
6428
  },
6429
+ "gpt-5.4-mini": {
6430
+ id: "gpt-5.4-mini",
6431
+ name: "GPT-5.4 Mini",
6432
+ api: "openai-responses",
6433
+ provider: "opencode",
6434
+ baseUrl: "https://opencode.ai/zen/v1",
6435
+ reasoning: true,
6436
+ input: ["text", "image"],
6437
+ cost: {
6438
+ input: 0.75,
6439
+ output: 4.5,
6440
+ cacheRead: 0.075,
6441
+ cacheWrite: 0,
6442
+ },
6443
+ contextWindow: 400000,
6444
+ maxTokens: 128000,
6445
+ },
6446
+ "gpt-5.4-nano": {
6447
+ id: "gpt-5.4-nano",
6448
+ name: "GPT-5.4 Nano",
6449
+ api: "openai-responses",
6450
+ provider: "opencode",
6451
+ baseUrl: "https://opencode.ai/zen/v1",
6452
+ reasoning: true,
6453
+ input: ["text", "image"],
6454
+ cost: {
6455
+ input: 0.2,
6456
+ output: 1.25,
6457
+ cacheRead: 0.02,
6458
+ cacheWrite: 0,
6459
+ },
6460
+ contextWindow: 400000,
6461
+ maxTokens: 128000,
6462
+ },
6241
6463
  "gpt-5.4-pro": {
6242
6464
  id: "gpt-5.4-pro",
6243
6465
  name: "GPT-5.4 Pro",
@@ -6272,14 +6494,14 @@ export const MODELS = {
6272
6494
  contextWindow: 262144,
6273
6495
  maxTokens: 65536,
6274
6496
  },
6275
- "mimo-v2-flash-free": {
6276
- id: "mimo-v2-flash-free",
6277
- name: "MiMo V2 Flash Free",
6497
+ "mimo-v2-omni-free": {
6498
+ id: "mimo-v2-omni-free",
6499
+ name: "MiMo V2 Omni Free",
6278
6500
  api: "openai-completions",
6279
6501
  provider: "opencode",
6280
6502
  baseUrl: "https://opencode.ai/zen/v1",
6281
6503
  reasoning: true,
6282
- input: ["text"],
6504
+ input: ["text", "image"],
6283
6505
  cost: {
6284
6506
  input: 0,
6285
6507
  output: 0,
@@ -6287,24 +6509,24 @@ export const MODELS = {
6287
6509
  cacheWrite: 0,
6288
6510
  },
6289
6511
  contextWindow: 262144,
6290
- maxTokens: 65536,
6512
+ maxTokens: 64000,
6291
6513
  },
6292
- "minimax-m2.1": {
6293
- id: "minimax-m2.1",
6294
- name: "MiniMax M2.1",
6514
+ "mimo-v2-pro-free": {
6515
+ id: "mimo-v2-pro-free",
6516
+ name: "MiMo V2 Pro Free",
6295
6517
  api: "openai-completions",
6296
6518
  provider: "opencode",
6297
6519
  baseUrl: "https://opencode.ai/zen/v1",
6298
6520
  reasoning: true,
6299
6521
  input: ["text"],
6300
6522
  cost: {
6301
- input: 0.3,
6302
- output: 1.2,
6303
- cacheRead: 0.1,
6523
+ input: 0,
6524
+ output: 0,
6525
+ cacheRead: 0,
6304
6526
  cacheWrite: 0,
6305
6527
  },
6306
- contextWindow: 204800,
6307
- maxTokens: 131072,
6528
+ contextWindow: 1048576,
6529
+ maxTokens: 64000,
6308
6530
  },
6309
6531
  "minimax-m2.5": {
6310
6532
  id: "minimax-m2.5",
@@ -6410,6 +6632,23 @@ export const MODELS = {
6410
6632
  contextWindow: 204800,
6411
6633
  maxTokens: 131072,
6412
6634
  },
6635
+ "minimax-m2.7": {
6636
+ id: "minimax-m2.7",
6637
+ name: "MiniMax M2.7",
6638
+ api: "anthropic-messages",
6639
+ provider: "opencode-go",
6640
+ baseUrl: "https://opencode.ai/zen/go",
6641
+ reasoning: true,
6642
+ input: ["text"],
6643
+ cost: {
6644
+ input: 0.3,
6645
+ output: 1.2,
6646
+ cacheRead: 0.06,
6647
+ cacheWrite: 0,
6648
+ },
6649
+ contextWindow: 204800,
6650
+ maxTokens: 131072,
6651
+ },
6413
6652
  },
6414
6653
  "openrouter": {
6415
6654
  "ai21/jamba-large-1.7": {
@@ -7364,40 +7603,6 @@ export const MODELS = {
7364
7603
  contextWindow: 1048576,
7365
7604
  maxTokens: 65536,
7366
7605
  },
7367
- "google/gemma-3-27b-it": {
7368
- id: "google/gemma-3-27b-it",
7369
- name: "Google: Gemma 3 27B",
7370
- api: "openai-completions",
7371
- provider: "openrouter",
7372
- baseUrl: "https://openrouter.ai/api/v1",
7373
- reasoning: false,
7374
- input: ["text", "image"],
7375
- cost: {
7376
- input: 0.03,
7377
- output: 0.11,
7378
- cacheRead: 0.015,
7379
- cacheWrite: 0,
7380
- },
7381
- contextWindow: 128000,
7382
- maxTokens: 65536,
7383
- },
7384
- "google/gemma-3-27b-it:free": {
7385
- id: "google/gemma-3-27b-it:free",
7386
- name: "Google: Gemma 3 27B (free)",
7387
- api: "openai-completions",
7388
- provider: "openrouter",
7389
- baseUrl: "https://openrouter.ai/api/v1",
7390
- reasoning: false,
7391
- input: ["text", "image"],
7392
- cost: {
7393
- input: 0,
7394
- output: 0,
7395
- cacheRead: 0,
7396
- cacheWrite: 0,
7397
- },
7398
- contextWindow: 131072,
7399
- maxTokens: 8192,
7400
- },
7401
7606
  "inception/mercury": {
7402
7607
  id: "inception/mercury",
7403
7608
  name: "Inception: Mercury",
@@ -7565,8 +7770,8 @@ export const MODELS = {
7565
7770
  cacheRead: 0,
7566
7771
  cacheWrite: 0,
7567
7772
  },
7568
- contextWindow: 128000,
7569
- maxTokens: 128000,
7773
+ contextWindow: 65536,
7774
+ maxTokens: 4096,
7570
7775
  },
7571
7776
  "meta-llama/llama-4-maverick": {
7572
7777
  id: "meta-llama/llama-4-maverick",
@@ -7662,13 +7867,47 @@ export const MODELS = {
7662
7867
  reasoning: true,
7663
7868
  input: ["text"],
7664
7869
  cost: {
7665
- input: 0.27,
7666
- output: 0.95,
7667
- cacheRead: 0.0299999997,
7870
+ input: 0.19999999999999998,
7871
+ output: 1.17,
7872
+ cacheRead: 0.09999999999999999,
7668
7873
  cacheWrite: 0,
7669
7874
  },
7670
7875
  contextWindow: 196608,
7671
- maxTokens: 4096,
7876
+ maxTokens: 65536,
7877
+ },
7878
+ "minimax/minimax-m2.5:free": {
7879
+ id: "minimax/minimax-m2.5:free",
7880
+ name: "MiniMax: MiniMax M2.5 (free)",
7881
+ api: "openai-completions",
7882
+ provider: "openrouter",
7883
+ baseUrl: "https://openrouter.ai/api/v1",
7884
+ reasoning: true,
7885
+ input: ["text"],
7886
+ cost: {
7887
+ input: 0,
7888
+ output: 0,
7889
+ cacheRead: 0,
7890
+ cacheWrite: 0,
7891
+ },
7892
+ contextWindow: 196608,
7893
+ maxTokens: 196608,
7894
+ },
7895
+ "minimax/minimax-m2.7": {
7896
+ id: "minimax/minimax-m2.7",
7897
+ name: "MiniMax: MiniMax M2.7",
7898
+ api: "openai-completions",
7899
+ provider: "openrouter",
7900
+ baseUrl: "https://openrouter.ai/api/v1",
7901
+ reasoning: true,
7902
+ input: ["text"],
7903
+ cost: {
7904
+ input: 0.3,
7905
+ output: 1.2,
7906
+ cacheRead: 0.06,
7907
+ cacheWrite: 0,
7908
+ },
7909
+ contextWindow: 204800,
7910
+ maxTokens: 131072,
7672
7911
  },
7673
7912
  "mistralai/codestral-2508": {
7674
7913
  id: "mistralai/codestral-2508",
@@ -7681,7 +7920,7 @@ export const MODELS = {
7681
7920
  cost: {
7682
7921
  input: 0.3,
7683
7922
  output: 0.8999999999999999,
7684
- cacheRead: 0,
7923
+ cacheRead: 0.03,
7685
7924
  cacheWrite: 0,
7686
7925
  },
7687
7926
  contextWindow: 256000,
@@ -7698,7 +7937,7 @@ export const MODELS = {
7698
7937
  cost: {
7699
7938
  input: 0.39999999999999997,
7700
7939
  output: 2,
7701
- cacheRead: 0,
7940
+ cacheRead: 0.04,
7702
7941
  cacheWrite: 0,
7703
7942
  },
7704
7943
  contextWindow: 262144,
@@ -7715,7 +7954,7 @@ export const MODELS = {
7715
7954
  cost: {
7716
7955
  input: 0.39999999999999997,
7717
7956
  output: 2,
7718
- cacheRead: 0,
7957
+ cacheRead: 0.04,
7719
7958
  cacheWrite: 0,
7720
7959
  },
7721
7960
  contextWindow: 131072,
@@ -7732,7 +7971,7 @@ export const MODELS = {
7732
7971
  cost: {
7733
7972
  input: 0.09999999999999999,
7734
7973
  output: 0.3,
7735
- cacheRead: 0,
7974
+ cacheRead: 0.01,
7736
7975
  cacheWrite: 0,
7737
7976
  },
7738
7977
  contextWindow: 131072,
@@ -7749,7 +7988,7 @@ export const MODELS = {
7749
7988
  cost: {
7750
7989
  input: 0.19999999999999998,
7751
7990
  output: 0.19999999999999998,
7752
- cacheRead: 0,
7991
+ cacheRead: 0.02,
7753
7992
  cacheWrite: 0,
7754
7993
  },
7755
7994
  contextWindow: 262144,
@@ -7766,7 +8005,7 @@ export const MODELS = {
7766
8005
  cost: {
7767
8006
  input: 0.09999999999999999,
7768
8007
  output: 0.09999999999999999,
7769
- cacheRead: 0,
8008
+ cacheRead: 0.01,
7770
8009
  cacheWrite: 0,
7771
8010
  },
7772
8011
  contextWindow: 131072,
@@ -7783,7 +8022,7 @@ export const MODELS = {
7783
8022
  cost: {
7784
8023
  input: 0.15,
7785
8024
  output: 0.15,
7786
- cacheRead: 0,
8025
+ cacheRead: 0.015,
7787
8026
  cacheWrite: 0,
7788
8027
  },
7789
8028
  contextWindow: 262144,
@@ -7800,7 +8039,7 @@ export const MODELS = {
7800
8039
  cost: {
7801
8040
  input: 2,
7802
8041
  output: 6,
7803
- cacheRead: 0,
8042
+ cacheRead: 0.19999999999999998,
7804
8043
  cacheWrite: 0,
7805
8044
  },
7806
8045
  contextWindow: 128000,
@@ -7817,7 +8056,7 @@ export const MODELS = {
7817
8056
  cost: {
7818
8057
  input: 2,
7819
8058
  output: 6,
7820
- cacheRead: 0,
8059
+ cacheRead: 0.19999999999999998,
7821
8060
  cacheWrite: 0,
7822
8061
  },
7823
8062
  contextWindow: 131072,
@@ -7834,7 +8073,7 @@ export const MODELS = {
7834
8073
  cost: {
7835
8074
  input: 2,
7836
8075
  output: 6,
7837
- cacheRead: 0,
8076
+ cacheRead: 0.19999999999999998,
7838
8077
  cacheWrite: 0,
7839
8078
  },
7840
8079
  contextWindow: 131072,
@@ -7851,7 +8090,7 @@ export const MODELS = {
7851
8090
  cost: {
7852
8091
  input: 0.5,
7853
8092
  output: 1.5,
7854
- cacheRead: 0,
8093
+ cacheRead: 0.049999999999999996,
7855
8094
  cacheWrite: 0,
7856
8095
  },
7857
8096
  contextWindow: 262144,
@@ -7868,7 +8107,7 @@ export const MODELS = {
7868
8107
  cost: {
7869
8108
  input: 0.39999999999999997,
7870
8109
  output: 2,
7871
- cacheRead: 0,
8110
+ cacheRead: 0.04,
7872
8111
  cacheWrite: 0,
7873
8112
  },
7874
8113
  contextWindow: 131072,
@@ -7885,7 +8124,7 @@ export const MODELS = {
7885
8124
  cost: {
7886
8125
  input: 0.39999999999999997,
7887
8126
  output: 2,
7888
- cacheRead: 0,
8127
+ cacheRead: 0.04,
7889
8128
  cacheWrite: 0,
7890
8129
  },
7891
8130
  contextWindow: 131072,
@@ -7919,7 +8158,7 @@ export const MODELS = {
7919
8158
  cost: {
7920
8159
  input: 0.19999999999999998,
7921
8160
  output: 0.6,
7922
- cacheRead: 0,
8161
+ cacheRead: 0.02,
7923
8162
  cacheWrite: 0,
7924
8163
  },
7925
8164
  contextWindow: 32768,
@@ -7942,6 +8181,23 @@ export const MODELS = {
7942
8181
  contextWindow: 32768,
7943
8182
  maxTokens: 16384,
7944
8183
  },
8184
+ "mistralai/mistral-small-2603": {
8185
+ id: "mistralai/mistral-small-2603",
8186
+ name: "Mistral: Mistral Small 4",
8187
+ api: "openai-completions",
8188
+ provider: "openrouter",
8189
+ baseUrl: "https://openrouter.ai/api/v1",
8190
+ reasoning: true,
8191
+ input: ["text", "image"],
8192
+ cost: {
8193
+ input: 0.15,
8194
+ output: 0.6,
8195
+ cacheRead: 0.015,
8196
+ cacheWrite: 0,
8197
+ },
8198
+ contextWindow: 262144,
8199
+ maxTokens: 4096,
8200
+ },
7945
8201
  "mistralai/mistral-small-3.1-24b-instruct:free": {
7946
8202
  id: "mistralai/mistral-small-3.1-24b-instruct:free",
7947
8203
  name: "Mistral: Mistral Small 3.1 24B (free)",
@@ -7968,13 +8224,13 @@ export const MODELS = {
7968
8224
  reasoning: false,
7969
8225
  input: ["text", "image"],
7970
8226
  cost: {
7971
- input: 0.06,
7972
- output: 0.18,
7973
- cacheRead: 0.03,
8227
+ input: 0.075,
8228
+ output: 0.19999999999999998,
8229
+ cacheRead: 0,
7974
8230
  cacheWrite: 0,
7975
8231
  },
7976
- contextWindow: 131072,
7977
- maxTokens: 131072,
8232
+ contextWindow: 128000,
8233
+ maxTokens: 4096,
7978
8234
  },
7979
8235
  "mistralai/mistral-small-creative": {
7980
8236
  id: "mistralai/mistral-small-creative",
@@ -7987,7 +8243,7 @@ export const MODELS = {
7987
8243
  cost: {
7988
8244
  input: 0.09999999999999999,
7989
8245
  output: 0.3,
7990
- cacheRead: 0,
8246
+ cacheRead: 0.01,
7991
8247
  cacheWrite: 0,
7992
8248
  },
7993
8249
  contextWindow: 32768,
@@ -8004,7 +8260,7 @@ export const MODELS = {
8004
8260
  cost: {
8005
8261
  input: 2,
8006
8262
  output: 6,
8007
- cacheRead: 0,
8263
+ cacheRead: 0.19999999999999998,
8008
8264
  cacheWrite: 0,
8009
8265
  },
8010
8266
  contextWindow: 65536,
@@ -8038,7 +8294,7 @@ export const MODELS = {
8038
8294
  cost: {
8039
8295
  input: 2,
8040
8296
  output: 6,
8041
- cacheRead: 0,
8297
+ cacheRead: 0.19999999999999998,
8042
8298
  cacheWrite: 0,
8043
8299
  },
8044
8300
  contextWindow: 131072,
@@ -8055,7 +8311,7 @@ export const MODELS = {
8055
8311
  cost: {
8056
8312
  input: 0.09999999999999999,
8057
8313
  output: 0.3,
8058
- cacheRead: 0,
8314
+ cacheRead: 0.01,
8059
8315
  cacheWrite: 0,
8060
8316
  },
8061
8317
  contextWindow: 32000,
@@ -8070,13 +8326,13 @@ export const MODELS = {
8070
8326
  reasoning: false,
8071
8327
  input: ["text"],
8072
8328
  cost: {
8073
- input: 0.55,
8074
- output: 2.2,
8329
+ input: 0.5700000000000001,
8330
+ output: 2.3,
8075
8331
  cacheRead: 0,
8076
8332
  cacheWrite: 0,
8077
8333
  },
8078
- contextWindow: 131000,
8079
- maxTokens: 4096,
8334
+ contextWindow: 131072,
8335
+ maxTokens: 131072,
8080
8336
  },
8081
8337
  "moonshotai/kimi-k2-0905": {
8082
8338
  id: "moonshotai/kimi-k2-0905",
@@ -8138,8 +8394,8 @@ export const MODELS = {
8138
8394
  reasoning: false,
8139
8395
  input: ["text"],
8140
8396
  cost: {
8141
- input: 0.27,
8142
- output: 1,
8397
+ input: 0.135,
8398
+ output: 0.5,
8143
8399
  cacheRead: 0,
8144
8400
  cacheWrite: 0,
8145
8401
  },
@@ -8214,6 +8470,23 @@ export const MODELS = {
8214
8470
  contextWindow: 256000,
8215
8471
  maxTokens: 4096,
8216
8472
  },
8473
+ "nvidia/nemotron-3-super-120b-a12b": {
8474
+ id: "nvidia/nemotron-3-super-120b-a12b",
8475
+ name: "NVIDIA: Nemotron 3 Super",
8476
+ api: "openai-completions",
8477
+ provider: "openrouter",
8478
+ baseUrl: "https://openrouter.ai/api/v1",
8479
+ reasoning: true,
8480
+ input: ["text"],
8481
+ cost: {
8482
+ input: 0.09999999999999999,
8483
+ output: 0.5,
8484
+ cacheRead: 0.09999999999999999,
8485
+ cacheWrite: 0,
8486
+ },
8487
+ contextWindow: 262144,
8488
+ maxTokens: 4096,
8489
+ },
8217
8490
  "nvidia/nemotron-3-super-120b-a12b:free": {
8218
8491
  id: "nvidia/nemotron-3-super-120b-a12b:free",
8219
8492
  name: "NVIDIA: Nemotron 3 Super (free)",
@@ -8928,18 +9201,52 @@ export const MODELS = {
8928
9201
  contextWindow: 1050000,
8929
9202
  maxTokens: 128000,
8930
9203
  },
8931
- "openai/gpt-5.4-pro": {
8932
- id: "openai/gpt-5.4-pro",
8933
- name: "OpenAI: GPT-5.4 Pro",
9204
+ "openai/gpt-5.4-mini": {
9205
+ id: "openai/gpt-5.4-mini",
9206
+ name: "OpenAI: GPT-5.4 Mini",
8934
9207
  api: "openai-completions",
8935
9208
  provider: "openrouter",
8936
9209
  baseUrl: "https://openrouter.ai/api/v1",
8937
9210
  reasoning: true,
8938
9211
  input: ["text", "image"],
8939
9212
  cost: {
8940
- input: 30,
8941
- output: 180,
8942
- cacheRead: 0,
9213
+ input: 0.75,
9214
+ output: 4.5,
9215
+ cacheRead: 0.075,
9216
+ cacheWrite: 0,
9217
+ },
9218
+ contextWindow: 400000,
9219
+ maxTokens: 128000,
9220
+ },
9221
+ "openai/gpt-5.4-nano": {
9222
+ id: "openai/gpt-5.4-nano",
9223
+ name: "OpenAI: GPT-5.4 Nano",
9224
+ api: "openai-completions",
9225
+ provider: "openrouter",
9226
+ baseUrl: "https://openrouter.ai/api/v1",
9227
+ reasoning: true,
9228
+ input: ["text", "image"],
9229
+ cost: {
9230
+ input: 0.19999999999999998,
9231
+ output: 1.25,
9232
+ cacheRead: 0.02,
9233
+ cacheWrite: 0,
9234
+ },
9235
+ contextWindow: 400000,
9236
+ maxTokens: 128000,
9237
+ },
9238
+ "openai/gpt-5.4-pro": {
9239
+ id: "openai/gpt-5.4-pro",
9240
+ name: "OpenAI: GPT-5.4 Pro",
9241
+ api: "openai-completions",
9242
+ provider: "openrouter",
9243
+ baseUrl: "https://openrouter.ai/api/v1",
9244
+ reasoning: true,
9245
+ input: ["text", "image"],
9246
+ cost: {
9247
+ input: 30,
9248
+ output: 180,
9249
+ cacheRead: 0,
8943
9250
  cacheWrite: 0,
8944
9251
  },
8945
9252
  contextWindow: 1050000,
@@ -8989,12 +9296,12 @@ export const MODELS = {
8989
9296
  input: ["text"],
8990
9297
  cost: {
8991
9298
  input: 0.03,
8992
- output: 0.14,
8993
- cacheRead: 0,
9299
+ output: 0.11,
9300
+ cacheRead: 0.015,
8994
9301
  cacheWrite: 0,
8995
9302
  },
8996
9303
  contextWindow: 131072,
8997
- maxTokens: 4096,
9304
+ maxTokens: 131072,
8998
9305
  },
8999
9306
  "openai/gpt-oss-20b:free": {
9000
9307
  id: "openai/gpt-oss-20b:free",
@@ -9036,7 +9343,7 @@ export const MODELS = {
9036
9343
  api: "openai-completions",
9037
9344
  provider: "openrouter",
9038
9345
  baseUrl: "https://openrouter.ai/api/v1",
9039
- reasoning: false,
9346
+ reasoning: true,
9040
9347
  input: ["text", "image"],
9041
9348
  cost: {
9042
9349
  input: 15,
@@ -9087,7 +9394,7 @@ export const MODELS = {
9087
9394
  api: "openai-completions",
9088
9395
  provider: "openrouter",
9089
9396
  baseUrl: "https://openrouter.ai/api/v1",
9090
- reasoning: false,
9397
+ reasoning: true,
9091
9398
  input: ["text"],
9092
9399
  cost: {
9093
9400
  input: 1.1,
@@ -9104,7 +9411,7 @@ export const MODELS = {
9104
9411
  api: "openai-completions",
9105
9412
  provider: "openrouter",
9106
9413
  baseUrl: "https://openrouter.ai/api/v1",
9107
- reasoning: false,
9414
+ reasoning: true,
9108
9415
  input: ["text"],
9109
9416
  cost: {
9110
9417
  input: 1.1,
@@ -9217,40 +9524,6 @@ export const MODELS = {
9217
9524
  contextWindow: 200000,
9218
9525
  maxTokens: 4096,
9219
9526
  },
9220
- "openrouter/healer-alpha": {
9221
- id: "openrouter/healer-alpha",
9222
- name: "Healer Alpha",
9223
- api: "openai-completions",
9224
- provider: "openrouter",
9225
- baseUrl: "https://openrouter.ai/api/v1",
9226
- reasoning: true,
9227
- input: ["text", "image"],
9228
- cost: {
9229
- input: 0,
9230
- output: 0,
9231
- cacheRead: 0,
9232
- cacheWrite: 0,
9233
- },
9234
- contextWindow: 262144,
9235
- maxTokens: 32000,
9236
- },
9237
- "openrouter/hunter-alpha": {
9238
- id: "openrouter/hunter-alpha",
9239
- name: "Hunter Alpha",
9240
- api: "openai-completions",
9241
- provider: "openrouter",
9242
- baseUrl: "https://openrouter.ai/api/v1",
9243
- reasoning: true,
9244
- input: ["text"],
9245
- cost: {
9246
- input: 0,
9247
- output: 0,
9248
- cacheRead: 0,
9249
- cacheWrite: 0,
9250
- },
9251
- contextWindow: 1048576,
9252
- maxTokens: 32000,
9253
- },
9254
9527
  "prime-intellect/intellect-3": {
9255
9528
  id: "prime-intellect/intellect-3",
9256
9529
  name: "Prime Intellect: INTELLECT-3",
@@ -9300,7 +9573,7 @@ export const MODELS = {
9300
9573
  cacheWrite: 0,
9301
9574
  },
9302
9575
  contextWindow: 32768,
9303
- maxTokens: 4096,
9576
+ maxTokens: 32768,
9304
9577
  },
9305
9578
  "qwen/qwen-max": {
9306
9579
  id: "qwen/qwen-max",
@@ -9328,9 +9601,9 @@ export const MODELS = {
9328
9601
  reasoning: false,
9329
9602
  input: ["text"],
9330
9603
  cost: {
9331
- input: 0.39999999999999997,
9332
- output: 1.2,
9333
- cacheRead: 0.08,
9604
+ input: 0.26,
9605
+ output: 0.78,
9606
+ cacheRead: 0.052000000000000005,
9334
9607
  cacheWrite: 0,
9335
9608
  },
9336
9609
  contextWindow: 1000000,
@@ -9396,8 +9669,8 @@ export const MODELS = {
9396
9669
  reasoning: false,
9397
9670
  input: ["text", "image"],
9398
9671
  cost: {
9399
- input: 0.7999999999999999,
9400
- output: 3.1999999999999997,
9672
+ input: 0.52,
9673
+ output: 2.08,
9401
9674
  cacheRead: 0,
9402
9675
  cacheWrite: 0,
9403
9676
  },
@@ -9464,13 +9737,13 @@ export const MODELS = {
9464
9737
  reasoning: true,
9465
9738
  input: ["text"],
9466
9739
  cost: {
9467
- input: 0.11,
9468
- output: 0.6,
9469
- cacheRead: 0.055,
9740
+ input: 0.14950000000000002,
9741
+ output: 1.495,
9742
+ cacheRead: 0,
9470
9743
  cacheWrite: 0,
9471
9744
  },
9472
- contextWindow: 262144,
9473
- maxTokens: 262144,
9745
+ contextWindow: 131072,
9746
+ maxTokens: 4096,
9474
9747
  },
9475
9748
  "qwen/qwen3-30b-a3b": {
9476
9749
  id: "qwen/qwen3-30b-a3b",
@@ -9515,13 +9788,13 @@ export const MODELS = {
9515
9788
  reasoning: true,
9516
9789
  input: ["text"],
9517
9790
  cost: {
9518
- input: 0.051,
9519
- output: 0.33999999999999997,
9520
- cacheRead: 0,
9791
+ input: 0.08,
9792
+ output: 0.39999999999999997,
9793
+ cacheRead: 0.08,
9521
9794
  cacheWrite: 0,
9522
9795
  },
9523
- contextWindow: 32768,
9524
- maxTokens: 4096,
9796
+ contextWindow: 131072,
9797
+ maxTokens: 131072,
9525
9798
  },
9526
9799
  "qwen/qwen3-32b": {
9527
9800
  id: "qwen/qwen3-32b",
@@ -9685,9 +9958,9 @@ export const MODELS = {
9685
9958
  reasoning: false,
9686
9959
  input: ["text"],
9687
9960
  cost: {
9688
- input: 1.2,
9689
- output: 6,
9690
- cacheRead: 0.24,
9961
+ input: 0.78,
9962
+ output: 3.9,
9963
+ cacheRead: 0.156,
9691
9964
  cacheWrite: 0,
9692
9965
  },
9693
9966
  contextWindow: 262144,
@@ -9724,7 +9997,7 @@ export const MODELS = {
9724
9997
  cacheRead: 0,
9725
9998
  cacheWrite: 0,
9726
9999
  },
9727
- contextWindow: 131072,
10000
+ contextWindow: 262144,
9728
10001
  maxTokens: 4096,
9729
10002
  },
9730
10003
  "qwen/qwen3-next-80b-a3b-instruct:free": {
@@ -9963,7 +10236,7 @@ export const MODELS = {
9963
10236
  cacheWrite: 0,
9964
10237
  },
9965
10238
  contextWindow: 256000,
9966
- maxTokens: 4096,
10239
+ maxTokens: 65536,
9967
10240
  },
9968
10241
  "qwen/qwen3.5-flash-02-23": {
9969
10242
  id: "qwen/qwen3.5-flash-02-23",
@@ -9974,8 +10247,8 @@ export const MODELS = {
9974
10247
  reasoning: true,
9975
10248
  input: ["text", "image"],
9976
10249
  cost: {
9977
- input: 0.09999999999999999,
9978
- output: 0.39999999999999997,
10250
+ input: 0.065,
10251
+ output: 0.26,
9979
10252
  cacheRead: 0,
9980
10253
  cacheWrite: 0,
9981
10254
  },
@@ -10009,12 +10282,12 @@ export const MODELS = {
10009
10282
  input: ["text"],
10010
10283
  cost: {
10011
10284
  input: 0.15,
10012
- output: 0.39999999999999997,
10285
+ output: 0.58,
10013
10286
  cacheRead: 0,
10014
10287
  cacheWrite: 0,
10015
10288
  },
10016
- contextWindow: 32768,
10017
- maxTokens: 32768,
10289
+ contextWindow: 131072,
10290
+ maxTokens: 131072,
10018
10291
  },
10019
10292
  "relace/relace-search": {
10020
10293
  id: "relace/relace-search",
@@ -10144,9 +10417,9 @@ export const MODELS = {
10144
10417
  reasoning: true,
10145
10418
  input: ["text"],
10146
10419
  cost: {
10147
- input: 0.25,
10148
- output: 0.85,
10149
- cacheRead: 0.125,
10420
+ input: 0.3,
10421
+ output: 1.1,
10422
+ cacheRead: 0.15,
10150
10423
  cacheWrite: 0,
10151
10424
  },
10152
10425
  contextWindow: 163840,
@@ -10339,6 +10612,40 @@ export const MODELS = {
10339
10612
  contextWindow: 262144,
10340
10613
  maxTokens: 65536,
10341
10614
  },
10615
+ "xiaomi/mimo-v2-omni": {
10616
+ id: "xiaomi/mimo-v2-omni",
10617
+ name: "Xiaomi: MiMo-V2-Omni",
10618
+ api: "openai-completions",
10619
+ provider: "openrouter",
10620
+ baseUrl: "https://openrouter.ai/api/v1",
10621
+ reasoning: true,
10622
+ input: ["text", "image"],
10623
+ cost: {
10624
+ input: 0.39999999999999997,
10625
+ output: 2,
10626
+ cacheRead: 0.08,
10627
+ cacheWrite: 0,
10628
+ },
10629
+ contextWindow: 262144,
10630
+ maxTokens: 65536,
10631
+ },
10632
+ "xiaomi/mimo-v2-pro": {
10633
+ id: "xiaomi/mimo-v2-pro",
10634
+ name: "Xiaomi: MiMo-V2-Pro",
10635
+ api: "openai-completions",
10636
+ provider: "openrouter",
10637
+ baseUrl: "https://openrouter.ai/api/v1",
10638
+ reasoning: true,
10639
+ input: ["text"],
10640
+ cost: {
10641
+ input: 1,
10642
+ output: 3,
10643
+ cacheRead: 0.19999999999999998,
10644
+ cacheWrite: 0,
10645
+ },
10646
+ contextWindow: 1048576,
10647
+ maxTokens: 131072,
10648
+ },
10342
10649
  "z-ai/glm-4-32b": {
10343
10650
  id: "z-ai/glm-4-32b",
10344
10651
  name: "Z.ai: GLM 4 32B ",
@@ -10467,13 +10774,13 @@ export const MODELS = {
10467
10774
  reasoning: true,
10468
10775
  input: ["text"],
10469
10776
  cost: {
10470
- input: 0.38,
10471
- output: 1.9800000000000002,
10472
- cacheRead: 0.19,
10777
+ input: 0.39,
10778
+ output: 1.75,
10779
+ cacheRead: 0.195,
10473
10780
  cacheWrite: 0,
10474
10781
  },
10475
10782
  contextWindow: 202752,
10476
- maxTokens: 4096,
10783
+ maxTokens: 65535,
10477
10784
  },
10478
10785
  "z-ai/glm-4.7-flash": {
10479
10786
  id: "z-ai/glm-4.7-flash",
@@ -10506,6 +10813,23 @@ export const MODELS = {
10506
10813
  cacheRead: 0.119,
10507
10814
  cacheWrite: 0,
10508
10815
  },
10816
+ contextWindow: 80000,
10817
+ maxTokens: 131072,
10818
+ },
10819
+ "z-ai/glm-5-turbo": {
10820
+ id: "z-ai/glm-5-turbo",
10821
+ name: "Z.ai: GLM 5 Turbo",
10822
+ api: "openai-completions",
10823
+ provider: "openrouter",
10824
+ baseUrl: "https://openrouter.ai/api/v1",
10825
+ reasoning: true,
10826
+ input: ["text"],
10827
+ cost: {
10828
+ input: 1.2,
10829
+ output: 4,
10830
+ cacheRead: 0.24,
10831
+ cacheWrite: 0,
10832
+ },
10509
10833
  contextWindow: 202752,
10510
10834
  maxTokens: 131072,
10511
10835
  },
@@ -10520,7 +10844,7 @@ export const MODELS = {
10520
10844
  reasoning: true,
10521
10845
  input: ["text"],
10522
10846
  cost: {
10523
- input: 0.06,
10847
+ input: 0.12,
10524
10848
  output: 0.24,
10525
10849
  cacheRead: 0,
10526
10850
  cacheWrite: 0,
@@ -10573,7 +10897,7 @@ export const MODELS = {
10573
10897
  cost: {
10574
10898
  input: 0.29,
10575
10899
  output: 0.59,
10576
- cacheRead: 0,
10900
+ cacheRead: 0.145,
10577
10901
  cacheWrite: 0,
10578
10902
  },
10579
10903
  contextWindow: 131072,
@@ -10588,9 +10912,9 @@ export const MODELS = {
10588
10912
  reasoning: true,
10589
10913
  input: ["text", "image"],
10590
10914
  cost: {
10591
- input: 0.3,
10592
- output: 2.9000000000000004,
10593
- cacheRead: 0,
10915
+ input: 0.22999999999999998,
10916
+ output: 2.3,
10917
+ cacheRead: 0.19999999999999998,
10594
10918
  cacheWrite: 0,
10595
10919
  },
10596
10920
  contextWindow: 262114,
@@ -10607,7 +10931,7 @@ export const MODELS = {
10607
10931
  cost: {
10608
10932
  input: 0.39999999999999997,
10609
10933
  output: 1.5999999999999999,
10610
- cacheRead: 0,
10934
+ cacheRead: 0.022,
10611
10935
  cacheWrite: 0,
10612
10936
  },
10613
10937
  contextWindow: 262144,
@@ -11100,7 +11424,7 @@ export const MODELS = {
11100
11424
  cost: {
11101
11425
  input: 0.27,
11102
11426
  output: 1,
11103
- cacheRead: 0,
11427
+ cacheRead: 0.135,
11104
11428
  cacheWrite: 0,
11105
11429
  },
11106
11430
  contextWindow: 131072,
@@ -11115,9 +11439,9 @@ export const MODELS = {
11115
11439
  reasoning: false,
11116
11440
  input: ["text"],
11117
11441
  cost: {
11118
- input: 0.26,
11119
- output: 0.38,
11120
- cacheRead: 0.13,
11442
+ input: 0.28,
11443
+ output: 0.42,
11444
+ cacheRead: 0.028,
11121
11445
  cacheWrite: 0,
11122
11446
  },
11123
11447
  contextWindow: 128000,
@@ -11151,7 +11475,7 @@ export const MODELS = {
11151
11475
  cost: {
11152
11476
  input: 0.15,
11153
11477
  output: 0.6,
11154
- cacheRead: 0,
11478
+ cacheRead: 0.024999999999999998,
11155
11479
  cacheWrite: 0,
11156
11480
  },
11157
11481
  contextWindow: 1048576,
@@ -11168,7 +11492,7 @@ export const MODELS = {
11168
11492
  cost: {
11169
11493
  input: 0.075,
11170
11494
  output: 0.3,
11171
- cacheRead: 0,
11495
+ cacheRead: 0.02,
11172
11496
  cacheWrite: 0,
11173
11497
  },
11174
11498
  contextWindow: 1048576,
@@ -11208,40 +11532,6 @@ export const MODELS = {
11208
11532
  contextWindow: 1048576,
11209
11533
  maxTokens: 65536,
11210
11534
  },
11211
- "google/gemini-2.5-flash-lite-preview-09-2025": {
11212
- id: "google/gemini-2.5-flash-lite-preview-09-2025",
11213
- name: "Gemini 2.5 Flash Lite Preview 09-2025",
11214
- api: "anthropic-messages",
11215
- provider: "vercel-ai-gateway",
11216
- baseUrl: "https://ai-gateway.vercel.sh",
11217
- reasoning: true,
11218
- input: ["text", "image"],
11219
- cost: {
11220
- input: 0.09999999999999999,
11221
- output: 0.39999999999999997,
11222
- cacheRead: 0.01,
11223
- cacheWrite: 0,
11224
- },
11225
- contextWindow: 1048576,
11226
- maxTokens: 65536,
11227
- },
11228
- "google/gemini-2.5-flash-preview-09-2025": {
11229
- id: "google/gemini-2.5-flash-preview-09-2025",
11230
- name: "Gemini 2.5 Flash Preview 09-2025",
11231
- api: "anthropic-messages",
11232
- provider: "vercel-ai-gateway",
11233
- baseUrl: "https://ai-gateway.vercel.sh",
11234
- reasoning: true,
11235
- input: ["text", "image"],
11236
- cost: {
11237
- input: 0.3,
11238
- output: 2.5,
11239
- cacheRead: 0.03,
11240
- cacheWrite: 0,
11241
- },
11242
- contextWindow: 1000000,
11243
- maxTokens: 65536,
11244
- },
11245
11535
  "google/gemini-2.5-pro": {
11246
11536
  id: "google/gemini-2.5-pro",
11247
11537
  name: "Gemini 2.5 Pro",
@@ -11423,7 +11713,7 @@ export const MODELS = {
11423
11713
  cost: {
11424
11714
  input: 0.09999999999999999,
11425
11715
  output: 0.09999999999999999,
11426
- cacheRead: 0,
11716
+ cacheRead: 0.09999999999999999,
11427
11717
  cacheWrite: 0,
11428
11718
  },
11429
11719
  contextWindow: 128000,
@@ -11596,8 +11886,42 @@ export const MODELS = {
11596
11886
  cacheRead: 0.03,
11597
11887
  cacheWrite: 0.375,
11598
11888
  },
11599
- contextWindow: 4096,
11600
- maxTokens: 4096,
11889
+ contextWindow: 204800,
11890
+ maxTokens: 131000,
11891
+ },
11892
+ "minimax/minimax-m2.7": {
11893
+ id: "minimax/minimax-m2.7",
11894
+ name: "Minimax M2.7",
11895
+ api: "anthropic-messages",
11896
+ provider: "vercel-ai-gateway",
11897
+ baseUrl: "https://ai-gateway.vercel.sh",
11898
+ reasoning: true,
11899
+ input: ["text", "image"],
11900
+ cost: {
11901
+ input: 0.3,
11902
+ output: 1.2,
11903
+ cacheRead: 0.06,
11904
+ cacheWrite: 0.375,
11905
+ },
11906
+ contextWindow: 204800,
11907
+ maxTokens: 131000,
11908
+ },
11909
+ "minimax/minimax-m2.7-highspeed": {
11910
+ id: "minimax/minimax-m2.7-highspeed",
11911
+ name: "MiniMax M2.7 High Speed",
11912
+ api: "anthropic-messages",
11913
+ provider: "vercel-ai-gateway",
11914
+ baseUrl: "https://ai-gateway.vercel.sh",
11915
+ reasoning: true,
11916
+ input: ["text", "image"],
11917
+ cost: {
11918
+ input: 0.6,
11919
+ output: 2.4,
11920
+ cacheRead: 0.06,
11921
+ cacheWrite: 0.375,
11922
+ },
11923
+ contextWindow: 204800,
11924
+ maxTokens: 131100,
11601
11925
  },
11602
11926
  "mistral/codestral": {
11603
11927
  id: "mistral/codestral",
@@ -11625,8 +11949,8 @@ export const MODELS = {
11625
11949
  reasoning: false,
11626
11950
  input: ["text"],
11627
11951
  cost: {
11628
- input: 0,
11629
- output: 0,
11952
+ input: 0.39999999999999997,
11953
+ output: 2,
11630
11954
  cacheRead: 0,
11631
11955
  cacheWrite: 0,
11632
11956
  },
@@ -11659,8 +11983,8 @@ export const MODELS = {
11659
11983
  reasoning: false,
11660
11984
  input: ["text"],
11661
11985
  cost: {
11662
- input: 0,
11663
- output: 0,
11986
+ input: 0.09999999999999999,
11987
+ output: 0.3,
11664
11988
  cacheRead: 0,
11665
11989
  cacheWrite: 0,
11666
11990
  },
@@ -11676,8 +12000,8 @@ export const MODELS = {
11676
12000
  reasoning: false,
11677
12001
  input: ["text"],
11678
12002
  cost: {
11679
- input: 0.04,
11680
- output: 0.04,
12003
+ input: 0.09999999999999999,
12004
+ output: 0.09999999999999999,
11681
12005
  cacheRead: 0,
11682
12006
  cacheWrite: 0,
11683
12007
  },
@@ -11693,8 +12017,8 @@ export const MODELS = {
11693
12017
  reasoning: false,
11694
12018
  input: ["text"],
11695
12019
  cost: {
11696
- input: 0.09999999999999999,
11697
- output: 0.09999999999999999,
12020
+ input: 0.15,
12021
+ output: 0.15,
11698
12022
  cacheRead: 0,
11699
12023
  cacheWrite: 0,
11700
12024
  },
@@ -11780,7 +12104,7 @@ export const MODELS = {
11780
12104
  cost: {
11781
12105
  input: 0.6,
11782
12106
  output: 2.5,
11783
- cacheRead: 0,
12107
+ cacheRead: 0.15,
11784
12108
  cacheWrite: 0,
11785
12109
  },
11786
12110
  contextWindow: 131072,
@@ -11797,7 +12121,7 @@ export const MODELS = {
11797
12121
  cost: {
11798
12122
  input: 0.6,
11799
12123
  output: 2.5,
11800
- cacheRead: 0,
12124
+ cacheRead: 0.15,
11801
12125
  cacheWrite: 0,
11802
12126
  },
11803
12127
  contextWindow: 256000,
@@ -11846,9 +12170,9 @@ export const MODELS = {
11846
12170
  reasoning: false,
11847
12171
  input: ["text"],
11848
12172
  cost: {
11849
- input: 2.4,
11850
- output: 10,
11851
- cacheRead: 0,
12173
+ input: 1.15,
12174
+ output: 8,
12175
+ cacheRead: 0.15,
11852
12176
  cacheWrite: 0,
11853
12177
  },
11854
12178
  contextWindow: 256000,
@@ -12313,6 +12637,40 @@ export const MODELS = {
12313
12637
  contextWindow: 1050000,
12314
12638
  maxTokens: 128000,
12315
12639
  },
12640
+ "openai/gpt-5.4-mini": {
12641
+ id: "openai/gpt-5.4-mini",
12642
+ name: "GPT 5.4 Mini",
12643
+ api: "anthropic-messages",
12644
+ provider: "vercel-ai-gateway",
12645
+ baseUrl: "https://ai-gateway.vercel.sh",
12646
+ reasoning: true,
12647
+ input: ["text", "image"],
12648
+ cost: {
12649
+ input: 0.75,
12650
+ output: 4.5,
12651
+ cacheRead: 0.075,
12652
+ cacheWrite: 0,
12653
+ },
12654
+ contextWindow: 400000,
12655
+ maxTokens: 128000,
12656
+ },
12657
+ "openai/gpt-5.4-nano": {
12658
+ id: "openai/gpt-5.4-nano",
12659
+ name: "GPT 5.4 Nano",
12660
+ api: "anthropic-messages",
12661
+ provider: "vercel-ai-gateway",
12662
+ baseUrl: "https://ai-gateway.vercel.sh",
12663
+ reasoning: true,
12664
+ input: ["text", "image"],
12665
+ cost: {
12666
+ input: 0.19999999999999998,
12667
+ output: 1.25,
12668
+ cacheRead: 0.02,
12669
+ cacheWrite: 0,
12670
+ },
12671
+ contextWindow: 400000,
12672
+ maxTokens: 128000,
12673
+ },
12316
12674
  "openai/gpt-5.4-pro": {
12317
12675
  id: "openai/gpt-5.4-pro",
12318
12676
  name: "GPT 5.4 Pro",
@@ -12475,8 +12833,8 @@ export const MODELS = {
12475
12833
  reasoning: false,
12476
12834
  input: ["text", "image"],
12477
12835
  cost: {
12478
- input: 1,
12479
- output: 1,
12836
+ input: 0,
12837
+ output: 0,
12480
12838
  cacheRead: 0,
12481
12839
  cacheWrite: 0,
12482
12840
  },
@@ -12492,8 +12850,8 @@ export const MODELS = {
12492
12850
  reasoning: false,
12493
12851
  input: ["text", "image"],
12494
12852
  cost: {
12495
- input: 3,
12496
- output: 15,
12853
+ input: 0,
12854
+ output: 0,
12497
12855
  cacheRead: 0,
12498
12856
  cacheWrite: 0,
12499
12857
  },
@@ -12517,40 +12875,6 @@ export const MODELS = {
12517
12875
  contextWindow: 131072,
12518
12876
  maxTokens: 131072,
12519
12877
  },
12520
- "vercel/v0-1.0-md": {
12521
- id: "vercel/v0-1.0-md",
12522
- name: "v0-1.0-md",
12523
- api: "anthropic-messages",
12524
- provider: "vercel-ai-gateway",
12525
- baseUrl: "https://ai-gateway.vercel.sh",
12526
- reasoning: false,
12527
- input: ["text", "image"],
12528
- cost: {
12529
- input: 3,
12530
- output: 15,
12531
- cacheRead: 0,
12532
- cacheWrite: 0,
12533
- },
12534
- contextWindow: 128000,
12535
- maxTokens: 32000,
12536
- },
12537
- "vercel/v0-1.5-md": {
12538
- id: "vercel/v0-1.5-md",
12539
- name: "v0-1.5-md",
12540
- api: "anthropic-messages",
12541
- provider: "vercel-ai-gateway",
12542
- baseUrl: "https://ai-gateway.vercel.sh",
12543
- reasoning: false,
12544
- input: ["text", "image"],
12545
- cost: {
12546
- input: 3,
12547
- output: 15,
12548
- cacheRead: 0,
12549
- cacheWrite: 0,
12550
- },
12551
- contextWindow: 128000,
12552
- maxTokens: 32768,
12553
- },
12554
12878
  "xai/grok-2-vision": {
12555
12879
  id: "xai/grok-2-vision",
12556
12880
  name: "Grok 2 Vision",
@@ -12579,7 +12903,7 @@ export const MODELS = {
12579
12903
  cost: {
12580
12904
  input: 3,
12581
12905
  output: 15,
12582
- cacheRead: 0,
12906
+ cacheRead: 0.75,
12583
12907
  cacheWrite: 0,
12584
12908
  },
12585
12909
  contextWindow: 131072,
@@ -12596,7 +12920,7 @@ export const MODELS = {
12596
12920
  cost: {
12597
12921
  input: 5,
12598
12922
  output: 25,
12599
- cacheRead: 0,
12923
+ cacheRead: 1.25,
12600
12924
  cacheWrite: 0,
12601
12925
  },
12602
12926
  contextWindow: 131072,
@@ -12613,7 +12937,7 @@ export const MODELS = {
12613
12937
  cost: {
12614
12938
  input: 0.3,
12615
12939
  output: 0.5,
12616
- cacheRead: 0,
12940
+ cacheRead: 0.075,
12617
12941
  cacheWrite: 0,
12618
12942
  },
12619
12943
  contextWindow: 131072,
@@ -12721,6 +13045,23 @@ export const MODELS = {
12721
13045
  contextWindow: 2000000,
12722
13046
  maxTokens: 30000,
12723
13047
  },
13048
+ "xai/grok-4.20-multi-agent": {
13049
+ id: "xai/grok-4.20-multi-agent",
13050
+ name: "Grok 4.20 Multi-Agent",
13051
+ api: "anthropic-messages",
13052
+ provider: "vercel-ai-gateway",
13053
+ baseUrl: "https://ai-gateway.vercel.sh",
13054
+ reasoning: true,
13055
+ input: ["text"],
13056
+ cost: {
13057
+ input: 2,
13058
+ output: 6,
13059
+ cacheRead: 0.19999999999999998,
13060
+ cacheWrite: 0,
13061
+ },
13062
+ contextWindow: 2000000,
13063
+ maxTokens: 2000000,
13064
+ },
12724
13065
  "xai/grok-4.20-multi-agent-beta": {
12725
13066
  id: "xai/grok-4.20-multi-agent-beta",
12726
13067
  name: "Grok 4.20 Multi Agent Beta",
@@ -12738,6 +13079,23 @@ export const MODELS = {
12738
13079
  contextWindow: 2000000,
12739
13080
  maxTokens: 2000000,
12740
13081
  },
13082
+ "xai/grok-4.20-non-reasoning": {
13083
+ id: "xai/grok-4.20-non-reasoning",
13084
+ name: "Grok 4.20 Non-Reasoning",
13085
+ api: "anthropic-messages",
13086
+ provider: "vercel-ai-gateway",
13087
+ baseUrl: "https://ai-gateway.vercel.sh",
13088
+ reasoning: false,
13089
+ input: ["text", "image"],
13090
+ cost: {
13091
+ input: 2,
13092
+ output: 6,
13093
+ cacheRead: 0.19999999999999998,
13094
+ cacheWrite: 0,
13095
+ },
13096
+ contextWindow: 2000000,
13097
+ maxTokens: 2000000,
13098
+ },
12741
13099
  "xai/grok-4.20-non-reasoning-beta": {
12742
13100
  id: "xai/grok-4.20-non-reasoning-beta",
12743
13101
  name: "Grok 4.20 Beta Non-Reasoning",
@@ -12755,6 +13113,23 @@ export const MODELS = {
12755
13113
  contextWindow: 2000000,
12756
13114
  maxTokens: 2000000,
12757
13115
  },
13116
+ "xai/grok-4.20-reasoning": {
13117
+ id: "xai/grok-4.20-reasoning",
13118
+ name: "Grok 4.20 Reasoning",
13119
+ api: "anthropic-messages",
13120
+ provider: "vercel-ai-gateway",
13121
+ baseUrl: "https://ai-gateway.vercel.sh",
13122
+ reasoning: true,
13123
+ input: ["text", "image"],
13124
+ cost: {
13125
+ input: 2,
13126
+ output: 6,
13127
+ cacheRead: 0.19999999999999998,
13128
+ cacheWrite: 0,
13129
+ },
13130
+ contextWindow: 2000000,
13131
+ maxTokens: 2000000,
13132
+ },
12758
13133
  "xai/grok-4.20-reasoning-beta": {
12759
13134
  id: "xai/grok-4.20-reasoning-beta",
12760
13135
  name: "Grok 4.20 Beta Reasoning",
@@ -12806,6 +13181,23 @@ export const MODELS = {
12806
13181
  contextWindow: 262144,
12807
13182
  maxTokens: 32000,
12808
13183
  },
13184
+ "xiaomi/mimo-v2-pro": {
13185
+ id: "xiaomi/mimo-v2-pro",
13186
+ name: "MiMo V2 Pro",
13187
+ api: "anthropic-messages",
13188
+ provider: "vercel-ai-gateway",
13189
+ baseUrl: "https://ai-gateway.vercel.sh",
13190
+ reasoning: true,
13191
+ input: ["text"],
13192
+ cost: {
13193
+ input: 1,
13194
+ output: 3,
13195
+ cacheRead: 0.19999999999999998,
13196
+ cacheWrite: 0,
13197
+ },
13198
+ contextWindow: 1000000,
13199
+ maxTokens: 128000,
13200
+ },
12809
13201
  "zai/glm-4.5": {
12810
13202
  id: "zai/glm-4.5",
12811
13203
  name: "GLM-4.5",
@@ -12866,8 +13258,8 @@ export const MODELS = {
12866
13258
  reasoning: true,
12867
13259
  input: ["text"],
12868
13260
  cost: {
12869
- input: 0.44999999999999996,
12870
- output: 1.7999999999999998,
13261
+ input: 0.6,
13262
+ output: 2.2,
12871
13263
  cacheRead: 0.11,
12872
13264
  cacheWrite: 0,
12873
13265
  },
@@ -12976,6 +13368,23 @@ export const MODELS = {
12976
13368
  contextWindow: 202800,
12977
13369
  maxTokens: 131100,
12978
13370
  },
13371
+ "zai/glm-5-turbo": {
13372
+ id: "zai/glm-5-turbo",
13373
+ name: "GLM 5 Turbo",
13374
+ api: "anthropic-messages",
13375
+ provider: "vercel-ai-gateway",
13376
+ baseUrl: "https://ai-gateway.vercel.sh",
13377
+ reasoning: true,
13378
+ input: ["text"],
13379
+ cost: {
13380
+ input: 1.2,
13381
+ output: 4,
13382
+ cacheRead: 0.24,
13383
+ cacheWrite: 0,
13384
+ },
13385
+ contextWindow: 202800,
13386
+ maxTokens: 131100,
13387
+ },
12979
13388
  },
12980
13389
  "xai": {
12981
13390
  "grok-2": {
@@ -13301,9 +13710,9 @@ export const MODELS = {
13301
13710
  contextWindow: 2000000,
13302
13711
  maxTokens: 30000,
13303
13712
  },
13304
- "grok-4.20-beta-latest-non-reasoning": {
13305
- id: "grok-4.20-beta-latest-non-reasoning",
13306
- name: "Grok 4.20 Beta (Non-Reasoning)",
13713
+ "grok-4.20-0309-non-reasoning": {
13714
+ id: "grok-4.20-0309-non-reasoning",
13715
+ name: "Grok 4.20 (Non-Reasoning)",
13307
13716
  api: "openai-completions",
13308
13717
  provider: "xai",
13309
13718
  baseUrl: "https://api.x.ai/v1",
@@ -13318,26 +13727,9 @@ export const MODELS = {
13318
13727
  contextWindow: 2000000,
13319
13728
  maxTokens: 30000,
13320
13729
  },
13321
- "grok-4.20-beta-latest-reasoning": {
13322
- id: "grok-4.20-beta-latest-reasoning",
13323
- name: "Grok 4.20 Beta (Reasoning)",
13324
- api: "openai-completions",
13325
- provider: "xai",
13326
- baseUrl: "https://api.x.ai/v1",
13327
- reasoning: true,
13328
- input: ["text", "image"],
13329
- cost: {
13330
- input: 2,
13331
- output: 6,
13332
- cacheRead: 0.2,
13333
- cacheWrite: 0,
13334
- },
13335
- contextWindow: 2000000,
13336
- maxTokens: 30000,
13337
- },
13338
- "grok-4.20-multi-agent-beta-latest": {
13339
- id: "grok-4.20-multi-agent-beta-latest",
13340
- name: "Grok 4.20 Multi-Agent Beta",
13730
+ "grok-4.20-0309-reasoning": {
13731
+ id: "grok-4.20-0309-reasoning",
13732
+ name: "Grok 4.20 (Reasoning)",
13341
13733
  api: "openai-completions",
13342
13734
  provider: "xai",
13343
13735
  baseUrl: "https://api.x.ai/v1",
@@ -13567,6 +13959,24 @@ export const MODELS = {
13567
13959
  contextWindow: 204800,
13568
13960
  maxTokens: 131072,
13569
13961
  },
13962
+ "glm-5-turbo": {
13963
+ id: "glm-5-turbo",
13964
+ name: "GLM-5-Turbo",
13965
+ api: "openai-completions",
13966
+ provider: "zai",
13967
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
13968
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
13969
+ reasoning: true,
13970
+ input: ["text"],
13971
+ cost: {
13972
+ input: 1.2,
13973
+ output: 4,
13974
+ cacheRead: 0.24,
13975
+ cacheWrite: 0,
13976
+ },
13977
+ contextWindow: 200000,
13978
+ maxTokens: 131072,
13979
+ },
13570
13980
  },
13571
13981
  };
13572
13982
  //# sourceMappingURL=models.generated.js.map