@dreb/ai 2.11.0 → 2.12.0

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.
@@ -3234,7 +3234,7 @@ export const MODELS = {
3234
3234
  cost: {
3235
3235
  input: 0.3,
3236
3236
  output: 2.5,
3237
- cacheRead: 0.075,
3237
+ cacheRead: 0.03,
3238
3238
  cacheWrite: 0,
3239
3239
  },
3240
3240
  contextWindow: 1048576,
@@ -3353,7 +3353,7 @@ export const MODELS = {
3353
3353
  cost: {
3354
3354
  input: 1.25,
3355
3355
  output: 10,
3356
- cacheRead: 0.31,
3356
+ cacheRead: 0.125,
3357
3357
  cacheWrite: 0,
3358
3358
  },
3359
3359
  contextWindow: 1048576,
@@ -4660,6 +4660,24 @@ export const MODELS = {
4660
4660
  contextWindow: 262144,
4661
4661
  maxTokens: 262144,
4662
4662
  },
4663
+ "moonshotai/Kimi-K2.6": {
4664
+ id: "moonshotai/Kimi-K2.6",
4665
+ name: "Kimi-K2.6",
4666
+ api: "openai-completions",
4667
+ provider: "huggingface",
4668
+ baseUrl: "https://router.huggingface.co/v1",
4669
+ compat: { "supportsDeveloperRole": false },
4670
+ reasoning: true,
4671
+ input: ["text", "image"],
4672
+ cost: {
4673
+ input: 0.95,
4674
+ output: 4,
4675
+ cacheRead: 0.16,
4676
+ cacheWrite: 0,
4677
+ },
4678
+ contextWindow: 262144,
4679
+ maxTokens: 262144,
4680
+ },
4663
4681
  "zai-org/GLM-4.7": {
4664
4682
  id: "zai-org/GLM-4.7",
4665
4683
  name: "GLM-4.7",
@@ -4751,6 +4769,23 @@ export const MODELS = {
4751
4769
  contextWindow: 262144,
4752
4770
  maxTokens: 32768,
4753
4771
  },
4772
+ "k2p6": {
4773
+ id: "k2p6",
4774
+ name: "Kimi K2.6",
4775
+ api: "anthropic-messages",
4776
+ provider: "kimi-coding",
4777
+ baseUrl: "https://api.kimi.com/coding",
4778
+ reasoning: true,
4779
+ input: ["text", "image"],
4780
+ cost: {
4781
+ input: 0,
4782
+ output: 0,
4783
+ cacheRead: 0,
4784
+ cacheWrite: 0,
4785
+ },
4786
+ contextWindow: 262144,
4787
+ maxTokens: 32768,
4788
+ },
4754
4789
  "kimi-k2-thinking": {
4755
4790
  id: "kimi-k2-thinking",
4756
4791
  name: "Kimi K2 Thinking",
@@ -6636,6 +6671,40 @@ export const MODELS = {
6636
6671
  contextWindow: 262144,
6637
6672
  maxTokens: 65536,
6638
6673
  },
6674
+ "kimi-k2.6": {
6675
+ id: "kimi-k2.6",
6676
+ name: "Kimi K2.6",
6677
+ api: "openai-completions",
6678
+ provider: "opencode",
6679
+ baseUrl: "https://opencode.ai/zen/v1",
6680
+ reasoning: true,
6681
+ input: ["text", "image"],
6682
+ cost: {
6683
+ input: 0.95,
6684
+ output: 4,
6685
+ cacheRead: 0.16,
6686
+ cacheWrite: 0,
6687
+ },
6688
+ contextWindow: 262144,
6689
+ maxTokens: 65536,
6690
+ },
6691
+ "ling-2.6-flash-free": {
6692
+ id: "ling-2.6-flash-free",
6693
+ name: "Ling 2.6 Flash Free",
6694
+ api: "openai-completions",
6695
+ provider: "opencode",
6696
+ baseUrl: "https://opencode.ai/zen/v1",
6697
+ reasoning: false,
6698
+ input: ["text"],
6699
+ cost: {
6700
+ input: 0,
6701
+ output: 0,
6702
+ cacheRead: 0,
6703
+ cacheWrite: 0,
6704
+ },
6705
+ contextWindow: 262100,
6706
+ maxTokens: 32800,
6707
+ },
6639
6708
  "minimax-m2.5": {
6640
6709
  id: "minimax-m2.5",
6641
6710
  name: "MiniMax M2.5",
@@ -6670,6 +6739,23 @@ export const MODELS = {
6670
6739
  contextWindow: 204800,
6671
6740
  maxTokens: 131072,
6672
6741
  },
6742
+ "minimax-m2.7": {
6743
+ id: "minimax-m2.7",
6744
+ name: "MiniMax M2.7",
6745
+ api: "openai-completions",
6746
+ provider: "opencode",
6747
+ baseUrl: "https://opencode.ai/zen/v1",
6748
+ reasoning: true,
6749
+ input: ["text"],
6750
+ cost: {
6751
+ input: 0.3,
6752
+ output: 1.2,
6753
+ cacheRead: 0.06,
6754
+ cacheWrite: 0,
6755
+ },
6756
+ contextWindow: 204800,
6757
+ maxTokens: 131072,
6758
+ },
6673
6759
  "nemotron-3-super-free": {
6674
6760
  id: "nemotron-3-super-free",
6675
6761
  name: "Nemotron 3 Super Free",
@@ -6774,6 +6860,23 @@ export const MODELS = {
6774
6860
  contextWindow: 262144,
6775
6861
  maxTokens: 65536,
6776
6862
  },
6863
+ "kimi-k2.6": {
6864
+ id: "kimi-k2.6",
6865
+ name: "Kimi K2.6 (3x limits)",
6866
+ api: "openai-completions",
6867
+ provider: "opencode-go",
6868
+ baseUrl: "https://opencode.ai/zen/go/v1",
6869
+ reasoning: true,
6870
+ input: ["text", "image"],
6871
+ cost: {
6872
+ input: 0.32,
6873
+ output: 1.34,
6874
+ cacheRead: 0.054,
6875
+ cacheWrite: 0,
6876
+ },
6877
+ contextWindow: 262144,
6878
+ maxTokens: 65536,
6879
+ },
6777
6880
  "mimo-v2-omni": {
6778
6881
  id: "mimo-v2-omni",
6779
6882
  name: "MiMo V2 Omni",
@@ -6811,9 +6914,9 @@ export const MODELS = {
6811
6914
  "minimax-m2.5": {
6812
6915
  id: "minimax-m2.5",
6813
6916
  name: "MiniMax M2.5",
6814
- api: "anthropic-messages",
6917
+ api: "openai-completions",
6815
6918
  provider: "opencode-go",
6816
- baseUrl: "https://opencode.ai/zen/go",
6919
+ baseUrl: "https://opencode.ai/zen/go/v1",
6817
6920
  reasoning: true,
6818
6921
  input: ["text"],
6819
6922
  cost: {
@@ -6823,7 +6926,7 @@ export const MODELS = {
6823
6926
  cacheWrite: 0,
6824
6927
  },
6825
6928
  contextWindow: 204800,
6826
- maxTokens: 131072,
6929
+ maxTokens: 65536,
6827
6930
  },
6828
6931
  "minimax-m2.7": {
6829
6932
  id: "minimax-m2.7",
@@ -7584,13 +7687,13 @@ export const MODELS = {
7584
7687
  reasoning: true,
7585
7688
  input: ["text"],
7586
7689
  cost: {
7587
- input: 0.25899999999999995,
7588
- output: 0.42,
7589
- cacheRead: 0.135,
7690
+ input: 0.252,
7691
+ output: 0.378,
7692
+ cacheRead: 0.0252,
7590
7693
  cacheWrite: 0,
7591
7694
  },
7592
- contextWindow: 163840,
7593
- maxTokens: 163840,
7695
+ contextWindow: 131072,
7696
+ maxTokens: 32768,
7594
7697
  },
7595
7698
  "deepseek/deepseek-v3.2-exp": {
7596
7699
  id: "deepseek/deepseek-v3.2-exp",
@@ -7640,7 +7743,7 @@ export const MODELS = {
7640
7743
  cacheRead: 0.024999999999999998,
7641
7744
  cacheWrite: 0.08333333333333334,
7642
7745
  },
7643
- contextWindow: 1048576,
7746
+ contextWindow: 1000000,
7644
7747
  maxTokens: 8192,
7645
7748
  },
7646
7749
  "google/gemini-2.0-flash-lite-001": {
@@ -7839,13 +7942,13 @@ export const MODELS = {
7839
7942
  reasoning: true,
7840
7943
  input: ["text", "image"],
7841
7944
  cost: {
7842
- input: 0.08,
7945
+ input: 0.07,
7843
7946
  output: 0.35,
7844
- cacheRead: 0.01,
7947
+ cacheRead: 0.04,
7845
7948
  cacheWrite: 0,
7846
7949
  },
7847
7950
  contextWindow: 262144,
7848
- maxTokens: 4096,
7951
+ maxTokens: 262144,
7849
7952
  },
7850
7953
  "google/gemma-4-26b-a4b-it:free": {
7851
7954
  id: "google/gemma-4-26b-a4b-it:free",
@@ -7915,6 +8018,23 @@ export const MODELS = {
7915
8018
  contextWindow: 128000,
7916
8019
  maxTokens: 50000,
7917
8020
  },
8021
+ "inclusionai/ling-2.6-flash:free": {
8022
+ id: "inclusionai/ling-2.6-flash:free",
8023
+ name: "inclusionAI: Ling-2.6-flash (free)",
8024
+ api: "openai-completions",
8025
+ provider: "openrouter",
8026
+ baseUrl: "https://openrouter.ai/api/v1",
8027
+ reasoning: false,
8028
+ input: ["text"],
8029
+ cost: {
8030
+ input: 0,
8031
+ output: 0,
8032
+ cacheRead: 0,
8033
+ cacheWrite: 0,
8034
+ },
8035
+ contextWindow: 262144,
8036
+ maxTokens: 32768,
8037
+ },
7918
8038
  "kwaipilot/kat-coder-pro-v2": {
7919
8039
  id: "kwaipilot/kat-coder-pro-v2",
7920
8040
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -7992,13 +8112,13 @@ export const MODELS = {
7992
8112
  reasoning: false,
7993
8113
  input: ["text"],
7994
8114
  cost: {
7995
- input: 0.09999999999999999,
7996
- output: 0.32,
8115
+ input: 0.12,
8116
+ output: 0.38,
7997
8117
  cacheRead: 0,
7998
8118
  cacheWrite: 0,
7999
8119
  },
8000
8120
  contextWindow: 131072,
8001
- maxTokens: 16384,
8121
+ maxTokens: 131072,
8002
8122
  },
8003
8123
  "meta-llama/llama-3.3-70b-instruct:free": {
8004
8124
  id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -8017,23 +8137,6 @@ export const MODELS = {
8017
8137
  contextWindow: 65536,
8018
8138
  maxTokens: 4096,
8019
8139
  },
8020
- "meta-llama/llama-4-maverick": {
8021
- id: "meta-llama/llama-4-maverick",
8022
- name: "Meta: Llama 4 Maverick",
8023
- api: "openai-completions",
8024
- provider: "openrouter",
8025
- baseUrl: "https://openrouter.ai/api/v1",
8026
- reasoning: false,
8027
- input: ["text", "image"],
8028
- cost: {
8029
- input: 0.15,
8030
- output: 0.6,
8031
- cacheRead: 0,
8032
- cacheWrite: 0,
8033
- },
8034
- contextWindow: 1048576,
8035
- maxTokens: 16384,
8036
- },
8037
8140
  "meta-llama/llama-4-scout": {
8038
8141
  id: "meta-llama/llama-4-scout",
8039
8142
  name: "Meta: Llama 4 Scout",
@@ -8111,9 +8214,9 @@ export const MODELS = {
8111
8214
  reasoning: true,
8112
8215
  input: ["text"],
8113
8216
  cost: {
8114
- input: 0.118,
8115
- output: 0.9900000000000001,
8116
- cacheRead: 0.059,
8217
+ input: 0.15,
8218
+ output: 1.2,
8219
+ cacheRead: 0.075,
8117
8220
  cacheWrite: 0,
8118
8221
  },
8119
8222
  contextWindow: 196608,
@@ -8592,9 +8695,26 @@ export const MODELS = {
8592
8695
  cacheRead: 0.07,
8593
8696
  cacheWrite: 0,
8594
8697
  },
8595
- contextWindow: 256000,
8698
+ contextWindow: 262144,
8596
8699
  maxTokens: 4096,
8597
8700
  },
8701
+ "moonshotai/kimi-k2.6": {
8702
+ id: "moonshotai/kimi-k2.6",
8703
+ name: "MoonshotAI: Kimi K2.6",
8704
+ api: "openai-completions",
8705
+ provider: "openrouter",
8706
+ baseUrl: "https://openrouter.ai/api/v1",
8707
+ reasoning: true,
8708
+ input: ["text", "image"],
8709
+ cost: {
8710
+ input: 0.6,
8711
+ output: 2.8,
8712
+ cacheRead: 0.19999999999999998,
8713
+ cacheWrite: 0,
8714
+ },
8715
+ contextWindow: 262144,
8716
+ maxTokens: 262144,
8717
+ },
8598
8718
  "nex-agi/deepseek-v3.1-nex-n1": {
8599
8719
  id: "nex-agi/deepseek-v3.1-nex-n1",
8600
8720
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -9071,23 +9191,6 @@ export const MODELS = {
9071
9191
  contextWindow: 128000,
9072
9192
  maxTokens: 16384,
9073
9193
  },
9074
- "openai/gpt-4o:extended": {
9075
- id: "openai/gpt-4o:extended",
9076
- name: "OpenAI: GPT-4o (extended)",
9077
- api: "openai-completions",
9078
- provider: "openrouter",
9079
- baseUrl: "https://openrouter.ai/api/v1",
9080
- reasoning: false,
9081
- input: ["text", "image"],
9082
- cost: {
9083
- input: 6,
9084
- output: 18,
9085
- cacheRead: 0,
9086
- cacheWrite: 0,
9087
- },
9088
- contextWindow: 128000,
9089
- maxTokens: 64000,
9090
- },
9091
9194
  "openai/gpt-5": {
9092
9195
  id: "openai/gpt-5",
9093
9196
  name: "OpenAI: GPT-5",
@@ -9751,23 +9854,6 @@ export const MODELS = {
9751
9854
  contextWindow: 2000000,
9752
9855
  maxTokens: 4096,
9753
9856
  },
9754
- "openrouter/elephant-alpha": {
9755
- id: "openrouter/elephant-alpha",
9756
- name: "Elephant",
9757
- api: "openai-completions",
9758
- provider: "openrouter",
9759
- baseUrl: "https://openrouter.ai/api/v1",
9760
- reasoning: false,
9761
- input: ["text"],
9762
- cost: {
9763
- input: 0,
9764
- output: 0,
9765
- cacheRead: 0,
9766
- cacheWrite: 0,
9767
- },
9768
- contextWindow: 262144,
9769
- maxTokens: 32768,
9770
- },
9771
9857
  "openrouter/free": {
9772
9858
  id: "openrouter/free",
9773
9859
  name: "Free Models Router",
@@ -9978,7 +10064,7 @@ export const MODELS = {
9978
10064
  api: "openai-completions",
9979
10065
  provider: "openrouter",
9980
10066
  baseUrl: "https://openrouter.ai/api/v1",
9981
- reasoning: true,
10067
+ reasoning: false,
9982
10068
  input: ["text"],
9983
10069
  cost: {
9984
10070
  input: 0.071,
@@ -10153,7 +10239,7 @@ export const MODELS = {
10153
10239
  cost: {
10154
10240
  input: 0.15,
10155
10241
  output: 0.7999999999999999,
10156
- cacheRead: 0.12,
10242
+ cacheRead: 0.11,
10157
10243
  cacheWrite: 0,
10158
10244
  },
10159
10245
  contextWindow: 262144,
@@ -11035,13 +11121,13 @@ export const MODELS = {
11035
11121
  reasoning: true,
11036
11122
  input: ["text"],
11037
11123
  cost: {
11038
- input: 0.39,
11039
- output: 1.75,
11040
- cacheRead: 0.195,
11124
+ input: 0.38,
11125
+ output: 1.74,
11126
+ cacheRead: 0,
11041
11127
  cacheWrite: 0,
11042
11128
  },
11043
11129
  contextWindow: 202752,
11044
- maxTokens: 65535,
11130
+ maxTokens: 4096,
11045
11131
  },
11046
11132
  "z-ai/glm-4.7-flash": {
11047
11133
  id: "z-ai/glm-4.7-flash",
@@ -11069,13 +11155,13 @@ export const MODELS = {
11069
11155
  reasoning: true,
11070
11156
  input: ["text"],
11071
11157
  cost: {
11072
- input: 0.72,
11073
- output: 2.3,
11074
- cacheRead: 0,
11158
+ input: 0.65,
11159
+ output: 2.08,
11160
+ cacheRead: 0.13,
11075
11161
  cacheWrite: 0,
11076
11162
  },
11077
- contextWindow: 80000,
11078
- maxTokens: 131072,
11163
+ contextWindow: 202752,
11164
+ maxTokens: 4096,
11079
11165
  },
11080
11166
  "z-ai/glm-5-turbo": {
11081
11167
  id: "z-ai/glm-5-turbo",
@@ -11103,9 +11189,9 @@ export const MODELS = {
11103
11189
  reasoning: true,
11104
11190
  input: ["text"],
11105
11191
  cost: {
11106
- input: 0.95,
11107
- output: 3.15,
11108
- cacheRead: 0.475,
11192
+ input: 1.0499999999999998,
11193
+ output: 3.5,
11194
+ cacheRead: 0.5249999999999999,
11109
11195
  cacheWrite: 0,
11110
11196
  },
11111
11197
  contextWindow: 202752,
@@ -11128,6 +11214,23 @@ export const MODELS = {
11128
11214
  contextWindow: 202752,
11129
11215
  maxTokens: 131072,
11130
11216
  },
11217
+ "~anthropic/claude-opus-latest": {
11218
+ id: "~anthropic/claude-opus-latest",
11219
+ name: "Anthropic: Claude Opus Latest",
11220
+ api: "openai-completions",
11221
+ provider: "openrouter",
11222
+ baseUrl: "https://openrouter.ai/api/v1",
11223
+ reasoning: true,
11224
+ input: ["text", "image"],
11225
+ cost: {
11226
+ input: 5,
11227
+ output: 25,
11228
+ cacheRead: 0.5,
11229
+ cacheWrite: 6.25,
11230
+ },
11231
+ contextWindow: 1000000,
11232
+ maxTokens: 128000,
11233
+ },
11131
11234
  },
11132
11235
  "vercel-ai-gateway": {
11133
11236
  "alibaba/qwen-3-14b": {
@@ -11198,6 +11301,23 @@ export const MODELS = {
11198
11301
  contextWindow: 128000,
11199
11302
  maxTokens: 8192,
11200
11303
  },
11304
+ "alibaba/qwen-3.6-max-preview": {
11305
+ id: "alibaba/qwen-3.6-max-preview",
11306
+ name: "Qwen 3.6 Max Preview",
11307
+ api: "anthropic-messages",
11308
+ provider: "vercel-ai-gateway",
11309
+ baseUrl: "https://ai-gateway.vercel.sh",
11310
+ reasoning: true,
11311
+ input: ["text", "image"],
11312
+ cost: {
11313
+ input: 1.3,
11314
+ output: 7.8,
11315
+ cacheRead: 0.26,
11316
+ cacheWrite: 1.625,
11317
+ },
11318
+ contextWindow: 240000,
11319
+ maxTokens: 64000,
11320
+ },
11201
11321
  "alibaba/qwen3-235b-a22b-thinking": {
11202
11322
  id: "alibaba/qwen3-235b-a22b-thinking",
11203
11323
  name: "Qwen3 235B A22B Thinking 2507",
@@ -12541,6 +12661,23 @@ export const MODELS = {
12541
12661
  contextWindow: 262114,
12542
12662
  maxTokens: 262114,
12543
12663
  },
12664
+ "moonshotai/kimi-k2.6": {
12665
+ id: "moonshotai/kimi-k2.6",
12666
+ name: "Kimi K2.6",
12667
+ api: "anthropic-messages",
12668
+ provider: "vercel-ai-gateway",
12669
+ baseUrl: "https://ai-gateway.vercel.sh",
12670
+ reasoning: true,
12671
+ input: ["text", "image"],
12672
+ cost: {
12673
+ input: 0.95,
12674
+ output: 4,
12675
+ cacheRead: 0.16,
12676
+ cacheWrite: 0,
12677
+ },
12678
+ contextWindow: 262000,
12679
+ maxTokens: 262000,
12680
+ },
12544
12681
  "nvidia/nemotron-nano-12b-v2-vl": {
12545
12682
  id: "nvidia/nemotron-nano-12b-v2-vl",
12546
12683
  name: "Nvidia Nemotron Nano 12B V2 VL",