@elyracode/ai 0.9.4 → 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)",
@@ -5453,6 +5471,23 @@ export const MODELS = {
5453
5471
  contextWindow: 204800,
5454
5472
  maxTokens: 131072,
5455
5473
  },
5474
+ "MiniMax-M3": {
5475
+ id: "MiniMax-M3",
5476
+ name: "MiniMax-M3",
5477
+ api: "anthropic-messages",
5478
+ provider: "minimax",
5479
+ baseUrl: "https://api.minimax.io/anthropic",
5480
+ reasoning: true,
5481
+ input: ["text", "image"],
5482
+ cost: {
5483
+ input: 0.6,
5484
+ output: 2.4,
5485
+ cacheRead: 0.12,
5486
+ cacheWrite: 0,
5487
+ },
5488
+ contextWindow: 512000,
5489
+ maxTokens: 128000,
5490
+ },
5456
5491
  },
5457
5492
  "minimax-cn": {
5458
5493
  "MiniMax-M2.7": {
@@ -5489,6 +5524,23 @@ export const MODELS = {
5489
5524
  contextWindow: 204800,
5490
5525
  maxTokens: 131072,
5491
5526
  },
5527
+ "MiniMax-M3": {
5528
+ id: "MiniMax-M3",
5529
+ name: "MiniMax-M3",
5530
+ api: "anthropic-messages",
5531
+ provider: "minimax-cn",
5532
+ baseUrl: "https://api.minimaxi.com/anthropic",
5533
+ reasoning: true,
5534
+ input: ["text", "image"],
5535
+ cost: {
5536
+ input: 0.6,
5537
+ output: 2.4,
5538
+ cacheRead: 0.12,
5539
+ cacheWrite: 0,
5540
+ },
5541
+ contextWindow: 512000,
5542
+ maxTokens: 128000,
5543
+ },
5492
5544
  },
5493
5545
  "mistral": {
5494
5546
  "codestral-latest": {
@@ -7800,26 +7852,26 @@ export const MODELS = {
7800
7852
  contextWindow: 204800,
7801
7853
  maxTokens: 131072,
7802
7854
  },
7803
- "minimax-m3-free": {
7804
- id: "minimax-m3-free",
7805
- name: "MiniMax M3 Free",
7806
- api: "anthropic-messages",
7855
+ "nemotron-3-ultra-free": {
7856
+ id: "nemotron-3-ultra-free",
7857
+ name: "Nemotron 3 Ultra Free",
7858
+ api: "openai-completions",
7807
7859
  provider: "opencode",
7808
- baseUrl: "https://opencode.ai/zen",
7860
+ baseUrl: "https://opencode.ai/zen/v1",
7809
7861
  reasoning: true,
7810
- input: ["text", "image"],
7862
+ input: ["text"],
7811
7863
  cost: {
7812
7864
  input: 0,
7813
7865
  output: 0,
7814
7866
  cacheRead: 0,
7815
7867
  cacheWrite: 0,
7816
7868
  },
7817
- contextWindow: 200000,
7818
- maxTokens: 32000,
7869
+ contextWindow: 1000000,
7870
+ maxTokens: 128000,
7819
7871
  },
7820
- "nemotron-3-ultra-free": {
7821
- id: "nemotron-3-ultra-free",
7822
- name: "Nemotron 3 Ultra Free",
7872
+ "north-mini-code-free": {
7873
+ id: "north-mini-code-free",
7874
+ name: "North Mini Code Free",
7823
7875
  api: "openai-completions",
7824
7876
  provider: "opencode",
7825
7877
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7831,8 +7883,8 @@ export const MODELS = {
7831
7883
  cacheRead: 0,
7832
7884
  cacheWrite: 0,
7833
7885
  },
7834
- contextWindow: 1000000,
7835
- maxTokens: 128000,
7886
+ contextWindow: 256000,
7887
+ maxTokens: 64000,
7836
7888
  },
7837
7889
  "qwen3.5-plus": {
7838
7890
  id: "qwen3.5-plus",
@@ -8053,9 +8105,9 @@ export const MODELS = {
8053
8105
  reasoning: true,
8054
8106
  input: ["text", "image"],
8055
8107
  cost: {
8056
- input: 0.6,
8057
- output: 2.4,
8058
- cacheRead: 0.12,
8108
+ input: 0.3,
8109
+ output: 1.2,
8110
+ cacheRead: 0.06,
8059
8111
  cacheWrite: 0,
8060
8112
  },
8061
8113
  contextWindow: 512000,
@@ -8234,6 +8286,24 @@ export const MODELS = {
8234
8286
  contextWindow: 200000,
8235
8287
  maxTokens: 4096,
8236
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
+ },
8237
8307
  "anthropic/claude-haiku-4.5": {
8238
8308
  id: "anthropic/claude-haiku-4.5",
8239
8309
  name: "Anthropic: Claude Haiku 4.5",
@@ -9035,8 +9105,8 @@ export const MODELS = {
9035
9105
  reasoning: false,
9036
9106
  input: ["text", "image"],
9037
9107
  cost: {
9038
- input: 0.04,
9039
- output: 0.13,
9108
+ input: 0.049999999999999996,
9109
+ output: 0.15,
9040
9110
  cacheRead: 0,
9041
9111
  cacheWrite: 0,
9042
9112
  },
@@ -9324,7 +9394,7 @@ export const MODELS = {
9324
9394
  reasoning: false,
9325
9395
  input: ["text", "image"],
9326
9396
  cost: {
9327
- input: 0.08,
9397
+ input: 0.09999999999999999,
9328
9398
  output: 0.3,
9329
9399
  cacheRead: 0,
9330
9400
  cacheWrite: 0,
@@ -9393,8 +9463,8 @@ export const MODELS = {
9393
9463
  input: ["text"],
9394
9464
  cost: {
9395
9465
  input: 0.15,
9396
- output: 1.15,
9397
- cacheRead: 0,
9466
+ output: 0.8999999999999999,
9467
+ cacheRead: 0.049999999999999996,
9398
9468
  cacheWrite: 0,
9399
9469
  },
9400
9470
  contextWindow: 204800,
@@ -9409,13 +9479,13 @@ export const MODELS = {
9409
9479
  reasoning: true,
9410
9480
  input: ["text"],
9411
9481
  cost: {
9412
- input: 0.27899999999999997,
9413
- output: 1.2,
9414
- cacheRead: 0,
9482
+ input: 0.27,
9483
+ output: 1.08,
9484
+ cacheRead: 0.054,
9415
9485
  cacheWrite: 0,
9416
9486
  },
9417
9487
  contextWindow: 204800,
9418
- maxTokens: 196608,
9488
+ maxTokens: 131072,
9419
9489
  },
9420
9490
  "minimax/minimax-m3": {
9421
9491
  id: "minimax/minimax-m3",
@@ -9800,13 +9870,13 @@ export const MODELS = {
9800
9870
  reasoning: true,
9801
9871
  input: ["text", "image"],
9802
9872
  cost: {
9803
- input: 0.684,
9804
- output: 3.42,
9805
- cacheRead: 0.144,
9873
+ input: 0.6799999999999999,
9874
+ output: 3.41,
9875
+ cacheRead: 0.33999999999999997,
9806
9876
  cacheWrite: 0,
9807
9877
  },
9808
9878
  contextWindow: 262144,
9809
- maxTokens: 262144,
9879
+ maxTokens: 262142,
9810
9880
  },
9811
9881
  "moonshotai/kimi-k2.6:free": {
9812
9882
  id: "moonshotai/kimi-k2.6:free",
@@ -9825,22 +9895,22 @@ export const MODELS = {
9825
9895
  contextWindow: 262144,
9826
9896
  maxTokens: 4096,
9827
9897
  },
9828
- "nex-agi/deepseek-v3.1-nex-n1": {
9829
- id: "nex-agi/deepseek-v3.1-nex-n1",
9830
- 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)",
9831
9901
  api: "openai-completions",
9832
9902
  provider: "openrouter",
9833
9903
  baseUrl: "https://openrouter.ai/api/v1",
9834
- reasoning: false,
9835
- input: ["text"],
9904
+ reasoning: true,
9905
+ input: ["text", "image"],
9836
9906
  cost: {
9837
- input: 0.135,
9838
- output: 0.5,
9907
+ input: 0,
9908
+ output: 0,
9839
9909
  cacheRead: 0,
9840
9910
  cacheWrite: 0,
9841
9911
  },
9842
- contextWindow: 131072,
9843
- maxTokens: 163840,
9912
+ contextWindow: 262144,
9913
+ maxTokens: 262144,
9844
9914
  },
9845
9915
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9846
9916
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -9851,7 +9921,7 @@ export const MODELS = {
9851
9921
  reasoning: true,
9852
9922
  input: ["text"],
9853
9923
  cost: {
9854
- input: 0.09999999999999999,
9924
+ input: 0.39999999999999997,
9855
9925
  output: 0.39999999999999997,
9856
9926
  cacheRead: 0,
9857
9927
  cacheWrite: 0,
@@ -11070,7 +11140,7 @@ export const MODELS = {
11070
11140
  reasoning: false,
11071
11141
  input: ["text"],
11072
11142
  cost: {
11073
- input: 0.071,
11143
+ input: 0.09,
11074
11144
  output: 0.09999999999999999,
11075
11145
  cacheRead: 0,
11076
11146
  cacheWrite: 0,
@@ -11104,8 +11174,8 @@ export const MODELS = {
11104
11174
  reasoning: true,
11105
11175
  input: ["text"],
11106
11176
  cost: {
11107
- input: 0.09,
11108
- output: 0.44999999999999996,
11177
+ input: 0.12,
11178
+ output: 0.5,
11109
11179
  cacheRead: 0,
11110
11180
  cacheWrite: 0,
11111
11181
  },
@@ -11563,13 +11633,13 @@ export const MODELS = {
11563
11633
  reasoning: true,
11564
11634
  input: ["text", "image"],
11565
11635
  cost: {
11566
- input: 0.04,
11636
+ input: 0.09999999999999999,
11567
11637
  output: 0.15,
11568
11638
  cacheRead: 0,
11569
11639
  cacheWrite: 0,
11570
11640
  },
11571
11641
  contextWindow: 262144,
11572
- maxTokens: 81920,
11642
+ maxTokens: 262144,
11573
11643
  },
11574
11644
  "qwen/qwen3.5-flash-02-23": {
11575
11645
  id: "qwen/qwen3.5-flash-02-23",
@@ -11631,13 +11701,13 @@ export const MODELS = {
11631
11701
  reasoning: true,
11632
11702
  input: ["text", "image"],
11633
11703
  cost: {
11634
- input: 0.29,
11635
- output: 3.1999999999999997,
11704
+ input: 0.28900000000000003,
11705
+ output: 2.4,
11636
11706
  cacheRead: 0,
11637
11707
  cacheWrite: 0,
11638
11708
  },
11639
11709
  contextWindow: 262144,
11640
- maxTokens: 262140,
11710
+ maxTokens: 131072,
11641
11711
  },
11642
11712
  "qwen/qwen3.6-35b-a3b": {
11643
11713
  id: "qwen/qwen3.6-35b-a3b",
@@ -12277,13 +12347,13 @@ export const MODELS = {
12277
12347
  reasoning: true,
12278
12348
  input: ["text", "image"],
12279
12349
  cost: {
12280
- input: 0.684,
12281
- output: 3.42,
12282
- cacheRead: 0.144,
12350
+ input: 0.6799999999999999,
12351
+ output: 3.41,
12352
+ cacheRead: 0.33999999999999997,
12283
12353
  cacheWrite: 0,
12284
12354
  },
12285
12355
  contextWindow: 262144,
12286
- maxTokens: 262144,
12356
+ maxTokens: 262142,
12287
12357
  },
12288
12358
  "~openai/gpt-latest": {
12289
12359
  id: "~openai/gpt-latest",
@@ -12724,8 +12794,8 @@ export const MODELS = {
12724
12794
  reasoning: true,
12725
12795
  input: ["text"],
12726
12796
  cost: {
12727
- input: 0.08,
12728
- output: 0.29,
12797
+ input: 0.12,
12798
+ output: 0.5,
12729
12799
  cacheRead: 0,
12730
12800
  cacheWrite: 0,
12731
12801
  },
@@ -13072,6 +13142,24 @@ export const MODELS = {
13072
13142
  contextWindow: 200000,
13073
13143
  maxTokens: 4096,
13074
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
+ },
13075
13163
  "anthropic/claude-haiku-4.5": {
13076
13164
  id: "anthropic/claude-haiku-4.5",
13077
13165
  name: "Claude Haiku 4.5",
@@ -13449,40 +13537,6 @@ export const MODELS = {
13449
13537
  contextWindow: 1000000,
13450
13538
  maxTokens: 384000,
13451
13539
  },
13452
- "google/gemini-2.0-flash": {
13453
- id: "google/gemini-2.0-flash",
13454
- name: "Gemini 2.0 Flash",
13455
- api: "anthropic-messages",
13456
- provider: "vercel-ai-gateway",
13457
- baseUrl: "https://ai-gateway.vercel.sh",
13458
- reasoning: false,
13459
- input: ["text", "image"],
13460
- cost: {
13461
- input: 0.15,
13462
- output: 0.6,
13463
- cacheRead: 0.024999999999999998,
13464
- cacheWrite: 0,
13465
- },
13466
- contextWindow: 1048576,
13467
- maxTokens: 8192,
13468
- },
13469
- "google/gemini-2.0-flash-lite": {
13470
- id: "google/gemini-2.0-flash-lite",
13471
- name: "Gemini 2.0 Flash Lite",
13472
- api: "anthropic-messages",
13473
- provider: "vercel-ai-gateway",
13474
- baseUrl: "https://ai-gateway.vercel.sh",
13475
- reasoning: false,
13476
- input: ["text", "image"],
13477
- cost: {
13478
- input: 0.075,
13479
- output: 0.3,
13480
- cacheRead: 0.02,
13481
- cacheWrite: 0,
13482
- },
13483
- contextWindow: 1048576,
13484
- maxTokens: 8192,
13485
- },
13486
13540
  "google/gemini-2.5-flash": {
13487
13541
  id: "google/gemini-2.5-flash",
13488
13542
  name: "Gemini 2.5 Flash",
@@ -15517,7 +15571,7 @@ export const MODELS = {
15517
15571
  cacheRead: 0.2,
15518
15572
  cacheWrite: 0,
15519
15573
  },
15520
- contextWindow: 2000000,
15574
+ contextWindow: 1000000,
15521
15575
  maxTokens: 30000,
15522
15576
  },
15523
15577
  "grok-4.20-0309-reasoning": {
@@ -15534,7 +15588,7 @@ export const MODELS = {
15534
15588
  cacheRead: 0.2,
15535
15589
  cacheWrite: 0,
15536
15590
  },
15537
- contextWindow: 2000000,
15591
+ contextWindow: 1000000,
15538
15592
  maxTokens: 30000,
15539
15593
  },
15540
15594
  "grok-4.3": {