@kolisachint/hoocode-ai 0.5.79 → 0.5.80

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.
@@ -7271,6 +7271,25 @@ export const MODELS = {
7271
7271
  contextWindow: 1000000,
7272
7272
  maxTokens: 384000,
7273
7273
  },
7274
+ "deepseek-v4.1-flash": {
7275
+ id: "deepseek-v4.1-flash",
7276
+ name: "DeepSeek V4.1 Flash",
7277
+ api: "openai-completions",
7278
+ provider: "opencode",
7279
+ baseUrl: "https://opencode.ai/zen/v1",
7280
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
7281
+ reasoning: true,
7282
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7283
+ input: ["text", "image"],
7284
+ cost: {
7285
+ input: 0.3,
7286
+ output: 1.2,
7287
+ cacheRead: 0.006,
7288
+ cacheWrite: 0,
7289
+ },
7290
+ contextWindow: 1000000,
7291
+ maxTokens: 384000,
7292
+ },
7274
7293
  "gemini-3-flash": {
7275
7294
  id: "gemini-3-flash",
7276
7295
  name: "Gemini 3 Flash",
@@ -8182,6 +8201,23 @@ export const MODELS = {
8182
8201
  contextWindow: 262144,
8183
8202
  maxTokens: 65536,
8184
8203
  },
8204
+ "qwen3.8-flash": {
8205
+ id: "qwen3.8-flash",
8206
+ name: "Qwen3.8 Flash",
8207
+ api: "anthropic-messages",
8208
+ provider: "opencode",
8209
+ baseUrl: "https://opencode.ai/zen",
8210
+ reasoning: true,
8211
+ input: ["text", "image"],
8212
+ cost: {
8213
+ input: 0.15,
8214
+ output: 0.47,
8215
+ cacheRead: 0.016,
8216
+ cacheWrite: 0.2,
8217
+ },
8218
+ contextWindow: 1000000,
8219
+ maxTokens: 131072,
8220
+ },
8185
8221
  },
8186
8222
  "opencode-go": {
8187
8223
  "deepseek-v4-flash": {
@@ -9598,9 +9634,9 @@ export const MODELS = {
9598
9634
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9599
9635
  input: ["text"],
9600
9636
  cost: {
9601
- input: 0.049280000000000004,
9602
- output: 0.09856000000000001,
9603
- cacheRead: 0.009856,
9637
+ input: 0.04368,
9638
+ output: 0.08736,
9639
+ cacheRead: 0.008735999999999999,
9604
9640
  cacheWrite: 0,
9605
9641
  },
9606
9642
  contextWindow: 1048576,
@@ -9617,9 +9653,9 @@ export const MODELS = {
9617
9653
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9618
9654
  input: ["text"],
9619
9655
  cost: {
9620
- input: 0.06,
9621
- output: 0.12,
9622
- cacheRead: 0.012,
9656
+ input: 0.04,
9657
+ output: 0.08,
9658
+ cacheRead: 0.016,
9623
9659
  cacheWrite: 0,
9624
9660
  },
9625
9661
  contextWindow: 1310720,
@@ -9712,13 +9748,13 @@ export const MODELS = {
9712
9748
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9713
9749
  input: ["text"],
9714
9750
  cost: {
9715
- input: 1.5999999999999999,
9716
- output: 3.1999999999999997,
9717
- cacheRead: 0.135,
9751
+ input: 0.422298,
9752
+ output: 0.844596,
9753
+ cacheRead: 0.0351915,
9718
9754
  cacheWrite: 0,
9719
9755
  },
9720
9756
  contextWindow: 1048576,
9721
- maxTokens: 393216,
9757
+ maxTokens: 384000,
9722
9758
  },
9723
9759
  "deepseek/deepseek-v4-pro-0813": {
9724
9760
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11367,9 +11403,9 @@ export const MODELS = {
11367
11403
  reasoning: true,
11368
11404
  input: ["text", "image"],
11369
11405
  cost: {
11370
- input: 2.0999999999999996,
11371
- output: 10.950000000000001,
11372
- cacheRead: 0.22999999999999998,
11406
+ input: 1.7,
11407
+ output: 8.5,
11408
+ cacheRead: 0.16999999999999998,
11373
11409
  cacheWrite: 0,
11374
11410
  },
11375
11411
  contextWindow: 1048576,
@@ -11503,13 +11539,13 @@ export const MODELS = {
11503
11539
  reasoning: true,
11504
11540
  input: ["text"],
11505
11541
  cost: {
11506
- input: 0.625,
11507
- output: 3.125,
11508
- cacheRead: 0.1875,
11542
+ input: 0.6,
11543
+ output: 2.4,
11544
+ cacheRead: 0.12,
11509
11545
  cacheWrite: 0,
11510
11546
  },
11511
11547
  contextWindow: 262144,
11512
- maxTokens: 32768,
11548
+ maxTokens: 182520,
11513
11549
  },
11514
11550
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11515
11551
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11537,13 +11573,13 @@ export const MODELS = {
11537
11573
  reasoning: true,
11538
11574
  input: ["text"],
11539
11575
  cost: {
11540
- input: 0.08,
11576
+ input: 0.07,
11541
11577
  output: 0.19999999999999998,
11542
11578
  cacheRead: 0.04,
11543
11579
  cacheWrite: 0,
11544
11580
  },
11545
11581
  contextWindow: 262144,
11546
- maxTokens: 131072,
11582
+ maxTokens: 235929,
11547
11583
  },
11548
11584
  "nvidia/nemotron-3.5-lightning:free": {
11549
11585
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -13174,6 +13210,23 @@ export const MODELS = {
13174
13210
  contextWindow: 262144,
13175
13211
  maxTokens: 32768,
13176
13212
  },
13213
+ "prism-ml/ternary-bonsai-2-27b": {
13214
+ id: "prism-ml/ternary-bonsai-2-27b",
13215
+ name: "PrismML: Ternary Bonsai 2 27B",
13216
+ api: "openai-completions",
13217
+ provider: "openrouter",
13218
+ baseUrl: "https://openrouter.ai/api/v1",
13219
+ reasoning: true,
13220
+ input: ["text", "image"],
13221
+ cost: {
13222
+ input: 0.075,
13223
+ output: 0.5,
13224
+ cacheRead: 0,
13225
+ cacheWrite: 0,
13226
+ },
13227
+ contextWindow: 262144,
13228
+ maxTokens: 32768,
13229
+ },
13177
13230
  "qwen/qwen-2.5-72b-instruct": {
13178
13231
  id: "qwen/qwen-2.5-72b-instruct",
13179
13232
  name: "Qwen2.5 72B Instruct",
@@ -13591,8 +13644,8 @@ export const MODELS = {
13591
13644
  reasoning: false,
13592
13645
  input: ["text", "image"],
13593
13646
  cost: {
13594
- input: 0.13,
13595
- output: 0.52,
13647
+ input: 0.19999999999999998,
13648
+ output: 0.7,
13596
13649
  cacheRead: 0,
13597
13650
  cacheWrite: 0,
13598
13651
  },
@@ -14220,9 +14273,9 @@ export const MODELS = {
14220
14273
  reasoning: true,
14221
14274
  input: ["text"],
14222
14275
  cost: {
14223
- input: 0.0825,
14224
- output: 0.33,
14225
- cacheRead: 0.020625,
14276
+ input: 0.13199999999999998,
14277
+ output: 0.5279999999999999,
14278
+ cacheRead: 0.032999999999999995,
14226
14279
  cacheWrite: 0,
14227
14280
  },
14228
14281
  contextWindow: 262144,
@@ -14789,6 +14842,23 @@ export const MODELS = {
14789
14842
  contextWindow: 1048576,
14790
14843
  maxTokens: 943718,
14791
14844
  },
14845
+ "z-ai/glm-5.3-flashx": {
14846
+ id: "z-ai/glm-5.3-flashx",
14847
+ name: "Z.ai: GLM 5.3 FlashX",
14848
+ api: "openai-completions",
14849
+ provider: "openrouter",
14850
+ baseUrl: "https://openrouter.ai/api/v1",
14851
+ reasoning: true,
14852
+ input: ["text", "image"],
14853
+ cost: {
14854
+ input: 0.37,
14855
+ output: 1.25,
14856
+ cacheRead: 0.075,
14857
+ cacheWrite: 0,
14858
+ },
14859
+ contextWindow: 1048576,
14860
+ maxTokens: 131072,
14861
+ },
14792
14862
  "z-ai/glm-5.3:batch": {
14793
14863
  id: "z-ai/glm-5.3:batch",
14794
14864
  name: "Z.ai: GLM 5.3 (batch)",
@@ -14903,13 +14973,13 @@ export const MODELS = {
14903
14973
  reasoning: true,
14904
14974
  input: ["text", "image"],
14905
14975
  cost: {
14906
- input: 0.14,
14907
- output: 0.42,
14908
- cacheRead: 0.004200000000000001,
14976
+ input: 0.13,
14977
+ output: 0.52,
14978
+ cacheRead: 0.0026000000000000003,
14909
14979
  cacheWrite: 0,
14910
14980
  },
14911
14981
  contextWindow: 1048576,
14912
- maxTokens: 131072,
14982
+ maxTokens: 943718,
14913
14983
  },
14914
14984
  "~deepseek/deepseek-pro-latest": {
14915
14985
  id: "~deepseek/deepseek-pro-latest",
@@ -14939,13 +15009,13 @@ export const MODELS = {
14939
15009
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14940
15010
  input: ["text"],
14941
15011
  cost: {
14942
- input: 0.055,
14943
- output: 0.165,
14944
- cacheRead: 0.00175,
15012
+ input: 0.04,
15013
+ output: 0.08,
15014
+ cacheRead: 0.016,
14945
15015
  cacheWrite: 0,
14946
15016
  },
14947
15017
  contextWindow: 1310720,
14948
- maxTokens: 384000,
15018
+ maxTokens: 943718,
14949
15019
  },
14950
15020
  "~google/gemini-flash-latest": {
14951
15021
  id: "~google/gemini-flash-latest",
@@ -14990,9 +15060,9 @@ export const MODELS = {
14990
15060
  reasoning: true,
14991
15061
  input: ["text", "image"],
14992
15062
  cost: {
14993
- input: 2.0999999999999996,
14994
- output: 10.950000000000001,
14995
- cacheRead: 0.22999999999999998,
15063
+ input: 1.7,
15064
+ output: 8.5,
15065
+ cacheRead: 0.16999999999999998,
14996
15066
  cacheWrite: 0,
14997
15067
  },
14998
15068
  contextWindow: 1048576,
@@ -15126,13 +15196,13 @@ export const MODELS = {
15126
15196
  reasoning: true,
15127
15197
  input: ["text"],
15128
15198
  cost: {
15129
- input: 0.8925000000000001,
15130
- output: 2.8049999999999997,
15131
- cacheRead: 0.146625,
15199
+ input: 0.8917999999999999,
15200
+ output: 2.8028,
15201
+ cacheRead: 0.16562,
15132
15202
  cacheWrite: 0,
15133
15203
  },
15134
15204
  contextWindow: 1310720,
15135
- maxTokens: 943718,
15205
+ maxTokens: 131072,
15136
15206
  },
15137
15207
  },
15138
15208
  "together": {
@@ -18530,10 +18600,10 @@ export const MODELS = {
18530
18600
  thinkingLevelMap: { "xhigh": "xhigh" },
18531
18601
  input: ["text", "image"],
18532
18602
  cost: {
18533
- input: 2,
18534
- output: 10,
18535
- cacheRead: 0.19999999999999998,
18536
- cacheWrite: 2.5,
18603
+ input: 4,
18604
+ output: 20,
18605
+ cacheRead: 0.39999999999999997,
18606
+ cacheWrite: 5,
18537
18607
  },
18538
18608
  contextWindow: 1050000,
18539
18609
  maxTokens: 128000,
@@ -18548,10 +18618,10 @@ export const MODELS = {
18548
18618
  thinkingLevelMap: { "xhigh": "xhigh" },
18549
18619
  input: ["text", "image"],
18550
18620
  cost: {
18551
- input: 4,
18552
- output: 20,
18553
- cacheRead: 0.39999999999999997,
18554
- cacheWrite: 5,
18621
+ input: 8,
18622
+ output: 40,
18623
+ cacheRead: 0.7999999999999999,
18624
+ cacheWrite: 10,
18555
18625
  },
18556
18626
  contextWindow: 1050000,
18557
18627
  maxTokens: 128000,