@hyperspaceng/neural-ai 0.70.3 → 0.70.7

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.
@@ -2539,6 +2539,23 @@ export const MODELS = {
2539
2539
  contextWindow: 272000,
2540
2540
  maxTokens: 128000,
2541
2541
  },
2542
+ "gpt-5.5-pro": {
2543
+ id: "gpt-5.5-pro",
2544
+ name: "GPT-5.5 Pro",
2545
+ api: "azure-openai-responses",
2546
+ provider: "azure-openai-responses",
2547
+ baseUrl: "",
2548
+ reasoning: true,
2549
+ input: ["text", "image"],
2550
+ cost: {
2551
+ input: 30,
2552
+ output: 180,
2553
+ cacheRead: 0,
2554
+ cacheWrite: 0,
2555
+ },
2556
+ contextWindow: 1050000,
2557
+ maxTokens: 128000,
2558
+ },
2542
2559
  "o1": {
2543
2560
  id: "o1",
2544
2561
  name: "o1",
@@ -2746,6 +2763,152 @@ export const MODELS = {
2746
2763
  maxTokens: 40000,
2747
2764
  },
2748
2765
  },
2766
+ "cloudflare-workers-ai": {
2767
+ "@cf/google/gemma-4-26b-a4b-it": {
2768
+ id: "@cf/google/gemma-4-26b-a4b-it",
2769
+ name: "Gemma 4 26B A4B IT",
2770
+ api: "openai-completions",
2771
+ provider: "cloudflare-workers-ai",
2772
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2773
+ compat: { "sendSessionAffinityHeaders": true },
2774
+ reasoning: true,
2775
+ input: ["text", "image"],
2776
+ cost: {
2777
+ input: 0.1,
2778
+ output: 0.3,
2779
+ cacheRead: 0,
2780
+ cacheWrite: 0,
2781
+ },
2782
+ contextWindow: 256000,
2783
+ maxTokens: 16384,
2784
+ },
2785
+ "@cf/meta/llama-4-scout-17b-16e-instruct": {
2786
+ id: "@cf/meta/llama-4-scout-17b-16e-instruct",
2787
+ name: "Llama 4 Scout 17B 16E Instruct",
2788
+ api: "openai-completions",
2789
+ provider: "cloudflare-workers-ai",
2790
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2791
+ compat: { "sendSessionAffinityHeaders": true },
2792
+ reasoning: false,
2793
+ input: ["text", "image"],
2794
+ cost: {
2795
+ input: 0.27,
2796
+ output: 0.85,
2797
+ cacheRead: 0,
2798
+ cacheWrite: 0,
2799
+ },
2800
+ contextWindow: 128000,
2801
+ maxTokens: 16384,
2802
+ },
2803
+ "@cf/moonshotai/kimi-k2.5": {
2804
+ id: "@cf/moonshotai/kimi-k2.5",
2805
+ name: "Kimi K2.5",
2806
+ api: "openai-completions",
2807
+ provider: "cloudflare-workers-ai",
2808
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2809
+ compat: { "sendSessionAffinityHeaders": true },
2810
+ reasoning: true,
2811
+ input: ["text", "image"],
2812
+ cost: {
2813
+ input: 0.6,
2814
+ output: 3,
2815
+ cacheRead: 0.1,
2816
+ cacheWrite: 0,
2817
+ },
2818
+ contextWindow: 256000,
2819
+ maxTokens: 256000,
2820
+ },
2821
+ "@cf/moonshotai/kimi-k2.6": {
2822
+ id: "@cf/moonshotai/kimi-k2.6",
2823
+ name: "Kimi K2.6",
2824
+ api: "openai-completions",
2825
+ provider: "cloudflare-workers-ai",
2826
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2827
+ compat: { "sendSessionAffinityHeaders": true },
2828
+ reasoning: true,
2829
+ input: ["text", "image"],
2830
+ cost: {
2831
+ input: 0.95,
2832
+ output: 4,
2833
+ cacheRead: 0.16,
2834
+ cacheWrite: 0,
2835
+ },
2836
+ contextWindow: 256000,
2837
+ maxTokens: 256000,
2838
+ },
2839
+ "@cf/nvidia/nemotron-3-120b-a12b": {
2840
+ id: "@cf/nvidia/nemotron-3-120b-a12b",
2841
+ name: "Nemotron 3 Super 120B",
2842
+ api: "openai-completions",
2843
+ provider: "cloudflare-workers-ai",
2844
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2845
+ compat: { "sendSessionAffinityHeaders": true },
2846
+ reasoning: true,
2847
+ input: ["text"],
2848
+ cost: {
2849
+ input: 0.5,
2850
+ output: 1.5,
2851
+ cacheRead: 0,
2852
+ cacheWrite: 0,
2853
+ },
2854
+ contextWindow: 256000,
2855
+ maxTokens: 256000,
2856
+ },
2857
+ "@cf/openai/gpt-oss-120b": {
2858
+ id: "@cf/openai/gpt-oss-120b",
2859
+ name: "GPT OSS 120B",
2860
+ api: "openai-completions",
2861
+ provider: "cloudflare-workers-ai",
2862
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2863
+ compat: { "sendSessionAffinityHeaders": true },
2864
+ reasoning: true,
2865
+ input: ["text"],
2866
+ cost: {
2867
+ input: 0.35,
2868
+ output: 0.75,
2869
+ cacheRead: 0,
2870
+ cacheWrite: 0,
2871
+ },
2872
+ contextWindow: 128000,
2873
+ maxTokens: 16384,
2874
+ },
2875
+ "@cf/openai/gpt-oss-20b": {
2876
+ id: "@cf/openai/gpt-oss-20b",
2877
+ name: "GPT OSS 20B",
2878
+ api: "openai-completions",
2879
+ provider: "cloudflare-workers-ai",
2880
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2881
+ compat: { "sendSessionAffinityHeaders": true },
2882
+ reasoning: true,
2883
+ input: ["text"],
2884
+ cost: {
2885
+ input: 0.2,
2886
+ output: 0.3,
2887
+ cacheRead: 0,
2888
+ cacheWrite: 0,
2889
+ },
2890
+ contextWindow: 128000,
2891
+ maxTokens: 16384,
2892
+ },
2893
+ "@cf/zai-org/glm-4.7-flash": {
2894
+ id: "@cf/zai-org/glm-4.7-flash",
2895
+ name: "GLM-4.7-Flash",
2896
+ api: "openai-completions",
2897
+ provider: "cloudflare-workers-ai",
2898
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
2899
+ compat: { "sendSessionAffinityHeaders": true },
2900
+ reasoning: true,
2901
+ input: ["text"],
2902
+ cost: {
2903
+ input: 0.06,
2904
+ output: 0.4,
2905
+ cacheRead: 0,
2906
+ cacheWrite: 0,
2907
+ },
2908
+ contextWindow: 131072,
2909
+ maxTokens: 131072,
2910
+ },
2911
+ },
2749
2912
  "deepseek": {
2750
2913
  "deepseek-v4-flash": {
2751
2914
  id: "deepseek-v4-flash",
@@ -2819,6 +2982,23 @@ export const MODELS = {
2819
2982
  contextWindow: 160000,
2820
2983
  maxTokens: 160000,
2821
2984
  },
2985
+ "accounts/fireworks/models/deepseek-v4-pro": {
2986
+ id: "accounts/fireworks/models/deepseek-v4-pro",
2987
+ name: "DeepSeek V4 Pro",
2988
+ api: "anthropic-messages",
2989
+ provider: "fireworks",
2990
+ baseUrl: "https://api.fireworks.ai/inference",
2991
+ reasoning: true,
2992
+ input: ["text"],
2993
+ cost: {
2994
+ input: 1.74,
2995
+ output: 3.48,
2996
+ cacheRead: 0.15,
2997
+ cacheWrite: 0,
2998
+ },
2999
+ contextWindow: 1000000,
3000
+ maxTokens: 384000,
3001
+ },
2822
3002
  "accounts/fireworks/models/glm-4p5": {
2823
3003
  id: "accounts/fireworks/models/glm-4p5",
2824
3004
  name: "GLM 4.5",
@@ -5057,6 +5237,24 @@ export const MODELS = {
5057
5237
  contextWindow: 163840,
5058
5238
  maxTokens: 65536,
5059
5239
  },
5240
+ "deepseek-ai/DeepSeek-V4-Pro": {
5241
+ id: "deepseek-ai/DeepSeek-V4-Pro",
5242
+ name: "DeepSeek V4 Pro",
5243
+ api: "openai-completions",
5244
+ provider: "huggingface",
5245
+ baseUrl: "https://router.huggingface.co/v1",
5246
+ compat: { "supportsDeveloperRole": false },
5247
+ reasoning: true,
5248
+ input: ["text"],
5249
+ cost: {
5250
+ input: 1.74,
5251
+ output: 3.48,
5252
+ cacheRead: 0.145,
5253
+ cacheWrite: 0,
5254
+ },
5255
+ contextWindow: 1048576,
5256
+ maxTokens: 393216,
5257
+ },
5060
5258
  "moonshotai/Kimi-K2-Instruct": {
5061
5259
  id: "moonshotai/Kimi-K2-Instruct",
5062
5260
  name: "Kimi-K2-Instruct",
@@ -6354,6 +6552,23 @@ export const MODELS = {
6354
6552
  contextWindow: 272000,
6355
6553
  maxTokens: 128000,
6356
6554
  },
6555
+ "gpt-5.5-pro": {
6556
+ id: "gpt-5.5-pro",
6557
+ name: "GPT-5.5 Pro",
6558
+ api: "openai-responses",
6559
+ provider: "openai",
6560
+ baseUrl: "https://api.openai.com/v1",
6561
+ reasoning: true,
6562
+ input: ["text", "image"],
6563
+ cost: {
6564
+ input: 30,
6565
+ output: 180,
6566
+ cacheRead: 0,
6567
+ cacheWrite: 0,
6568
+ },
6569
+ contextWindow: 1050000,
6570
+ maxTokens: 128000,
6571
+ },
6357
6572
  "o1": {
6358
6573
  id: "o1",
6359
6574
  name: "o1",
@@ -6681,23 +6896,6 @@ export const MODELS = {
6681
6896
  contextWindow: 200000,
6682
6897
  maxTokens: 128000,
6683
6898
  },
6684
- "claude-3-5-haiku": {
6685
- id: "claude-3-5-haiku",
6686
- name: "Claude Haiku 3.5",
6687
- api: "anthropic-messages",
6688
- provider: "opencode",
6689
- baseUrl: "https://opencode.ai/zen",
6690
- reasoning: false,
6691
- input: ["text", "image"],
6692
- cost: {
6693
- input: 0.8,
6694
- output: 4,
6695
- cacheRead: 0.08,
6696
- cacheWrite: 1,
6697
- },
6698
- contextWindow: 200000,
6699
- maxTokens: 8192,
6700
- },
6701
6899
  "claude-haiku-4-5": {
6702
6900
  id: "claude-haiku-4-5",
6703
6901
  name: "Claude Haiku 4.5",
@@ -7155,7 +7353,7 @@ export const MODELS = {
7155
7353
  cacheWrite: 0,
7156
7354
  },
7157
7355
  contextWindow: 1050000,
7158
- maxTokens: 130000,
7356
+ maxTokens: 128000,
7159
7357
  },
7160
7358
  "gpt-5.5-pro": {
7161
7359
  id: "gpt-5.5-pro",
@@ -7225,23 +7423,6 @@ export const MODELS = {
7225
7423
  contextWindow: 262144,
7226
7424
  maxTokens: 65536,
7227
7425
  },
7228
- "ling-2.6-flash-free": {
7229
- id: "ling-2.6-flash-free",
7230
- name: "Ling 2.6 Flash Free",
7231
- api: "openai-completions",
7232
- provider: "opencode",
7233
- baseUrl: "https://opencode.ai/zen/v1",
7234
- reasoning: false,
7235
- input: ["text"],
7236
- cost: {
7237
- input: 0,
7238
- output: 0,
7239
- cacheRead: 0,
7240
- cacheWrite: 0,
7241
- },
7242
- contextWindow: 262100,
7243
- maxTokens: 32800,
7244
- },
7245
7426
  "minimax-m2.5": {
7246
7427
  id: "minimax-m2.5",
7247
7428
  name: "MiniMax M2.5",
@@ -7358,7 +7539,7 @@ export const MODELS = {
7358
7539
  cost: {
7359
7540
  input: 0.14,
7360
7541
  output: 0.28,
7361
- cacheRead: 0.028,
7542
+ cacheRead: 0.0028,
7362
7543
  cacheWrite: 0,
7363
7544
  },
7364
7545
  contextWindow: 1000000,
@@ -7376,7 +7557,7 @@ export const MODELS = {
7376
7557
  cost: {
7377
7558
  input: 1.74,
7378
7559
  output: 3.48,
7379
- cacheRead: 0.145,
7560
+ cacheRead: 0.0145,
7380
7561
  cacheWrite: 0,
7381
7562
  },
7382
7563
  contextWindow: 1000000,
@@ -7396,8 +7577,8 @@ export const MODELS = {
7396
7577
  cacheRead: 0.2,
7397
7578
  cacheWrite: 0,
7398
7579
  },
7399
- contextWindow: 204800,
7400
- maxTokens: 131072,
7580
+ contextWindow: 202752,
7581
+ maxTokens: 32768,
7401
7582
  },
7402
7583
  "glm-5.1": {
7403
7584
  id: "glm-5.1",
@@ -7413,8 +7594,8 @@ export const MODELS = {
7413
7594
  cacheRead: 0.26,
7414
7595
  cacheWrite: 0,
7415
7596
  },
7416
- contextWindow: 204800,
7417
- maxTokens: 131072,
7597
+ contextWindow: 202752,
7598
+ maxTokens: 32768,
7418
7599
  },
7419
7600
  "kimi-k2.5": {
7420
7601
  id: "kimi-k2.5",
@@ -7498,7 +7679,7 @@ export const MODELS = {
7498
7679
  cacheRead: 0.08,
7499
7680
  cacheWrite: 0,
7500
7681
  },
7501
- contextWindow: 262144,
7682
+ contextWindow: 1000000,
7502
7683
  maxTokens: 128000,
7503
7684
  },
7504
7685
  "mimo-v2.5-pro": {
@@ -8331,7 +8512,7 @@ export const MODELS = {
8331
8512
  cost: {
8332
8513
  input: 0.14,
8333
8514
  output: 0.28,
8334
- cacheRead: 0.028,
8515
+ cacheRead: 0.0028,
8335
8516
  cacheWrite: 0,
8336
8517
  },
8337
8518
  contextWindow: 1048576,
@@ -8349,7 +8530,7 @@ export const MODELS = {
8349
8530
  cost: {
8350
8531
  input: 0.435,
8351
8532
  output: 0.87,
8352
- cacheRead: 0.03625,
8533
+ cacheRead: 0.003625,
8353
8534
  cacheWrite: 0,
8354
8535
  },
8355
8536
  contextWindow: 1048576,
@@ -8712,18 +8893,18 @@ export const MODELS = {
8712
8893
  contextWindow: 262144,
8713
8894
  maxTokens: 32768,
8714
8895
  },
8715
- "inclusionai/ling-2.6-flash:free": {
8716
- id: "inclusionai/ling-2.6-flash:free",
8717
- name: "inclusionAI: Ling-2.6-flash (free)",
8896
+ "inclusionai/ling-2.6-flash": {
8897
+ id: "inclusionai/ling-2.6-flash",
8898
+ name: "inclusionAI: Ling-2.6-flash",
8718
8899
  api: "openai-completions",
8719
8900
  provider: "openrouter",
8720
8901
  baseUrl: "https://openrouter.ai/api/v1",
8721
8902
  reasoning: false,
8722
8903
  input: ["text"],
8723
8904
  cost: {
8724
- input: 0,
8725
- output: 0,
8726
- cacheRead: 0,
8905
+ input: 0.08,
8906
+ output: 0.24,
8907
+ cacheRead: 0.016,
8727
8908
  cacheWrite: 0,
8728
8909
  },
8729
8910
  contextWindow: 262144,
@@ -9180,7 +9361,7 @@ export const MODELS = {
9180
9361
  reasoning: false,
9181
9362
  input: ["text"],
9182
9363
  cost: {
9183
- input: 0.01,
9364
+ input: 0.02,
9184
9365
  output: 0.03,
9185
9366
  cacheRead: 0,
9186
9367
  cacheWrite: 0,
@@ -9239,23 +9420,6 @@ export const MODELS = {
9239
9420
  contextWindow: 128000,
9240
9421
  maxTokens: 16384,
9241
9422
  },
9242
- "mistralai/mistral-small-creative": {
9243
- id: "mistralai/mistral-small-creative",
9244
- name: "Mistral: Mistral Small Creative",
9245
- api: "openai-completions",
9246
- provider: "openrouter",
9247
- baseUrl: "https://openrouter.ai/api/v1",
9248
- reasoning: false,
9249
- input: ["text"],
9250
- cost: {
9251
- input: 0.09999999999999999,
9252
- output: 0.3,
9253
- cacheRead: 0.01,
9254
- cacheWrite: 0,
9255
- },
9256
- contextWindow: 32768,
9257
- maxTokens: 4096,
9258
- },
9259
9423
  "mistralai/mixtral-8x22b-instruct": {
9260
9424
  id: "mistralai/mixtral-8x22b-instruct",
9261
9425
  name: "Mistral: Mixtral 8x22B Instruct",
@@ -9401,13 +9565,13 @@ export const MODELS = {
9401
9565
  reasoning: true,
9402
9566
  input: ["text", "image"],
9403
9567
  cost: {
9404
- input: 0.7448,
9405
- output: 4.655,
9406
- cacheRead: 0.1463,
9568
+ input: 0.75,
9569
+ output: 3.5,
9570
+ cacheRead: 0.15,
9407
9571
  cacheWrite: 0,
9408
9572
  },
9409
- contextWindow: 256000,
9410
- maxTokens: 65536,
9573
+ contextWindow: 262144,
9574
+ maxTokens: 16384,
9411
9575
  },
9412
9576
  "nex-agi/deepseek-v3.1-nex-n1": {
9413
9577
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9494,6 +9658,23 @@ export const MODELS = {
9494
9658
  contextWindow: 256000,
9495
9659
  maxTokens: 4096,
9496
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
+ },
9497
9678
  "nvidia/nemotron-3-super-120b-a12b": {
9498
9679
  id: "nvidia/nemotron-3-super-120b-a12b",
9499
9680
  name: "NVIDIA: Nemotron 3 Super",
@@ -10565,17 +10746,51 @@ export const MODELS = {
10565
10746
  contextWindow: 200000,
10566
10747
  maxTokens: 4096,
10567
10748
  },
10568
- "prime-intellect/intellect-3": {
10569
- id: "prime-intellect/intellect-3",
10570
- name: "Prime Intellect: INTELLECT-3",
10749
+ "poolside/laguna-m.1:free": {
10750
+ id: "poolside/laguna-m.1:free",
10751
+ name: "Poolside: Laguna M.1 (free)",
10571
10752
  api: "openai-completions",
10572
10753
  provider: "openrouter",
10573
10754
  baseUrl: "https://openrouter.ai/api/v1",
10574
10755
  reasoning: true,
10575
10756
  input: ["text"],
10576
10757
  cost: {
10577
- input: 0.19999999999999998,
10578
- output: 1.1,
10758
+ input: 0,
10759
+ output: 0,
10760
+ cacheRead: 0,
10761
+ cacheWrite: 0,
10762
+ },
10763
+ contextWindow: 131072,
10764
+ maxTokens: 8192,
10765
+ },
10766
+ "poolside/laguna-xs.2:free": {
10767
+ id: "poolside/laguna-xs.2:free",
10768
+ name: "Poolside: Laguna XS.2 (free)",
10769
+ api: "openai-completions",
10770
+ provider: "openrouter",
10771
+ baseUrl: "https://openrouter.ai/api/v1",
10772
+ reasoning: true,
10773
+ input: ["text"],
10774
+ cost: {
10775
+ input: 0,
10776
+ output: 0,
10777
+ cacheRead: 0,
10778
+ cacheWrite: 0,
10779
+ },
10780
+ contextWindow: 131072,
10781
+ maxTokens: 8192,
10782
+ },
10783
+ "prime-intellect/intellect-3": {
10784
+ id: "prime-intellect/intellect-3",
10785
+ name: "Prime Intellect: INTELLECT-3",
10786
+ api: "openai-completions",
10787
+ provider: "openrouter",
10788
+ baseUrl: "https://openrouter.ai/api/v1",
10789
+ reasoning: true,
10790
+ input: ["text"],
10791
+ cost: {
10792
+ input: 0.19999999999999998,
10793
+ output: 1.1,
10579
10794
  cacheRead: 0,
10580
10795
  cacheWrite: 0,
10581
10796
  },
@@ -10591,8 +10806,8 @@ export const MODELS = {
10591
10806
  reasoning: false,
10592
10807
  input: ["text"],
10593
10808
  cost: {
10594
- input: 0.12,
10595
- output: 0.39,
10809
+ input: 0.36,
10810
+ output: 0.39999999999999997,
10596
10811
  cacheRead: 0,
10597
10812
  cacheWrite: 0,
10598
10813
  },
@@ -11296,9 +11511,26 @@ export const MODELS = {
11296
11511
  contextWindow: 1000000,
11297
11512
  maxTokens: 65536,
11298
11513
  },
11299
- "qwen/qwen3.6-plus": {
11300
- id: "qwen/qwen3.6-plus",
11301
- name: "Qwen: Qwen3.6 Plus",
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",
11302
11534
  api: "openai-completions",
11303
11535
  provider: "openrouter",
11304
11536
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11306,29 +11538,63 @@ export const MODELS = {
11306
11538
  input: ["text", "image"],
11307
11539
  cost: {
11308
11540
  input: 0.325,
11309
- output: 1.95,
11541
+ output: 3.25,
11310
11542
  cacheRead: 0,
11311
- cacheWrite: 0.40625,
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,
11312
11561
  },
11313
11562
  contextWindow: 1000000,
11314
11563
  maxTokens: 65536,
11315
11564
  },
11316
- "qwen/qwq-32b": {
11317
- id: "qwen/qwq-32b",
11318
- name: "Qwen: QwQ 32B",
11565
+ "qwen/qwen3.6-max-preview": {
11566
+ id: "qwen/qwen3.6-max-preview",
11567
+ name: "Qwen: Qwen3.6 Max Preview",
11319
11568
  api: "openai-completions",
11320
11569
  provider: "openrouter",
11321
11570
  baseUrl: "https://openrouter.ai/api/v1",
11322
11571
  reasoning: true,
11323
11572
  input: ["text"],
11324
11573
  cost: {
11325
- input: 0.15,
11326
- output: 0.58,
11574
+ input: 1.04,
11575
+ output: 6.24,
11327
11576
  cacheRead: 0,
11328
- cacheWrite: 0,
11577
+ cacheWrite: 1.3,
11329
11578
  },
11330
- contextWindow: 131072,
11331
- maxTokens: 131072,
11579
+ contextWindow: 262144,
11580
+ maxTokens: 65536,
11581
+ },
11582
+ "qwen/qwen3.6-plus": {
11583
+ id: "qwen/qwen3.6-plus",
11584
+ name: "Qwen: Qwen3.6 Plus",
11585
+ api: "openai-completions",
11586
+ provider: "openrouter",
11587
+ baseUrl: "https://openrouter.ai/api/v1",
11588
+ reasoning: true,
11589
+ input: ["text", "image"],
11590
+ cost: {
11591
+ input: 0.325,
11592
+ output: 1.95,
11593
+ cacheRead: 0,
11594
+ cacheWrite: 0.40625,
11595
+ },
11596
+ contextWindow: 1000000,
11597
+ maxTokens: 65536,
11332
11598
  },
11333
11599
  "rekaai/reka-edge": {
11334
11600
  id: "rekaai/reka-edge",
@@ -11959,6 +12225,23 @@ export const MODELS = {
11959
12225
  contextWindow: 202752,
11960
12226
  maxTokens: 131072,
11961
12227
  },
12228
+ "~anthropic/claude-haiku-latest": {
12229
+ id: "~anthropic/claude-haiku-latest",
12230
+ name: "Anthropic Claude Haiku Latest",
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,
12238
+ output: 5,
12239
+ cacheRead: 0.09999999999999999,
12240
+ cacheWrite: 1.25,
12241
+ },
12242
+ contextWindow: 200000,
12243
+ maxTokens: 64000,
12244
+ },
11962
12245
  "~anthropic/claude-opus-latest": {
11963
12246
  id: "~anthropic/claude-opus-latest",
11964
12247
  name: "Anthropic: Claude Opus Latest",
@@ -11976,6 +12259,108 @@ export const MODELS = {
11976
12259
  contextWindow: 1000000,
11977
12260
  maxTokens: 128000,
11978
12261
  },
12262
+ "~anthropic/claude-sonnet-latest": {
12263
+ id: "~anthropic/claude-sonnet-latest",
12264
+ name: "Anthropic Claude Sonnet 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: 3,
12272
+ output: 15,
12273
+ cacheRead: 0.3,
12274
+ cacheWrite: 3.75,
12275
+ },
12276
+ contextWindow: 1000000,
12277
+ maxTokens: 128000,
12278
+ },
12279
+ "~google/gemini-flash-latest": {
12280
+ id: "~google/gemini-flash-latest",
12281
+ name: "Google Gemini Flash 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: 0.5,
12289
+ output: 3,
12290
+ cacheRead: 0.049999999999999996,
12291
+ cacheWrite: 0.08333333333333334,
12292
+ },
12293
+ contextWindow: 1048576,
12294
+ maxTokens: 65536,
12295
+ },
12296
+ "~google/gemini-pro-latest": {
12297
+ id: "~google/gemini-pro-latest",
12298
+ name: "Google Gemini Pro 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: 2,
12306
+ output: 12,
12307
+ cacheRead: 0.19999999999999998,
12308
+ cacheWrite: 0.375,
12309
+ },
12310
+ contextWindow: 1048576,
12311
+ maxTokens: 65536,
12312
+ },
12313
+ "~moonshotai/kimi-latest": {
12314
+ id: "~moonshotai/kimi-latest",
12315
+ name: "MoonshotAI Kimi 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: 0.75,
12323
+ output: 3.5,
12324
+ cacheRead: 0.15,
12325
+ cacheWrite: 0,
12326
+ },
12327
+ contextWindow: 262144,
12328
+ maxTokens: 16384,
12329
+ },
12330
+ "~openai/gpt-latest": {
12331
+ id: "~openai/gpt-latest",
12332
+ name: "OpenAI GPT 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: 5,
12340
+ output: 30,
12341
+ cacheRead: 0.5,
12342
+ cacheWrite: 0,
12343
+ },
12344
+ contextWindow: 1050000,
12345
+ maxTokens: 128000,
12346
+ },
12347
+ "~openai/gpt-mini-latest": {
12348
+ id: "~openai/gpt-mini-latest",
12349
+ name: "OpenAI GPT Mini Latest",
12350
+ api: "openai-completions",
12351
+ provider: "openrouter",
12352
+ baseUrl: "https://openrouter.ai/api/v1",
12353
+ reasoning: true,
12354
+ input: ["text", "image"],
12355
+ cost: {
12356
+ input: 0.75,
12357
+ output: 4.5,
12358
+ cacheRead: 0.075,
12359
+ cacheWrite: 0,
12360
+ },
12361
+ contextWindow: 400000,
12362
+ maxTokens: 128000,
12363
+ },
11979
12364
  },
11980
12365
  "vercel-ai-gateway": {
11981
12366
  "alibaba/qwen-3-14b": {
@@ -12065,20 +12450,20 @@ export const MODELS = {
12065
12450
  },
12066
12451
  "alibaba/qwen3-235b-a22b-thinking": {
12067
12452
  id: "alibaba/qwen3-235b-a22b-thinking",
12068
- name: "Qwen3 235B A22B Thinking 2507",
12453
+ name: "Qwen3 VL 235B A22B Thinking",
12069
12454
  api: "anthropic-messages",
12070
12455
  provider: "vercel-ai-gateway",
12071
12456
  baseUrl: "https://ai-gateway.vercel.sh",
12072
12457
  reasoning: true,
12073
12458
  input: ["text", "image"],
12074
12459
  cost: {
12075
- input: 0.22999999999999998,
12076
- output: 2.3,
12077
- cacheRead: 0.19999999999999998,
12460
+ input: 0.39999999999999997,
12461
+ output: 4,
12462
+ cacheRead: 0,
12078
12463
  cacheWrite: 0,
12079
12464
  },
12080
- contextWindow: 262114,
12081
- maxTokens: 262114,
12465
+ contextWindow: 131072,
12466
+ maxTokens: 32768,
12082
12467
  },
12083
12468
  "alibaba/qwen3-coder": {
12084
12469
  id: "alibaba/qwen3-coder",
@@ -12250,6 +12635,23 @@ export const MODELS = {
12250
12635
  contextWindow: 1000000,
12251
12636
  maxTokens: 64000,
12252
12637
  },
12638
+ "alibaba/qwen3.6-27b": {
12639
+ id: "alibaba/qwen3.6-27b",
12640
+ name: "Qwen 3.6 27B",
12641
+ api: "anthropic-messages",
12642
+ provider: "vercel-ai-gateway",
12643
+ baseUrl: "https://ai-gateway.vercel.sh",
12644
+ reasoning: true,
12645
+ input: ["text", "image"],
12646
+ cost: {
12647
+ input: 0.6,
12648
+ output: 3.5999999999999996,
12649
+ cacheRead: 0,
12650
+ cacheWrite: 0,
12651
+ },
12652
+ contextWindow: 256000,
12653
+ maxTokens: 256000,
12654
+ },
12253
12655
  "alibaba/qwen3.6-plus": {
12254
12656
  id: "alibaba/qwen3.6-plus",
12255
12657
  name: "Qwen 3.6 Plus",
@@ -12630,16 +13032,16 @@ export const MODELS = {
12630
13032
  api: "anthropic-messages",
12631
13033
  provider: "vercel-ai-gateway",
12632
13034
  baseUrl: "https://ai-gateway.vercel.sh",
12633
- reasoning: true,
13035
+ reasoning: false,
12634
13036
  input: ["text"],
12635
13037
  cost: {
12636
- input: 0.28,
12637
- output: 0.42,
12638
- cacheRead: 0.028,
13038
+ input: 0.62,
13039
+ output: 1.85,
13040
+ cacheRead: 0,
12639
13041
  cacheWrite: 0,
12640
13042
  },
12641
13043
  contextWindow: 128000,
12642
- maxTokens: 64000,
13044
+ maxTokens: 8000,
12643
13045
  },
12644
13046
  "deepseek/deepseek-v4-flash": {
12645
13047
  id: "deepseek/deepseek-v4-flash",
@@ -12652,7 +13054,7 @@ export const MODELS = {
12652
13054
  cost: {
12653
13055
  input: 0.14,
12654
13056
  output: 0.28,
12655
- cacheRead: 0.028,
13057
+ cacheRead: 0.0028,
12656
13058
  cacheWrite: 0,
12657
13059
  },
12658
13060
  contextWindow: 1000000,
@@ -12667,9 +13069,9 @@ export const MODELS = {
12667
13069
  reasoning: true,
12668
13070
  input: ["text"],
12669
13071
  cost: {
12670
- input: 1.74,
12671
- output: 3.48,
12672
- cacheRead: 0.145,
13072
+ input: 0.435,
13073
+ output: 0.87,
13074
+ cacheRead: 0.0036,
12673
13075
  cacheWrite: 0,
12674
13076
  },
12675
13077
  contextWindow: 1000000,
@@ -14477,6 +14879,40 @@ export const MODELS = {
14477
14879
  contextWindow: 1000000,
14478
14880
  maxTokens: 128000,
14479
14881
  },
14882
+ "xiaomi/mimo-v2.5": {
14883
+ id: "xiaomi/mimo-v2.5",
14884
+ name: "MiMo M2.5",
14885
+ api: "anthropic-messages",
14886
+ provider: "vercel-ai-gateway",
14887
+ baseUrl: "https://ai-gateway.vercel.sh",
14888
+ reasoning: true,
14889
+ input: ["text", "image"],
14890
+ cost: {
14891
+ input: 0.39999999999999997,
14892
+ output: 2,
14893
+ cacheRead: 0.08,
14894
+ cacheWrite: 0,
14895
+ },
14896
+ contextWindow: 1050000,
14897
+ maxTokens: 131100,
14898
+ },
14899
+ "xiaomi/mimo-v2.5-pro": {
14900
+ id: "xiaomi/mimo-v2.5-pro",
14901
+ name: "MiMo V2.5 Pro",
14902
+ api: "anthropic-messages",
14903
+ provider: "vercel-ai-gateway",
14904
+ baseUrl: "https://ai-gateway.vercel.sh",
14905
+ reasoning: true,
14906
+ input: ["text", "image"],
14907
+ cost: {
14908
+ input: 1,
14909
+ output: 3,
14910
+ cacheRead: 0.19999999999999998,
14911
+ cacheWrite: 0,
14912
+ },
14913
+ contextWindow: 1050000,
14914
+ maxTokens: 131000,
14915
+ },
14480
14916
  "zai/glm-4.5": {
14481
14917
  id: "zai/glm-4.5",
14482
14918
  name: "GLM-4.5",
@@ -15182,6 +15618,24 @@ export const MODELS = {
15182
15618
  contextWindow: 200000,
15183
15619
  maxTokens: 131072,
15184
15620
  },
15621
+ "glm-5v-turbo": {
15622
+ id: "glm-5v-turbo",
15623
+ name: "glm-5v-turbo",
15624
+ api: "openai-completions",
15625
+ provider: "zai",
15626
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
15627
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
15628
+ reasoning: true,
15629
+ input: ["text", "image"],
15630
+ cost: {
15631
+ input: 0,
15632
+ output: 0,
15633
+ cacheRead: 0,
15634
+ cacheWrite: 0,
15635
+ },
15636
+ contextWindow: 200000,
15637
+ maxTokens: 131072,
15638
+ },
15185
15639
  },
15186
15640
  };
15187
15641
  //# sourceMappingURL=models.generated.js.map