@elyracode/ai 0.9.5 → 0.9.6

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.
@@ -8,7 +8,7 @@ export const MODELS = {
8
8
  api: "bedrock-converse-stream",
9
9
  provider: "amazon-bedrock",
10
10
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
11
- reasoning: false,
11
+ reasoning: true,
12
12
  input: ["text", "image"],
13
13
  cost: {
14
14
  input: 0.33,
@@ -1128,7 +1128,7 @@ export const MODELS = {
1128
1128
  api: "bedrock-converse-stream",
1129
1129
  provider: "amazon-bedrock",
1130
1130
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1131
- reasoning: false,
1131
+ reasoning: true,
1132
1132
  input: ["text"],
1133
1133
  cost: {
1134
1134
  input: 0.15,
@@ -1145,7 +1145,7 @@ export const MODELS = {
1145
1145
  api: "bedrock-converse-stream",
1146
1146
  provider: "amazon-bedrock",
1147
1147
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1148
- reasoning: false,
1148
+ reasoning: true,
1149
1149
  input: ["text"],
1150
1150
  cost: {
1151
1151
  input: 0.15,
@@ -1162,7 +1162,7 @@ export const MODELS = {
1162
1162
  api: "bedrock-converse-stream",
1163
1163
  provider: "amazon-bedrock",
1164
1164
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1165
- reasoning: false,
1165
+ reasoning: true,
1166
1166
  input: ["text"],
1167
1167
  cost: {
1168
1168
  input: 0.07,
@@ -1179,7 +1179,7 @@ export const MODELS = {
1179
1179
  api: "bedrock-converse-stream",
1180
1180
  provider: "amazon-bedrock",
1181
1181
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1182
- reasoning: false,
1182
+ reasoning: true,
1183
1183
  input: ["text"],
1184
1184
  cost: {
1185
1185
  input: 0.07,
@@ -1722,6 +1722,24 @@ export const MODELS = {
1722
1722
  contextWindow: 200000,
1723
1723
  maxTokens: 4096,
1724
1724
  },
1725
+ "claude-fable-5": {
1726
+ id: "claude-fable-5",
1727
+ name: "Claude Fable 5",
1728
+ api: "anthropic-messages",
1729
+ provider: "anthropic",
1730
+ baseUrl: "https://api.anthropic.com",
1731
+ reasoning: true,
1732
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1733
+ input: ["text", "image"],
1734
+ cost: {
1735
+ input: 10,
1736
+ output: 50,
1737
+ cacheRead: 1,
1738
+ cacheWrite: 12.5,
1739
+ },
1740
+ contextWindow: 1000000,
1741
+ maxTokens: 128000,
1742
+ },
1725
1743
  "claude-haiku-4-5": {
1726
1744
  id: "claude-haiku-4-5",
1727
1745
  name: "Claude Haiku 4.5 (latest)",
@@ -7834,26 +7852,26 @@ export const MODELS = {
7834
7852
  contextWindow: 204800,
7835
7853
  maxTokens: 131072,
7836
7854
  },
7837
- "minimax-m3-free": {
7838
- id: "minimax-m3-free",
7839
- name: "MiniMax M3 Free",
7840
- api: "anthropic-messages",
7855
+ "nemotron-3-ultra-free": {
7856
+ id: "nemotron-3-ultra-free",
7857
+ name: "Nemotron 3 Ultra Free",
7858
+ api: "openai-completions",
7841
7859
  provider: "opencode",
7842
- baseUrl: "https://opencode.ai/zen",
7860
+ baseUrl: "https://opencode.ai/zen/v1",
7843
7861
  reasoning: true,
7844
- input: ["text", "image"],
7862
+ input: ["text"],
7845
7863
  cost: {
7846
7864
  input: 0,
7847
7865
  output: 0,
7848
7866
  cacheRead: 0,
7849
7867
  cacheWrite: 0,
7850
7868
  },
7851
- contextWindow: 200000,
7852
- maxTokens: 32000,
7869
+ contextWindow: 1000000,
7870
+ maxTokens: 128000,
7853
7871
  },
7854
- "nemotron-3-ultra-free": {
7855
- id: "nemotron-3-ultra-free",
7856
- name: "Nemotron 3 Ultra Free",
7872
+ "north-mini-code-free": {
7873
+ id: "north-mini-code-free",
7874
+ name: "North Mini Code Free",
7857
7875
  api: "openai-completions",
7858
7876
  provider: "opencode",
7859
7877
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7865,8 +7883,8 @@ export const MODELS = {
7865
7883
  cacheRead: 0,
7866
7884
  cacheWrite: 0,
7867
7885
  },
7868
- contextWindow: 1000000,
7869
- maxTokens: 128000,
7886
+ contextWindow: 256000,
7887
+ maxTokens: 64000,
7870
7888
  },
7871
7889
  "qwen3.5-plus": {
7872
7890
  id: "qwen3.5-plus",
@@ -8087,9 +8105,9 @@ export const MODELS = {
8087
8105
  reasoning: true,
8088
8106
  input: ["text", "image"],
8089
8107
  cost: {
8090
- input: 0.6,
8091
- output: 2.4,
8092
- cacheRead: 0.12,
8108
+ input: 0.3,
8109
+ output: 1.2,
8110
+ cacheRead: 0.06,
8093
8111
  cacheWrite: 0,
8094
8112
  },
8095
8113
  contextWindow: 512000,
@@ -8268,6 +8286,24 @@ export const MODELS = {
8268
8286
  contextWindow: 200000,
8269
8287
  maxTokens: 4096,
8270
8288
  },
8289
+ "anthropic/claude-fable-5": {
8290
+ id: "anthropic/claude-fable-5",
8291
+ name: "Anthropic: Claude Fable 5",
8292
+ api: "openai-completions",
8293
+ provider: "openrouter",
8294
+ baseUrl: "https://openrouter.ai/api/v1",
8295
+ reasoning: true,
8296
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
8297
+ input: ["text", "image"],
8298
+ cost: {
8299
+ input: 10,
8300
+ output: 50,
8301
+ cacheRead: 1,
8302
+ cacheWrite: 12.5,
8303
+ },
8304
+ contextWindow: 1000000,
8305
+ maxTokens: 128000,
8306
+ },
8271
8307
  "anthropic/claude-haiku-4.5": {
8272
8308
  id: "anthropic/claude-haiku-4.5",
8273
8309
  name: "Anthropic: Claude Haiku 4.5",
@@ -9069,8 +9105,8 @@ export const MODELS = {
9069
9105
  reasoning: false,
9070
9106
  input: ["text", "image"],
9071
9107
  cost: {
9072
- input: 0.04,
9073
- output: 0.13,
9108
+ input: 0.049999999999999996,
9109
+ output: 0.15,
9074
9110
  cacheRead: 0,
9075
9111
  cacheWrite: 0,
9076
9112
  },
@@ -9358,7 +9394,7 @@ export const MODELS = {
9358
9394
  reasoning: false,
9359
9395
  input: ["text", "image"],
9360
9396
  cost: {
9361
- input: 0.08,
9397
+ input: 0.09999999999999999,
9362
9398
  output: 0.3,
9363
9399
  cacheRead: 0,
9364
9400
  cacheWrite: 0,
@@ -9427,8 +9463,8 @@ export const MODELS = {
9427
9463
  input: ["text"],
9428
9464
  cost: {
9429
9465
  input: 0.15,
9430
- output: 1.15,
9431
- cacheRead: 0,
9466
+ output: 0.8999999999999999,
9467
+ cacheRead: 0.049999999999999996,
9432
9468
  cacheWrite: 0,
9433
9469
  },
9434
9470
  contextWindow: 204800,
@@ -9443,13 +9479,13 @@ export const MODELS = {
9443
9479
  reasoning: true,
9444
9480
  input: ["text"],
9445
9481
  cost: {
9446
- input: 0.27899999999999997,
9447
- output: 1.2,
9448
- cacheRead: 0,
9482
+ input: 0.27,
9483
+ output: 1.08,
9484
+ cacheRead: 0.054,
9449
9485
  cacheWrite: 0,
9450
9486
  },
9451
9487
  contextWindow: 204800,
9452
- maxTokens: 196608,
9488
+ maxTokens: 131072,
9453
9489
  },
9454
9490
  "minimax/minimax-m3": {
9455
9491
  id: "minimax/minimax-m3",
@@ -9834,13 +9870,13 @@ export const MODELS = {
9834
9870
  reasoning: true,
9835
9871
  input: ["text", "image"],
9836
9872
  cost: {
9837
- input: 0.684,
9838
- output: 3.42,
9839
- cacheRead: 0.144,
9873
+ input: 0.6799999999999999,
9874
+ output: 3.41,
9875
+ cacheRead: 0.33999999999999997,
9840
9876
  cacheWrite: 0,
9841
9877
  },
9842
9878
  contextWindow: 262144,
9843
- maxTokens: 262144,
9879
+ maxTokens: 262142,
9844
9880
  },
9845
9881
  "moonshotai/kimi-k2.6:free": {
9846
9882
  id: "moonshotai/kimi-k2.6:free",
@@ -9859,22 +9895,22 @@ export const MODELS = {
9859
9895
  contextWindow: 262144,
9860
9896
  maxTokens: 4096,
9861
9897
  },
9862
- "nex-agi/deepseek-v3.1-nex-n1": {
9863
- id: "nex-agi/deepseek-v3.1-nex-n1",
9864
- name: "Nex AGI: DeepSeek V3.1 Nex N1",
9898
+ "nex-agi/nex-n2-pro:free": {
9899
+ id: "nex-agi/nex-n2-pro:free",
9900
+ name: "Nex AGI: Nex-N2-Pro (free)",
9865
9901
  api: "openai-completions",
9866
9902
  provider: "openrouter",
9867
9903
  baseUrl: "https://openrouter.ai/api/v1",
9868
- reasoning: false,
9869
- input: ["text"],
9904
+ reasoning: true,
9905
+ input: ["text", "image"],
9870
9906
  cost: {
9871
- input: 0.135,
9872
- output: 0.5,
9907
+ input: 0,
9908
+ output: 0,
9873
9909
  cacheRead: 0,
9874
9910
  cacheWrite: 0,
9875
9911
  },
9876
- contextWindow: 131072,
9877
- maxTokens: 163840,
9912
+ contextWindow: 262144,
9913
+ maxTokens: 262144,
9878
9914
  },
9879
9915
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9880
9916
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -9885,7 +9921,7 @@ export const MODELS = {
9885
9921
  reasoning: true,
9886
9922
  input: ["text"],
9887
9923
  cost: {
9888
- input: 0.09999999999999999,
9924
+ input: 0.39999999999999997,
9889
9925
  output: 0.39999999999999997,
9890
9926
  cacheRead: 0,
9891
9927
  cacheWrite: 0,
@@ -11104,7 +11140,7 @@ export const MODELS = {
11104
11140
  reasoning: false,
11105
11141
  input: ["text"],
11106
11142
  cost: {
11107
- input: 0.071,
11143
+ input: 0.09,
11108
11144
  output: 0.09999999999999999,
11109
11145
  cacheRead: 0,
11110
11146
  cacheWrite: 0,
@@ -11138,8 +11174,8 @@ export const MODELS = {
11138
11174
  reasoning: true,
11139
11175
  input: ["text"],
11140
11176
  cost: {
11141
- input: 0.09,
11142
- output: 0.44999999999999996,
11177
+ input: 0.12,
11178
+ output: 0.5,
11143
11179
  cacheRead: 0,
11144
11180
  cacheWrite: 0,
11145
11181
  },
@@ -11597,13 +11633,13 @@ export const MODELS = {
11597
11633
  reasoning: true,
11598
11634
  input: ["text", "image"],
11599
11635
  cost: {
11600
- input: 0.04,
11636
+ input: 0.09999999999999999,
11601
11637
  output: 0.15,
11602
11638
  cacheRead: 0,
11603
11639
  cacheWrite: 0,
11604
11640
  },
11605
11641
  contextWindow: 262144,
11606
- maxTokens: 81920,
11642
+ maxTokens: 262144,
11607
11643
  },
11608
11644
  "qwen/qwen3.5-flash-02-23": {
11609
11645
  id: "qwen/qwen3.5-flash-02-23",
@@ -12311,13 +12347,13 @@ export const MODELS = {
12311
12347
  reasoning: true,
12312
12348
  input: ["text", "image"],
12313
12349
  cost: {
12314
- input: 0.684,
12315
- output: 3.42,
12316
- cacheRead: 0.144,
12350
+ input: 0.6799999999999999,
12351
+ output: 3.41,
12352
+ cacheRead: 0.33999999999999997,
12317
12353
  cacheWrite: 0,
12318
12354
  },
12319
12355
  contextWindow: 262144,
12320
- maxTokens: 262144,
12356
+ maxTokens: 262142,
12321
12357
  },
12322
12358
  "~openai/gpt-latest": {
12323
12359
  id: "~openai/gpt-latest",
@@ -12758,8 +12794,8 @@ export const MODELS = {
12758
12794
  reasoning: true,
12759
12795
  input: ["text"],
12760
12796
  cost: {
12761
- input: 0.08,
12762
- output: 0.29,
12797
+ input: 0.12,
12798
+ output: 0.5,
12763
12799
  cacheRead: 0,
12764
12800
  cacheWrite: 0,
12765
12801
  },
@@ -13106,6 +13142,24 @@ export const MODELS = {
13106
13142
  contextWindow: 200000,
13107
13143
  maxTokens: 4096,
13108
13144
  },
13145
+ "anthropic/claude-fable-5": {
13146
+ id: "anthropic/claude-fable-5",
13147
+ name: "Claude Fable 5",
13148
+ api: "anthropic-messages",
13149
+ provider: "vercel-ai-gateway",
13150
+ baseUrl: "https://ai-gateway.vercel.sh",
13151
+ reasoning: true,
13152
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
13153
+ input: ["text", "image"],
13154
+ cost: {
13155
+ input: 10,
13156
+ output: 50,
13157
+ cacheRead: 1,
13158
+ cacheWrite: 12.5,
13159
+ },
13160
+ contextWindow: 1000000,
13161
+ maxTokens: 128000,
13162
+ },
13109
13163
  "anthropic/claude-haiku-4.5": {
13110
13164
  id: "anthropic/claude-haiku-4.5",
13111
13165
  name: "Claude Haiku 4.5",
@@ -13483,40 +13537,6 @@ export const MODELS = {
13483
13537
  contextWindow: 1000000,
13484
13538
  maxTokens: 384000,
13485
13539
  },
13486
- "google/gemini-2.0-flash": {
13487
- id: "google/gemini-2.0-flash",
13488
- name: "Gemini 2.0 Flash",
13489
- api: "anthropic-messages",
13490
- provider: "vercel-ai-gateway",
13491
- baseUrl: "https://ai-gateway.vercel.sh",
13492
- reasoning: false,
13493
- input: ["text", "image"],
13494
- cost: {
13495
- input: 0.15,
13496
- output: 0.6,
13497
- cacheRead: 0.024999999999999998,
13498
- cacheWrite: 0,
13499
- },
13500
- contextWindow: 1048576,
13501
- maxTokens: 8192,
13502
- },
13503
- "google/gemini-2.0-flash-lite": {
13504
- id: "google/gemini-2.0-flash-lite",
13505
- name: "Gemini 2.0 Flash Lite",
13506
- api: "anthropic-messages",
13507
- provider: "vercel-ai-gateway",
13508
- baseUrl: "https://ai-gateway.vercel.sh",
13509
- reasoning: false,
13510
- input: ["text", "image"],
13511
- cost: {
13512
- input: 0.075,
13513
- output: 0.3,
13514
- cacheRead: 0.02,
13515
- cacheWrite: 0,
13516
- },
13517
- contextWindow: 1048576,
13518
- maxTokens: 8192,
13519
- },
13520
13540
  "google/gemini-2.5-flash": {
13521
13541
  id: "google/gemini-2.5-flash",
13522
13542
  name: "Gemini 2.5 Flash",
@@ -15551,7 +15571,7 @@ export const MODELS = {
15551
15571
  cacheRead: 0.2,
15552
15572
  cacheWrite: 0,
15553
15573
  },
15554
- contextWindow: 2000000,
15574
+ contextWindow: 1000000,
15555
15575
  maxTokens: 30000,
15556
15576
  },
15557
15577
  "grok-4.20-0309-reasoning": {
@@ -15568,7 +15588,7 @@ export const MODELS = {
15568
15588
  cacheRead: 0.2,
15569
15589
  cacheWrite: 0,
15570
15590
  },
15571
- contextWindow: 2000000,
15591
+ contextWindow: 1000000,
15572
15592
  maxTokens: 30000,
15573
15593
  },
15574
15594
  "grok-4.3": {