@elyracode/ai 0.9.40 → 0.9.41

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.
@@ -9926,6 +9926,25 @@ export const MODELS = {
9926
9926
  contextWindow: 1000000,
9927
9927
  maxTokens: 384000,
9928
9928
  },
9929
+ "deepseek-v4.1-flash": {
9930
+ id: "deepseek-v4.1-flash",
9931
+ name: "DeepSeek V4.1 Flash",
9932
+ api: "openai-completions",
9933
+ provider: "opencode",
9934
+ baseUrl: "https://opencode.ai/zen/v1",
9935
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9936
+ reasoning: true,
9937
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9938
+ input: ["text", "image"],
9939
+ cost: {
9940
+ input: 0.3,
9941
+ output: 1.2,
9942
+ cacheRead: 0.006,
9943
+ cacheWrite: 0,
9944
+ },
9945
+ contextWindow: 1000000,
9946
+ maxTokens: 384000,
9947
+ },
9929
9948
  "gemini-3-flash": {
9930
9949
  id: "gemini-3-flash",
9931
9950
  name: "Gemini 3 Flash",
@@ -10836,6 +10855,23 @@ export const MODELS = {
10836
10855
  contextWindow: 262144,
10837
10856
  maxTokens: 65536,
10838
10857
  },
10858
+ "qwen3.8-flash": {
10859
+ id: "qwen3.8-flash",
10860
+ name: "Qwen3.8 Flash",
10861
+ api: "anthropic-messages",
10862
+ provider: "opencode",
10863
+ baseUrl: "https://opencode.ai/zen",
10864
+ reasoning: true,
10865
+ input: ["text", "image"],
10866
+ cost: {
10867
+ input: 0.15,
10868
+ output: 0.47,
10869
+ cacheRead: 0.016,
10870
+ cacheWrite: 0.2,
10871
+ },
10872
+ contextWindow: 1000000,
10873
+ maxTokens: 131072,
10874
+ },
10839
10875
  },
10840
10876
  "opencode-go": {
10841
10877
  "deepseek-v4-flash": {
@@ -12248,9 +12284,9 @@ export const MODELS = {
12248
12284
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12249
12285
  input: ["text"],
12250
12286
  cost: {
12251
- input: 0.048440000000000004,
12252
- output: 0.09688000000000001,
12253
- cacheRead: 0.009688,
12287
+ input: 0.0364,
12288
+ output: 0.0728,
12289
+ cacheRead: 0.00728,
12254
12290
  cacheWrite: 0,
12255
12291
  },
12256
12292
  contextWindow: 1048576,
@@ -12267,9 +12303,9 @@ export const MODELS = {
12267
12303
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12268
12304
  input: ["text"],
12269
12305
  cost: {
12270
- input: 0.06,
12271
- output: 0.12,
12272
- cacheRead: 0.012,
12306
+ input: 0.04,
12307
+ output: 0.08,
12308
+ cacheRead: 0.016,
12273
12309
  cacheWrite: 0,
12274
12310
  },
12275
12311
  contextWindow: 1310720,
@@ -12294,25 +12330,6 @@ export const MODELS = {
12294
12330
  contextWindow: 1048576,
12295
12331
  maxTokens: 943718,
12296
12332
  },
12297
- "deepseek/deepseek-v4-flash-0731:free": {
12298
- id: "deepseek/deepseek-v4-flash-0731:free",
12299
- name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
12300
- api: "openai-completions",
12301
- provider: "openrouter",
12302
- baseUrl: "https://openrouter.ai/api/v1",
12303
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12304
- reasoning: true,
12305
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12306
- input: ["text"],
12307
- cost: {
12308
- input: 0,
12309
- output: 0,
12310
- cacheRead: 0,
12311
- cacheWrite: 0,
12312
- },
12313
- contextWindow: 1048576,
12314
- maxTokens: 393216,
12315
- },
12316
12333
  "deepseek/deepseek-v4-flash-vision-exp": {
12317
12334
  id: "deepseek/deepseek-v4-flash-vision-exp",
12318
12335
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12362,13 +12379,13 @@ export const MODELS = {
12362
12379
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12363
12380
  input: ["text"],
12364
12381
  cost: {
12365
- input: 1.5999999999999999,
12366
- output: 3.1999999999999997,
12367
- cacheRead: 0.135,
12382
+ input: 0.422298,
12383
+ output: 0.844596,
12384
+ cacheRead: 0.0351915,
12368
12385
  cacheWrite: 0,
12369
12386
  },
12370
12387
  contextWindow: 1048576,
12371
- maxTokens: 393216,
12388
+ maxTokens: 384000,
12372
12389
  },
12373
12390
  "deepseek/deepseek-v4-pro-0813": {
12374
12391
  id: "deepseek/deepseek-v4-pro-0813",
@@ -12381,13 +12398,13 @@ export const MODELS = {
12381
12398
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12382
12399
  input: ["text"],
12383
12400
  cost: {
12384
- input: 0.57816,
12385
- output: 1.73448,
12386
- cacheRead: 0.018396000000000003,
12401
+ input: 0.66,
12402
+ output: 1.9800000000000002,
12403
+ cacheRead: 0.022,
12387
12404
  cacheWrite: 0,
12388
12405
  },
12389
12406
  contextWindow: 1048576,
12390
- maxTokens: 393216,
12407
+ maxTokens: 384000,
12391
12408
  },
12392
12409
  "deepseek/deepseek-v4-pro-0813:batch": {
12393
12410
  id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -12934,7 +12951,7 @@ export const MODELS = {
12934
12951
  cacheRead: 0.049999999999999996,
12935
12952
  cacheWrite: 0,
12936
12953
  },
12937
- contextWindow: 1000000,
12954
+ contextWindow: 262144,
12938
12955
  maxTokens: 235929,
12939
12956
  },
12940
12957
  "google/gemma-4-26b-a4b-it:free": {
@@ -13303,13 +13320,13 @@ export const MODELS = {
13303
13320
  reasoning: true,
13304
13321
  input: ["text", "image"],
13305
13322
  cost: {
13306
- input: 0.35,
13307
- output: 1.5,
13323
+ input: 0.3,
13324
+ output: 1.2,
13308
13325
  cacheRead: 0.04,
13309
13326
  cacheWrite: 0,
13310
13327
  },
13311
13328
  contextWindow: 131072,
13312
- maxTokens: 117964,
13329
+ maxTokens: 16384,
13313
13330
  },
13314
13331
  "meta/muse-glimmer-30b:batch": {
13315
13332
  id: "meta/muse-glimmer-30b:batch",
@@ -13855,6 +13872,23 @@ export const MODELS = {
13855
13872
  contextWindow: 262144,
13856
13873
  maxTokens: 209715,
13857
13874
  },
13875
+ "mistralai/mistral-small-3.1-24b-instruct": {
13876
+ id: "mistralai/mistral-small-3.1-24b-instruct",
13877
+ name: "Mistral: Mistral Small 3.1 24B",
13878
+ api: "openai-completions",
13879
+ provider: "openrouter",
13880
+ baseUrl: "https://openrouter.ai/api/v1",
13881
+ reasoning: false,
13882
+ input: ["text", "image"],
13883
+ cost: {
13884
+ input: 0.351,
13885
+ output: 0.5549999999999999,
13886
+ cacheRead: 0,
13887
+ cacheWrite: 0,
13888
+ },
13889
+ contextWindow: 128000,
13890
+ maxTokens: 102400,
13891
+ },
13858
13892
  "mistralai/mistral-small-3.2-24b-instruct": {
13859
13893
  id: "mistralai/mistral-small-3.2-24b-instruct",
13860
13894
  name: "Mistral: Mistral Small 3.2 24B",
@@ -14017,9 +14051,9 @@ export const MODELS = {
14017
14051
  reasoning: true,
14018
14052
  input: ["text", "image"],
14019
14053
  cost: {
14020
- input: 1.95,
14021
- output: 10.92,
14022
- cacheRead: 0.2262,
14054
+ input: 1.7,
14055
+ output: 8.5,
14056
+ cacheRead: 0.16999999999999998,
14023
14057
  cacheWrite: 0,
14024
14058
  },
14025
14059
  contextWindow: 1048576,
@@ -14153,13 +14187,13 @@ export const MODELS = {
14153
14187
  reasoning: true,
14154
14188
  input: ["text"],
14155
14189
  cost: {
14156
- input: 0.625,
14157
- output: 3.125,
14158
- cacheRead: 0.1875,
14190
+ input: 0.6,
14191
+ output: 2.4,
14192
+ cacheRead: 0.12,
14159
14193
  cacheWrite: 0,
14160
14194
  },
14161
14195
  contextWindow: 262144,
14162
- maxTokens: 32768,
14196
+ maxTokens: 182520,
14163
14197
  },
14164
14198
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
14165
14199
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14187,13 +14221,13 @@ export const MODELS = {
14187
14221
  reasoning: true,
14188
14222
  input: ["text"],
14189
14223
  cost: {
14190
- input: 0.08,
14224
+ input: 0.07,
14191
14225
  output: 0.19999999999999998,
14192
14226
  cacheRead: 0.04,
14193
14227
  cacheWrite: 0,
14194
14228
  },
14195
14229
  contextWindow: 262144,
14196
- maxTokens: 131072,
14230
+ maxTokens: 235929,
14197
14231
  },
14198
14232
  "nvidia/nemotron-3.5-lightning:free": {
14199
14233
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -16161,8 +16195,8 @@ export const MODELS = {
16161
16195
  reasoning: false,
16162
16196
  input: ["text", "image"],
16163
16197
  cost: {
16164
- input: 0.13,
16165
- output: 0.52,
16198
+ input: 0.19999999999999998,
16199
+ output: 0.7,
16166
16200
  cacheRead: 0,
16167
16201
  cacheWrite: 0,
16168
16202
  },
@@ -16280,13 +16314,13 @@ export const MODELS = {
16280
16314
  reasoning: true,
16281
16315
  input: ["text", "image"],
16282
16316
  cost: {
16283
- input: 0.1625,
16284
- output: 1.3,
16285
- cacheRead: 0,
16317
+ input: 0.3125,
16318
+ output: 1.25,
16319
+ cacheRead: 0.15625,
16286
16320
  cacheWrite: 0,
16287
16321
  },
16288
16322
  contextWindow: 262144,
16289
- maxTokens: 65536,
16323
+ maxTokens: 16384,
16290
16324
  },
16291
16325
  "qwen/qwen3.5-397b-a17b": {
16292
16326
  id: "qwen/qwen3.5-397b-a17b",
@@ -16320,7 +16354,7 @@ export const MODELS = {
16320
16354
  cacheWrite: 0,
16321
16355
  },
16322
16356
  contextWindow: 262144,
16323
- maxTokens: 235929,
16357
+ maxTokens: 32768,
16324
16358
  },
16325
16359
  "qwen/qwen3.5-9b:batch": {
16326
16360
  id: "qwen/qwen3.5-9b:batch",
@@ -16569,9 +16603,9 @@ export const MODELS = {
16569
16603
  reasoning: true,
16570
16604
  input: ["text", "image"],
16571
16605
  cost: {
16572
- input: 0.21400000000000002,
16573
- output: 2.5500000000000003,
16574
- cacheRead: 0.15,
16606
+ input: 0.42,
16607
+ output: 3,
16608
+ cacheRead: 0.08499999999999999,
16575
16609
  cacheWrite: 0,
16576
16610
  },
16577
16611
  contextWindow: 1000000,
@@ -16790,9 +16824,9 @@ export const MODELS = {
16790
16824
  reasoning: true,
16791
16825
  input: ["text"],
16792
16826
  cost: {
16793
- input: 0.0825,
16794
- output: 0.33,
16795
- cacheRead: 0.020625,
16827
+ input: 0.13199999999999998,
16828
+ output: 0.5279999999999999,
16829
+ cacheRead: 0.032999999999999995,
16796
16830
  cacheWrite: 0,
16797
16831
  },
16798
16832
  contextWindow: 262144,
@@ -17266,9 +17300,9 @@ export const MODELS = {
17266
17300
  reasoning: true,
17267
17301
  input: ["text"],
17268
17302
  cost: {
17269
- input: 0.5544,
17270
- output: 1.7424,
17271
- cacheRead: 0.10296000000000001,
17303
+ input: 0.6496,
17304
+ output: 2.0416,
17305
+ cacheRead: 0.12064,
17272
17306
  cacheWrite: 0,
17273
17307
  },
17274
17308
  contextWindow: 1048576,
@@ -17300,9 +17334,9 @@ export const MODELS = {
17300
17334
  reasoning: true,
17301
17335
  input: ["text"],
17302
17336
  cost: {
17303
- input: 0.9099999999999999,
17304
- output: 2.8600000000000003,
17305
- cacheRead: 0.16899999999999998,
17337
+ input: 0.896,
17338
+ output: 2.816,
17339
+ cacheRead: 0.16640000000000002,
17306
17340
  cacheWrite: 0,
17307
17341
  },
17308
17342
  contextWindow: 1310720,
@@ -17342,6 +17376,23 @@ export const MODELS = {
17342
17376
  contextWindow: 1048576,
17343
17377
  maxTokens: 943718,
17344
17378
  },
17379
+ "z-ai/glm-5.3-flashx": {
17380
+ id: "z-ai/glm-5.3-flashx",
17381
+ name: "Z.ai: GLM 5.3 FlashX",
17382
+ api: "openai-completions",
17383
+ provider: "openrouter",
17384
+ baseUrl: "https://openrouter.ai/api/v1",
17385
+ reasoning: true,
17386
+ input: ["text", "image"],
17387
+ cost: {
17388
+ input: 0.37,
17389
+ output: 1.25,
17390
+ cacheRead: 0.075,
17391
+ cacheWrite: 0,
17392
+ },
17393
+ contextWindow: 1048576,
17394
+ maxTokens: 131072,
17395
+ },
17345
17396
  "z-ai/glm-5.3:batch": {
17346
17397
  id: "z-ai/glm-5.3:batch",
17347
17398
  name: "Z.ai: GLM 5.3 (batch)",
@@ -17454,13 +17505,13 @@ export const MODELS = {
17454
17505
  reasoning: true,
17455
17506
  input: ["text", "image"],
17456
17507
  cost: {
17457
- input: 0.14,
17458
- output: 0.42,
17459
- cacheRead: 0.004200000000000001,
17508
+ input: 0.13,
17509
+ output: 0.52,
17510
+ cacheRead: 0.0026000000000000003,
17460
17511
  cacheWrite: 0,
17461
17512
  },
17462
17513
  contextWindow: 1048576,
17463
- maxTokens: 131072,
17514
+ maxTokens: 943718,
17464
17515
  },
17465
17516
  "~deepseek/deepseek-pro-latest": {
17466
17517
  id: "~deepseek/deepseek-pro-latest",
@@ -17471,9 +17522,9 @@ export const MODELS = {
17471
17522
  reasoning: true,
17472
17523
  input: ["text"],
17473
17524
  cost: {
17474
- input: 0.57816,
17475
- output: 1.73448,
17476
- cacheRead: 0.018396000000000003,
17525
+ input: 0.56496,
17526
+ output: 1.69488,
17527
+ cacheRead: 0.017976000000000002,
17477
17528
  cacheWrite: 0,
17478
17529
  },
17479
17530
  contextWindow: 1048576,
@@ -17490,13 +17541,13 @@ export const MODELS = {
17490
17541
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17491
17542
  input: ["text"],
17492
17543
  cost: {
17493
- input: 0.054119999999999994,
17494
- output: 0.16236,
17495
- cacheRead: 0.001722,
17544
+ input: 0.04,
17545
+ output: 0.08,
17546
+ cacheRead: 0.016,
17496
17547
  cacheWrite: 0,
17497
17548
  },
17498
17549
  contextWindow: 1310720,
17499
- maxTokens: 384000,
17550
+ maxTokens: 943718,
17500
17551
  },
17501
17552
  "~google/gemini-flash-latest": {
17502
17553
  id: "~google/gemini-flash-latest",
@@ -17541,9 +17592,9 @@ export const MODELS = {
17541
17592
  reasoning: true,
17542
17593
  input: ["text", "image"],
17543
17594
  cost: {
17544
- input: 1.95,
17545
- output: 10.92,
17546
- cacheRead: 0.2262,
17595
+ input: 1.7,
17596
+ output: 8.5,
17597
+ cacheRead: 0.16999999999999998,
17547
17598
  cacheWrite: 0,
17548
17599
  },
17549
17600
  contextWindow: 1048576,
@@ -17666,7 +17717,7 @@ export const MODELS = {
17666
17717
  cacheWrite: 0,
17667
17718
  },
17668
17719
  contextWindow: 1310720,
17669
- maxTokens: 131072,
17720
+ maxTokens: 943718,
17670
17721
  },
17671
17722
  "~z-ai/glm-latest": {
17672
17723
  id: "~z-ai/glm-latest",
@@ -17677,9 +17728,9 @@ export const MODELS = {
17677
17728
  reasoning: true,
17678
17729
  input: ["text"],
17679
17730
  cost: {
17680
- input: 0.8917999999999999,
17681
- output: 2.8028,
17682
- cacheRead: 0.16562,
17731
+ input: 0.8442,
17732
+ output: 2.6532,
17733
+ cacheRead: 0.15678,
17683
17734
  cacheWrite: 0,
17684
17735
  },
17685
17736
  contextWindow: 1310720,
@@ -20116,6 +20167,23 @@ export const MODELS = {
20116
20167
  contextWindow: 262144,
20117
20168
  maxTokens: 4000,
20118
20169
  },
20170
+ "mixedbread/toast-1": {
20171
+ id: "mixedbread/toast-1",
20172
+ name: "Toast 1",
20173
+ api: "anthropic-messages",
20174
+ provider: "vercel-ai-gateway",
20175
+ baseUrl: "https://ai-gateway.vercel.sh",
20176
+ reasoning: false,
20177
+ input: ["text"],
20178
+ cost: {
20179
+ input: 0.3,
20180
+ output: 0.72,
20181
+ cacheRead: 0.036,
20182
+ cacheWrite: 0,
20183
+ },
20184
+ contextWindow: 131000,
20185
+ maxTokens: 4000,
20186
+ },
20119
20187
  "moonshotai/kimi-k2": {
20120
20188
  id: "moonshotai/kimi-k2",
20121
20189
  name: "Kimi K2 Instruct",
@@ -21058,10 +21126,10 @@ export const MODELS = {
21058
21126
  reasoning: true,
21059
21127
  input: ["text", "image"],
21060
21128
  cost: {
21061
- input: 2,
21062
- output: 10,
21063
- cacheRead: 0.19999999999999998,
21064
- cacheWrite: 2.5,
21129
+ input: 4,
21130
+ output: 20,
21131
+ cacheRead: 0.39999999999999997,
21132
+ cacheWrite: 5,
21065
21133
  },
21066
21134
  contextWindow: 1050000,
21067
21135
  maxTokens: 128000,
@@ -21075,10 +21143,10 @@ export const MODELS = {
21075
21143
  reasoning: true,
21076
21144
  input: ["text", "image"],
21077
21145
  cost: {
21078
- input: 4,
21079
- output: 20,
21080
- cacheRead: 0.39999999999999997,
21081
- cacheWrite: 5,
21146
+ input: 8,
21147
+ output: 40,
21148
+ cacheRead: 0.7999999999999999,
21149
+ cacheWrite: 10,
21082
21150
  },
21083
21151
  contextWindow: 1050000,
21084
21152
  maxTokens: 128000,
@@ -21372,6 +21440,40 @@ export const MODELS = {
21372
21440
  contextWindow: 256000,
21373
21441
  maxTokens: 32768,
21374
21442
  },
21443
+ "quiverai/arrow-2": {
21444
+ id: "quiverai/arrow-2",
21445
+ name: "Arrow 2",
21446
+ api: "anthropic-messages",
21447
+ provider: "vercel-ai-gateway",
21448
+ baseUrl: "https://ai-gateway.vercel.sh",
21449
+ reasoning: true,
21450
+ input: ["text", "image"],
21451
+ cost: {
21452
+ input: 4,
21453
+ output: 20,
21454
+ cacheRead: 0.39999999999999997,
21455
+ cacheWrite: 5,
21456
+ },
21457
+ contextWindow: 131072,
21458
+ maxTokens: 131072,
21459
+ },
21460
+ "quiverai/arrow-2-telos": {
21461
+ id: "quiverai/arrow-2-telos",
21462
+ name: "Arrow 2 Telos",
21463
+ api: "anthropic-messages",
21464
+ provider: "vercel-ai-gateway",
21465
+ baseUrl: "https://ai-gateway.vercel.sh",
21466
+ reasoning: true,
21467
+ input: ["text", "image"],
21468
+ cost: {
21469
+ input: 6,
21470
+ output: 30,
21471
+ cacheRead: 0.6,
21472
+ cacheWrite: 7.5,
21473
+ },
21474
+ contextWindow: 131072,
21475
+ maxTokens: 131072,
21476
+ },
21375
21477
  "sakana/fugu-max": {
21376
21478
  id: "sakana/fugu-max",
21377
21479
  name: "Fugu Max",