@dreb/ai 2.42.0 → 2.43.2

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.
@@ -3368,7 +3368,7 @@ export const MODELS = {
3368
3368
  input: 1,
3369
3369
  output: 6,
3370
3370
  cacheRead: 0.1,
3371
- cacheWrite: 0,
3371
+ cacheWrite: 1.25,
3372
3372
  },
3373
3373
  contextWindow: 1050000,
3374
3374
  maxTokens: 128000,
@@ -3386,7 +3386,7 @@ export const MODELS = {
3386
3386
  input: 5,
3387
3387
  output: 30,
3388
3388
  cacheRead: 0.5,
3389
- cacheWrite: 0,
3389
+ cacheWrite: 6.25,
3390
3390
  },
3391
3391
  contextWindow: 1050000,
3392
3392
  maxTokens: 128000,
@@ -3404,7 +3404,7 @@ export const MODELS = {
3404
3404
  input: 2.5,
3405
3405
  output: 15,
3406
3406
  cacheRead: 0.25,
3407
- cacheWrite: 0,
3407
+ cacheWrite: 3.125,
3408
3408
  },
3409
3409
  contextWindow: 1050000,
3410
3410
  maxTokens: 128000,
@@ -5280,13 +5280,49 @@ export const MODELS = {
5280
5280
  },
5281
5281
  },
5282
5282
  "kimi-coding-oauth": {
5283
+ "k3": {
5284
+ id: "k3",
5285
+ name: "Kimi K3",
5286
+ api: "openai-completions",
5287
+ provider: "kimi-coding-oauth",
5288
+ baseUrl: "https://api.kimi.com/coding/v1",
5289
+ compat: { "thinkingFormat": "kimi", "supportsDeveloperRole": false, "reasoningEffortMap": { "minimal": "low", "low": "low", "medium": "high", "high": "high", "xhigh": "max" } },
5290
+ reasoning: true,
5291
+ input: ["text", "image"],
5292
+ cost: {
5293
+ input: 0,
5294
+ output: 0,
5295
+ cacheRead: 0,
5296
+ cacheWrite: 0,
5297
+ },
5298
+ contextWindow: 1048576,
5299
+ maxTokens: 32768,
5300
+ },
5283
5301
  "kimi-for-coding": {
5284
5302
  id: "kimi-for-coding",
5285
5303
  name: "Kimi For Coding",
5286
5304
  api: "openai-completions",
5287
5305
  provider: "kimi-coding-oauth",
5288
5306
  baseUrl: "https://api.kimi.com/coding/v1",
5289
- compat: { "thinkingFormat": "kimi", "supportsDeveloperRole": false },
5307
+ compat: { "thinkingFormat": "kimi", "supportsDeveloperRole": false, "reasoningEffortMap": { "minimal": "auto", "low": "auto", "medium": "auto", "high": "auto", "xhigh": "auto" } },
5308
+ reasoning: true,
5309
+ input: ["text", "image"],
5310
+ cost: {
5311
+ input: 0,
5312
+ output: 0,
5313
+ cacheRead: 0,
5314
+ cacheWrite: 0,
5315
+ },
5316
+ contextWindow: 262144,
5317
+ maxTokens: 32768,
5318
+ },
5319
+ "kimi-for-coding-highspeed": {
5320
+ id: "kimi-for-coding-highspeed",
5321
+ name: "Kimi For Coding Highspeed",
5322
+ api: "openai-completions",
5323
+ provider: "kimi-coding-oauth",
5324
+ baseUrl: "https://api.kimi.com/coding/v1",
5325
+ compat: { "thinkingFormat": "kimi", "supportsDeveloperRole": false, "reasoningEffortMap": { "minimal": "auto", "low": "auto", "medium": "auto", "high": "auto", "xhigh": "auto" } },
5290
5326
  reasoning: true,
5291
5327
  input: ["text", "image"],
5292
5328
  cost: {
@@ -7786,9 +7822,9 @@ export const MODELS = {
7786
7822
  reasoning: true,
7787
7823
  input: ["text"],
7788
7824
  cost: {
7789
- input: 0.435,
7790
- output: 0.87,
7791
- cacheRead: 0.003625,
7825
+ input: 0.14,
7826
+ output: 0.28,
7827
+ cacheRead: 0.0028,
7792
7828
  cacheWrite: 0,
7793
7829
  },
7794
7830
  contextWindow: 1000000,
@@ -7898,7 +7934,7 @@ export const MODELS = {
7898
7934
  },
7899
7935
  "kimi-k3": {
7900
7936
  id: "kimi-k3",
7901
- name: "Kimi K3",
7937
+ name: "Kimi K3 (2x usage)",
7902
7938
  api: "openai-completions",
7903
7939
  provider: "opencode-go",
7904
7940
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9063,13 +9099,13 @@ export const MODELS = {
9063
9099
  reasoning: true,
9064
9100
  input: ["text", "image"],
9065
9101
  cost: {
9066
- input: 0.22,
9067
- output: 0.55,
9068
- cacheRead: 0.12,
9102
+ input: 0.12,
9103
+ output: 0.37,
9104
+ cacheRead: 0,
9069
9105
  cacheWrite: 0,
9070
9106
  },
9071
9107
  contextWindow: 262144,
9072
- maxTokens: 262144,
9108
+ maxTokens: 16384,
9073
9109
  },
9074
9110
  "google/gemma-4-31b-it:free": {
9075
9111
  id: "google/gemma-4-31b-it:free",
@@ -9779,11 +9815,11 @@ export const MODELS = {
9779
9815
  cost: {
9780
9816
  input: 0.6,
9781
9817
  output: 2.5,
9782
- cacheRead: 0,
9818
+ cacheRead: 0.15,
9783
9819
  cacheWrite: 0,
9784
9820
  },
9785
9821
  contextWindow: 262144,
9786
- maxTokens: 262144,
9822
+ maxTokens: 100352,
9787
9823
  },
9788
9824
  "moonshotai/kimi-k2.5": {
9789
9825
  id: "moonshotai/kimi-k2.5",
@@ -9828,9 +9864,9 @@ export const MODELS = {
9828
9864
  reasoning: true,
9829
9865
  input: ["text", "image"],
9830
9866
  cost: {
9831
- input: 0.75,
9832
- output: 3.5,
9833
- cacheRead: 0.16,
9867
+ input: 0.85,
9868
+ output: 3.79,
9869
+ cacheRead: 0.17800000000000002,
9834
9870
  cacheWrite: 0,
9835
9871
  },
9836
9872
  contextWindow: 262144,
@@ -9981,13 +10017,13 @@ export const MODELS = {
9981
10017
  reasoning: true,
9982
10018
  input: ["text"],
9983
10019
  cost: {
9984
- input: 0,
9985
- output: 0,
9986
- cacheRead: 0,
10020
+ input: 0.6,
10021
+ output: 3.5999999999999996,
10022
+ cacheRead: 0.19999999999999998,
9987
10023
  cacheWrite: 0,
9988
10024
  },
9989
10025
  contextWindow: 1000000,
9990
- maxTokens: 202800,
10026
+ maxTokens: 4096,
9991
10027
  },
9992
10028
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
9993
10029
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11060,6 +11096,23 @@ export const MODELS = {
11060
11096
  contextWindow: 2000000,
11061
11097
  maxTokens: 4096,
11062
11098
  },
11099
+ "openrouter/auto-beta": {
11100
+ id: "openrouter/auto-beta",
11101
+ name: "Auto Router (Beta)",
11102
+ api: "openai-completions",
11103
+ provider: "openrouter",
11104
+ baseUrl: "https://openrouter.ai/api/v1",
11105
+ reasoning: true,
11106
+ input: ["text", "image"],
11107
+ cost: {
11108
+ input: -1000000,
11109
+ output: -1000000,
11110
+ cacheRead: 0,
11111
+ cacheWrite: 0,
11112
+ },
11113
+ contextWindow: 2000000,
11114
+ maxTokens: 4096,
11115
+ },
11063
11116
  "openrouter/free": {
11064
11117
  id: "openrouter/free",
11065
11118
  name: "Free Models Router",
@@ -11307,13 +11360,13 @@ export const MODELS = {
11307
11360
  reasoning: true,
11308
11361
  input: ["text"],
11309
11362
  cost: {
11310
- input: 0.12,
11311
- output: 0.5,
11363
+ input: 0.13,
11364
+ output: 0.52,
11312
11365
  cacheRead: 0,
11313
11366
  cacheWrite: 0,
11314
11367
  },
11315
11368
  contextWindow: 131072,
11316
- maxTokens: 16384,
11369
+ maxTokens: 8192,
11317
11370
  },
11318
11371
  "qwen/qwen3-30b-a3b-instruct-2507": {
11319
11372
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -11715,13 +11768,13 @@ export const MODELS = {
11715
11768
  reasoning: true,
11716
11769
  input: ["text", "image"],
11717
11770
  cost: {
11718
- input: 0.195,
11719
- output: 1.56,
11771
+ input: 0.26,
11772
+ output: 2.6,
11720
11773
  cacheRead: 0,
11721
11774
  cacheWrite: 0,
11722
11775
  },
11723
11776
  contextWindow: 262144,
11724
- maxTokens: 65536,
11777
+ maxTokens: 81920,
11725
11778
  },
11726
11779
  "qwen/qwen3.5-35b-a3b": {
11727
11780
  id: "qwen/qwen3.5-35b-a3b",
@@ -12114,6 +12167,23 @@ export const MODELS = {
12114
12167
  contextWindow: 32768,
12115
12168
  maxTokens: 32768,
12116
12169
  },
12170
+ "thinkingmachines/inkling": {
12171
+ id: "thinkingmachines/inkling",
12172
+ name: "Thinking Machines: Inkling",
12173
+ api: "openai-completions",
12174
+ provider: "openrouter",
12175
+ baseUrl: "https://openrouter.ai/api/v1",
12176
+ reasoning: true,
12177
+ input: ["text", "image"],
12178
+ cost: {
12179
+ input: 1,
12180
+ output: 4.05,
12181
+ cacheRead: 0.16999999999999998,
12182
+ cacheWrite: 0,
12183
+ },
12184
+ contextWindow: 1048576,
12185
+ maxTokens: 4096,
12186
+ },
12117
12187
  "upstage/solar-pro-3": {
12118
12188
  id: "upstage/solar-pro-3",
12119
12189
  name: "Upstage: Solar Pro 3",
@@ -12176,7 +12246,7 @@ export const MODELS = {
12176
12246
  cost: {
12177
12247
  input: 2,
12178
12248
  output: 6,
12179
- cacheRead: 0.5,
12249
+ cacheRead: 0.3,
12180
12250
  cacheWrite: 0,
12181
12251
  },
12182
12252
  contextWindow: 500000,
@@ -12412,9 +12482,9 @@ export const MODELS = {
12412
12482
  reasoning: true,
12413
12483
  input: ["text"],
12414
12484
  cost: {
12415
- input: 0.9254,
12416
- output: 2.9084,
12417
- cacheRead: 0.17186,
12485
+ input: 0.273,
12486
+ output: 0.858,
12487
+ cacheRead: 0.050699999999999995,
12418
12488
  cacheWrite: 0,
12419
12489
  },
12420
12490
  contextWindow: 1048576,
@@ -12601,7 +12671,7 @@ export const MODELS = {
12601
12671
  cost: {
12602
12672
  input: 2,
12603
12673
  output: 6,
12604
- cacheRead: 0.5,
12674
+ cacheRead: 0.3,
12605
12675
  cacheWrite: 0,
12606
12676
  },
12607
12677
  contextWindow: 500000,