@eminent337/aery-ai 0.67.75 → 0.67.77

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 (62) hide show
  1. package/README.md +12 -5
  2. package/dist/env-api-keys.d.ts +9 -0
  3. package/dist/env-api-keys.d.ts.map +1 -1
  4. package/dist/env-api-keys.js +89 -34
  5. package/dist/env-api-keys.js.map +1 -1
  6. package/dist/index.d.ts +2 -2
  7. package/dist/index.d.ts.map +1 -1
  8. package/dist/index.js +1 -1
  9. package/dist/index.js.map +1 -1
  10. package/dist/models.d.ts +2 -1
  11. package/dist/models.d.ts.map +1 -1
  12. package/dist/models.generated.d.ts +2877 -1647
  13. package/dist/models.generated.d.ts.map +1 -1
  14. package/dist/models.generated.js +1702 -496
  15. package/dist/models.generated.js.map +1 -1
  16. package/dist/models.js +7 -2
  17. package/dist/models.js.map +1 -1
  18. package/dist/providers/amazon-bedrock.d.ts.map +1 -1
  19. package/dist/providers/amazon-bedrock.js +97 -34
  20. package/dist/providers/amazon-bedrock.js.map +1 -1
  21. package/dist/providers/anthropic.d.ts.map +1 -1
  22. package/dist/providers/anthropic.js +42 -17
  23. package/dist/providers/anthropic.js.map +1 -1
  24. package/dist/providers/azure-openai-responses.d.ts.map +1 -1
  25. package/dist/providers/azure-openai-responses.js +24 -5
  26. package/dist/providers/azure-openai-responses.js.map +1 -1
  27. package/dist/providers/cloudflare.d.ts +7 -0
  28. package/dist/providers/cloudflare.d.ts.map +1 -0
  29. package/dist/providers/cloudflare.js +19 -0
  30. package/dist/providers/cloudflare.js.map +1 -0
  31. package/dist/providers/google-gemini-cli.d.ts.map +1 -1
  32. package/dist/providers/google-gemini-cli.js +2 -2
  33. package/dist/providers/google-gemini-cli.js.map +1 -1
  34. package/dist/providers/google-vertex.d.ts.map +1 -1
  35. package/dist/providers/google-vertex.js +34 -13
  36. package/dist/providers/google-vertex.js.map +1 -1
  37. package/dist/providers/openai-codex-responses.d.ts.map +1 -1
  38. package/dist/providers/openai-codex-responses.js +11 -10
  39. package/dist/providers/openai-codex-responses.js.map +1 -1
  40. package/dist/providers/openai-completions.d.ts.map +1 -1
  41. package/dist/providers/openai-completions.js +102 -47
  42. package/dist/providers/openai-completions.js.map +1 -1
  43. package/dist/providers/openai-responses.d.ts.map +1 -1
  44. package/dist/providers/openai-responses.js +26 -23
  45. package/dist/providers/openai-responses.js.map +1 -1
  46. package/dist/providers/simple-options.d.ts.map +1 -1
  47. package/dist/providers/simple-options.js +2 -0
  48. package/dist/providers/simple-options.js.map +1 -1
  49. package/dist/providers/transform-messages.d.ts.map +1 -1
  50. package/dist/providers/transform-messages.js +2 -0
  51. package/dist/providers/transform-messages.js.map +1 -1
  52. package/dist/types.d.ts +36 -5
  53. package/dist/types.d.ts.map +1 -1
  54. package/dist/types.js.map +1 -1
  55. package/dist/utils/typebox-helpers.d.ts +1 -1
  56. package/dist/utils/typebox-helpers.d.ts.map +1 -1
  57. package/dist/utils/typebox-helpers.js +1 -1
  58. package/dist/utils/typebox-helpers.js.map +1 -1
  59. package/dist/utils/validation.d.ts.map +1 -1
  60. package/dist/utils/validation.js +242 -41
  61. package/dist/utils/validation.js.map +1 -1
  62. package/package.json +2 -4
@@ -325,6 +325,40 @@ export const MODELS = {
325
325
  contextWindow: 1000000,
326
326
  maxTokens: 64000,
327
327
  },
328
+ "au.anthropic.claude-opus-4-6-v1": {
329
+ id: "au.anthropic.claude-opus-4-6-v1",
330
+ name: "AU Anthropic Claude Opus 4.6",
331
+ api: "bedrock-converse-stream",
332
+ provider: "amazon-bedrock",
333
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
334
+ reasoning: true,
335
+ input: ["text", "image"],
336
+ cost: {
337
+ input: 16.5,
338
+ output: 82.5,
339
+ cacheRead: 0.5,
340
+ cacheWrite: 6.25,
341
+ },
342
+ contextWindow: 1000000,
343
+ maxTokens: 128000,
344
+ },
345
+ "au.anthropic.claude-sonnet-4-6": {
346
+ id: "au.anthropic.claude-sonnet-4-6",
347
+ name: "AU Anthropic Claude Sonnet 4.6",
348
+ api: "bedrock-converse-stream",
349
+ provider: "amazon-bedrock",
350
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
351
+ reasoning: true,
352
+ input: ["text", "image"],
353
+ cost: {
354
+ input: 3.3,
355
+ output: 16.5,
356
+ cacheRead: 0.33,
357
+ cacheWrite: 4.125,
358
+ },
359
+ contextWindow: 1000000,
360
+ maxTokens: 128000,
361
+ },
328
362
  "deepseek.r1-v1:0": {
329
363
  id: "deepseek.r1-v1:0",
330
364
  name: "DeepSeek-R1",
@@ -381,7 +415,7 @@ export const MODELS = {
381
415
  name: "Claude Haiku 4.5 (EU)",
382
416
  api: "bedrock-converse-stream",
383
417
  provider: "amazon-bedrock",
384
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
418
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
385
419
  reasoning: true,
386
420
  input: ["text", "image"],
387
421
  cost: {
@@ -398,7 +432,7 @@ export const MODELS = {
398
432
  name: "Claude Opus 4.5 (EU)",
399
433
  api: "bedrock-converse-stream",
400
434
  provider: "amazon-bedrock",
401
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
435
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
402
436
  reasoning: true,
403
437
  input: ["text", "image"],
404
438
  cost: {
@@ -415,7 +449,7 @@ export const MODELS = {
415
449
  name: "Claude Opus 4.6 (EU)",
416
450
  api: "bedrock-converse-stream",
417
451
  provider: "amazon-bedrock",
418
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
452
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
419
453
  reasoning: true,
420
454
  input: ["text", "image"],
421
455
  cost: {
@@ -432,7 +466,7 @@ export const MODELS = {
432
466
  name: "Claude Opus 4.7 (EU)",
433
467
  api: "bedrock-converse-stream",
434
468
  provider: "amazon-bedrock",
435
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
469
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
436
470
  reasoning: true,
437
471
  input: ["text", "image"],
438
472
  cost: {
@@ -449,7 +483,7 @@ export const MODELS = {
449
483
  name: "Claude Sonnet 4 (EU)",
450
484
  api: "bedrock-converse-stream",
451
485
  provider: "amazon-bedrock",
452
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
486
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
453
487
  reasoning: true,
454
488
  input: ["text", "image"],
455
489
  cost: {
@@ -466,7 +500,7 @@ export const MODELS = {
466
500
  name: "Claude Sonnet 4.5 (EU)",
467
501
  api: "bedrock-converse-stream",
468
502
  provider: "amazon-bedrock",
469
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
503
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
470
504
  reasoning: true,
471
505
  input: ["text", "image"],
472
506
  cost: {
@@ -483,7 +517,7 @@ export const MODELS = {
483
517
  name: "Claude Sonnet 4.6 (EU)",
484
518
  api: "bedrock-converse-stream",
485
519
  provider: "amazon-bedrock",
486
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
520
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
487
521
  reasoning: true,
488
522
  input: ["text", "image"],
489
523
  cost: {
@@ -2488,6 +2522,23 @@ export const MODELS = {
2488
2522
  contextWindow: 1050000,
2489
2523
  maxTokens: 128000,
2490
2524
  },
2525
+ "gpt-5.5": {
2526
+ id: "gpt-5.5",
2527
+ name: "GPT-5.5",
2528
+ api: "azure-openai-responses",
2529
+ provider: "azure-openai-responses",
2530
+ baseUrl: "",
2531
+ reasoning: true,
2532
+ input: ["text", "image"],
2533
+ cost: {
2534
+ input: 5,
2535
+ output: 30,
2536
+ cacheRead: 0.5,
2537
+ cacheWrite: 0,
2538
+ },
2539
+ contextWindow: 272000,
2540
+ maxTokens: 128000,
2541
+ },
2491
2542
  "o1": {
2492
2543
  id: "o1",
2493
2544
  name: "o1",
@@ -2695,221 +2746,733 @@ export const MODELS = {
2695
2746
  maxTokens: 40000,
2696
2747
  },
2697
2748
  },
2698
- "github-copilot": {
2699
- "claude-haiku-4.5": {
2700
- id: "claude-haiku-4.5",
2701
- name: "Claude Haiku 4.5",
2702
- api: "anthropic-messages",
2703
- provider: "github-copilot",
2704
- baseUrl: "https://api.individual.githubcopilot.com",
2705
- 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" },
2749
+ "cloudflare-workers-ai": {
2750
+ "@cf/google/gemma-4-26b-a4b-it": {
2751
+ id: "@cf/google/gemma-4-26b-a4b-it",
2752
+ name: "Gemma 4 26B A4B IT",
2753
+ api: "openai-completions",
2754
+ provider: "cloudflare-workers-ai",
2755
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2756
+ compat: { "sendSessionAffinityHeaders": true },
2706
2757
  reasoning: true,
2707
2758
  input: ["text", "image"],
2708
2759
  cost: {
2709
- input: 0,
2710
- output: 0,
2760
+ input: 0.1,
2761
+ output: 0.3,
2711
2762
  cacheRead: 0,
2712
2763
  cacheWrite: 0,
2713
2764
  },
2714
- contextWindow: 144000,
2715
- maxTokens: 32000,
2765
+ contextWindow: 256000,
2766
+ maxTokens: 16384,
2716
2767
  },
2717
- "claude-opus-4.5": {
2718
- id: "claude-opus-4.5",
2719
- name: "Claude Opus 4.5",
2720
- api: "anthropic-messages",
2721
- provider: "github-copilot",
2722
- baseUrl: "https://api.individual.githubcopilot.com",
2723
- 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" },
2724
- reasoning: true,
2768
+ "@cf/meta/llama-4-scout-17b-16e-instruct": {
2769
+ id: "@cf/meta/llama-4-scout-17b-16e-instruct",
2770
+ name: "Llama 4 Scout 17B 16E Instruct",
2771
+ api: "openai-completions",
2772
+ provider: "cloudflare-workers-ai",
2773
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2774
+ compat: { "sendSessionAffinityHeaders": true },
2775
+ reasoning: false,
2725
2776
  input: ["text", "image"],
2726
2777
  cost: {
2727
- input: 0,
2728
- output: 0,
2778
+ input: 0.27,
2779
+ output: 0.85,
2729
2780
  cacheRead: 0,
2730
2781
  cacheWrite: 0,
2731
2782
  },
2732
- contextWindow: 160000,
2733
- maxTokens: 32000,
2783
+ contextWindow: 128000,
2784
+ maxTokens: 16384,
2734
2785
  },
2735
- "claude-opus-4.6": {
2736
- id: "claude-opus-4.6",
2737
- name: "Claude Opus 4.6",
2738
- api: "anthropic-messages",
2739
- provider: "github-copilot",
2740
- baseUrl: "https://api.individual.githubcopilot.com",
2741
- 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" },
2786
+ "@cf/moonshotai/kimi-k2.5": {
2787
+ id: "@cf/moonshotai/kimi-k2.5",
2788
+ name: "Kimi K2.5",
2789
+ api: "openai-completions",
2790
+ provider: "cloudflare-workers-ai",
2791
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2792
+ compat: { "sendSessionAffinityHeaders": true },
2742
2793
  reasoning: true,
2743
2794
  input: ["text", "image"],
2744
2795
  cost: {
2745
- input: 0,
2746
- output: 0,
2747
- cacheRead: 0,
2796
+ input: 0.6,
2797
+ output: 3,
2798
+ cacheRead: 0.1,
2748
2799
  cacheWrite: 0,
2749
2800
  },
2750
- contextWindow: 1000000,
2751
- maxTokens: 64000,
2801
+ contextWindow: 256000,
2802
+ maxTokens: 256000,
2752
2803
  },
2753
- "claude-opus-4.7": {
2754
- id: "claude-opus-4.7",
2755
- name: "Claude Opus 4.7",
2756
- api: "anthropic-messages",
2757
- provider: "github-copilot",
2758
- baseUrl: "https://api.individual.githubcopilot.com",
2759
- 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" },
2804
+ "@cf/moonshotai/kimi-k2.6": {
2805
+ id: "@cf/moonshotai/kimi-k2.6",
2806
+ name: "Kimi K2.6",
2807
+ api: "openai-completions",
2808
+ provider: "cloudflare-workers-ai",
2809
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2810
+ compat: { "sendSessionAffinityHeaders": true },
2760
2811
  reasoning: true,
2761
2812
  input: ["text", "image"],
2762
2813
  cost: {
2763
- input: 0,
2764
- output: 0,
2765
- cacheRead: 0,
2814
+ input: 0.95,
2815
+ output: 4,
2816
+ cacheRead: 0.16,
2766
2817
  cacheWrite: 0,
2767
2818
  },
2768
- contextWindow: 144000,
2769
- maxTokens: 64000,
2819
+ contextWindow: 256000,
2820
+ maxTokens: 256000,
2770
2821
  },
2771
- "claude-sonnet-4": {
2772
- id: "claude-sonnet-4",
2773
- name: "Claude Sonnet 4",
2774
- api: "anthropic-messages",
2775
- provider: "github-copilot",
2776
- baseUrl: "https://api.individual.githubcopilot.com",
2777
- 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" },
2822
+ "@cf/nvidia/nemotron-3-120b-a12b": {
2823
+ id: "@cf/nvidia/nemotron-3-120b-a12b",
2824
+ name: "Nemotron 3 Super 120B",
2825
+ api: "openai-completions",
2826
+ provider: "cloudflare-workers-ai",
2827
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2828
+ compat: { "sendSessionAffinityHeaders": true },
2778
2829
  reasoning: true,
2779
- input: ["text", "image"],
2830
+ input: ["text"],
2780
2831
  cost: {
2781
- input: 0,
2782
- output: 0,
2832
+ input: 0.5,
2833
+ output: 1.5,
2783
2834
  cacheRead: 0,
2784
2835
  cacheWrite: 0,
2785
2836
  },
2786
- contextWindow: 216000,
2787
- maxTokens: 16000,
2837
+ contextWindow: 256000,
2838
+ maxTokens: 256000,
2788
2839
  },
2789
- "claude-sonnet-4.5": {
2790
- id: "claude-sonnet-4.5",
2791
- name: "Claude Sonnet 4.5",
2792
- api: "anthropic-messages",
2793
- provider: "github-copilot",
2794
- baseUrl: "https://api.individual.githubcopilot.com",
2795
- 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" },
2840
+ "@cf/openai/gpt-oss-120b": {
2841
+ id: "@cf/openai/gpt-oss-120b",
2842
+ name: "GPT OSS 120B",
2843
+ api: "openai-completions",
2844
+ provider: "cloudflare-workers-ai",
2845
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2846
+ compat: { "sendSessionAffinityHeaders": true },
2796
2847
  reasoning: true,
2797
- input: ["text", "image"],
2848
+ input: ["text"],
2798
2849
  cost: {
2799
- input: 0,
2800
- output: 0,
2850
+ input: 0.35,
2851
+ output: 0.75,
2801
2852
  cacheRead: 0,
2802
2853
  cacheWrite: 0,
2803
2854
  },
2804
- contextWindow: 144000,
2805
- maxTokens: 32000,
2855
+ contextWindow: 128000,
2856
+ maxTokens: 16384,
2806
2857
  },
2807
- "claude-sonnet-4.6": {
2808
- id: "claude-sonnet-4.6",
2809
- name: "Claude Sonnet 4.6",
2810
- api: "anthropic-messages",
2811
- provider: "github-copilot",
2812
- baseUrl: "https://api.individual.githubcopilot.com",
2813
- 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" },
2858
+ "@cf/openai/gpt-oss-20b": {
2859
+ id: "@cf/openai/gpt-oss-20b",
2860
+ name: "GPT OSS 20B",
2861
+ api: "openai-completions",
2862
+ provider: "cloudflare-workers-ai",
2863
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2864
+ compat: { "sendSessionAffinityHeaders": true },
2814
2865
  reasoning: true,
2815
- input: ["text", "image"],
2866
+ input: ["text"],
2816
2867
  cost: {
2817
- input: 0,
2818
- output: 0,
2868
+ input: 0.2,
2869
+ output: 0.3,
2819
2870
  cacheRead: 0,
2820
2871
  cacheWrite: 0,
2821
2872
  },
2822
- contextWindow: 1000000,
2823
- maxTokens: 32000,
2873
+ contextWindow: 128000,
2874
+ maxTokens: 16384,
2824
2875
  },
2825
- "gemini-2.5-pro": {
2826
- id: "gemini-2.5-pro",
2827
- name: "Gemini 2.5 Pro",
2876
+ "@cf/zai-org/glm-4.7-flash": {
2877
+ id: "@cf/zai-org/glm-4.7-flash",
2878
+ name: "GLM-4.7-Flash",
2828
2879
  api: "openai-completions",
2829
- provider: "github-copilot",
2830
- baseUrl: "https://api.individual.githubcopilot.com",
2831
- 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" },
2832
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2833
- reasoning: false,
2834
- input: ["text", "image"],
2880
+ provider: "cloudflare-workers-ai",
2881
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2882
+ compat: { "sendSessionAffinityHeaders": true },
2883
+ reasoning: true,
2884
+ input: ["text"],
2835
2885
  cost: {
2836
- input: 0,
2837
- output: 0,
2886
+ input: 0.06,
2887
+ output: 0.4,
2838
2888
  cacheRead: 0,
2839
2889
  cacheWrite: 0,
2840
2890
  },
2841
- contextWindow: 128000,
2842
- maxTokens: 64000,
2891
+ contextWindow: 131072,
2892
+ maxTokens: 131072,
2843
2893
  },
2844
- "gemini-3-flash-preview": {
2845
- id: "gemini-3-flash-preview",
2846
- name: "Gemini 3 Flash",
2894
+ },
2895
+ "deepseek": {
2896
+ "deepseek-v4-flash": {
2897
+ id: "deepseek-v4-flash",
2898
+ name: "DeepSeek V4 Flash",
2847
2899
  api: "openai-completions",
2848
- provider: "github-copilot",
2849
- baseUrl: "https://api.individual.githubcopilot.com",
2850
- 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" },
2851
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2900
+ provider: "deepseek",
2901
+ baseUrl: "https://api.deepseek.com",
2902
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
2852
2903
  reasoning: true,
2853
- input: ["text", "image"],
2904
+ input: ["text"],
2854
2905
  cost: {
2855
- input: 0,
2856
- output: 0,
2857
- cacheRead: 0,
2906
+ input: 0.14,
2907
+ output: 0.28,
2908
+ cacheRead: 0.028,
2858
2909
  cacheWrite: 0,
2859
2910
  },
2860
- contextWindow: 128000,
2861
- maxTokens: 64000,
2911
+ contextWindow: 1000000,
2912
+ maxTokens: 384000,
2862
2913
  },
2863
- "gemini-3-pro-preview": {
2864
- id: "gemini-3-pro-preview",
2865
- name: "Gemini 3 Pro Preview",
2914
+ "deepseek-v4-pro": {
2915
+ id: "deepseek-v4-pro",
2916
+ name: "DeepSeek V4 Pro",
2866
2917
  api: "openai-completions",
2867
- provider: "github-copilot",
2868
- baseUrl: "https://api.individual.githubcopilot.com",
2869
- 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" },
2870
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2918
+ provider: "deepseek",
2919
+ baseUrl: "https://api.deepseek.com",
2920
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek", "reasoningEffortMap": { "minimal": "high", "low": "high", "medium": "high", "high": "high", "xhigh": "max" } },
2871
2921
  reasoning: true,
2872
- input: ["text", "image"],
2922
+ input: ["text"],
2873
2923
  cost: {
2874
- input: 0,
2875
- output: 0,
2876
- cacheRead: 0,
2924
+ input: 1.74,
2925
+ output: 3.48,
2926
+ cacheRead: 0.145,
2877
2927
  cacheWrite: 0,
2878
2928
  },
2879
- contextWindow: 128000,
2880
- maxTokens: 64000,
2929
+ contextWindow: 1000000,
2930
+ maxTokens: 384000,
2881
2931
  },
2882
- "gemini-3.1-pro-preview": {
2883
- id: "gemini-3.1-pro-preview",
2884
- name: "Gemini 3.1 Pro Preview",
2885
- api: "openai-completions",
2886
- provider: "github-copilot",
2887
- baseUrl: "https://api.individual.githubcopilot.com",
2888
- 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" },
2889
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2932
+ },
2933
+ "fireworks": {
2934
+ "accounts/fireworks/models/deepseek-v3p1": {
2935
+ id: "accounts/fireworks/models/deepseek-v3p1",
2936
+ name: "DeepSeek V3.1",
2937
+ api: "anthropic-messages",
2938
+ provider: "fireworks",
2939
+ baseUrl: "https://api.fireworks.ai/inference",
2890
2940
  reasoning: true,
2891
- input: ["text", "image"],
2941
+ input: ["text"],
2892
2942
  cost: {
2893
- input: 0,
2894
- output: 0,
2943
+ input: 0.56,
2944
+ output: 1.68,
2895
2945
  cacheRead: 0,
2896
2946
  cacheWrite: 0,
2897
2947
  },
2898
- contextWindow: 128000,
2899
- maxTokens: 64000,
2948
+ contextWindow: 163840,
2949
+ maxTokens: 163840,
2900
2950
  },
2901
- "gpt-4.1": {
2902
- id: "gpt-4.1",
2903
- name: "GPT-4.1",
2904
- api: "openai-completions",
2905
- provider: "github-copilot",
2906
- baseUrl: "https://api.individual.githubcopilot.com",
2907
- 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" },
2908
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2909
- reasoning: false,
2910
- input: ["text", "image"],
2911
- cost: {
2912
- input: 0,
2951
+ "accounts/fireworks/models/deepseek-v3p2": {
2952
+ id: "accounts/fireworks/models/deepseek-v3p2",
2953
+ name: "DeepSeek V3.2",
2954
+ api: "anthropic-messages",
2955
+ provider: "fireworks",
2956
+ baseUrl: "https://api.fireworks.ai/inference",
2957
+ reasoning: true,
2958
+ input: ["text"],
2959
+ cost: {
2960
+ input: 0.56,
2961
+ output: 1.68,
2962
+ cacheRead: 0.28,
2963
+ cacheWrite: 0,
2964
+ },
2965
+ contextWindow: 160000,
2966
+ maxTokens: 160000,
2967
+ },
2968
+ "accounts/fireworks/models/deepseek-v4-pro": {
2969
+ id: "accounts/fireworks/models/deepseek-v4-pro",
2970
+ name: "DeepSeek V4 Pro",
2971
+ api: "anthropic-messages",
2972
+ provider: "fireworks",
2973
+ baseUrl: "https://api.fireworks.ai/inference",
2974
+ reasoning: true,
2975
+ input: ["text"],
2976
+ cost: {
2977
+ input: 1.74,
2978
+ output: 3.48,
2979
+ cacheRead: 0.15,
2980
+ cacheWrite: 0,
2981
+ },
2982
+ contextWindow: 1000000,
2983
+ maxTokens: 384000,
2984
+ },
2985
+ "accounts/fireworks/models/glm-4p5": {
2986
+ id: "accounts/fireworks/models/glm-4p5",
2987
+ name: "GLM 4.5",
2988
+ api: "anthropic-messages",
2989
+ provider: "fireworks",
2990
+ baseUrl: "https://api.fireworks.ai/inference",
2991
+ reasoning: true,
2992
+ input: ["text"],
2993
+ cost: {
2994
+ input: 0.55,
2995
+ output: 2.19,
2996
+ cacheRead: 0,
2997
+ cacheWrite: 0,
2998
+ },
2999
+ contextWindow: 131072,
3000
+ maxTokens: 131072,
3001
+ },
3002
+ "accounts/fireworks/models/glm-4p5-air": {
3003
+ id: "accounts/fireworks/models/glm-4p5-air",
3004
+ name: "GLM 4.5 Air",
3005
+ api: "anthropic-messages",
3006
+ provider: "fireworks",
3007
+ baseUrl: "https://api.fireworks.ai/inference",
3008
+ reasoning: true,
3009
+ input: ["text"],
3010
+ cost: {
3011
+ input: 0.22,
3012
+ output: 0.88,
3013
+ cacheRead: 0,
3014
+ cacheWrite: 0,
3015
+ },
3016
+ contextWindow: 131072,
3017
+ maxTokens: 131072,
3018
+ },
3019
+ "accounts/fireworks/models/glm-4p7": {
3020
+ id: "accounts/fireworks/models/glm-4p7",
3021
+ name: "GLM 4.7",
3022
+ api: "anthropic-messages",
3023
+ provider: "fireworks",
3024
+ baseUrl: "https://api.fireworks.ai/inference",
3025
+ reasoning: true,
3026
+ input: ["text"],
3027
+ cost: {
3028
+ input: 0.6,
3029
+ output: 2.2,
3030
+ cacheRead: 0.3,
3031
+ cacheWrite: 0,
3032
+ },
3033
+ contextWindow: 198000,
3034
+ maxTokens: 198000,
3035
+ },
3036
+ "accounts/fireworks/models/glm-5": {
3037
+ id: "accounts/fireworks/models/glm-5",
3038
+ name: "GLM 5",
3039
+ api: "anthropic-messages",
3040
+ provider: "fireworks",
3041
+ baseUrl: "https://api.fireworks.ai/inference",
3042
+ reasoning: true,
3043
+ input: ["text"],
3044
+ cost: {
3045
+ input: 1,
3046
+ output: 3.2,
3047
+ cacheRead: 0.5,
3048
+ cacheWrite: 0,
3049
+ },
3050
+ contextWindow: 202752,
3051
+ maxTokens: 131072,
3052
+ },
3053
+ "accounts/fireworks/models/glm-5p1": {
3054
+ id: "accounts/fireworks/models/glm-5p1",
3055
+ name: "GLM 5.1",
3056
+ api: "anthropic-messages",
3057
+ provider: "fireworks",
3058
+ baseUrl: "https://api.fireworks.ai/inference",
3059
+ reasoning: true,
3060
+ input: ["text"],
3061
+ cost: {
3062
+ input: 1.4,
3063
+ output: 4.4,
3064
+ cacheRead: 0.26,
3065
+ cacheWrite: 0,
3066
+ },
3067
+ contextWindow: 202800,
3068
+ maxTokens: 131072,
3069
+ },
3070
+ "accounts/fireworks/models/gpt-oss-120b": {
3071
+ id: "accounts/fireworks/models/gpt-oss-120b",
3072
+ name: "GPT OSS 120B",
3073
+ api: "anthropic-messages",
3074
+ provider: "fireworks",
3075
+ baseUrl: "https://api.fireworks.ai/inference",
3076
+ reasoning: true,
3077
+ input: ["text"],
3078
+ cost: {
3079
+ input: 0.15,
3080
+ output: 0.6,
3081
+ cacheRead: 0,
3082
+ cacheWrite: 0,
3083
+ },
3084
+ contextWindow: 131072,
3085
+ maxTokens: 32768,
3086
+ },
3087
+ "accounts/fireworks/models/gpt-oss-20b": {
3088
+ id: "accounts/fireworks/models/gpt-oss-20b",
3089
+ name: "GPT OSS 20B",
3090
+ api: "anthropic-messages",
3091
+ provider: "fireworks",
3092
+ baseUrl: "https://api.fireworks.ai/inference",
3093
+ reasoning: true,
3094
+ input: ["text"],
3095
+ cost: {
3096
+ input: 0.05,
3097
+ output: 0.2,
3098
+ cacheRead: 0,
3099
+ cacheWrite: 0,
3100
+ },
3101
+ contextWindow: 131072,
3102
+ maxTokens: 32768,
3103
+ },
3104
+ "accounts/fireworks/models/kimi-k2-instruct": {
3105
+ id: "accounts/fireworks/models/kimi-k2-instruct",
3106
+ name: "Kimi K2 Instruct",
3107
+ api: "anthropic-messages",
3108
+ provider: "fireworks",
3109
+ baseUrl: "https://api.fireworks.ai/inference",
3110
+ reasoning: false,
3111
+ input: ["text"],
3112
+ cost: {
3113
+ input: 1,
3114
+ output: 3,
3115
+ cacheRead: 0,
3116
+ cacheWrite: 0,
3117
+ },
3118
+ contextWindow: 128000,
3119
+ maxTokens: 16384,
3120
+ },
3121
+ "accounts/fireworks/models/kimi-k2-thinking": {
3122
+ id: "accounts/fireworks/models/kimi-k2-thinking",
3123
+ name: "Kimi K2 Thinking",
3124
+ api: "anthropic-messages",
3125
+ provider: "fireworks",
3126
+ baseUrl: "https://api.fireworks.ai/inference",
3127
+ reasoning: true,
3128
+ input: ["text"],
3129
+ cost: {
3130
+ input: 0.6,
3131
+ output: 2.5,
3132
+ cacheRead: 0.3,
3133
+ cacheWrite: 0,
3134
+ },
3135
+ contextWindow: 256000,
3136
+ maxTokens: 256000,
3137
+ },
3138
+ "accounts/fireworks/models/kimi-k2p5": {
3139
+ id: "accounts/fireworks/models/kimi-k2p5",
3140
+ name: "Kimi K2.5",
3141
+ api: "anthropic-messages",
3142
+ provider: "fireworks",
3143
+ baseUrl: "https://api.fireworks.ai/inference",
3144
+ reasoning: true,
3145
+ input: ["text", "image"],
3146
+ cost: {
3147
+ input: 0.6,
3148
+ output: 3,
3149
+ cacheRead: 0.1,
3150
+ cacheWrite: 0,
3151
+ },
3152
+ contextWindow: 256000,
3153
+ maxTokens: 256000,
3154
+ },
3155
+ "accounts/fireworks/models/kimi-k2p6": {
3156
+ id: "accounts/fireworks/models/kimi-k2p6",
3157
+ name: "Kimi K2.6",
3158
+ api: "anthropic-messages",
3159
+ provider: "fireworks",
3160
+ baseUrl: "https://api.fireworks.ai/inference",
3161
+ reasoning: true,
3162
+ input: ["text", "image"],
3163
+ cost: {
3164
+ input: 0.95,
3165
+ output: 4,
3166
+ cacheRead: 0.16,
3167
+ cacheWrite: 0,
3168
+ },
3169
+ contextWindow: 262000,
3170
+ maxTokens: 262000,
3171
+ },
3172
+ "accounts/fireworks/models/minimax-m2p1": {
3173
+ id: "accounts/fireworks/models/minimax-m2p1",
3174
+ name: "MiniMax-M2.1",
3175
+ api: "anthropic-messages",
3176
+ provider: "fireworks",
3177
+ baseUrl: "https://api.fireworks.ai/inference",
3178
+ reasoning: true,
3179
+ input: ["text"],
3180
+ cost: {
3181
+ input: 0.3,
3182
+ output: 1.2,
3183
+ cacheRead: 0.03,
3184
+ cacheWrite: 0,
3185
+ },
3186
+ contextWindow: 200000,
3187
+ maxTokens: 200000,
3188
+ },
3189
+ "accounts/fireworks/models/minimax-m2p5": {
3190
+ id: "accounts/fireworks/models/minimax-m2p5",
3191
+ name: "MiniMax-M2.5",
3192
+ api: "anthropic-messages",
3193
+ provider: "fireworks",
3194
+ baseUrl: "https://api.fireworks.ai/inference",
3195
+ reasoning: true,
3196
+ input: ["text"],
3197
+ cost: {
3198
+ input: 0.3,
3199
+ output: 1.2,
3200
+ cacheRead: 0.03,
3201
+ cacheWrite: 0,
3202
+ },
3203
+ contextWindow: 196608,
3204
+ maxTokens: 196608,
3205
+ },
3206
+ "accounts/fireworks/models/minimax-m2p7": {
3207
+ id: "accounts/fireworks/models/minimax-m2p7",
3208
+ name: "MiniMax-M2.7",
3209
+ api: "anthropic-messages",
3210
+ provider: "fireworks",
3211
+ baseUrl: "https://api.fireworks.ai/inference",
3212
+ reasoning: true,
3213
+ input: ["text"],
3214
+ cost: {
3215
+ input: 0.3,
3216
+ output: 1.2,
3217
+ cacheRead: 0.03,
3218
+ cacheWrite: 0,
3219
+ },
3220
+ contextWindow: 196608,
3221
+ maxTokens: 196608,
3222
+ },
3223
+ "accounts/fireworks/models/qwen3p6-plus": {
3224
+ id: "accounts/fireworks/models/qwen3p6-plus",
3225
+ name: "Qwen 3.6 Plus",
3226
+ api: "anthropic-messages",
3227
+ provider: "fireworks",
3228
+ baseUrl: "https://api.fireworks.ai/inference",
3229
+ reasoning: true,
3230
+ input: ["text", "image"],
3231
+ cost: {
3232
+ input: 0.5,
3233
+ output: 3,
3234
+ cacheRead: 0.1,
3235
+ cacheWrite: 0,
3236
+ },
3237
+ contextWindow: 128000,
3238
+ maxTokens: 8192,
3239
+ },
3240
+ "accounts/fireworks/routers/kimi-k2p5-turbo": {
3241
+ id: "accounts/fireworks/routers/kimi-k2p5-turbo",
3242
+ name: "Kimi K2.5 Turbo (firepass)",
3243
+ api: "anthropic-messages",
3244
+ provider: "fireworks",
3245
+ baseUrl: "https://api.fireworks.ai/inference",
3246
+ reasoning: true,
3247
+ input: ["text", "image"],
3248
+ cost: {
3249
+ input: 0,
3250
+ output: 0,
3251
+ cacheRead: 0,
3252
+ cacheWrite: 0,
3253
+ },
3254
+ contextWindow: 256000,
3255
+ maxTokens: 256000,
3256
+ },
3257
+ },
3258
+ "github-copilot": {
3259
+ "claude-haiku-4.5": {
3260
+ id: "claude-haiku-4.5",
3261
+ name: "Claude Haiku 4.5",
3262
+ api: "anthropic-messages",
3263
+ provider: "github-copilot",
3264
+ baseUrl: "https://api.individual.githubcopilot.com",
3265
+ 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" },
3266
+ compat: { "supportsEagerToolInputStreaming": false },
3267
+ reasoning: true,
3268
+ input: ["text", "image"],
3269
+ cost: {
3270
+ input: 0,
3271
+ output: 0,
3272
+ cacheRead: 0,
3273
+ cacheWrite: 0,
3274
+ },
3275
+ contextWindow: 144000,
3276
+ maxTokens: 32000,
3277
+ },
3278
+ "claude-opus-4.5": {
3279
+ id: "claude-opus-4.5",
3280
+ name: "Claude Opus 4.5",
3281
+ api: "anthropic-messages",
3282
+ provider: "github-copilot",
3283
+ baseUrl: "https://api.individual.githubcopilot.com",
3284
+ 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" },
3285
+ reasoning: true,
3286
+ input: ["text", "image"],
3287
+ cost: {
3288
+ input: 0,
3289
+ output: 0,
3290
+ cacheRead: 0,
3291
+ cacheWrite: 0,
3292
+ },
3293
+ contextWindow: 160000,
3294
+ maxTokens: 32000,
3295
+ },
3296
+ "claude-opus-4.6": {
3297
+ id: "claude-opus-4.6",
3298
+ name: "Claude Opus 4.6",
3299
+ api: "anthropic-messages",
3300
+ provider: "github-copilot",
3301
+ baseUrl: "https://api.individual.githubcopilot.com",
3302
+ 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" },
3303
+ reasoning: true,
3304
+ input: ["text", "image"],
3305
+ cost: {
3306
+ input: 0,
3307
+ output: 0,
3308
+ cacheRead: 0,
3309
+ cacheWrite: 0,
3310
+ },
3311
+ contextWindow: 1000000,
3312
+ maxTokens: 64000,
3313
+ },
3314
+ "claude-opus-4.7": {
3315
+ id: "claude-opus-4.7",
3316
+ name: "Claude Opus 4.7",
3317
+ api: "anthropic-messages",
3318
+ provider: "github-copilot",
3319
+ baseUrl: "https://api.individual.githubcopilot.com",
3320
+ 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" },
3321
+ reasoning: true,
3322
+ input: ["text", "image"],
3323
+ cost: {
3324
+ input: 0,
3325
+ output: 0,
3326
+ cacheRead: 0,
3327
+ cacheWrite: 0,
3328
+ },
3329
+ contextWindow: 144000,
3330
+ maxTokens: 64000,
3331
+ },
3332
+ "claude-sonnet-4": {
3333
+ id: "claude-sonnet-4",
3334
+ name: "Claude Sonnet 4",
3335
+ api: "anthropic-messages",
3336
+ provider: "github-copilot",
3337
+ baseUrl: "https://api.individual.githubcopilot.com",
3338
+ 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" },
3339
+ compat: { "supportsEagerToolInputStreaming": false },
3340
+ reasoning: true,
3341
+ input: ["text", "image"],
3342
+ cost: {
3343
+ input: 0,
3344
+ output: 0,
3345
+ cacheRead: 0,
3346
+ cacheWrite: 0,
3347
+ },
3348
+ contextWindow: 216000,
3349
+ maxTokens: 16000,
3350
+ },
3351
+ "claude-sonnet-4.5": {
3352
+ id: "claude-sonnet-4.5",
3353
+ name: "Claude Sonnet 4.5",
3354
+ api: "anthropic-messages",
3355
+ provider: "github-copilot",
3356
+ baseUrl: "https://api.individual.githubcopilot.com",
3357
+ 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" },
3358
+ compat: { "supportsEagerToolInputStreaming": false },
3359
+ reasoning: true,
3360
+ input: ["text", "image"],
3361
+ cost: {
3362
+ input: 0,
3363
+ output: 0,
3364
+ cacheRead: 0,
3365
+ cacheWrite: 0,
3366
+ },
3367
+ contextWindow: 144000,
3368
+ maxTokens: 32000,
3369
+ },
3370
+ "claude-sonnet-4.6": {
3371
+ id: "claude-sonnet-4.6",
3372
+ name: "Claude Sonnet 4.6",
3373
+ api: "anthropic-messages",
3374
+ provider: "github-copilot",
3375
+ baseUrl: "https://api.individual.githubcopilot.com",
3376
+ 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" },
3377
+ reasoning: true,
3378
+ input: ["text", "image"],
3379
+ cost: {
3380
+ input: 0,
3381
+ output: 0,
3382
+ cacheRead: 0,
3383
+ cacheWrite: 0,
3384
+ },
3385
+ contextWindow: 1000000,
3386
+ maxTokens: 32000,
3387
+ },
3388
+ "gemini-2.5-pro": {
3389
+ id: "gemini-2.5-pro",
3390
+ name: "Gemini 2.5 Pro",
3391
+ api: "openai-completions",
3392
+ provider: "github-copilot",
3393
+ baseUrl: "https://api.individual.githubcopilot.com",
3394
+ 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" },
3395
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3396
+ reasoning: false,
3397
+ input: ["text", "image"],
3398
+ cost: {
3399
+ input: 0,
3400
+ output: 0,
3401
+ cacheRead: 0,
3402
+ cacheWrite: 0,
3403
+ },
3404
+ contextWindow: 128000,
3405
+ maxTokens: 64000,
3406
+ },
3407
+ "gemini-3-flash-preview": {
3408
+ id: "gemini-3-flash-preview",
3409
+ name: "Gemini 3 Flash",
3410
+ api: "openai-completions",
3411
+ provider: "github-copilot",
3412
+ baseUrl: "https://api.individual.githubcopilot.com",
3413
+ 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" },
3414
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3415
+ reasoning: true,
3416
+ input: ["text", "image"],
3417
+ cost: {
3418
+ input: 0,
3419
+ output: 0,
3420
+ cacheRead: 0,
3421
+ cacheWrite: 0,
3422
+ },
3423
+ contextWindow: 128000,
3424
+ maxTokens: 64000,
3425
+ },
3426
+ "gemini-3-pro-preview": {
3427
+ id: "gemini-3-pro-preview",
3428
+ name: "Gemini 3 Pro Preview",
3429
+ api: "openai-completions",
3430
+ provider: "github-copilot",
3431
+ baseUrl: "https://api.individual.githubcopilot.com",
3432
+ 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" },
3433
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3434
+ reasoning: true,
3435
+ input: ["text", "image"],
3436
+ cost: {
3437
+ input: 0,
3438
+ output: 0,
3439
+ cacheRead: 0,
3440
+ cacheWrite: 0,
3441
+ },
3442
+ contextWindow: 128000,
3443
+ maxTokens: 64000,
3444
+ },
3445
+ "gemini-3.1-pro-preview": {
3446
+ id: "gemini-3.1-pro-preview",
3447
+ name: "Gemini 3.1 Pro Preview",
3448
+ api: "openai-completions",
3449
+ provider: "github-copilot",
3450
+ baseUrl: "https://api.individual.githubcopilot.com",
3451
+ 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" },
3452
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3453
+ reasoning: true,
3454
+ input: ["text", "image"],
3455
+ cost: {
3456
+ input: 0,
3457
+ output: 0,
3458
+ cacheRead: 0,
3459
+ cacheWrite: 0,
3460
+ },
3461
+ contextWindow: 128000,
3462
+ maxTokens: 64000,
3463
+ },
3464
+ "gpt-4.1": {
3465
+ id: "gpt-4.1",
3466
+ name: "GPT-4.1",
3467
+ api: "openai-completions",
3468
+ provider: "github-copilot",
3469
+ baseUrl: "https://api.individual.githubcopilot.com",
3470
+ 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" },
3471
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3472
+ reasoning: false,
3473
+ input: ["text", "image"],
3474
+ cost: {
3475
+ input: 0,
2913
3476
  output: 0,
2914
3477
  cacheRead: 0,
2915
3478
  cacheWrite: 0,
@@ -3134,6 +3697,24 @@ export const MODELS = {
3134
3697
  contextWindow: 400000,
3135
3698
  maxTokens: 128000,
3136
3699
  },
3700
+ "gpt-5.5": {
3701
+ id: "gpt-5.5",
3702
+ name: "GPT-5.5",
3703
+ api: "openai-responses",
3704
+ provider: "github-copilot",
3705
+ baseUrl: "https://api.individual.githubcopilot.com",
3706
+ 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" },
3707
+ reasoning: true,
3708
+ input: ["text", "image"],
3709
+ cost: {
3710
+ input: 0,
3711
+ output: 0,
3712
+ cacheRead: 0,
3713
+ cacheWrite: 0,
3714
+ },
3715
+ contextWindow: 400000,
3716
+ maxTokens: 128000,
3717
+ },
3137
3718
  "grok-code-fast-1": {
3138
3719
  id: "grok-code-fast-1",
3139
3720
  name: "Grok Code Fast 1",
@@ -3251,7 +3832,7 @@ export const MODELS = {
3251
3832
  cost: {
3252
3833
  input: 0.3,
3253
3834
  output: 2.5,
3254
- cacheRead: 0.075,
3835
+ cacheRead: 0.03,
3255
3836
  cacheWrite: 0,
3256
3837
  },
3257
3838
  contextWindow: 1048576,
@@ -3580,8 +4161,8 @@ export const MODELS = {
3580
4161
  contextWindow: 131072,
3581
4162
  maxTokens: 8192,
3582
4163
  },
3583
- "gemma-4-26b-it": {
3584
- id: "gemma-4-26b-it",
4164
+ "gemma-4-26b-a4b-it": {
4165
+ id: "gemma-4-26b-a4b-it",
3585
4166
  name: "Gemma 4 26B",
3586
4167
  api: "google-generative-ai",
3587
4168
  provider: "google",
@@ -3839,9 +4420,26 @@ export const MODELS = {
3839
4420
  contextWindow: 1048576,
3840
4421
  maxTokens: 65535,
3841
4422
  },
3842
- "gemini-3-pro-preview": {
3843
- id: "gemini-3-pro-preview",
3844
- name: "Gemini 3 Pro Preview (Cloud Code Assist)",
4423
+ "gemini-3-pro-preview": {
4424
+ id: "gemini-3-pro-preview",
4425
+ name: "Gemini 3 Pro Preview (Cloud Code Assist)",
4426
+ api: "google-gemini-cli",
4427
+ provider: "google-gemini-cli",
4428
+ baseUrl: "https://cloudcode-pa.googleapis.com",
4429
+ reasoning: true,
4430
+ input: ["text", "image"],
4431
+ cost: {
4432
+ input: 0,
4433
+ output: 0,
4434
+ cacheRead: 0,
4435
+ cacheWrite: 0,
4436
+ },
4437
+ contextWindow: 1048576,
4438
+ maxTokens: 65535,
4439
+ },
4440
+ "gemini-3.1-flash-lite-preview": {
4441
+ id: "gemini-3.1-flash-lite-preview",
4442
+ name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
3845
4443
  api: "google-gemini-cli",
3846
4444
  provider: "google-gemini-cli",
3847
4445
  baseUrl: "https://cloudcode-pa.googleapis.com",
@@ -4622,6 +5220,24 @@ export const MODELS = {
4622
5220
  contextWindow: 163840,
4623
5221
  maxTokens: 65536,
4624
5222
  },
5223
+ "deepseek-ai/DeepSeek-V4-Pro": {
5224
+ id: "deepseek-ai/DeepSeek-V4-Pro",
5225
+ name: "DeepSeek V4 Pro",
5226
+ api: "openai-completions",
5227
+ provider: "huggingface",
5228
+ baseUrl: "https://router.huggingface.co/v1",
5229
+ compat: { "supportsDeveloperRole": false },
5230
+ reasoning: true,
5231
+ input: ["text"],
5232
+ cost: {
5233
+ input: 1.74,
5234
+ output: 3.48,
5235
+ cacheRead: 0.145,
5236
+ cacheWrite: 0,
5237
+ },
5238
+ contextWindow: 1048576,
5239
+ maxTokens: 393216,
5240
+ },
4625
5241
  "moonshotai/Kimi-K2-Instruct": {
4626
5242
  id: "moonshotai/Kimi-K2-Instruct",
4627
5243
  name: "Kimi-K2-Instruct",
@@ -4694,6 +5310,24 @@ export const MODELS = {
4694
5310
  contextWindow: 262144,
4695
5311
  maxTokens: 262144,
4696
5312
  },
5313
+ "moonshotai/Kimi-K2.6": {
5314
+ id: "moonshotai/Kimi-K2.6",
5315
+ name: "Kimi-K2.6",
5316
+ api: "openai-completions",
5317
+ provider: "huggingface",
5318
+ baseUrl: "https://router.huggingface.co/v1",
5319
+ compat: { "supportsDeveloperRole": false },
5320
+ reasoning: true,
5321
+ input: ["text", "image"],
5322
+ cost: {
5323
+ input: 0.95,
5324
+ output: 4,
5325
+ cacheRead: 0.16,
5326
+ cacheWrite: 0,
5327
+ },
5328
+ contextWindow: 262144,
5329
+ maxTokens: 262144,
5330
+ },
4697
5331
  "zai-org/GLM-4.7": {
4698
5332
  id: "zai-org/GLM-4.7",
4699
5333
  name: "GLM-4.7",
@@ -4768,12 +5402,31 @@ export const MODELS = {
4768
5402
  },
4769
5403
  },
4770
5404
  "kimi-coding": {
5405
+ "k2p6": {
5406
+ id: "k2p6",
5407
+ name: "Kimi K2.6",
5408
+ api: "anthropic-messages",
5409
+ provider: "kimi-coding",
5410
+ baseUrl: "https://api.kimi.com/coding",
5411
+ headers: { "User-Agent": "KimiCLI/1.5" },
5412
+ reasoning: true,
5413
+ input: ["text", "image"],
5414
+ cost: {
5415
+ input: 0,
5416
+ output: 0,
5417
+ cacheRead: 0,
5418
+ cacheWrite: 0,
5419
+ },
5420
+ contextWindow: 262144,
5421
+ maxTokens: 32768,
5422
+ },
4771
5423
  "kimi-for-coding": {
4772
5424
  id: "kimi-for-coding",
4773
5425
  name: "Kimi For Coding",
4774
5426
  api: "anthropic-messages",
4775
5427
  provider: "kimi-coding",
4776
5428
  baseUrl: "https://api.kimi.com/coding",
5429
+ headers: { "User-Agent": "KimiCLI/1.5" },
4777
5430
  reasoning: true,
4778
5431
  input: ["text", "image"],
4779
5432
  cost: {
@@ -4791,6 +5444,7 @@ export const MODELS = {
4791
5444
  api: "anthropic-messages",
4792
5445
  provider: "kimi-coding",
4793
5446
  baseUrl: "https://api.kimi.com/coding",
5447
+ headers: { "User-Agent": "KimiCLI/1.5" },
4794
5448
  reasoning: true,
4795
5449
  input: ["text"],
4796
5450
  cost: {
@@ -5864,6 +6518,23 @@ export const MODELS = {
5864
6518
  contextWindow: 1050000,
5865
6519
  maxTokens: 128000,
5866
6520
  },
6521
+ "gpt-5.5": {
6522
+ id: "gpt-5.5",
6523
+ name: "GPT-5.5",
6524
+ api: "openai-responses",
6525
+ provider: "openai",
6526
+ baseUrl: "https://api.openai.com/v1",
6527
+ reasoning: true,
6528
+ input: ["text", "image"],
6529
+ cost: {
6530
+ input: 5,
6531
+ output: 30,
6532
+ cacheRead: 0.5,
6533
+ cacheWrite: 0,
6534
+ },
6535
+ contextWindow: 272000,
6536
+ maxTokens: 128000,
6537
+ },
5867
6538
  "o1": {
5868
6539
  id: "o1",
5869
6540
  name: "o1",
@@ -6155,6 +6826,23 @@ export const MODELS = {
6155
6826
  contextWindow: 272000,
6156
6827
  maxTokens: 128000,
6157
6828
  },
6829
+ "gpt-5.5": {
6830
+ id: "gpt-5.5",
6831
+ name: "GPT-5.5",
6832
+ api: "openai-codex-responses",
6833
+ provider: "openai-codex",
6834
+ baseUrl: "https://chatgpt.com/backend-api",
6835
+ reasoning: true,
6836
+ input: ["text", "image"],
6837
+ cost: {
6838
+ input: 5,
6839
+ output: 30,
6840
+ cacheRead: 0.5,
6841
+ cacheWrite: 0,
6842
+ },
6843
+ contextWindow: 272000,
6844
+ maxTokens: 128000,
6845
+ },
6158
6846
  },
6159
6847
  "opencode": {
6160
6848
  "big-pickle": {
@@ -6174,23 +6862,6 @@ export const MODELS = {
6174
6862
  contextWindow: 200000,
6175
6863
  maxTokens: 128000,
6176
6864
  },
6177
- "claude-3-5-haiku": {
6178
- id: "claude-3-5-haiku",
6179
- name: "Claude Haiku 3.5",
6180
- api: "anthropic-messages",
6181
- provider: "opencode",
6182
- baseUrl: "https://opencode.ai/zen",
6183
- reasoning: false,
6184
- input: ["text", "image"],
6185
- cost: {
6186
- input: 0.8,
6187
- output: 4,
6188
- cacheRead: 0.08,
6189
- cacheWrite: 1,
6190
- },
6191
- contextWindow: 200000,
6192
- maxTokens: 8192,
6193
- },
6194
6865
  "claude-haiku-4-5": {
6195
6866
  id: "claude-haiku-4-5",
6196
6867
  name: "Claude Haiku 4.5",
@@ -6633,6 +7304,57 @@ export const MODELS = {
6633
7304
  contextWindow: 1050000,
6634
7305
  maxTokens: 128000,
6635
7306
  },
7307
+ "gpt-5.5": {
7308
+ id: "gpt-5.5",
7309
+ name: "GPT-5.5",
7310
+ api: "openai-responses",
7311
+ provider: "opencode",
7312
+ baseUrl: "https://opencode.ai/zen/v1",
7313
+ reasoning: true,
7314
+ input: ["text", "image"],
7315
+ cost: {
7316
+ input: 5,
7317
+ output: 30,
7318
+ cacheRead: 0.5,
7319
+ cacheWrite: 0,
7320
+ },
7321
+ contextWindow: 1050000,
7322
+ maxTokens: 128000,
7323
+ },
7324
+ "gpt-5.5-pro": {
7325
+ id: "gpt-5.5-pro",
7326
+ name: "GPT-5.5 Pro",
7327
+ api: "openai-responses",
7328
+ provider: "opencode",
7329
+ baseUrl: "https://opencode.ai/zen/v1",
7330
+ reasoning: true,
7331
+ input: ["text", "image"],
7332
+ cost: {
7333
+ input: 30,
7334
+ output: 180,
7335
+ cacheRead: 30,
7336
+ cacheWrite: 0,
7337
+ },
7338
+ contextWindow: 1050000,
7339
+ maxTokens: 128000,
7340
+ },
7341
+ "hy3-preview-free": {
7342
+ id: "hy3-preview-free",
7343
+ name: "Hy3 preview Free",
7344
+ api: "openai-completions",
7345
+ provider: "opencode",
7346
+ baseUrl: "https://opencode.ai/zen/v1",
7347
+ reasoning: true,
7348
+ input: ["text"],
7349
+ cost: {
7350
+ input: 0,
7351
+ output: 0,
7352
+ cacheRead: 0,
7353
+ cacheWrite: 0,
7354
+ },
7355
+ contextWindow: 256000,
7356
+ maxTokens: 64000,
7357
+ },
6636
7358
  "kimi-k2.5": {
6637
7359
  id: "kimi-k2.5",
6638
7360
  name: "Kimi K2.5",
@@ -6650,6 +7372,40 @@ export const MODELS = {
6650
7372
  contextWindow: 262144,
6651
7373
  maxTokens: 65536,
6652
7374
  },
7375
+ "kimi-k2.6": {
7376
+ id: "kimi-k2.6",
7377
+ name: "Kimi K2.6",
7378
+ api: "openai-completions",
7379
+ provider: "opencode",
7380
+ baseUrl: "https://opencode.ai/zen/v1",
7381
+ reasoning: true,
7382
+ input: ["text", "image"],
7383
+ cost: {
7384
+ input: 0.95,
7385
+ output: 4,
7386
+ cacheRead: 0.16,
7387
+ cacheWrite: 0,
7388
+ },
7389
+ contextWindow: 262144,
7390
+ maxTokens: 65536,
7391
+ },
7392
+ "ling-2.6-flash-free": {
7393
+ id: "ling-2.6-flash-free",
7394
+ name: "Ling 2.6 Flash Free",
7395
+ api: "openai-completions",
7396
+ provider: "opencode",
7397
+ baseUrl: "https://opencode.ai/zen/v1",
7398
+ reasoning: false,
7399
+ input: ["text"],
7400
+ cost: {
7401
+ input: 0,
7402
+ output: 0,
7403
+ cacheRead: 0,
7404
+ cacheWrite: 0,
7405
+ },
7406
+ contextWindow: 262100,
7407
+ maxTokens: 32800,
7408
+ },
6653
7409
  "minimax-m2.5": {
6654
7410
  id: "minimax-m2.5",
6655
7411
  name: "MiniMax M2.5",
@@ -6684,6 +7440,23 @@ export const MODELS = {
6684
7440
  contextWindow: 204800,
6685
7441
  maxTokens: 131072,
6686
7442
  },
7443
+ "minimax-m2.7": {
7444
+ id: "minimax-m2.7",
7445
+ name: "MiniMax M2.7",
7446
+ api: "openai-completions",
7447
+ provider: "opencode",
7448
+ baseUrl: "https://opencode.ai/zen/v1",
7449
+ reasoning: true,
7450
+ input: ["text"],
7451
+ cost: {
7452
+ input: 0.3,
7453
+ output: 1.2,
7454
+ cacheRead: 0.06,
7455
+ cacheWrite: 0,
7456
+ },
7457
+ contextWindow: 204800,
7458
+ maxTokens: 131072,
7459
+ },
6687
7460
  "nemotron-3-super-free": {
6688
7461
  id: "nemotron-3-super-free",
6689
7462
  name: "Nemotron 3 Super Free",
@@ -6704,10 +7477,9 @@ export const MODELS = {
6704
7477
  "qwen3.5-plus": {
6705
7478
  id: "qwen3.5-plus",
6706
7479
  name: "Qwen3.5 Plus",
6707
- api: "openai-completions",
7480
+ api: "anthropic-messages",
6708
7481
  provider: "opencode",
6709
- baseUrl: "https://opencode.ai/zen/v1",
6710
- compat: { "cacheControlFormat": "anthropic" },
7482
+ baseUrl: "https://opencode.ai/zen",
6711
7483
  reasoning: true,
6712
7484
  input: ["text", "image"],
6713
7485
  cost: {
@@ -6722,10 +7494,9 @@ export const MODELS = {
6722
7494
  "qwen3.6-plus": {
6723
7495
  id: "qwen3.6-plus",
6724
7496
  name: "Qwen3.6 Plus",
6725
- api: "openai-completions",
7497
+ api: "anthropic-messages",
6726
7498
  provider: "opencode",
6727
- baseUrl: "https://opencode.ai/zen/v1",
6728
- compat: { "cacheControlFormat": "anthropic" },
7499
+ baseUrl: "https://opencode.ai/zen",
6729
7500
  reasoning: true,
6730
7501
  input: ["text", "image"],
6731
7502
  cost: {
@@ -6739,6 +7510,42 @@ export const MODELS = {
6739
7510
  },
6740
7511
  },
6741
7512
  "opencode-go": {
7513
+ "deepseek-v4-flash": {
7514
+ id: "deepseek-v4-flash",
7515
+ name: "DeepSeek V4 Flash",
7516
+ api: "openai-completions",
7517
+ provider: "opencode-go",
7518
+ baseUrl: "https://opencode.ai/zen/go/v1",
7519
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
7520
+ reasoning: true,
7521
+ input: ["text"],
7522
+ cost: {
7523
+ input: 0.14,
7524
+ output: 0.28,
7525
+ cacheRead: 0.0028,
7526
+ cacheWrite: 0,
7527
+ },
7528
+ contextWindow: 1000000,
7529
+ maxTokens: 384000,
7530
+ },
7531
+ "deepseek-v4-pro": {
7532
+ id: "deepseek-v4-pro",
7533
+ name: "DeepSeek V4 Pro",
7534
+ api: "openai-completions",
7535
+ provider: "opencode-go",
7536
+ baseUrl: "https://opencode.ai/zen/go/v1",
7537
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
7538
+ reasoning: true,
7539
+ input: ["text"],
7540
+ cost: {
7541
+ input: 1.74,
7542
+ output: 3.48,
7543
+ cacheRead: 0.0145,
7544
+ cacheWrite: 0,
7545
+ },
7546
+ contextWindow: 1000000,
7547
+ maxTokens: 384000,
7548
+ },
6742
7549
  "glm-5": {
6743
7550
  id: "glm-5",
6744
7551
  name: "GLM-5",
@@ -6753,8 +7560,8 @@ export const MODELS = {
6753
7560
  cacheRead: 0.2,
6754
7561
  cacheWrite: 0,
6755
7562
  },
6756
- contextWindow: 204800,
6757
- maxTokens: 131072,
7563
+ contextWindow: 202752,
7564
+ maxTokens: 32768,
6758
7565
  },
6759
7566
  "glm-5.1": {
6760
7567
  id: "glm-5.1",
@@ -6770,8 +7577,8 @@ export const MODELS = {
6770
7577
  cacheRead: 0.26,
6771
7578
  cacheWrite: 0,
6772
7579
  },
6773
- contextWindow: 204800,
6774
- maxTokens: 131072,
7580
+ contextWindow: 202752,
7581
+ maxTokens: 32768,
6775
7582
  },
6776
7583
  "kimi-k2.5": {
6777
7584
  id: "kimi-k2.5",
@@ -6790,9 +7597,60 @@ export const MODELS = {
6790
7597
  contextWindow: 262144,
6791
7598
  maxTokens: 65536,
6792
7599
  },
6793
- "mimo-v2-omni": {
6794
- id: "mimo-v2-omni",
6795
- name: "MiMo V2 Omni",
7600
+ "kimi-k2.6": {
7601
+ id: "kimi-k2.6",
7602
+ name: "Kimi K2.6 (3x limits)",
7603
+ api: "openai-completions",
7604
+ provider: "opencode-go",
7605
+ baseUrl: "https://opencode.ai/zen/go/v1",
7606
+ reasoning: true,
7607
+ input: ["text", "image"],
7608
+ cost: {
7609
+ input: 0.32,
7610
+ output: 1.34,
7611
+ cacheRead: 0.054,
7612
+ cacheWrite: 0,
7613
+ },
7614
+ contextWindow: 262144,
7615
+ maxTokens: 65536,
7616
+ },
7617
+ "mimo-v2-omni": {
7618
+ id: "mimo-v2-omni",
7619
+ name: "MiMo V2 Omni",
7620
+ api: "openai-completions",
7621
+ provider: "opencode-go",
7622
+ baseUrl: "https://opencode.ai/zen/go/v1",
7623
+ reasoning: true,
7624
+ input: ["text", "image"],
7625
+ cost: {
7626
+ input: 0.4,
7627
+ output: 2,
7628
+ cacheRead: 0.08,
7629
+ cacheWrite: 0,
7630
+ },
7631
+ contextWindow: 262144,
7632
+ maxTokens: 128000,
7633
+ },
7634
+ "mimo-v2-pro": {
7635
+ id: "mimo-v2-pro",
7636
+ name: "MiMo V2 Pro",
7637
+ api: "openai-completions",
7638
+ provider: "opencode-go",
7639
+ baseUrl: "https://opencode.ai/zen/go/v1",
7640
+ reasoning: true,
7641
+ input: ["text"],
7642
+ cost: {
7643
+ input: 1,
7644
+ output: 3,
7645
+ cacheRead: 0.2,
7646
+ cacheWrite: 0,
7647
+ },
7648
+ contextWindow: 1048576,
7649
+ maxTokens: 128000,
7650
+ },
7651
+ "mimo-v2.5": {
7652
+ id: "mimo-v2.5",
7653
+ name: "MiMo V2.5",
6796
7654
  api: "openai-completions",
6797
7655
  provider: "opencode-go",
6798
7656
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -6804,12 +7662,12 @@ export const MODELS = {
6804
7662
  cacheRead: 0.08,
6805
7663
  cacheWrite: 0,
6806
7664
  },
6807
- contextWindow: 262144,
6808
- maxTokens: 64000,
7665
+ contextWindow: 1000000,
7666
+ maxTokens: 128000,
6809
7667
  },
6810
- "mimo-v2-pro": {
6811
- id: "mimo-v2-pro",
6812
- name: "MiMo V2 Pro",
7668
+ "mimo-v2.5-pro": {
7669
+ id: "mimo-v2.5-pro",
7670
+ name: "MiMo V2.5 Pro",
6813
7671
  api: "openai-completions",
6814
7672
  provider: "opencode-go",
6815
7673
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -6822,7 +7680,7 @@ export const MODELS = {
6822
7680
  cacheWrite: 0,
6823
7681
  },
6824
7682
  contextWindow: 1048576,
6825
- maxTokens: 64000,
7683
+ maxTokens: 128000,
6826
7684
  },
6827
7685
  "minimax-m2.5": {
6828
7686
  id: "minimax-m2.5",
@@ -6861,10 +7719,9 @@ export const MODELS = {
6861
7719
  "qwen3.5-plus": {
6862
7720
  id: "qwen3.5-plus",
6863
7721
  name: "Qwen3.5 Plus",
6864
- api: "openai-completions",
7722
+ api: "anthropic-messages",
6865
7723
  provider: "opencode-go",
6866
- baseUrl: "https://opencode.ai/zen/go/v1",
6867
- compat: { "cacheControlFormat": "anthropic" },
7724
+ baseUrl: "https://opencode.ai/zen/go",
6868
7725
  reasoning: true,
6869
7726
  input: ["text", "image"],
6870
7727
  cost: {
@@ -6879,10 +7736,9 @@ export const MODELS = {
6879
7736
  "qwen3.6-plus": {
6880
7737
  id: "qwen3.6-plus",
6881
7738
  name: "Qwen3.6 Plus",
6882
- api: "openai-completions",
7739
+ api: "anthropic-messages",
6883
7740
  provider: "opencode-go",
6884
- baseUrl: "https://opencode.ai/zen/go/v1",
6885
- compat: { "cacheControlFormat": "anthropic" },
7741
+ baseUrl: "https://opencode.ai/zen/go",
6886
7742
  reasoning: true,
6887
7743
  input: ["text", "image"],
6888
7744
  cost: {
@@ -6945,7 +7801,7 @@ export const MODELS = {
6945
7801
  cacheWrite: 0,
6946
7802
  },
6947
7803
  contextWindow: 65536,
6948
- maxTokens: 4096,
7804
+ maxTokens: 16384,
6949
7805
  },
6950
7806
  "amazon/nova-2-lite-v1": {
6951
7807
  id: "amazon/nova-2-lite-v1",
@@ -7270,17 +8126,17 @@ export const MODELS = {
7270
8126
  contextWindow: 1000000,
7271
8127
  maxTokens: 128000,
7272
8128
  },
7273
- "arcee-ai/trinity-large-preview:free": {
7274
- id: "arcee-ai/trinity-large-preview:free",
7275
- name: "Arcee AI: Trinity Large Preview (free)",
8129
+ "arcee-ai/trinity-large-preview": {
8130
+ id: "arcee-ai/trinity-large-preview",
8131
+ name: "Arcee AI: Trinity Large Preview",
7276
8132
  api: "openai-completions",
7277
8133
  provider: "openrouter",
7278
8134
  baseUrl: "https://openrouter.ai/api/v1",
7279
8135
  reasoning: false,
7280
8136
  input: ["text"],
7281
8137
  cost: {
7282
- input: 0,
7283
- output: 0,
8138
+ input: 0.15,
8139
+ output: 0.44999999999999996,
7284
8140
  cacheRead: 0,
7285
8141
  cacheWrite: 0,
7286
8142
  },
@@ -7506,7 +8362,7 @@ export const MODELS = {
7506
8362
  cacheWrite: 0,
7507
8363
  },
7508
8364
  contextWindow: 163840,
7509
- maxTokens: 163840,
8365
+ maxTokens: 16384,
7510
8366
  },
7511
8367
  "deepseek/deepseek-chat-v3-0324": {
7512
8368
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7523,7 +8379,7 @@ export const MODELS = {
7523
8379
  cacheWrite: 0,
7524
8380
  },
7525
8381
  contextWindow: 163840,
7526
- maxTokens: 4096,
8382
+ maxTokens: 16384,
7527
8383
  },
7528
8384
  "deepseek/deepseek-chat-v3.1": {
7529
8385
  id: "deepseek/deepseek-chat-v3.1",
@@ -7574,7 +8430,7 @@ export const MODELS = {
7574
8430
  cacheWrite: 0,
7575
8431
  },
7576
8432
  contextWindow: 163840,
7577
- maxTokens: 4096,
8433
+ maxTokens: 32768,
7578
8434
  },
7579
8435
  "deepseek/deepseek-v3.1-terminus": {
7580
8436
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7587,11 +8443,11 @@ export const MODELS = {
7587
8443
  cost: {
7588
8444
  input: 0.21,
7589
8445
  output: 0.7899999999999999,
7590
- cacheRead: 0.1300000002,
8446
+ cacheRead: 0.13,
7591
8447
  cacheWrite: 0,
7592
8448
  },
7593
8449
  contextWindow: 163840,
7594
- maxTokens: 4096,
8450
+ maxTokens: 32768,
7595
8451
  },
7596
8452
  "deepseek/deepseek-v3.2": {
7597
8453
  id: "deepseek/deepseek-v3.2",
@@ -7602,13 +8458,13 @@ export const MODELS = {
7602
8458
  reasoning: true,
7603
8459
  input: ["text"],
7604
8460
  cost: {
7605
- input: 0.25899999999999995,
7606
- output: 0.42,
7607
- cacheRead: 0.135,
8461
+ input: 0.252,
8462
+ output: 0.378,
8463
+ cacheRead: 0.0252,
7608
8464
  cacheWrite: 0,
7609
8465
  },
7610
- contextWindow: 163840,
7611
- maxTokens: 163840,
8466
+ contextWindow: 131072,
8467
+ maxTokens: 65536,
7612
8468
  },
7613
8469
  "deepseek/deepseek-v3.2-exp": {
7614
8470
  id: "deepseek/deepseek-v3.2-exp",
@@ -7627,6 +8483,42 @@ export const MODELS = {
7627
8483
  contextWindow: 163840,
7628
8484
  maxTokens: 65536,
7629
8485
  },
8486
+ "deepseek/deepseek-v4-flash": {
8487
+ id: "deepseek/deepseek-v4-flash",
8488
+ name: "DeepSeek: DeepSeek V4 Flash",
8489
+ api: "openai-completions",
8490
+ provider: "openrouter",
8491
+ baseUrl: "https://openrouter.ai/api/v1",
8492
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
8493
+ reasoning: true,
8494
+ input: ["text"],
8495
+ cost: {
8496
+ input: 0.14,
8497
+ output: 0.28,
8498
+ cacheRead: 0.0028,
8499
+ cacheWrite: 0,
8500
+ },
8501
+ contextWindow: 1048576,
8502
+ maxTokens: 384000,
8503
+ },
8504
+ "deepseek/deepseek-v4-pro": {
8505
+ id: "deepseek/deepseek-v4-pro",
8506
+ name: "DeepSeek: DeepSeek V4 Pro",
8507
+ api: "openai-completions",
8508
+ provider: "openrouter",
8509
+ baseUrl: "https://openrouter.ai/api/v1",
8510
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
8511
+ reasoning: true,
8512
+ input: ["text"],
8513
+ cost: {
8514
+ input: 0.435,
8515
+ output: 0.87,
8516
+ cacheRead: 0.003625,
8517
+ cacheWrite: 0,
8518
+ },
8519
+ contextWindow: 1048576,
8520
+ maxTokens: 384000,
8521
+ },
7630
8522
  "essentialai/rnj-1-instruct": {
7631
8523
  id: "essentialai/rnj-1-instruct",
7632
8524
  name: "EssentialAI: Rnj 1 Instruct",
@@ -7848,6 +8740,40 @@ export const MODELS = {
7848
8740
  contextWindow: 1048576,
7849
8741
  maxTokens: 65536,
7850
8742
  },
8743
+ "google/gemma-3-12b-it": {
8744
+ id: "google/gemma-3-12b-it",
8745
+ name: "Google: Gemma 3 12B",
8746
+ api: "openai-completions",
8747
+ provider: "openrouter",
8748
+ baseUrl: "https://openrouter.ai/api/v1",
8749
+ reasoning: false,
8750
+ input: ["text", "image"],
8751
+ cost: {
8752
+ input: 0.04,
8753
+ output: 0.13,
8754
+ cacheRead: 0,
8755
+ cacheWrite: 0,
8756
+ },
8757
+ contextWindow: 131072,
8758
+ maxTokens: 16384,
8759
+ },
8760
+ "google/gemma-3-27b-it": {
8761
+ id: "google/gemma-3-27b-it",
8762
+ name: "Google: Gemma 3 27B",
8763
+ api: "openai-completions",
8764
+ provider: "openrouter",
8765
+ baseUrl: "https://openrouter.ai/api/v1",
8766
+ reasoning: false,
8767
+ input: ["text", "image"],
8768
+ cost: {
8769
+ input: 0.08,
8770
+ output: 0.16,
8771
+ cacheRead: 0,
8772
+ cacheWrite: 0,
8773
+ },
8774
+ contextWindow: 131072,
8775
+ maxTokens: 16384,
8776
+ },
7851
8777
  "google/gemma-4-26b-a4b-it": {
7852
8778
  id: "google/gemma-4-26b-a4b-it",
7853
8779
  name: "Google: Gemma 4 26B A4B ",
@@ -7857,9 +8783,9 @@ export const MODELS = {
7857
8783
  reasoning: true,
7858
8784
  input: ["text", "image"],
7859
8785
  cost: {
7860
- input: 0.08,
7861
- output: 0.35,
7862
- cacheRead: 0.01,
8786
+ input: 0.06,
8787
+ output: 0.33,
8788
+ cacheRead: 0,
7863
8789
  cacheWrite: 0,
7864
8790
  },
7865
8791
  contextWindow: 262144,
@@ -7893,11 +8819,11 @@ export const MODELS = {
7893
8819
  cost: {
7894
8820
  input: 0.13,
7895
8821
  output: 0.38,
7896
- cacheRead: 0.019999999499999997,
8822
+ cacheRead: 0,
7897
8823
  cacheWrite: 0,
7898
8824
  },
7899
8825
  contextWindow: 262144,
7900
- maxTokens: 4096,
8826
+ maxTokens: 16384,
7901
8827
  },
7902
8828
  "google/gemma-4-31b-it:free": {
7903
8829
  id: "google/gemma-4-31b-it:free",
@@ -7933,6 +8859,40 @@ export const MODELS = {
7933
8859
  contextWindow: 128000,
7934
8860
  maxTokens: 50000,
7935
8861
  },
8862
+ "inclusionai/ling-2.6-1t:free": {
8863
+ id: "inclusionai/ling-2.6-1t:free",
8864
+ name: "inclusionAI: Ling-2.6-1T (free)",
8865
+ api: "openai-completions",
8866
+ provider: "openrouter",
8867
+ baseUrl: "https://openrouter.ai/api/v1",
8868
+ reasoning: false,
8869
+ input: ["text"],
8870
+ cost: {
8871
+ input: 0,
8872
+ output: 0,
8873
+ cacheRead: 0,
8874
+ cacheWrite: 0,
8875
+ },
8876
+ contextWindow: 262144,
8877
+ maxTokens: 32768,
8878
+ },
8879
+ "inclusionai/ling-2.6-flash:free": {
8880
+ id: "inclusionai/ling-2.6-flash:free",
8881
+ name: "inclusionAI: Ling-2.6-flash (free)",
8882
+ api: "openai-completions",
8883
+ provider: "openrouter",
8884
+ baseUrl: "https://openrouter.ai/api/v1",
8885
+ reasoning: false,
8886
+ input: ["text"],
8887
+ cost: {
8888
+ input: 0,
8889
+ output: 0,
8890
+ cacheRead: 0,
8891
+ cacheWrite: 0,
8892
+ },
8893
+ contextWindow: 262144,
8894
+ maxTokens: 32768,
8895
+ },
7936
8896
  "kwaipilot/kat-coder-pro-v2": {
7937
8897
  id: "kwaipilot/kat-coder-pro-v2",
7938
8898
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -7982,7 +8942,7 @@ export const MODELS = {
7982
8942
  cacheWrite: 0,
7983
8943
  },
7984
8944
  contextWindow: 131072,
7985
- maxTokens: 4096,
8945
+ maxTokens: 16384,
7986
8946
  },
7987
8947
  "meta-llama/llama-3.1-8b-instruct": {
7988
8948
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8010,13 +8970,13 @@ export const MODELS = {
8010
8970
  reasoning: false,
8011
8971
  input: ["text"],
8012
8972
  cost: {
8013
- input: 0.12,
8014
- output: 0.38,
8973
+ input: 0.09999999999999999,
8974
+ output: 0.32,
8015
8975
  cacheRead: 0,
8016
8976
  cacheWrite: 0,
8017
8977
  },
8018
8978
  contextWindow: 131072,
8019
- maxTokens: 131072,
8979
+ maxTokens: 16384,
8020
8980
  },
8021
8981
  "meta-llama/llama-3.3-70b-instruct:free": {
8022
8982
  id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -8112,13 +9072,13 @@ export const MODELS = {
8112
9072
  reasoning: true,
8113
9073
  input: ["text"],
8114
9074
  cost: {
8115
- input: 0.118,
8116
- output: 0.9900000000000001,
8117
- cacheRead: 0.059,
9075
+ input: 0.15,
9076
+ output: 1.15,
9077
+ cacheRead: 0.03,
8118
9078
  cacheWrite: 0,
8119
9079
  },
8120
9080
  contextWindow: 196608,
8121
- maxTokens: 65536,
9081
+ maxTokens: 131072,
8122
9082
  },
8123
9083
  "minimax/minimax-m2.5:free": {
8124
9084
  id: "minimax/minimax-m2.5:free",
@@ -8441,7 +9401,7 @@ export const MODELS = {
8441
9401
  cacheWrite: 0,
8442
9402
  },
8443
9403
  contextWindow: 128000,
8444
- maxTokens: 4096,
9404
+ maxTokens: 16384,
8445
9405
  },
8446
9406
  "mistralai/mistral-small-creative": {
8447
9407
  id: "mistralai/mistral-small-creative",
@@ -8596,6 +9556,23 @@ export const MODELS = {
8596
9556
  contextWindow: 262144,
8597
9557
  maxTokens: 4096,
8598
9558
  },
9559
+ "moonshotai/kimi-k2.6": {
9560
+ id: "moonshotai/kimi-k2.6",
9561
+ name: "MoonshotAI: Kimi K2.6",
9562
+ api: "openai-completions",
9563
+ provider: "openrouter",
9564
+ baseUrl: "https://openrouter.ai/api/v1",
9565
+ reasoning: true,
9566
+ input: ["text", "image"],
9567
+ cost: {
9568
+ input: 0.7448,
9569
+ output: 4.655,
9570
+ cacheRead: 0.1463,
9571
+ cacheWrite: 0,
9572
+ },
9573
+ contextWindow: 256000,
9574
+ maxTokens: 65536,
9575
+ },
8599
9576
  "nex-agi/deepseek-v3.1-nex-n1": {
8600
9577
  id: "nex-agi/deepseek-v3.1-nex-n1",
8601
9578
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -8645,7 +9622,7 @@ export const MODELS = {
8645
9622
  cacheWrite: 0,
8646
9623
  },
8647
9624
  contextWindow: 131072,
8648
- maxTokens: 4096,
9625
+ maxTokens: 16384,
8649
9626
  },
8650
9627
  "nvidia/nemotron-3-nano-30b-a3b": {
8651
9628
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8662,7 +9639,7 @@ export const MODELS = {
8662
9639
  cacheWrite: 0,
8663
9640
  },
8664
9641
  contextWindow: 262144,
8665
- maxTokens: 4096,
9642
+ maxTokens: 228000,
8666
9643
  },
8667
9644
  "nvidia/nemotron-3-nano-30b-a3b:free": {
8668
9645
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8681,6 +9658,23 @@ export const MODELS = {
8681
9658
  contextWindow: 256000,
8682
9659
  maxTokens: 4096,
8683
9660
  },
9661
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
9662
+ id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
9663
+ name: "NVIDIA: Nemotron 3 Nano Omni (free)",
9664
+ api: "openai-completions",
9665
+ provider: "openrouter",
9666
+ baseUrl: "https://openrouter.ai/api/v1",
9667
+ reasoning: true,
9668
+ input: ["text", "image"],
9669
+ cost: {
9670
+ input: 0,
9671
+ output: 0,
9672
+ cacheRead: 0,
9673
+ cacheWrite: 0,
9674
+ },
9675
+ contextWindow: 256000,
9676
+ maxTokens: 65536,
9677
+ },
8684
9678
  "nvidia/nemotron-3-super-120b-a12b": {
8685
9679
  id: "nvidia/nemotron-3-super-120b-a12b",
8686
9680
  name: "NVIDIA: Nemotron 3 Super",
@@ -8747,7 +9741,7 @@ export const MODELS = {
8747
9741
  cacheWrite: 0,
8748
9742
  },
8749
9743
  contextWindow: 131072,
8750
- maxTokens: 4096,
9744
+ maxTokens: 16384,
8751
9745
  },
8752
9746
  "nvidia/nemotron-nano-9b-v2:free": {
8753
9747
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9106,40 +10100,6 @@ export const MODELS = {
9106
10100
  contextWindow: 400000,
9107
10101
  maxTokens: 128000,
9108
10102
  },
9109
- "openai/gpt-5-image": {
9110
- id: "openai/gpt-5-image",
9111
- name: "OpenAI: GPT-5 Image",
9112
- api: "openai-completions",
9113
- provider: "openrouter",
9114
- baseUrl: "https://openrouter.ai/api/v1",
9115
- reasoning: true,
9116
- input: ["text", "image"],
9117
- cost: {
9118
- input: 10,
9119
- output: 10,
9120
- cacheRead: 1.25,
9121
- cacheWrite: 0,
9122
- },
9123
- contextWindow: 400000,
9124
- maxTokens: 128000,
9125
- },
9126
- "openai/gpt-5-image-mini": {
9127
- id: "openai/gpt-5-image-mini",
9128
- name: "OpenAI: GPT-5 Image Mini",
9129
- api: "openai-completions",
9130
- provider: "openrouter",
9131
- baseUrl: "https://openrouter.ai/api/v1",
9132
- reasoning: true,
9133
- input: ["text", "image"],
9134
- cost: {
9135
- input: 2.5,
9136
- output: 2,
9137
- cacheRead: 0.25,
9138
- cacheWrite: 0,
9139
- },
9140
- contextWindow: 400000,
9141
- maxTokens: 128000,
9142
- },
9143
10103
  "openai/gpt-5-mini": {
9144
10104
  id: "openai/gpt-5-mini",
9145
10105
  name: "OpenAI: GPT-5 Mini",
@@ -9446,6 +10406,40 @@ export const MODELS = {
9446
10406
  contextWindow: 1050000,
9447
10407
  maxTokens: 128000,
9448
10408
  },
10409
+ "openai/gpt-5.5": {
10410
+ id: "openai/gpt-5.5",
10411
+ name: "OpenAI: GPT-5.5",
10412
+ api: "openai-completions",
10413
+ provider: "openrouter",
10414
+ baseUrl: "https://openrouter.ai/api/v1",
10415
+ reasoning: true,
10416
+ input: ["text", "image"],
10417
+ cost: {
10418
+ input: 5,
10419
+ output: 30,
10420
+ cacheRead: 0.5,
10421
+ cacheWrite: 0,
10422
+ },
10423
+ contextWindow: 1050000,
10424
+ maxTokens: 128000,
10425
+ },
10426
+ "openai/gpt-5.5-pro": {
10427
+ id: "openai/gpt-5.5-pro",
10428
+ name: "OpenAI: GPT-5.5 Pro",
10429
+ api: "openai-completions",
10430
+ provider: "openrouter",
10431
+ baseUrl: "https://openrouter.ai/api/v1",
10432
+ reasoning: true,
10433
+ input: ["text", "image"],
10434
+ cost: {
10435
+ input: 30,
10436
+ output: 180,
10437
+ cacheRead: 0,
10438
+ cacheWrite: 0,
10439
+ },
10440
+ contextWindow: 1050000,
10441
+ maxTokens: 128000,
10442
+ },
9449
10443
  "openai/gpt-audio": {
9450
10444
  id: "openai/gpt-audio",
9451
10445
  name: "OpenAI: GPT Audio",
@@ -9495,7 +10489,7 @@ export const MODELS = {
9495
10489
  cacheWrite: 0,
9496
10490
  },
9497
10491
  contextWindow: 131072,
9498
- maxTokens: 4096,
10492
+ maxTokens: 131072,
9499
10493
  },
9500
10494
  "openai/gpt-oss-120b:free": {
9501
10495
  id: "openai/gpt-oss-120b:free",
@@ -9529,7 +10523,7 @@ export const MODELS = {
9529
10523
  cacheWrite: 0,
9530
10524
  },
9531
10525
  contextWindow: 131072,
9532
- maxTokens: 4096,
10526
+ maxTokens: 131072,
9533
10527
  },
9534
10528
  "openai/gpt-oss-20b:free": {
9535
10529
  id: "openai/gpt-oss-20b:free",
@@ -9735,39 +10729,56 @@ export const MODELS = {
9735
10729
  contextWindow: 2000000,
9736
10730
  maxTokens: 4096,
9737
10731
  },
9738
- "openrouter/elephant-alpha": {
9739
- id: "openrouter/elephant-alpha",
9740
- name: "Elephant",
10732
+ "openrouter/free": {
10733
+ id: "openrouter/free",
10734
+ name: "Free Models Router",
9741
10735
  api: "openai-completions",
9742
10736
  provider: "openrouter",
9743
10737
  baseUrl: "https://openrouter.ai/api/v1",
9744
- reasoning: false,
9745
- input: ["text"],
10738
+ reasoning: true,
10739
+ input: ["text", "image"],
9746
10740
  cost: {
9747
10741
  input: 0,
9748
10742
  output: 0,
9749
10743
  cacheRead: 0,
9750
10744
  cacheWrite: 0,
9751
10745
  },
9752
- contextWindow: 262144,
9753
- maxTokens: 32768,
10746
+ contextWindow: 200000,
10747
+ maxTokens: 4096,
10748
+ },
10749
+ "poolside/laguna-m.1:free": {
10750
+ id: "poolside/laguna-m.1:free",
10751
+ name: "Poolside: Laguna M.1 (free)",
10752
+ api: "openai-completions",
10753
+ provider: "openrouter",
10754
+ baseUrl: "https://openrouter.ai/api/v1",
10755
+ reasoning: true,
10756
+ input: ["text"],
10757
+ cost: {
10758
+ input: 0,
10759
+ output: 0,
10760
+ cacheRead: 0,
10761
+ cacheWrite: 0,
10762
+ },
10763
+ contextWindow: 131072,
10764
+ maxTokens: 8192,
9754
10765
  },
9755
- "openrouter/free": {
9756
- id: "openrouter/free",
9757
- name: "Free Models Router",
10766
+ "poolside/laguna-xs.2:free": {
10767
+ id: "poolside/laguna-xs.2:free",
10768
+ name: "Poolside: Laguna XS.2 (free)",
9758
10769
  api: "openai-completions",
9759
10770
  provider: "openrouter",
9760
10771
  baseUrl: "https://openrouter.ai/api/v1",
9761
10772
  reasoning: true,
9762
- input: ["text", "image"],
10773
+ input: ["text"],
9763
10774
  cost: {
9764
10775
  input: 0,
9765
10776
  output: 0,
9766
10777
  cacheRead: 0,
9767
10778
  cacheWrite: 0,
9768
10779
  },
9769
- contextWindow: 200000,
9770
- maxTokens: 4096,
10780
+ contextWindow: 131072,
10781
+ maxTokens: 8192,
9771
10782
  },
9772
10783
  "prime-intellect/intellect-3": {
9773
10784
  id: "prime-intellect/intellect-3",
@@ -9795,8 +10806,8 @@ export const MODELS = {
9795
10806
  reasoning: false,
9796
10807
  input: ["text"],
9797
10808
  cost: {
9798
- input: 0.12,
9799
- output: 0.39,
10809
+ input: 0.36,
10810
+ output: 0.39999999999999997,
9800
10811
  cacheRead: 0,
9801
10812
  cacheWrite: 0,
9802
10813
  },
@@ -9971,7 +10982,7 @@ export const MODELS = {
9971
10982
  cacheWrite: 0,
9972
10983
  },
9973
10984
  contextWindow: 262144,
9974
- maxTokens: 4096,
10985
+ maxTokens: 16384,
9975
10986
  },
9976
10987
  "qwen/qwen3-235b-a22b-thinking-2507": {
9977
10988
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -9982,13 +10993,13 @@ export const MODELS = {
9982
10993
  reasoning: true,
9983
10994
  input: ["text"],
9984
10995
  cost: {
9985
- input: 0.13,
9986
- output: 0.6,
10996
+ input: 0.14950000000000002,
10997
+ output: 1.495,
9987
10998
  cacheRead: 0,
9988
10999
  cacheWrite: 0,
9989
11000
  },
9990
- contextWindow: 262144,
9991
- maxTokens: 262144,
11001
+ contextWindow: 131072,
11002
+ maxTokens: 4096,
9992
11003
  },
9993
11004
  "qwen/qwen3-30b-a3b": {
9994
11005
  id: "qwen/qwen3-30b-a3b",
@@ -10005,7 +11016,7 @@ export const MODELS = {
10005
11016
  cacheWrite: 0,
10006
11017
  },
10007
11018
  contextWindow: 40960,
10008
- maxTokens: 40960,
11019
+ maxTokens: 16384,
10009
11020
  },
10010
11021
  "qwen/qwen3-30b-a3b-instruct-2507": {
10011
11022
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10085,12 +11096,12 @@ export const MODELS = {
10085
11096
  input: ["text"],
10086
11097
  cost: {
10087
11098
  input: 0.22,
10088
- output: 1,
10089
- cacheRead: 0.022,
11099
+ output: 1.7999999999999998,
11100
+ cacheRead: 0,
10090
11101
  cacheWrite: 0,
10091
11102
  },
10092
11103
  contextWindow: 262144,
10093
- maxTokens: 4096,
11104
+ maxTokens: 65536,
10094
11105
  },
10095
11106
  "qwen/qwen3-coder-30b-a3b-instruct": {
10096
11107
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10135,9 +11146,9 @@ export const MODELS = {
10135
11146
  reasoning: false,
10136
11147
  input: ["text"],
10137
11148
  cost: {
10138
- input: 0.15,
11149
+ input: 0.14,
10139
11150
  output: 0.7999999999999999,
10140
- cacheRead: 0.12,
11151
+ cacheRead: 0.09,
10141
11152
  cacheWrite: 0,
10142
11153
  },
10143
11154
  contextWindow: 262144,
@@ -10226,7 +11237,7 @@ export const MODELS = {
10226
11237
  cacheWrite: 0,
10227
11238
  },
10228
11239
  contextWindow: 262144,
10229
- maxTokens: 4096,
11240
+ maxTokens: 16384,
10230
11241
  },
10231
11242
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10232
11243
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10277,7 +11288,7 @@ export const MODELS = {
10277
11288
  cacheWrite: 0,
10278
11289
  },
10279
11290
  contextWindow: 262144,
10280
- maxTokens: 4096,
11291
+ maxTokens: 16384,
10281
11292
  },
10282
11293
  "qwen/qwen3-vl-235b-a22b-thinking": {
10283
11294
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10500,6 +11511,74 @@ export const MODELS = {
10500
11511
  contextWindow: 1000000,
10501
11512
  maxTokens: 65536,
10502
11513
  },
11514
+ "qwen/qwen3.5-plus-20260420": {
11515
+ id: "qwen/qwen3.5-plus-20260420",
11516
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
11517
+ api: "openai-completions",
11518
+ provider: "openrouter",
11519
+ baseUrl: "https://openrouter.ai/api/v1",
11520
+ reasoning: true,
11521
+ input: ["text", "image"],
11522
+ cost: {
11523
+ input: 0.39999999999999997,
11524
+ output: 2.4,
11525
+ cacheRead: 0,
11526
+ cacheWrite: 0,
11527
+ },
11528
+ contextWindow: 1000000,
11529
+ maxTokens: 65536,
11530
+ },
11531
+ "qwen/qwen3.6-27b": {
11532
+ id: "qwen/qwen3.6-27b",
11533
+ name: "Qwen: Qwen3.6 27B",
11534
+ api: "openai-completions",
11535
+ provider: "openrouter",
11536
+ baseUrl: "https://openrouter.ai/api/v1",
11537
+ reasoning: true,
11538
+ input: ["text", "image"],
11539
+ cost: {
11540
+ input: 0.325,
11541
+ output: 3.25,
11542
+ cacheRead: 0,
11543
+ cacheWrite: 0,
11544
+ },
11545
+ contextWindow: 256000,
11546
+ maxTokens: 65536,
11547
+ },
11548
+ "qwen/qwen3.6-flash": {
11549
+ id: "qwen/qwen3.6-flash",
11550
+ name: "Qwen: Qwen3.6 Flash",
11551
+ api: "openai-completions",
11552
+ provider: "openrouter",
11553
+ baseUrl: "https://openrouter.ai/api/v1",
11554
+ reasoning: true,
11555
+ input: ["text", "image"],
11556
+ cost: {
11557
+ input: 0.25,
11558
+ output: 1.5,
11559
+ cacheRead: 0,
11560
+ cacheWrite: 0.3125,
11561
+ },
11562
+ contextWindow: 1000000,
11563
+ maxTokens: 65536,
11564
+ },
11565
+ "qwen/qwen3.6-max-preview": {
11566
+ id: "qwen/qwen3.6-max-preview",
11567
+ name: "Qwen: Qwen3.6 Max Preview",
11568
+ api: "openai-completions",
11569
+ provider: "openrouter",
11570
+ baseUrl: "https://openrouter.ai/api/v1",
11571
+ reasoning: true,
11572
+ input: ["text"],
11573
+ cost: {
11574
+ input: 1.04,
11575
+ output: 6.24,
11576
+ cacheRead: 0,
11577
+ cacheWrite: 1.3,
11578
+ },
11579
+ contextWindow: 262144,
11580
+ maxTokens: 65536,
11581
+ },
10503
11582
  "qwen/qwen3.6-plus": {
10504
11583
  id: "qwen/qwen3.6-plus",
10505
11584
  name: "Qwen: Qwen3.6 Plus",
@@ -10619,6 +11698,23 @@ export const MODELS = {
10619
11698
  contextWindow: 262144,
10620
11699
  maxTokens: 65536,
10621
11700
  },
11701
+ "tencent/hy3-preview:free": {
11702
+ id: "tencent/hy3-preview:free",
11703
+ name: "Tencent: Hy3 preview (free)",
11704
+ api: "openai-completions",
11705
+ provider: "openrouter",
11706
+ baseUrl: "https://openrouter.ai/api/v1",
11707
+ reasoning: true,
11708
+ input: ["text"],
11709
+ cost: {
11710
+ input: 0,
11711
+ output: 0,
11712
+ cacheRead: 0,
11713
+ cacheWrite: 0,
11714
+ },
11715
+ contextWindow: 262144,
11716
+ maxTokens: 262144,
11717
+ },
10622
11718
  "thedrummer/rocinante-12b": {
10623
11719
  id: "thedrummer/rocinante-12b",
10624
11720
  name: "TheDrummer: Rocinante 12B",
@@ -10891,6 +11987,40 @@ export const MODELS = {
10891
11987
  contextWindow: 1048576,
10892
11988
  maxTokens: 131072,
10893
11989
  },
11990
+ "xiaomi/mimo-v2.5": {
11991
+ id: "xiaomi/mimo-v2.5",
11992
+ name: "Xiaomi: MiMo-V2.5",
11993
+ api: "openai-completions",
11994
+ provider: "openrouter",
11995
+ baseUrl: "https://openrouter.ai/api/v1",
11996
+ reasoning: true,
11997
+ input: ["text", "image"],
11998
+ cost: {
11999
+ input: 0.39999999999999997,
12000
+ output: 2,
12001
+ cacheRead: 0.08,
12002
+ cacheWrite: 0,
12003
+ },
12004
+ contextWindow: 1048576,
12005
+ maxTokens: 131072,
12006
+ },
12007
+ "xiaomi/mimo-v2.5-pro": {
12008
+ id: "xiaomi/mimo-v2.5-pro",
12009
+ name: "Xiaomi: MiMo-V2.5-Pro",
12010
+ api: "openai-completions",
12011
+ provider: "openrouter",
12012
+ baseUrl: "https://openrouter.ai/api/v1",
12013
+ reasoning: true,
12014
+ input: ["text"],
12015
+ cost: {
12016
+ input: 1,
12017
+ output: 3,
12018
+ cacheRead: 0.19999999999999998,
12019
+ cacheWrite: 0,
12020
+ },
12021
+ contextWindow: 1048576,
12022
+ maxTokens: 131072,
12023
+ },
10894
12024
  "z-ai/glm-4-32b": {
10895
12025
  id: "z-ai/glm-4-32b",
10896
12026
  name: "Z.ai: GLM 4 32B ",
@@ -11004,11 +12134,11 @@ export const MODELS = {
11004
12134
  cost: {
11005
12135
  input: 0.3,
11006
12136
  output: 0.8999999999999999,
11007
- cacheRead: 0,
12137
+ cacheRead: 0.049999999999999996,
11008
12138
  cacheWrite: 0,
11009
12139
  },
11010
12140
  contextWindow: 131072,
11011
- maxTokens: 131072,
12141
+ maxTokens: 24000,
11012
12142
  },
11013
12143
  "z-ai/glm-4.7": {
11014
12144
  id: "z-ai/glm-4.7",
@@ -11019,13 +12149,13 @@ export const MODELS = {
11019
12149
  reasoning: true,
11020
12150
  input: ["text"],
11021
12151
  cost: {
11022
- input: 0.39,
11023
- output: 1.75,
11024
- cacheRead: 0.195,
12152
+ input: 0.38,
12153
+ output: 1.74,
12154
+ cacheRead: 0,
11025
12155
  cacheWrite: 0,
11026
12156
  },
11027
12157
  contextWindow: 202752,
11028
- maxTokens: 65535,
12158
+ maxTokens: 4096,
11029
12159
  },
11030
12160
  "z-ai/glm-4.7-flash": {
11031
12161
  id: "z-ai/glm-4.7-flash",
@@ -11038,11 +12168,11 @@ export const MODELS = {
11038
12168
  cost: {
11039
12169
  input: 0.06,
11040
12170
  output: 0.39999999999999997,
11041
- cacheRead: 0.0100000002,
12171
+ cacheRead: 0.01,
11042
12172
  cacheWrite: 0,
11043
12173
  },
11044
12174
  contextWindow: 202752,
11045
- maxTokens: 4096,
12175
+ maxTokens: 16384,
11046
12176
  },
11047
12177
  "z-ai/glm-5": {
11048
12178
  id: "z-ai/glm-5",
@@ -11058,8 +12188,8 @@ export const MODELS = {
11058
12188
  cacheRead: 0.119,
11059
12189
  cacheWrite: 0,
11060
12190
  },
11061
- contextWindow: 80000,
11062
- maxTokens: 131072,
12191
+ contextWindow: 202752,
12192
+ maxTokens: 16384,
11063
12193
  },
11064
12194
  "z-ai/glm-5-turbo": {
11065
12195
  id: "z-ai/glm-5-turbo",
@@ -11078,39 +12208,175 @@ export const MODELS = {
11078
12208
  contextWindow: 202752,
11079
12209
  maxTokens: 131072,
11080
12210
  },
11081
- "z-ai/glm-5.1": {
11082
- id: "z-ai/glm-5.1",
11083
- name: "Z.ai: GLM 5.1",
12211
+ "z-ai/glm-5.1": {
12212
+ id: "z-ai/glm-5.1",
12213
+ name: "Z.ai: GLM 5.1",
12214
+ api: "openai-completions",
12215
+ provider: "openrouter",
12216
+ baseUrl: "https://openrouter.ai/api/v1",
12217
+ reasoning: true,
12218
+ input: ["text"],
12219
+ cost: {
12220
+ input: 1.0499999999999998,
12221
+ output: 3.5,
12222
+ cacheRead: 0.5249999999999999,
12223
+ cacheWrite: 0,
12224
+ },
12225
+ contextWindow: 202752,
12226
+ maxTokens: 65535,
12227
+ },
12228
+ "z-ai/glm-5v-turbo": {
12229
+ id: "z-ai/glm-5v-turbo",
12230
+ name: "Z.ai: GLM 5V Turbo",
12231
+ api: "openai-completions",
12232
+ provider: "openrouter",
12233
+ baseUrl: "https://openrouter.ai/api/v1",
12234
+ reasoning: true,
12235
+ input: ["text", "image"],
12236
+ cost: {
12237
+ input: 1.2,
12238
+ output: 4,
12239
+ cacheRead: 0.24,
12240
+ cacheWrite: 0,
12241
+ },
12242
+ contextWindow: 202752,
12243
+ maxTokens: 131072,
12244
+ },
12245
+ "~anthropic/claude-haiku-latest": {
12246
+ id: "~anthropic/claude-haiku-latest",
12247
+ name: "Anthropic Claude Haiku Latest",
12248
+ api: "openai-completions",
12249
+ provider: "openrouter",
12250
+ baseUrl: "https://openrouter.ai/api/v1",
12251
+ reasoning: true,
12252
+ input: ["text", "image"],
12253
+ cost: {
12254
+ input: 1,
12255
+ output: 5,
12256
+ cacheRead: 0.09999999999999999,
12257
+ cacheWrite: 1.25,
12258
+ },
12259
+ contextWindow: 200000,
12260
+ maxTokens: 64000,
12261
+ },
12262
+ "~anthropic/claude-opus-latest": {
12263
+ id: "~anthropic/claude-opus-latest",
12264
+ name: "Anthropic: Claude Opus Latest",
12265
+ api: "openai-completions",
12266
+ provider: "openrouter",
12267
+ baseUrl: "https://openrouter.ai/api/v1",
12268
+ reasoning: true,
12269
+ input: ["text", "image"],
12270
+ cost: {
12271
+ input: 5,
12272
+ output: 25,
12273
+ cacheRead: 0.5,
12274
+ cacheWrite: 6.25,
12275
+ },
12276
+ contextWindow: 1000000,
12277
+ maxTokens: 128000,
12278
+ },
12279
+ "~anthropic/claude-sonnet-latest": {
12280
+ id: "~anthropic/claude-sonnet-latest",
12281
+ name: "Anthropic Claude Sonnet Latest",
12282
+ api: "openai-completions",
12283
+ provider: "openrouter",
12284
+ baseUrl: "https://openrouter.ai/api/v1",
12285
+ reasoning: true,
12286
+ input: ["text", "image"],
12287
+ cost: {
12288
+ input: 3,
12289
+ output: 15,
12290
+ cacheRead: 0.3,
12291
+ cacheWrite: 3.75,
12292
+ },
12293
+ contextWindow: 1000000,
12294
+ maxTokens: 128000,
12295
+ },
12296
+ "~google/gemini-flash-latest": {
12297
+ id: "~google/gemini-flash-latest",
12298
+ name: "Google Gemini Flash Latest",
12299
+ api: "openai-completions",
12300
+ provider: "openrouter",
12301
+ baseUrl: "https://openrouter.ai/api/v1",
12302
+ reasoning: true,
12303
+ input: ["text", "image"],
12304
+ cost: {
12305
+ input: 0.5,
12306
+ output: 3,
12307
+ cacheRead: 0.049999999999999996,
12308
+ cacheWrite: 0.08333333333333334,
12309
+ },
12310
+ contextWindow: 1048576,
12311
+ maxTokens: 65536,
12312
+ },
12313
+ "~google/gemini-pro-latest": {
12314
+ id: "~google/gemini-pro-latest",
12315
+ name: "Google Gemini Pro Latest",
12316
+ api: "openai-completions",
12317
+ provider: "openrouter",
12318
+ baseUrl: "https://openrouter.ai/api/v1",
12319
+ reasoning: true,
12320
+ input: ["text", "image"],
12321
+ cost: {
12322
+ input: 2,
12323
+ output: 12,
12324
+ cacheRead: 0.19999999999999998,
12325
+ cacheWrite: 0.375,
12326
+ },
12327
+ contextWindow: 1048576,
12328
+ maxTokens: 65536,
12329
+ },
12330
+ "~moonshotai/kimi-latest": {
12331
+ id: "~moonshotai/kimi-latest",
12332
+ name: "MoonshotAI Kimi Latest",
12333
+ api: "openai-completions",
12334
+ provider: "openrouter",
12335
+ baseUrl: "https://openrouter.ai/api/v1",
12336
+ reasoning: true,
12337
+ input: ["text", "image"],
12338
+ cost: {
12339
+ input: 0.7448,
12340
+ output: 4.655,
12341
+ cacheRead: 0.1463,
12342
+ cacheWrite: 0,
12343
+ },
12344
+ contextWindow: 256000,
12345
+ maxTokens: 65536,
12346
+ },
12347
+ "~openai/gpt-latest": {
12348
+ id: "~openai/gpt-latest",
12349
+ name: "OpenAI GPT Latest",
11084
12350
  api: "openai-completions",
11085
12351
  provider: "openrouter",
11086
12352
  baseUrl: "https://openrouter.ai/api/v1",
11087
12353
  reasoning: true,
11088
- input: ["text"],
12354
+ input: ["text", "image"],
11089
12355
  cost: {
11090
- input: 0.95,
11091
- output: 3.15,
11092
- cacheRead: 0.475,
12356
+ input: 5,
12357
+ output: 30,
12358
+ cacheRead: 0.5,
11093
12359
  cacheWrite: 0,
11094
12360
  },
11095
- contextWindow: 202752,
11096
- maxTokens: 65535,
12361
+ contextWindow: 1050000,
12362
+ maxTokens: 128000,
11097
12363
  },
11098
- "z-ai/glm-5v-turbo": {
11099
- id: "z-ai/glm-5v-turbo",
11100
- name: "Z.ai: GLM 5V Turbo",
12364
+ "~openai/gpt-mini-latest": {
12365
+ id: "~openai/gpt-mini-latest",
12366
+ name: "OpenAI GPT Mini Latest",
11101
12367
  api: "openai-completions",
11102
12368
  provider: "openrouter",
11103
12369
  baseUrl: "https://openrouter.ai/api/v1",
11104
12370
  reasoning: true,
11105
12371
  input: ["text", "image"],
11106
12372
  cost: {
11107
- input: 1.2,
11108
- output: 4,
11109
- cacheRead: 0.24,
12373
+ input: 0.75,
12374
+ output: 4.5,
12375
+ cacheRead: 0.075,
11110
12376
  cacheWrite: 0,
11111
12377
  },
11112
- contextWindow: 202752,
11113
- maxTokens: 131072,
12378
+ contextWindow: 400000,
12379
+ maxTokens: 128000,
11114
12380
  },
11115
12381
  },
11116
12382
  "vercel-ai-gateway": {
@@ -11182,6 +12448,23 @@ export const MODELS = {
11182
12448
  contextWindow: 128000,
11183
12449
  maxTokens: 8192,
11184
12450
  },
12451
+ "alibaba/qwen-3.6-max-preview": {
12452
+ id: "alibaba/qwen-3.6-max-preview",
12453
+ name: "Qwen 3.6 Max Preview",
12454
+ api: "anthropic-messages",
12455
+ provider: "vercel-ai-gateway",
12456
+ baseUrl: "https://ai-gateway.vercel.sh",
12457
+ reasoning: true,
12458
+ input: ["text", "image"],
12459
+ cost: {
12460
+ input: 1.3,
12461
+ output: 7.8,
12462
+ cacheRead: 0.26,
12463
+ cacheWrite: 1.625,
12464
+ },
12465
+ contextWindow: 240000,
12466
+ maxTokens: 64000,
12467
+ },
11185
12468
  "alibaba/qwen3-235b-a22b-thinking": {
11186
12469
  id: "alibaba/qwen3-235b-a22b-thinking",
11187
12470
  name: "Qwen3 235B A22B Thinking 2507",
@@ -11381,7 +12664,7 @@ export const MODELS = {
11381
12664
  input: 0.5,
11382
12665
  output: 3,
11383
12666
  cacheRead: 0.09999999999999999,
11384
- cacheWrite: 0,
12667
+ cacheWrite: 0.625,
11385
12668
  },
11386
12669
  contextWindow: 1000000,
11387
12670
  maxTokens: 64000,
@@ -11760,6 +13043,40 @@ export const MODELS = {
11760
13043
  contextWindow: 128000,
11761
13044
  maxTokens: 64000,
11762
13045
  },
13046
+ "deepseek/deepseek-v4-flash": {
13047
+ id: "deepseek/deepseek-v4-flash",
13048
+ name: "DeepSeek V4 Flash",
13049
+ api: "anthropic-messages",
13050
+ provider: "vercel-ai-gateway",
13051
+ baseUrl: "https://ai-gateway.vercel.sh",
13052
+ reasoning: true,
13053
+ input: ["text"],
13054
+ cost: {
13055
+ input: 0.14,
13056
+ output: 0.28,
13057
+ cacheRead: 0.0028,
13058
+ cacheWrite: 0,
13059
+ },
13060
+ contextWindow: 1000000,
13061
+ maxTokens: 384000,
13062
+ },
13063
+ "deepseek/deepseek-v4-pro": {
13064
+ id: "deepseek/deepseek-v4-pro",
13065
+ name: "DeepSeek V4 Pro",
13066
+ api: "anthropic-messages",
13067
+ provider: "vercel-ai-gateway",
13068
+ baseUrl: "https://ai-gateway.vercel.sh",
13069
+ reasoning: true,
13070
+ input: ["text"],
13071
+ cost: {
13072
+ input: 0.435,
13073
+ output: 0.87,
13074
+ cacheRead: 0.0036,
13075
+ cacheWrite: 0,
13076
+ },
13077
+ contextWindow: 1000000,
13078
+ maxTokens: 384000,
13079
+ },
11763
13080
  "google/gemini-2.0-flash": {
11764
13081
  id: "google/gemini-2.0-flash",
11765
13082
  name: "Gemini 2.0 Flash",
@@ -12525,6 +13842,23 @@ export const MODELS = {
12525
13842
  contextWindow: 262114,
12526
13843
  maxTokens: 262114,
12527
13844
  },
13845
+ "moonshotai/kimi-k2.6": {
13846
+ id: "moonshotai/kimi-k2.6",
13847
+ name: "Kimi K2.6",
13848
+ api: "anthropic-messages",
13849
+ provider: "vercel-ai-gateway",
13850
+ baseUrl: "https://ai-gateway.vercel.sh",
13851
+ reasoning: true,
13852
+ input: ["text", "image"],
13853
+ cost: {
13854
+ input: 0.95,
13855
+ output: 4,
13856
+ cacheRead: 0.16,
13857
+ cacheWrite: 0,
13858
+ },
13859
+ contextWindow: 262000,
13860
+ maxTokens: 262000,
13861
+ },
12528
13862
  "nvidia/nemotron-nano-12b-v2-vl": {
12529
13863
  id: "nvidia/nemotron-nano-12b-v2-vl",
12530
13864
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -13018,6 +14352,40 @@ export const MODELS = {
13018
14352
  contextWindow: 1050000,
13019
14353
  maxTokens: 128000,
13020
14354
  },
14355
+ "openai/gpt-5.5": {
14356
+ id: "openai/gpt-5.5",
14357
+ name: "GPT 5.5",
14358
+ api: "anthropic-messages",
14359
+ provider: "vercel-ai-gateway",
14360
+ baseUrl: "https://ai-gateway.vercel.sh",
14361
+ reasoning: true,
14362
+ input: ["text", "image"],
14363
+ cost: {
14364
+ input: 5,
14365
+ output: 30,
14366
+ cacheRead: 0.5,
14367
+ cacheWrite: 0,
14368
+ },
14369
+ contextWindow: 1000000,
14370
+ maxTokens: 128000,
14371
+ },
14372
+ "openai/gpt-5.5-pro": {
14373
+ id: "openai/gpt-5.5-pro",
14374
+ name: "GPT 5.5 Pro",
14375
+ api: "anthropic-messages",
14376
+ provider: "vercel-ai-gateway",
14377
+ baseUrl: "https://ai-gateway.vercel.sh",
14378
+ reasoning: true,
14379
+ input: ["text", "image"],
14380
+ cost: {
14381
+ input: 30,
14382
+ output: 180,
14383
+ cacheRead: 0,
14384
+ cacheWrite: 0,
14385
+ },
14386
+ contextWindow: 1000000,
14387
+ maxTokens: 128000,
14388
+ },
13021
14389
  "openai/gpt-oss-20b": {
13022
14390
  id: "openai/gpt-oss-20b",
13023
14391
  name: "GPT OSS 120B",
@@ -13486,9 +14854,9 @@ export const MODELS = {
13486
14854
  reasoning: true,
13487
14855
  input: ["text"],
13488
14856
  cost: {
13489
- input: 0.09,
13490
- output: 0.29,
13491
- cacheRead: 0.045,
14857
+ input: 0.09999999999999999,
14858
+ output: 0.3,
14859
+ cacheRead: 0.01,
13492
14860
  cacheWrite: 0,
13493
14861
  },
13494
14862
  contextWindow: 262144,
@@ -13705,15 +15073,15 @@ export const MODELS = {
13705
15073
  provider: "vercel-ai-gateway",
13706
15074
  baseUrl: "https://ai-gateway.vercel.sh",
13707
15075
  reasoning: true,
13708
- input: ["text", "image"],
15076
+ input: ["text"],
13709
15077
  cost: {
13710
15078
  input: 1.4,
13711
15079
  output: 4.4,
13712
15080
  cacheRead: 0.26,
13713
15081
  cacheWrite: 0,
13714
15082
  },
13715
- contextWindow: 202752,
13716
- maxTokens: 202752,
15083
+ contextWindow: 202800,
15084
+ maxTokens: 64000,
13717
15085
  },
13718
15086
  "zai/glm-5v-turbo": {
13719
15087
  id: "zai/glm-5v-turbo",
@@ -14144,24 +15512,6 @@ export const MODELS = {
14144
15512
  },
14145
15513
  },
14146
15514
  "zai": {
14147
- "glm-4.5": {
14148
- id: "glm-4.5",
14149
- name: "GLM-4.5",
14150
- api: "openai-completions",
14151
- provider: "zai",
14152
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14153
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14154
- reasoning: true,
14155
- input: ["text"],
14156
- cost: {
14157
- input: 0,
14158
- output: 0,
14159
- cacheRead: 0,
14160
- cacheWrite: 0,
14161
- },
14162
- contextWindow: 131072,
14163
- maxTokens: 98304,
14164
- },
14165
15515
  "glm-4.5-air": {
14166
15516
  id: "glm-4.5-air",
14167
15517
  name: "GLM-4.5-Air",
@@ -14180,78 +15530,6 @@ export const MODELS = {
14180
15530
  contextWindow: 131072,
14181
15531
  maxTokens: 98304,
14182
15532
  },
14183
- "glm-4.5-flash": {
14184
- id: "glm-4.5-flash",
14185
- name: "GLM-4.5-Flash",
14186
- api: "openai-completions",
14187
- provider: "zai",
14188
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14189
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14190
- reasoning: true,
14191
- input: ["text"],
14192
- cost: {
14193
- input: 0,
14194
- output: 0,
14195
- cacheRead: 0,
14196
- cacheWrite: 0,
14197
- },
14198
- contextWindow: 131072,
14199
- maxTokens: 98304,
14200
- },
14201
- "glm-4.5v": {
14202
- id: "glm-4.5v",
14203
- name: "GLM-4.5V",
14204
- api: "openai-completions",
14205
- provider: "zai",
14206
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14207
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14208
- reasoning: true,
14209
- input: ["text", "image"],
14210
- cost: {
14211
- input: 0,
14212
- output: 0,
14213
- cacheRead: 0,
14214
- cacheWrite: 0,
14215
- },
14216
- contextWindow: 64000,
14217
- maxTokens: 16384,
14218
- },
14219
- "glm-4.6": {
14220
- id: "glm-4.6",
14221
- name: "GLM-4.6",
14222
- api: "openai-completions",
14223
- provider: "zai",
14224
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14225
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14226
- reasoning: true,
14227
- input: ["text"],
14228
- cost: {
14229
- input: 0,
14230
- output: 0,
14231
- cacheRead: 0,
14232
- cacheWrite: 0,
14233
- },
14234
- contextWindow: 204800,
14235
- maxTokens: 131072,
14236
- },
14237
- "glm-4.6v": {
14238
- id: "glm-4.6v",
14239
- name: "GLM-4.6V",
14240
- api: "openai-completions",
14241
- provider: "zai",
14242
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14243
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14244
- reasoning: true,
14245
- input: ["text", "image"],
14246
- cost: {
14247
- input: 0,
14248
- output: 0,
14249
- cacheRead: 0,
14250
- cacheWrite: 0,
14251
- },
14252
- contextWindow: 128000,
14253
- maxTokens: 32768,
14254
- },
14255
15533
  "glm-4.7": {
14256
15534
  id: "glm-4.7",
14257
15535
  name: "GLM-4.7",
@@ -14270,60 +15548,6 @@ export const MODELS = {
14270
15548
  contextWindow: 204800,
14271
15549
  maxTokens: 131072,
14272
15550
  },
14273
- "glm-4.7-flash": {
14274
- id: "glm-4.7-flash",
14275
- name: "GLM-4.7-Flash",
14276
- api: "openai-completions",
14277
- provider: "zai",
14278
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14279
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14280
- reasoning: true,
14281
- input: ["text"],
14282
- cost: {
14283
- input: 0,
14284
- output: 0,
14285
- cacheRead: 0,
14286
- cacheWrite: 0,
14287
- },
14288
- contextWindow: 200000,
14289
- maxTokens: 131072,
14290
- },
14291
- "glm-4.7-flashx": {
14292
- id: "glm-4.7-flashx",
14293
- name: "GLM-4.7-FlashX",
14294
- api: "openai-completions",
14295
- provider: "zai",
14296
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14297
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14298
- reasoning: true,
14299
- input: ["text"],
14300
- cost: {
14301
- input: 0.07,
14302
- output: 0.4,
14303
- cacheRead: 0.01,
14304
- cacheWrite: 0,
14305
- },
14306
- contextWindow: 200000,
14307
- maxTokens: 131072,
14308
- },
14309
- "glm-5": {
14310
- id: "glm-5",
14311
- name: "GLM-5",
14312
- api: "openai-completions",
14313
- provider: "zai",
14314
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14315
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14316
- reasoning: true,
14317
- input: ["text"],
14318
- cost: {
14319
- input: 0,
14320
- output: 0,
14321
- cacheRead: 0,
14322
- cacheWrite: 0,
14323
- },
14324
- contextWindow: 204800,
14325
- maxTokens: 131072,
14326
- },
14327
15551
  "glm-5-turbo": {
14328
15552
  id: "glm-5-turbo",
14329
15553
  name: "GLM-5-Turbo",
@@ -14360,24 +15584,6 @@ export const MODELS = {
14360
15584
  contextWindow: 200000,
14361
15585
  maxTokens: 131072,
14362
15586
  },
14363
- "glm-5v-turbo": {
14364
- id: "glm-5v-turbo",
14365
- name: "glm-5v-turbo",
14366
- api: "openai-completions",
14367
- provider: "zai",
14368
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14369
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14370
- reasoning: true,
14371
- input: ["text", "image"],
14372
- cost: {
14373
- input: 0,
14374
- output: 0,
14375
- cacheRead: 0,
14376
- cacheWrite: 0,
14377
- },
14378
- contextWindow: 200000,
14379
- maxTokens: 131072,
14380
- },
14381
15587
  },
14382
15588
  };
14383
15589
  //# sourceMappingURL=models.generated.js.map