@hyperspaceng/neural-ai 0.68.1 → 0.68.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -381,7 +381,7 @@ export const MODELS = {
381
381
  name: "Claude Haiku 4.5 (EU)",
382
382
  api: "bedrock-converse-stream",
383
383
  provider: "amazon-bedrock",
384
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
384
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
385
385
  reasoning: true,
386
386
  input: ["text", "image"],
387
387
  cost: {
@@ -398,7 +398,7 @@ export const MODELS = {
398
398
  name: "Claude Opus 4.5 (EU)",
399
399
  api: "bedrock-converse-stream",
400
400
  provider: "amazon-bedrock",
401
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
401
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
402
402
  reasoning: true,
403
403
  input: ["text", "image"],
404
404
  cost: {
@@ -415,7 +415,7 @@ export const MODELS = {
415
415
  name: "Claude Opus 4.6 (EU)",
416
416
  api: "bedrock-converse-stream",
417
417
  provider: "amazon-bedrock",
418
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
418
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
419
419
  reasoning: true,
420
420
  input: ["text", "image"],
421
421
  cost: {
@@ -432,7 +432,7 @@ export const MODELS = {
432
432
  name: "Claude Opus 4.7 (EU)",
433
433
  api: "bedrock-converse-stream",
434
434
  provider: "amazon-bedrock",
435
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
435
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
436
436
  reasoning: true,
437
437
  input: ["text", "image"],
438
438
  cost: {
@@ -449,7 +449,7 @@ export const MODELS = {
449
449
  name: "Claude Sonnet 4 (EU)",
450
450
  api: "bedrock-converse-stream",
451
451
  provider: "amazon-bedrock",
452
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
452
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
453
453
  reasoning: true,
454
454
  input: ["text", "image"],
455
455
  cost: {
@@ -466,7 +466,7 @@ export const MODELS = {
466
466
  name: "Claude Sonnet 4.5 (EU)",
467
467
  api: "bedrock-converse-stream",
468
468
  provider: "amazon-bedrock",
469
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
469
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
470
470
  reasoning: true,
471
471
  input: ["text", "image"],
472
472
  cost: {
@@ -483,7 +483,7 @@ export const MODELS = {
483
483
  name: "Claude Sonnet 4.6 (EU)",
484
484
  api: "bedrock-converse-stream",
485
485
  provider: "amazon-bedrock",
486
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
486
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
487
487
  reasoning: true,
488
488
  input: ["text", "image"],
489
489
  cost: {
@@ -2695,6 +2695,314 @@ export const MODELS = {
2695
2695
  maxTokens: 40000,
2696
2696
  },
2697
2697
  },
2698
+ "fireworks": {
2699
+ "accounts/fireworks/models/deepseek-v3p1": {
2700
+ id: "accounts/fireworks/models/deepseek-v3p1",
2701
+ name: "DeepSeek V3.1",
2702
+ api: "anthropic-messages",
2703
+ provider: "fireworks",
2704
+ baseUrl: "https://api.fireworks.ai/inference",
2705
+ reasoning: true,
2706
+ input: ["text"],
2707
+ cost: {
2708
+ input: 0.56,
2709
+ output: 1.68,
2710
+ cacheRead: 0,
2711
+ cacheWrite: 0,
2712
+ },
2713
+ contextWindow: 163840,
2714
+ maxTokens: 163840,
2715
+ },
2716
+ "accounts/fireworks/models/deepseek-v3p2": {
2717
+ id: "accounts/fireworks/models/deepseek-v3p2",
2718
+ name: "DeepSeek V3.2",
2719
+ api: "anthropic-messages",
2720
+ provider: "fireworks",
2721
+ baseUrl: "https://api.fireworks.ai/inference",
2722
+ reasoning: true,
2723
+ input: ["text"],
2724
+ cost: {
2725
+ input: 0.56,
2726
+ output: 1.68,
2727
+ cacheRead: 0.28,
2728
+ cacheWrite: 0,
2729
+ },
2730
+ contextWindow: 160000,
2731
+ maxTokens: 160000,
2732
+ },
2733
+ "accounts/fireworks/models/glm-4p5": {
2734
+ id: "accounts/fireworks/models/glm-4p5",
2735
+ name: "GLM 4.5",
2736
+ api: "anthropic-messages",
2737
+ provider: "fireworks",
2738
+ baseUrl: "https://api.fireworks.ai/inference",
2739
+ reasoning: true,
2740
+ input: ["text"],
2741
+ cost: {
2742
+ input: 0.55,
2743
+ output: 2.19,
2744
+ cacheRead: 0,
2745
+ cacheWrite: 0,
2746
+ },
2747
+ contextWindow: 131072,
2748
+ maxTokens: 131072,
2749
+ },
2750
+ "accounts/fireworks/models/glm-4p5-air": {
2751
+ id: "accounts/fireworks/models/glm-4p5-air",
2752
+ name: "GLM 4.5 Air",
2753
+ api: "anthropic-messages",
2754
+ provider: "fireworks",
2755
+ baseUrl: "https://api.fireworks.ai/inference",
2756
+ reasoning: true,
2757
+ input: ["text"],
2758
+ cost: {
2759
+ input: 0.22,
2760
+ output: 0.88,
2761
+ cacheRead: 0,
2762
+ cacheWrite: 0,
2763
+ },
2764
+ contextWindow: 131072,
2765
+ maxTokens: 131072,
2766
+ },
2767
+ "accounts/fireworks/models/glm-4p7": {
2768
+ id: "accounts/fireworks/models/glm-4p7",
2769
+ name: "GLM 4.7",
2770
+ api: "anthropic-messages",
2771
+ provider: "fireworks",
2772
+ baseUrl: "https://api.fireworks.ai/inference",
2773
+ reasoning: true,
2774
+ input: ["text"],
2775
+ cost: {
2776
+ input: 0.6,
2777
+ output: 2.2,
2778
+ cacheRead: 0.3,
2779
+ cacheWrite: 0,
2780
+ },
2781
+ contextWindow: 198000,
2782
+ maxTokens: 198000,
2783
+ },
2784
+ "accounts/fireworks/models/glm-5": {
2785
+ id: "accounts/fireworks/models/glm-5",
2786
+ name: "GLM 5",
2787
+ api: "anthropic-messages",
2788
+ provider: "fireworks",
2789
+ baseUrl: "https://api.fireworks.ai/inference",
2790
+ reasoning: true,
2791
+ input: ["text"],
2792
+ cost: {
2793
+ input: 1,
2794
+ output: 3.2,
2795
+ cacheRead: 0.5,
2796
+ cacheWrite: 0,
2797
+ },
2798
+ contextWindow: 202752,
2799
+ maxTokens: 131072,
2800
+ },
2801
+ "accounts/fireworks/models/glm-5p1": {
2802
+ id: "accounts/fireworks/models/glm-5p1",
2803
+ name: "GLM 5.1",
2804
+ api: "anthropic-messages",
2805
+ provider: "fireworks",
2806
+ baseUrl: "https://api.fireworks.ai/inference",
2807
+ reasoning: true,
2808
+ input: ["text"],
2809
+ cost: {
2810
+ input: 1.4,
2811
+ output: 4.4,
2812
+ cacheRead: 0.26,
2813
+ cacheWrite: 0,
2814
+ },
2815
+ contextWindow: 202800,
2816
+ maxTokens: 131072,
2817
+ },
2818
+ "accounts/fireworks/models/gpt-oss-120b": {
2819
+ id: "accounts/fireworks/models/gpt-oss-120b",
2820
+ name: "GPT OSS 120B",
2821
+ api: "anthropic-messages",
2822
+ provider: "fireworks",
2823
+ baseUrl: "https://api.fireworks.ai/inference",
2824
+ reasoning: true,
2825
+ input: ["text"],
2826
+ cost: {
2827
+ input: 0.15,
2828
+ output: 0.6,
2829
+ cacheRead: 0,
2830
+ cacheWrite: 0,
2831
+ },
2832
+ contextWindow: 131072,
2833
+ maxTokens: 32768,
2834
+ },
2835
+ "accounts/fireworks/models/gpt-oss-20b": {
2836
+ id: "accounts/fireworks/models/gpt-oss-20b",
2837
+ name: "GPT OSS 20B",
2838
+ api: "anthropic-messages",
2839
+ provider: "fireworks",
2840
+ baseUrl: "https://api.fireworks.ai/inference",
2841
+ reasoning: true,
2842
+ input: ["text"],
2843
+ cost: {
2844
+ input: 0.05,
2845
+ output: 0.2,
2846
+ cacheRead: 0,
2847
+ cacheWrite: 0,
2848
+ },
2849
+ contextWindow: 131072,
2850
+ maxTokens: 32768,
2851
+ },
2852
+ "accounts/fireworks/models/kimi-k2-instruct": {
2853
+ id: "accounts/fireworks/models/kimi-k2-instruct",
2854
+ name: "Kimi K2 Instruct",
2855
+ api: "anthropic-messages",
2856
+ provider: "fireworks",
2857
+ baseUrl: "https://api.fireworks.ai/inference",
2858
+ reasoning: false,
2859
+ input: ["text"],
2860
+ cost: {
2861
+ input: 1,
2862
+ output: 3,
2863
+ cacheRead: 0,
2864
+ cacheWrite: 0,
2865
+ },
2866
+ contextWindow: 128000,
2867
+ maxTokens: 16384,
2868
+ },
2869
+ "accounts/fireworks/models/kimi-k2-thinking": {
2870
+ id: "accounts/fireworks/models/kimi-k2-thinking",
2871
+ name: "Kimi K2 Thinking",
2872
+ api: "anthropic-messages",
2873
+ provider: "fireworks",
2874
+ baseUrl: "https://api.fireworks.ai/inference",
2875
+ reasoning: true,
2876
+ input: ["text"],
2877
+ cost: {
2878
+ input: 0.6,
2879
+ output: 2.5,
2880
+ cacheRead: 0.3,
2881
+ cacheWrite: 0,
2882
+ },
2883
+ contextWindow: 256000,
2884
+ maxTokens: 256000,
2885
+ },
2886
+ "accounts/fireworks/models/kimi-k2p5": {
2887
+ id: "accounts/fireworks/models/kimi-k2p5",
2888
+ name: "Kimi K2.5",
2889
+ api: "anthropic-messages",
2890
+ provider: "fireworks",
2891
+ baseUrl: "https://api.fireworks.ai/inference",
2892
+ reasoning: true,
2893
+ input: ["text", "image"],
2894
+ cost: {
2895
+ input: 0.6,
2896
+ output: 3,
2897
+ cacheRead: 0.1,
2898
+ cacheWrite: 0,
2899
+ },
2900
+ contextWindow: 256000,
2901
+ maxTokens: 256000,
2902
+ },
2903
+ "accounts/fireworks/models/kimi-k2p6": {
2904
+ id: "accounts/fireworks/models/kimi-k2p6",
2905
+ name: "Kimi K2.6",
2906
+ api: "anthropic-messages",
2907
+ provider: "fireworks",
2908
+ baseUrl: "https://api.fireworks.ai/inference",
2909
+ reasoning: true,
2910
+ input: ["text", "image"],
2911
+ cost: {
2912
+ input: 0.95,
2913
+ output: 4,
2914
+ cacheRead: 0.16,
2915
+ cacheWrite: 0,
2916
+ },
2917
+ contextWindow: 262000,
2918
+ maxTokens: 262000,
2919
+ },
2920
+ "accounts/fireworks/models/minimax-m2p1": {
2921
+ id: "accounts/fireworks/models/minimax-m2p1",
2922
+ name: "MiniMax-M2.1",
2923
+ api: "anthropic-messages",
2924
+ provider: "fireworks",
2925
+ baseUrl: "https://api.fireworks.ai/inference",
2926
+ reasoning: true,
2927
+ input: ["text"],
2928
+ cost: {
2929
+ input: 0.3,
2930
+ output: 1.2,
2931
+ cacheRead: 0.03,
2932
+ cacheWrite: 0,
2933
+ },
2934
+ contextWindow: 200000,
2935
+ maxTokens: 200000,
2936
+ },
2937
+ "accounts/fireworks/models/minimax-m2p5": {
2938
+ id: "accounts/fireworks/models/minimax-m2p5",
2939
+ name: "MiniMax-M2.5",
2940
+ api: "anthropic-messages",
2941
+ provider: "fireworks",
2942
+ baseUrl: "https://api.fireworks.ai/inference",
2943
+ reasoning: true,
2944
+ input: ["text"],
2945
+ cost: {
2946
+ input: 0.3,
2947
+ output: 1.2,
2948
+ cacheRead: 0.03,
2949
+ cacheWrite: 0,
2950
+ },
2951
+ contextWindow: 196608,
2952
+ maxTokens: 196608,
2953
+ },
2954
+ "accounts/fireworks/models/minimax-m2p7": {
2955
+ id: "accounts/fireworks/models/minimax-m2p7",
2956
+ name: "MiniMax-M2.7",
2957
+ api: "anthropic-messages",
2958
+ provider: "fireworks",
2959
+ baseUrl: "https://api.fireworks.ai/inference",
2960
+ reasoning: true,
2961
+ input: ["text"],
2962
+ cost: {
2963
+ input: 0.3,
2964
+ output: 1.2,
2965
+ cacheRead: 0.03,
2966
+ cacheWrite: 0,
2967
+ },
2968
+ contextWindow: 196608,
2969
+ maxTokens: 196608,
2970
+ },
2971
+ "accounts/fireworks/models/qwen3p6-plus": {
2972
+ id: "accounts/fireworks/models/qwen3p6-plus",
2973
+ name: "Qwen 3.6 Plus",
2974
+ api: "anthropic-messages",
2975
+ provider: "fireworks",
2976
+ baseUrl: "https://api.fireworks.ai/inference",
2977
+ reasoning: true,
2978
+ input: ["text", "image"],
2979
+ cost: {
2980
+ input: 0.5,
2981
+ output: 3,
2982
+ cacheRead: 0.1,
2983
+ cacheWrite: 0,
2984
+ },
2985
+ contextWindow: 128000,
2986
+ maxTokens: 8192,
2987
+ },
2988
+ "accounts/fireworks/routers/kimi-k2p5-turbo": {
2989
+ id: "accounts/fireworks/routers/kimi-k2p5-turbo",
2990
+ name: "Kimi K2.5 Turbo (firepass)",
2991
+ api: "anthropic-messages",
2992
+ provider: "fireworks",
2993
+ baseUrl: "https://api.fireworks.ai/inference",
2994
+ reasoning: true,
2995
+ input: ["text", "image"],
2996
+ cost: {
2997
+ input: 0,
2998
+ output: 0,
2999
+ cacheRead: 0,
3000
+ cacheWrite: 0,
3001
+ },
3002
+ contextWindow: 256000,
3003
+ maxTokens: 256000,
3004
+ },
3005
+ },
2698
3006
  "github-copilot": {
2699
3007
  "claude-haiku-4.5": {
2700
3008
  id: "claude-haiku-4.5",
@@ -3580,8 +3888,8 @@ export const MODELS = {
3580
3888
  contextWindow: 131072,
3581
3889
  maxTokens: 8192,
3582
3890
  },
3583
- "gemma-4-26b-it": {
3584
- id: "gemma-4-26b-it",
3891
+ "gemma-4-26b-a4b-it": {
3892
+ id: "gemma-4-26b-a4b-it",
3585
3893
  name: "Gemma 4 26B",
3586
3894
  api: "google-generative-ai",
3587
3895
  provider: "google",
@@ -6906,7 +7214,7 @@ export const MODELS = {
6906
7214
  cacheWrite: 0,
6907
7215
  },
6908
7216
  contextWindow: 262144,
6909
- maxTokens: 64000,
7217
+ maxTokens: 128000,
6910
7218
  },
6911
7219
  "mimo-v2-pro": {
6912
7220
  id: "mimo-v2-pro",
@@ -6923,7 +7231,41 @@ export const MODELS = {
6923
7231
  cacheWrite: 0,
6924
7232
  },
6925
7233
  contextWindow: 1048576,
6926
- maxTokens: 64000,
7234
+ maxTokens: 128000,
7235
+ },
7236
+ "mimo-v2.5": {
7237
+ id: "mimo-v2.5",
7238
+ name: "MiMo V2.5",
7239
+ api: "openai-completions",
7240
+ provider: "opencode-go",
7241
+ baseUrl: "https://opencode.ai/zen/go/v1",
7242
+ reasoning: true,
7243
+ input: ["text", "image"],
7244
+ cost: {
7245
+ input: 0.4,
7246
+ output: 2,
7247
+ cacheRead: 0.08,
7248
+ cacheWrite: 0,
7249
+ },
7250
+ contextWindow: 262144,
7251
+ maxTokens: 128000,
7252
+ },
7253
+ "mimo-v2.5-pro": {
7254
+ id: "mimo-v2.5-pro",
7255
+ name: "MiMo V2.5 Pro",
7256
+ api: "openai-completions",
7257
+ provider: "opencode-go",
7258
+ baseUrl: "https://opencode.ai/zen/go/v1",
7259
+ reasoning: true,
7260
+ input: ["text"],
7261
+ cost: {
7262
+ input: 1,
7263
+ output: 3,
7264
+ cacheRead: 0.2,
7265
+ cacheWrite: 0,
7266
+ },
7267
+ contextWindow: 1048576,
7268
+ maxTokens: 128000,
6927
7269
  },
6928
7270
  "minimax-m2.5": {
6929
7271
  id: "minimax-m2.5",
@@ -7369,17 +7711,17 @@ export const MODELS = {
7369
7711
  contextWindow: 1000000,
7370
7712
  maxTokens: 128000,
7371
7713
  },
7372
- "arcee-ai/trinity-large-preview:free": {
7373
- id: "arcee-ai/trinity-large-preview:free",
7374
- name: "Arcee AI: Trinity Large Preview (free)",
7714
+ "arcee-ai/trinity-large-preview": {
7715
+ id: "arcee-ai/trinity-large-preview",
7716
+ name: "Arcee AI: Trinity Large Preview",
7375
7717
  api: "openai-completions",
7376
7718
  provider: "openrouter",
7377
7719
  baseUrl: "https://openrouter.ai/api/v1",
7378
7720
  reasoning: false,
7379
7721
  input: ["text"],
7380
7722
  cost: {
7381
- input: 0,
7382
- output: 0,
7723
+ input: 0.15,
7724
+ output: 0.44999999999999996,
7383
7725
  cacheRead: 0,
7384
7726
  cacheWrite: 0,
7385
7727
  },
@@ -7707,7 +8049,7 @@ export const MODELS = {
7707
8049
  cacheWrite: 0,
7708
8050
  },
7709
8051
  contextWindow: 131072,
7710
- maxTokens: 32768,
8052
+ maxTokens: 65536,
7711
8053
  },
7712
8054
  "deepseek/deepseek-v3.2-exp": {
7713
8055
  id: "deepseek/deepseek-v3.2-exp",
@@ -7757,7 +8099,7 @@ export const MODELS = {
7757
8099
  cacheRead: 0.024999999999999998,
7758
8100
  cacheWrite: 0.08333333333333334,
7759
8101
  },
7760
- contextWindow: 1048576,
8102
+ contextWindow: 1000000,
7761
8103
  maxTokens: 8192,
7762
8104
  },
7763
8105
  "google/gemini-2.0-flash-lite-001": {
@@ -7957,12 +8299,12 @@ export const MODELS = {
7957
8299
  input: ["text", "image"],
7958
8300
  cost: {
7959
8301
  input: 0.07,
7960
- output: 0.35,
7961
- cacheRead: 0.04,
8302
+ output: 0.33999999999999997,
8303
+ cacheRead: 0,
7962
8304
  cacheWrite: 0,
7963
8305
  },
7964
8306
  contextWindow: 262144,
7965
- maxTokens: 262144,
8307
+ maxTokens: 4096,
7966
8308
  },
7967
8309
  "google/gemma-4-26b-a4b-it:free": {
7968
8310
  id: "google/gemma-4-26b-a4b-it:free",
@@ -7992,7 +8334,7 @@ export const MODELS = {
7992
8334
  cost: {
7993
8335
  input: 0.13,
7994
8336
  output: 0.38,
7995
- cacheRead: 0.019999999499999997,
8337
+ cacheRead: 0,
7996
8338
  cacheWrite: 0,
7997
8339
  },
7998
8340
  contextWindow: 262144,
@@ -8721,13 +9063,13 @@ export const MODELS = {
8721
9063
  reasoning: true,
8722
9064
  input: ["text", "image"],
8723
9065
  cost: {
8724
- input: 0.7999999999999999,
9066
+ input: 0.75,
8725
9067
  output: 3.5,
8726
- cacheRead: 0.19999999999999998,
9068
+ cacheRead: 0.15,
8727
9069
  cacheWrite: 0,
8728
9070
  },
8729
9071
  contextWindow: 262144,
8730
- maxTokens: 262144,
9072
+ maxTokens: 4096,
8731
9073
  },
8732
9074
  "nex-agi/deepseek-v3.1-nex-n1": {
8733
9075
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10064,13 +10406,13 @@ export const MODELS = {
10064
10406
  reasoning: true,
10065
10407
  input: ["text"],
10066
10408
  cost: {
10067
- input: 0.13,
10068
- output: 0.6,
10409
+ input: 0.14950000000000002,
10410
+ output: 1.495,
10069
10411
  cacheRead: 0,
10070
10412
  cacheWrite: 0,
10071
10413
  },
10072
- contextWindow: 262144,
10073
- maxTokens: 262144,
10414
+ contextWindow: 131072,
10415
+ maxTokens: 4096,
10074
10416
  },
10075
10417
  "qwen/qwen3-30b-a3b": {
10076
10418
  id: "qwen/qwen3-30b-a3b",
@@ -10973,6 +11315,40 @@ export const MODELS = {
10973
11315
  contextWindow: 1048576,
10974
11316
  maxTokens: 131072,
10975
11317
  },
11318
+ "xiaomi/mimo-v2.5": {
11319
+ id: "xiaomi/mimo-v2.5",
11320
+ name: "Xiaomi: MiMo-V2.5",
11321
+ api: "openai-completions",
11322
+ provider: "openrouter",
11323
+ baseUrl: "https://openrouter.ai/api/v1",
11324
+ reasoning: true,
11325
+ input: ["text", "image"],
11326
+ cost: {
11327
+ input: 0.39999999999999997,
11328
+ output: 2,
11329
+ cacheRead: 0.08,
11330
+ cacheWrite: 0,
11331
+ },
11332
+ contextWindow: 1048576,
11333
+ maxTokens: 131072,
11334
+ },
11335
+ "xiaomi/mimo-v2.5-pro": {
11336
+ id: "xiaomi/mimo-v2.5-pro",
11337
+ name: "Xiaomi: MiMo-V2.5-Pro",
11338
+ api: "openai-completions",
11339
+ provider: "openrouter",
11340
+ baseUrl: "https://openrouter.ai/api/v1",
11341
+ reasoning: true,
11342
+ input: ["text"],
11343
+ cost: {
11344
+ input: 1,
11345
+ output: 3,
11346
+ cacheRead: 0.19999999999999998,
11347
+ cacheWrite: 0,
11348
+ },
11349
+ contextWindow: 1048576,
11350
+ maxTokens: 131072,
11351
+ },
10976
11352
  "z-ai/glm-4-32b": {
10977
11353
  id: "z-ai/glm-4-32b",
10978
11354
  name: "Z.ai: GLM 4 32B ",
@@ -11497,7 +11873,7 @@ export const MODELS = {
11497
11873
  input: 0.5,
11498
11874
  output: 3,
11499
11875
  cacheRead: 0.09999999999999999,
11500
- cacheWrite: 0,
11876
+ cacheWrite: 0.625,
11501
11877
  },
11502
11878
  contextWindow: 1000000,
11503
11879
  maxTokens: 64000,
@@ -13619,9 +13995,9 @@ export const MODELS = {
13619
13995
  reasoning: true,
13620
13996
  input: ["text"],
13621
13997
  cost: {
13622
- input: 0.09,
13623
- output: 0.29,
13624
- cacheRead: 0.045,
13998
+ input: 0.09999999999999999,
13999
+ output: 0.3,
14000
+ cacheRead: 0.01,
13625
14001
  cacheWrite: 0,
13626
14002
  },
13627
14003
  contextWindow: 262144,
@@ -13838,15 +14214,15 @@ export const MODELS = {
13838
14214
  provider: "vercel-ai-gateway",
13839
14215
  baseUrl: "https://ai-gateway.vercel.sh",
13840
14216
  reasoning: true,
13841
- input: ["text", "image"],
14217
+ input: ["text"],
13842
14218
  cost: {
13843
14219
  input: 1.4,
13844
14220
  output: 4.4,
13845
14221
  cacheRead: 0.26,
13846
14222
  cacheWrite: 0,
13847
14223
  },
13848
- contextWindow: 202752,
13849
- maxTokens: 202752,
14224
+ contextWindow: 202800,
14225
+ maxTokens: 64000,
13850
14226
  },
13851
14227
  "zai/glm-5v-turbo": {
13852
14228
  id: "zai/glm-5v-turbo",