@dreb/ai 2.29.0 → 2.30.1

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.
@@ -3217,25 +3217,6 @@ export const MODELS = {
3217
3217
  contextWindow: 400000,
3218
3218
  maxTokens: 128000,
3219
3219
  },
3220
- "raptor-mini": {
3221
- id: "raptor-mini",
3222
- name: "Raptor mini",
3223
- api: "openai-completions",
3224
- provider: "github-copilot",
3225
- baseUrl: "https://api.individual.githubcopilot.com",
3226
- 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" },
3227
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3228
- reasoning: true,
3229
- input: ["text", "image"],
3230
- cost: {
3231
- input: 0.25,
3232
- output: 2,
3233
- cacheRead: 0.025,
3234
- cacheWrite: 0,
3235
- },
3236
- contextWindow: 400000,
3237
- maxTokens: 128000,
3238
- },
3239
3220
  },
3240
3221
  "google": {
3241
3222
  "gemini-2.0-flash": {
@@ -6825,26 +6806,26 @@ export const MODELS = {
6825
6806
  contextWindow: 1000000,
6826
6807
  maxTokens: 384000,
6827
6808
  },
6828
- "glm-5": {
6829
- id: "glm-5",
6830
- name: "GLM-5",
6809
+ "glm-5.1": {
6810
+ id: "glm-5.1",
6811
+ name: "GLM-5.1",
6831
6812
  api: "openai-completions",
6832
6813
  provider: "opencode-go",
6833
6814
  baseUrl: "https://opencode.ai/zen/go/v1",
6834
6815
  reasoning: true,
6835
6816
  input: ["text"],
6836
6817
  cost: {
6837
- input: 1,
6838
- output: 3.2,
6839
- cacheRead: 0.2,
6818
+ input: 1.4,
6819
+ output: 4.4,
6820
+ cacheRead: 0.26,
6840
6821
  cacheWrite: 0,
6841
6822
  },
6842
6823
  contextWindow: 202752,
6843
6824
  maxTokens: 32768,
6844
6825
  },
6845
- "glm-5.1": {
6846
- id: "glm-5.1",
6847
- name: "GLM-5.1",
6826
+ "glm-5.2": {
6827
+ id: "glm-5.2",
6828
+ name: "GLM-5.2",
6848
6829
  api: "openai-completions",
6849
6830
  provider: "opencode-go",
6850
6831
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -6856,8 +6837,8 @@ export const MODELS = {
6856
6837
  cacheRead: 0.26,
6857
6838
  cacheWrite: 0,
6858
6839
  },
6859
- contextWindow: 202752,
6860
- maxTokens: 32768,
6840
+ contextWindow: 1000000,
6841
+ maxTokens: 131072,
6861
6842
  },
6862
6843
  "kimi-k2.6": {
6863
6844
  id: "kimi-k2.6",
@@ -7558,6 +7539,23 @@ export const MODELS = {
7558
7539
  contextWindow: 128000,
7559
7540
  maxTokens: 4000,
7560
7541
  },
7542
+ "cohere/north-mini-code:free": {
7543
+ id: "cohere/north-mini-code:free",
7544
+ name: "Cohere: North Mini Code (free)",
7545
+ api: "openai-completions",
7546
+ provider: "openrouter",
7547
+ baseUrl: "https://openrouter.ai/api/v1",
7548
+ reasoning: true,
7549
+ input: ["text"],
7550
+ cost: {
7551
+ input: 0,
7552
+ output: 0,
7553
+ cacheRead: 0,
7554
+ cacheWrite: 0,
7555
+ },
7556
+ contextWindow: 256000,
7557
+ maxTokens: 64000,
7558
+ },
7561
7559
  "deepseek/deepseek-chat": {
7562
7560
  id: "deepseek/deepseek-chat",
7563
7561
  name: "DeepSeek: DeepSeek V3",
@@ -7703,13 +7701,13 @@ export const MODELS = {
7703
7701
  reasoning: true,
7704
7702
  input: ["text"],
7705
7703
  cost: {
7706
- input: 0.098,
7707
- output: 0.196,
7704
+ input: 0.09,
7705
+ output: 0.18,
7708
7706
  cacheRead: 0.02,
7709
7707
  cacheWrite: 0,
7710
7708
  },
7711
7709
  contextWindow: 1048576,
7712
- maxTokens: 4096,
7710
+ maxTokens: 65536,
7713
7711
  },
7714
7712
  "deepseek/deepseek-v4-pro": {
7715
7713
  id: "deepseek/deepseek-v4-pro",
@@ -7862,7 +7860,24 @@ export const MODELS = {
7862
7860
  cacheWrite: 0.08333333333333334,
7863
7861
  },
7864
7862
  contextWindow: 1048576,
7865
- maxTokens: 65536,
7863
+ maxTokens: 65535,
7864
+ },
7865
+ "google/gemini-3-pro-image": {
7866
+ id: "google/gemini-3-pro-image",
7867
+ name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
7868
+ api: "openai-completions",
7869
+ provider: "openrouter",
7870
+ baseUrl: "https://openrouter.ai/api/v1",
7871
+ reasoning: true,
7872
+ input: ["text", "image"],
7873
+ cost: {
7874
+ input: 2,
7875
+ output: 12,
7876
+ cacheRead: 0.19999999999999998,
7877
+ cacheWrite: 0.375,
7878
+ },
7879
+ contextWindow: 65536,
7880
+ maxTokens: 32768,
7866
7881
  },
7867
7882
  "google/gemini-3.1-flash-lite": {
7868
7883
  id: "google/gemini-3.1-flash-lite",
@@ -8049,7 +8064,7 @@ export const MODELS = {
8049
8064
  cacheWrite: 0,
8050
8065
  },
8051
8066
  contextWindow: 262144,
8052
- maxTokens: 32768,
8067
+ maxTokens: 8192,
8053
8068
  },
8054
8069
  "ibm-granite/granite-4.1-8b": {
8055
8070
  id: "ibm-granite/granite-4.1-8b",
@@ -8153,6 +8168,23 @@ export const MODELS = {
8153
8168
  contextWindow: 256000,
8154
8169
  maxTokens: 80000,
8155
8170
  },
8171
+ "liquid/lfm-2.5-1.2b-thinking:free": {
8172
+ id: "liquid/lfm-2.5-1.2b-thinking:free",
8173
+ name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
8174
+ api: "openai-completions",
8175
+ provider: "openrouter",
8176
+ baseUrl: "https://openrouter.ai/api/v1",
8177
+ reasoning: true,
8178
+ input: ["text"],
8179
+ cost: {
8180
+ input: 0,
8181
+ output: 0,
8182
+ cacheRead: 0,
8183
+ cacheWrite: 0,
8184
+ },
8185
+ contextWindow: 32768,
8186
+ maxTokens: 4096,
8187
+ },
8156
8188
  "meta-llama/llama-3.1-70b-instruct": {
8157
8189
  id: "meta-llama/llama-3.1-70b-instruct",
8158
8190
  name: "Meta: Llama 3.1 70B Instruct",
@@ -8723,13 +8755,13 @@ export const MODELS = {
8723
8755
  reasoning: true,
8724
8756
  input: ["text", "image"],
8725
8757
  cost: {
8726
- input: 0.6799999999999999,
8727
- output: 3.41,
8728
- cacheRead: 0.33999999999999997,
8758
+ input: 0.67,
8759
+ output: 3.5,
8760
+ cacheRead: 0.19999999999999998,
8729
8761
  cacheWrite: 0,
8730
8762
  },
8731
8763
  contextWindow: 262144,
8732
- maxTokens: 262142,
8764
+ maxTokens: 262144,
8733
8765
  },
8734
8766
  "moonshotai/kimi-k2.7-code": {
8735
8767
  id: "moonshotai/kimi-k2.7-code",
@@ -8740,9 +8772,9 @@ export const MODELS = {
8740
8772
  reasoning: true,
8741
8773
  input: ["text", "image"],
8742
8774
  cost: {
8743
- input: 0.75,
8744
- output: 3.5,
8745
- cacheRead: 0.16,
8775
+ input: 0.6799999999999999,
8776
+ output: 3.41,
8777
+ cacheRead: 0.144,
8746
8778
  cacheWrite: 0,
8747
8779
  },
8748
8780
  contextWindow: 262144,
@@ -8877,8 +8909,8 @@ export const MODELS = {
8877
8909
  input: ["text"],
8878
8910
  cost: {
8879
8911
  input: 0.5,
8880
- output: 2.5,
8881
- cacheRead: 0.15,
8912
+ output: 2.2,
8913
+ cacheRead: 0.09999999999999999,
8882
8914
  cacheWrite: 0,
8883
8915
  },
8884
8916
  contextWindow: 1000000,
@@ -9681,7 +9713,7 @@ export const MODELS = {
9681
9713
  cacheWrite: 0,
9682
9714
  },
9683
9715
  contextWindow: 131072,
9684
- maxTokens: 8192,
9716
+ maxTokens: 32768,
9685
9717
  },
9686
9718
  "openai/gpt-oss-safeguard-20b": {
9687
9719
  id: "openai/gpt-oss-safeguard-20b",
@@ -9694,7 +9726,7 @@ export const MODELS = {
9694
9726
  cost: {
9695
9727
  input: 0.075,
9696
9728
  output: 0.3,
9697
- cacheRead: 0.037,
9729
+ cacheRead: 0.0375,
9698
9730
  cacheWrite: 0,
9699
9731
  },
9700
9732
  contextWindow: 131072,
@@ -9904,6 +9936,23 @@ export const MODELS = {
9904
9936
  contextWindow: 1048756,
9905
9937
  maxTokens: 262144,
9906
9938
  },
9939
+ "poolside/laguna-m.1": {
9940
+ id: "poolside/laguna-m.1",
9941
+ name: "Poolside: Laguna M.1",
9942
+ api: "openai-completions",
9943
+ provider: "openrouter",
9944
+ baseUrl: "https://openrouter.ai/api/v1",
9945
+ reasoning: true,
9946
+ input: ["text"],
9947
+ cost: {
9948
+ input: 0.19999999999999998,
9949
+ output: 0.39999999999999997,
9950
+ cacheRead: 0.09999999999999999,
9951
+ cacheWrite: 0,
9952
+ },
9953
+ contextWindow: 262144,
9954
+ maxTokens: 32768,
9955
+ },
9907
9956
  "poolside/laguna-m.1:free": {
9908
9957
  id: "poolside/laguna-m.1:free",
9909
9958
  name: "Poolside: Laguna M.1 (free)",
@@ -9921,6 +9970,23 @@ export const MODELS = {
9921
9970
  contextWindow: 262144,
9922
9971
  maxTokens: 32768,
9923
9972
  },
9973
+ "poolside/laguna-xs.2": {
9974
+ id: "poolside/laguna-xs.2",
9975
+ name: "Poolside: Laguna XS.2",
9976
+ api: "openai-completions",
9977
+ provider: "openrouter",
9978
+ baseUrl: "https://openrouter.ai/api/v1",
9979
+ reasoning: true,
9980
+ input: ["text"],
9981
+ cost: {
9982
+ input: 0.09999999999999999,
9983
+ output: 0.19999999999999998,
9984
+ cacheRead: 0.049999999999999996,
9985
+ cacheWrite: 0,
9986
+ },
9987
+ contextWindow: 262144,
9988
+ maxTokens: 32768,
9989
+ },
9924
9990
  "poolside/laguna-xs.2:free": {
9925
9991
  id: "poolside/laguna-xs.2:free",
9926
9992
  name: "Poolside: Laguna XS.2 (free)",
@@ -9972,6 +10038,23 @@ export const MODELS = {
9972
10038
  contextWindow: 131072,
9973
10039
  maxTokens: 16384,
9974
10040
  },
10041
+ "qwen/qwen-2.5-7b-instruct": {
10042
+ id: "qwen/qwen-2.5-7b-instruct",
10043
+ name: "Qwen: Qwen2.5 7B Instruct",
10044
+ api: "openai-completions",
10045
+ provider: "openrouter",
10046
+ baseUrl: "https://openrouter.ai/api/v1",
10047
+ reasoning: false,
10048
+ input: ["text"],
10049
+ cost: {
10050
+ input: 0.04,
10051
+ output: 0.09999999999999999,
10052
+ cacheRead: 0,
10053
+ cacheWrite: 0,
10054
+ },
10055
+ contextWindow: 131072,
10056
+ maxTokens: 32768,
10057
+ },
9975
10058
  "qwen/qwen-plus": {
9976
10059
  id: "qwen/qwen-plus",
9977
10060
  name: "Qwen: Qwen-Plus",
@@ -10527,7 +10610,7 @@ export const MODELS = {
10527
10610
  cost: {
10528
10611
  input: 0.14,
10529
10612
  output: 1,
10530
- cacheRead: 0.049999999999999996,
10613
+ cacheRead: 0,
10531
10614
  cacheWrite: 0,
10532
10615
  },
10533
10616
  contextWindow: 262144,
@@ -10542,13 +10625,13 @@ export const MODELS = {
10542
10625
  reasoning: true,
10543
10626
  input: ["text", "image"],
10544
10627
  cost: {
10545
- input: 0.39,
10546
- output: 2.34,
10628
+ input: 0.385,
10629
+ output: 2.4499999999999997,
10547
10630
  cacheRead: 0,
10548
10631
  cacheWrite: 0,
10549
10632
  },
10550
- contextWindow: 262144,
10551
- maxTokens: 65536,
10633
+ contextWindow: 256000,
10634
+ maxTokens: 4096,
10552
10635
  },
10553
10636
  "qwen/qwen3.5-9b": {
10554
10637
  id: "qwen/qwen3.5-9b",
@@ -10644,9 +10727,9 @@ export const MODELS = {
10644
10727
  reasoning: true,
10645
10728
  input: ["text", "image"],
10646
10729
  cost: {
10647
- input: 0.15,
10730
+ input: 0.14,
10648
10731
  output: 1,
10649
- cacheRead: 0.049999999999999996,
10732
+ cacheRead: 0,
10650
10733
  cacheWrite: 0,
10651
10734
  },
10652
10735
  contextWindow: 262144,
@@ -10831,13 +10914,13 @@ export const MODELS = {
10831
10914
  reasoning: true,
10832
10915
  input: ["text"],
10833
10916
  cost: {
10834
- input: 0.063,
10835
- output: 0.21,
10836
- cacheRead: 0.020999999999999998,
10917
+ input: 0.06599999999999999,
10918
+ output: 0.26,
10919
+ cacheRead: 0.029,
10837
10920
  cacheWrite: 0,
10838
10921
  },
10839
10922
  contextWindow: 262144,
10840
- maxTokens: 4096,
10923
+ maxTokens: 262144,
10841
10924
  },
10842
10925
  "thedrummer/rocinante-12b": {
10843
10926
  id: "thedrummer/rocinante-12b",
@@ -10941,23 +11024,6 @@ export const MODELS = {
10941
11024
  contextWindow: 256000,
10942
11025
  maxTokens: 4096,
10943
11026
  },
10944
- "xiaomi/mimo-v2-flash": {
10945
- id: "xiaomi/mimo-v2-flash",
10946
- name: "Xiaomi: MiMo-V2-Flash",
10947
- api: "openai-completions",
10948
- provider: "openrouter",
10949
- baseUrl: "https://openrouter.ai/api/v1",
10950
- reasoning: true,
10951
- input: ["text"],
10952
- cost: {
10953
- input: 0.09999999999999999,
10954
- output: 0.3,
10955
- cacheRead: 0.01,
10956
- cacheWrite: 0,
10957
- },
10958
- contextWindow: 262144,
10959
- maxTokens: 65536,
10960
- },
10961
11027
  "xiaomi/mimo-v2.5": {
10962
11028
  id: "xiaomi/mimo-v2.5",
10963
11029
  name: "Xiaomi: MiMo-V2.5",
@@ -11018,13 +11084,13 @@ export const MODELS = {
11018
11084
  reasoning: true,
11019
11085
  input: ["text"],
11020
11086
  cost: {
11021
- input: 0.125,
11087
+ input: 0.13,
11022
11088
  output: 0.85,
11023
- cacheRead: 0.06,
11089
+ cacheRead: 0.024999999999999998,
11024
11090
  cacheWrite: 0,
11025
11091
  },
11026
11092
  contextWindow: 131072,
11027
- maxTokens: 131070,
11093
+ maxTokens: 98304,
11028
11094
  },
11029
11095
  "z-ai/glm-4.5v": {
11030
11096
  id: "z-ai/glm-4.5v",
@@ -11162,6 +11228,23 @@ export const MODELS = {
11162
11228
  contextWindow: 202752,
11163
11229
  maxTokens: 4096,
11164
11230
  },
11231
+ "z-ai/glm-5.2": {
11232
+ id: "z-ai/glm-5.2",
11233
+ name: "Z.ai: GLM 5.2",
11234
+ api: "openai-completions",
11235
+ provider: "openrouter",
11236
+ baseUrl: "https://openrouter.ai/api/v1",
11237
+ reasoning: true,
11238
+ input: ["text"],
11239
+ cost: {
11240
+ input: 1.2,
11241
+ output: 4.1,
11242
+ cacheRead: 0.19999999999999998,
11243
+ cacheWrite: 0,
11244
+ },
11245
+ contextWindow: 1048576,
11246
+ maxTokens: 131072,
11247
+ },
11165
11248
  "~anthropic/claude-fable-latest": {
11166
11249
  id: "~anthropic/claude-fable-latest",
11167
11250
  name: "Anthropic: Claude Fable Latest",
@@ -11273,13 +11356,13 @@ export const MODELS = {
11273
11356
  reasoning: true,
11274
11357
  input: ["text", "image"],
11275
11358
  cost: {
11276
- input: 0.6799999999999999,
11277
- output: 3.41,
11278
- cacheRead: 0.33999999999999997,
11359
+ input: 0.67,
11360
+ output: 3.5,
11361
+ cacheRead: 0.19999999999999998,
11279
11362
  cacheWrite: 0,
11280
11363
  },
11281
11364
  contextWindow: 262144,
11282
- maxTokens: 262142,
11365
+ maxTokens: 262144,
11283
11366
  },
11284
11367
  "~openai/gpt-latest": {
11285
11368
  id: "~openai/gpt-latest",
@@ -12754,13 +12837,13 @@ export const MODELS = {
12754
12837
  reasoning: false,
12755
12838
  input: ["text"],
12756
12839
  cost: {
12757
- input: 0.02,
12758
- output: 0.04,
12840
+ input: 0.15,
12841
+ output: 0.15,
12759
12842
  cacheRead: 0,
12760
12843
  cacheWrite: 0,
12761
12844
  },
12762
- contextWindow: 131072,
12763
- maxTokens: 131072,
12845
+ contextWindow: 128000,
12846
+ maxTokens: 128000,
12764
12847
  },
12765
12848
  "mistral/mistral-small": {
12766
12849
  id: "mistral/mistral-small",
@@ -12913,7 +12996,7 @@ export const MODELS = {
12913
12996
  cacheWrite: 0,
12914
12997
  },
12915
12998
  contextWindow: 262144,
12916
- maxTokens: 4096,
12999
+ maxTokens: 32768,
12917
13000
  },
12918
13001
  "nvidia/nemotron-3-super-120b-a12b": {
12919
13002
  id: "nvidia/nemotron-3-super-120b-a12b",
@@ -14139,6 +14222,23 @@ export const MODELS = {
14139
14222
  contextWindow: 202800,
14140
14223
  maxTokens: 64000,
14141
14224
  },
14225
+ "zai/glm-5.2": {
14226
+ id: "zai/glm-5.2",
14227
+ name: "GLM 5.2",
14228
+ api: "anthropic-messages",
14229
+ provider: "vercel-ai-gateway",
14230
+ baseUrl: "https://ai-gateway.vercel.sh",
14231
+ reasoning: true,
14232
+ input: ["text"],
14233
+ cost: {
14234
+ input: 1.5,
14235
+ output: 4.5,
14236
+ cacheRead: 0.3,
14237
+ cacheWrite: 0,
14238
+ },
14239
+ contextWindow: 1000000,
14240
+ maxTokens: 128000,
14241
+ },
14142
14242
  "zai/glm-5v-turbo": {
14143
14243
  id: "zai/glm-5v-turbo",
14144
14244
  name: "GLM 5V Turbo",