@kolisachint/hoocode-ai 0.5.64 → 0.5.66

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.
@@ -1276,7 +1276,7 @@ export const MODELS = {
1276
1276
  provider: "fireworks",
1277
1277
  baseUrl: "https://api.fireworks.ai/inference",
1278
1278
  reasoning: true,
1279
- input: ["text", "image"],
1279
+ input: ["text"],
1280
1280
  cost: {
1281
1281
  input: 0.3,
1282
1282
  output: 1.2,
@@ -1331,7 +1331,7 @@ export const MODELS = {
1331
1331
  cost: {
1332
1332
  input: 0.6,
1333
1333
  output: 2.4,
1334
- cacheRead: 0.119,
1334
+ cacheRead: 0.12,
1335
1335
  cacheWrite: 0,
1336
1336
  },
1337
1337
  contextWindow: 262144,
@@ -1395,7 +1395,7 @@ export const MODELS = {
1395
1395
  provider: "fireworks",
1396
1396
  baseUrl: "https://api.fireworks.ai/inference",
1397
1397
  reasoning: true,
1398
- input: ["text"],
1398
+ input: ["text", "image"],
1399
1399
  cost: {
1400
1400
  input: 2,
1401
1401
  output: 6,
@@ -4121,7 +4121,7 @@ export const MODELS = {
4121
4121
  },
4122
4122
  "kimi-for-coding": {
4123
4123
  id: "kimi-for-coding",
4124
- name: "Kimi K2.7 Code",
4124
+ name: "kimi-for-coding",
4125
4125
  api: "anthropic-messages",
4126
4126
  provider: "kimi-coding",
4127
4127
  baseUrl: "https://api.kimi.com/coding",
@@ -4134,7 +4134,7 @@ export const MODELS = {
4134
4134
  cacheRead: 0,
4135
4135
  cacheWrite: 0,
4136
4136
  },
4137
- contextWindow: 262144,
4137
+ contextWindow: 1048576,
4138
4138
  maxTokens: 32768,
4139
4139
  },
4140
4140
  "kimi-for-coding-highspeed": {
@@ -9023,9 +9023,9 @@ export const MODELS = {
9023
9023
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9024
9024
  input: ["text"],
9025
9025
  cost: {
9026
- input: 0.049,
9027
- output: 0.098,
9028
- cacheRead: 0.0098,
9026
+ input: 0.08553999999999999,
9027
+ output: 0.17107999999999998,
9028
+ cacheRead: 0.017108,
9029
9029
  cacheWrite: 0,
9030
9030
  },
9031
9031
  contextWindow: 1048576,
@@ -9042,9 +9042,9 @@ export const MODELS = {
9042
9042
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9043
9043
  input: ["text"],
9044
9044
  cost: {
9045
- input: 0.04,
9046
- output: 0.08,
9047
- cacheRead: 0.008,
9045
+ input: 0.06,
9046
+ output: 0.12,
9047
+ cacheRead: 0.012,
9048
9048
  cacheWrite: 0,
9049
9049
  },
9050
9050
  contextWindow: 1310720,
@@ -9137,9 +9137,9 @@ export const MODELS = {
9137
9137
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9138
9138
  input: ["text"],
9139
9139
  cost: {
9140
- input: 0.57816,
9141
- output: 1.73448,
9142
- cacheRead: 0.018396000000000003,
9140
+ input: 0.57948,
9141
+ output: 1.73844,
9142
+ cacheRead: 0.018438,
9143
9143
  cacheWrite: 0,
9144
9144
  },
9145
9145
  contextWindow: 1048576,
@@ -9302,23 +9302,6 @@ export const MODELS = {
9302
9302
  contextWindow: 1048576,
9303
9303
  maxTokens: 65536,
9304
9304
  },
9305
- "google/gemini-2.5-pro-preview-05-06": {
9306
- id: "google/gemini-2.5-pro-preview-05-06",
9307
- name: "Google: Gemini 2.5 Pro Preview 05-06",
9308
- api: "openai-completions",
9309
- provider: "openrouter",
9310
- baseUrl: "https://openrouter.ai/api/v1",
9311
- reasoning: true,
9312
- input: ["text", "image"],
9313
- cost: {
9314
- input: 1.25,
9315
- output: 10,
9316
- cacheRead: 0.125,
9317
- cacheWrite: 0.375,
9318
- },
9319
- contextWindow: 1048576,
9320
- maxTokens: 65535,
9321
- },
9322
9305
  "google/gemini-2.5-pro:batch": {
9323
9306
  id: "google/gemini-2.5-pro:batch",
9324
9307
  name: "Google: Gemini 2.5 Pro (batch)",
@@ -10059,13 +10042,13 @@ export const MODELS = {
10059
10042
  reasoning: false,
10060
10043
  input: ["text", "image"],
10061
10044
  cost: {
10062
- input: 0.19999999999999998,
10063
- output: 0.696,
10045
+ input: 0.1875,
10046
+ output: 0.6525,
10064
10047
  cacheRead: 0,
10065
10048
  cacheWrite: 0,
10066
10049
  },
10067
10050
  contextWindow: 1048576,
10068
- maxTokens: 115200,
10051
+ maxTokens: 16384,
10069
10052
  },
10070
10053
  "meta-llama/llama-4-scout": {
10071
10054
  id: "meta-llama/llama-4-scout",
@@ -10926,13 +10909,13 @@ export const MODELS = {
10926
10909
  reasoning: true,
10927
10910
  input: ["text"],
10928
10911
  cost: {
10929
- input: 0.08499999999999999,
10930
- output: 0.39999999999999997,
10912
+ input: 0.08,
10913
+ output: 0.44999999999999996,
10931
10914
  cacheRead: 0,
10932
10915
  cacheWrite: 0,
10933
10916
  },
10934
10917
  contextWindow: 262144,
10935
- maxTokens: 16384,
10918
+ maxTokens: 235929,
10936
10919
  },
10937
10920
  "nvidia/nemotron-3-super-120b-a12b:free": {
10938
10921
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -10960,13 +10943,13 @@ export const MODELS = {
10960
10943
  reasoning: true,
10961
10944
  input: ["text"],
10962
10945
  cost: {
10963
- input: 0.625,
10964
- output: 3.125,
10965
- cacheRead: 0.1875,
10946
+ input: 0.6,
10947
+ output: 2.4,
10948
+ cacheRead: 0.12,
10966
10949
  cacheWrite: 0,
10967
10950
  },
10968
10951
  contextWindow: 262144,
10969
- maxTokens: 32768,
10952
+ maxTokens: 182520,
10970
10953
  },
10971
10954
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10972
10955
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11121,23 +11104,6 @@ export const MODELS = {
11121
11104
  contextWindow: 128000,
11122
11105
  maxTokens: 4096,
11123
11106
  },
11124
- "openai/gpt-4-turbo-preview": {
11125
- id: "openai/gpt-4-turbo-preview",
11126
- name: "OpenAI: GPT-4 Turbo Preview",
11127
- api: "openai-completions",
11128
- provider: "openrouter",
11129
- baseUrl: "https://openrouter.ai/api/v1",
11130
- reasoning: false,
11131
- input: ["text"],
11132
- cost: {
11133
- input: 10,
11134
- output: 30,
11135
- cacheRead: 0,
11136
- cacheWrite: 0,
11137
- },
11138
- contextWindow: 128000,
11139
- maxTokens: 4096,
11140
- },
11141
11107
  "openai/gpt-4-turbo:batch": {
11142
11108
  id: "openai/gpt-4-turbo:batch",
11143
11109
  name: "OpenAI: GPT-4 Turbo (batch)",
@@ -12713,13 +12679,13 @@ export const MODELS = {
12713
12679
  reasoning: true,
12714
12680
  input: ["text"],
12715
12681
  cost: {
12716
- input: 0.22749999999999998,
12717
- output: 0.9099999999999999,
12682
+ input: 0.12,
12683
+ output: 0.24,
12718
12684
  cacheRead: 0,
12719
12685
  cacheWrite: 0,
12720
12686
  },
12721
12687
  contextWindow: 131072,
12722
- maxTokens: 8192,
12688
+ maxTokens: 16384,
12723
12689
  },
12724
12690
  "qwen/qwen3-235b-a22b": {
12725
12691
  id: "qwen/qwen3-235b-a22b",
@@ -13008,7 +12974,7 @@ export const MODELS = {
13008
12974
  cacheWrite: 0,
13009
12975
  },
13010
12976
  contextWindow: 262144,
13011
- maxTokens: 235929,
12977
+ maxTokens: 32768,
13012
12978
  },
13013
12979
  "qwen/qwen3-vl-235b-a22b-instruct": {
13014
12980
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13172,13 +13138,13 @@ export const MODELS = {
13172
13138
  reasoning: true,
13173
13139
  input: ["text", "image"],
13174
13140
  cost: {
13175
- input: 0.3125,
13176
- output: 1.25,
13177
- cacheRead: 0.15625,
13141
+ input: 0.1625,
13142
+ output: 1.3,
13143
+ cacheRead: 0,
13178
13144
  cacheWrite: 0,
13179
13145
  },
13180
13146
  contextWindow: 262144,
13181
- maxTokens: 16384,
13147
+ maxTokens: 65536,
13182
13148
  },
13183
13149
  "qwen/qwen3.5-397b-a17b": {
13184
13150
  id: "qwen/qwen3.5-397b-a17b",
@@ -13665,9 +13631,9 @@ export const MODELS = {
13665
13631
  reasoning: true,
13666
13632
  input: ["text"],
13667
13633
  cost: {
13668
- input: 0.13199999999999998,
13669
- output: 0.5279999999999999,
13670
- cacheRead: 0.032999999999999995,
13634
+ input: 0.0825,
13635
+ output: 0.33,
13636
+ cacheRead: 0.020625,
13671
13637
  cacheWrite: 0,
13672
13638
  },
13673
13639
  contextWindow: 262144,
@@ -14175,13 +14141,13 @@ export const MODELS = {
14175
14141
  reasoning: true,
14176
14142
  input: ["text"],
14177
14143
  cost: {
14178
- input: 0.6,
14179
- output: 2,
14180
- cacheRead: 0.15,
14144
+ input: 1.4,
14145
+ output: 4.4,
14146
+ cacheRead: 0.14,
14181
14147
  cacheWrite: 0,
14182
14148
  },
14183
14149
  contextWindow: 1048576,
14184
- maxTokens: 182476,
14150
+ maxTokens: 128000,
14185
14151
  },
14186
14152
  "z-ai/glm-5.2:batch": {
14187
14153
  id: "z-ai/glm-5.2:batch",
@@ -14209,13 +14175,13 @@ export const MODELS = {
14209
14175
  reasoning: true,
14210
14176
  input: ["text"],
14211
14177
  cost: {
14212
- input: 1.092,
14213
- output: 3.432,
14214
- cacheRead: 0.20279999999999998,
14178
+ input: 1.4,
14179
+ output: 4.4,
14180
+ cacheRead: 0.26,
14215
14181
  cacheWrite: 0,
14216
14182
  },
14217
14183
  contextWindow: 1310720,
14218
- maxTokens: 131072,
14184
+ maxTokens: 943717,
14219
14185
  },
14220
14186
  "z-ai/glm-5.3-flash": {
14221
14187
  id: "z-ai/glm-5.3-flash",
@@ -14226,9 +14192,9 @@ export const MODELS = {
14226
14192
  reasoning: true,
14227
14193
  input: ["text", "image"],
14228
14194
  cost: {
14229
- input: 0.15,
14230
- output: 0.5,
14231
- cacheRead: 0.03,
14195
+ input: 0.075,
14196
+ output: 0.25,
14197
+ cacheRead: 0.015,
14232
14198
  cacheWrite: 0,
14233
14199
  },
14234
14200
  contextWindow: 1310720,
@@ -14356,6 +14322,40 @@ export const MODELS = {
14356
14322
  contextWindow: 1000000,
14357
14323
  maxTokens: 128000,
14358
14324
  },
14325
+ "~deepseek/deepseek-flash-latest": {
14326
+ id: "~deepseek/deepseek-flash-latest",
14327
+ name: "DeepSeek: DeepSeek Flash Latest",
14328
+ api: "openai-completions",
14329
+ provider: "openrouter",
14330
+ baseUrl: "https://openrouter.ai/api/v1",
14331
+ reasoning: true,
14332
+ input: ["text", "image"],
14333
+ cost: {
14334
+ input: 0.15,
14335
+ output: 0.6,
14336
+ cacheRead: 0.015,
14337
+ cacheWrite: 0,
14338
+ },
14339
+ contextWindow: 1048576,
14340
+ maxTokens: 393216,
14341
+ },
14342
+ "~deepseek/deepseek-pro-latest": {
14343
+ id: "~deepseek/deepseek-pro-latest",
14344
+ name: "DeepSeek: DeepSeek Pro Latest",
14345
+ api: "openai-completions",
14346
+ provider: "openrouter",
14347
+ baseUrl: "https://openrouter.ai/api/v1",
14348
+ reasoning: true,
14349
+ input: ["text"],
14350
+ cost: {
14351
+ input: 0.57948,
14352
+ output: 1.73844,
14353
+ cacheRead: 0.018438,
14354
+ cacheWrite: 0,
14355
+ },
14356
+ contextWindow: 1048576,
14357
+ maxTokens: 393216,
14358
+ },
14359
14359
  "~deepseek/deepseek-v4-flash-latest": {
14360
14360
  id: "~deepseek/deepseek-v4-flash-latest",
14361
14361
  name: "DeepSeek: DeepSeek V4 Flash Latest",
@@ -14367,13 +14367,13 @@ export const MODELS = {
14367
14367
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14368
14368
  input: ["text"],
14369
14369
  cost: {
14370
- input: 0.035199999999999995,
14371
- output: 0.1056,
14372
- cacheRead: 0.0011200000000000001,
14370
+ input: 0.04,
14371
+ output: 0.09999999999999999,
14372
+ cacheRead: 0.01,
14373
14373
  cacheWrite: 0,
14374
14374
  },
14375
14375
  contextWindow: 1310720,
14376
- maxTokens: 131072,
14376
+ maxTokens: 393216,
14377
14377
  },
14378
14378
  "~google/gemini-flash-latest": {
14379
14379
  id: "~google/gemini-flash-latest",
@@ -14420,7 +14420,7 @@ export const MODELS = {
14420
14420
  cost: {
14421
14421
  input: 2.0999999999999996,
14422
14422
  output: 10.950000000000001,
14423
- cacheRead: 0,
14423
+ cacheRead: 0.22999999999999998,
14424
14424
  cacheWrite: 0,
14425
14425
  },
14426
14426
  contextWindow: 1048576,
@@ -14554,9 +14554,9 @@ export const MODELS = {
14554
14554
  reasoning: true,
14555
14555
  input: ["text"],
14556
14556
  cost: {
14557
- input: 0.936,
14558
- output: 3.168,
14559
- cacheRead: 0.1872,
14557
+ input: 0.8775,
14558
+ output: 2.9699999999999998,
14559
+ cacheRead: 0.1755,
14560
14560
  cacheWrite: 0,
14561
14561
  },
14562
14562
  contextWindow: 1310720,
@@ -15060,7 +15060,7 @@ export const MODELS = {
15060
15060
  cost: {
15061
15061
  input: 1.3,
15062
15062
  output: 7.8,
15063
- cacheRead: 0.26,
15063
+ cacheRead: 0.13,
15064
15064
  cacheWrite: 1.625,
15065
15065
  },
15066
15066
  contextWindow: 240000,
@@ -15298,7 +15298,7 @@ export const MODELS = {
15298
15298
  cost: {
15299
15299
  input: 0.09999999999999999,
15300
15300
  output: 0.39999999999999997,
15301
- cacheRead: 0.001,
15301
+ cacheRead: 0.01,
15302
15302
  cacheWrite: 0.125,
15303
15303
  },
15304
15304
  contextWindow: 1000000,
@@ -15314,7 +15314,7 @@ export const MODELS = {
15314
15314
  input: ["text", "image"],
15315
15315
  cost: {
15316
15316
  input: 0.39999999999999997,
15317
- output: 2.4,
15317
+ output: 2.5,
15318
15318
  cacheRead: 0.04,
15319
15319
  cacheWrite: 0.5,
15320
15320
  },
@@ -15349,7 +15349,7 @@ export const MODELS = {
15349
15349
  cost: {
15350
15350
  input: 0.5,
15351
15351
  output: 3,
15352
- cacheRead: 0.09999999999999999,
15352
+ cacheRead: 0.049999999999999996,
15353
15353
  cacheWrite: 0.625,
15354
15354
  },
15355
15355
  contextWindow: 1000000,
@@ -15449,7 +15449,7 @@ export const MODELS = {
15449
15449
  reasoning: true,
15450
15450
  input: ["text", "image"],
15451
15451
  cost: {
15452
- input: 0.16,
15452
+ input: 0.15,
15453
15453
  output: 0.47,
15454
15454
  cacheRead: 0.016,
15455
15455
  cacheWrite: 0.19999999999999998,
@@ -16104,13 +16104,13 @@ export const MODELS = {
16104
16104
  reasoning: true,
16105
16105
  input: ["text", "image"],
16106
16106
  cost: {
16107
- input: 0.3,
16108
- output: 1.2,
16109
- cacheRead: 0.03,
16107
+ input: 0.15,
16108
+ output: 0.6,
16109
+ cacheRead: 0.015,
16110
16110
  cacheWrite: 0,
16111
16111
  },
16112
- contextWindow: 1048576,
16113
- maxTokens: 32768,
16112
+ contextWindow: 1000000,
16113
+ maxTokens: 384000,
16114
16114
  },
16115
16115
  "google/gemini-2.5-flash": {
16116
16116
  id: "google/gemini-2.5-flash",
@@ -16393,9 +16393,9 @@ export const MODELS = {
16393
16393
  reasoning: true,
16394
16394
  input: ["text"],
16395
16395
  cost: {
16396
- input: 0.06,
16397
- output: 0.18,
16398
- cacheRead: 0.012,
16396
+ input: 0.020999999999999998,
16397
+ output: 0.063,
16398
+ cacheRead: 0.004200000000000001,
16399
16399
  cacheWrite: 0,
16400
16400
  },
16401
16401
  contextWindow: 256000,
@@ -16922,46 +16922,12 @@ export const MODELS = {
16922
16922
  cost: {
16923
16923
  input: 0.3,
16924
16924
  output: 0.8999999999999999,
16925
- cacheRead: 0,
16925
+ cacheRead: 0.03,
16926
16926
  cacheWrite: 0,
16927
16927
  },
16928
16928
  contextWindow: 128000,
16929
16929
  maxTokens: 4000,
16930
16930
  },
16931
- "mistral/devstral-2": {
16932
- id: "mistral/devstral-2",
16933
- name: "Devstral 2",
16934
- api: "anthropic-messages",
16935
- provider: "vercel-ai-gateway",
16936
- baseUrl: "https://ai-gateway.vercel.sh",
16937
- reasoning: false,
16938
- input: ["text"],
16939
- cost: {
16940
- input: 0.39999999999999997,
16941
- output: 2,
16942
- cacheRead: 0,
16943
- cacheWrite: 0,
16944
- },
16945
- contextWindow: 256000,
16946
- maxTokens: 256000,
16947
- },
16948
- "mistral/devstral-small-2": {
16949
- id: "mistral/devstral-small-2",
16950
- name: "Devstral Small 2",
16951
- api: "anthropic-messages",
16952
- provider: "vercel-ai-gateway",
16953
- baseUrl: "https://ai-gateway.vercel.sh",
16954
- reasoning: false,
16955
- input: ["text", "image"],
16956
- cost: {
16957
- input: 0.09999999999999999,
16958
- output: 0.3,
16959
- cacheRead: 0,
16960
- cacheWrite: 0,
16961
- },
16962
- contextWindow: 256000,
16963
- maxTokens: 256000,
16964
- },
16965
16931
  "mistral/ministral-14b": {
16966
16932
  id: "mistral/ministral-14b",
16967
16933
  name: "Ministral 14B",
@@ -16973,10 +16939,10 @@ export const MODELS = {
16973
16939
  cost: {
16974
16940
  input: 0.19999999999999998,
16975
16941
  output: 0.19999999999999998,
16976
- cacheRead: 0,
16942
+ cacheRead: 0.02,
16977
16943
  cacheWrite: 0,
16978
16944
  },
16979
- contextWindow: 256000,
16945
+ contextWindow: 262144,
16980
16946
  maxTokens: 256000,
16981
16947
  },
16982
16948
  "mistral/ministral-3b": {
@@ -16990,10 +16956,10 @@ export const MODELS = {
16990
16956
  cost: {
16991
16957
  input: 0.09999999999999999,
16992
16958
  output: 0.09999999999999999,
16993
- cacheRead: 0,
16959
+ cacheRead: 0.01,
16994
16960
  cacheWrite: 0,
16995
16961
  },
16996
- contextWindow: 128000,
16962
+ contextWindow: 131072,
16997
16963
  maxTokens: 4000,
16998
16964
  },
16999
16965
  "mistral/ministral-8b": {
@@ -17007,10 +16973,10 @@ export const MODELS = {
17007
16973
  cost: {
17008
16974
  input: 0.15,
17009
16975
  output: 0.15,
17010
- cacheRead: 0,
16976
+ cacheRead: 0.015,
17011
16977
  cacheWrite: 0,
17012
16978
  },
17013
- contextWindow: 128000,
16979
+ contextWindow: 262144,
17014
16980
  maxTokens: 4000,
17015
16981
  },
17016
16982
  "mistral/mistral-large-3": {
@@ -17024,29 +16990,12 @@ export const MODELS = {
17024
16990
  cost: {
17025
16991
  input: 0.5,
17026
16992
  output: 1.5,
17027
- cacheRead: 0,
16993
+ cacheRead: 0.049999999999999996,
17028
16994
  cacheWrite: 0,
17029
16995
  },
17030
- contextWindow: 256000,
16996
+ contextWindow: 262144,
17031
16997
  maxTokens: 256000,
17032
16998
  },
17033
- "mistral/mistral-medium": {
17034
- id: "mistral/mistral-medium",
17035
- name: "Mistral Medium 3.1",
17036
- api: "anthropic-messages",
17037
- provider: "vercel-ai-gateway",
17038
- baseUrl: "https://ai-gateway.vercel.sh",
17039
- reasoning: false,
17040
- input: ["text", "image"],
17041
- cost: {
17042
- input: 0.39999999999999997,
17043
- output: 2,
17044
- cacheRead: 0,
17045
- cacheWrite: 0,
17046
- },
17047
- contextWindow: 128000,
17048
- maxTokens: 64000,
17049
- },
17050
16999
  "mistral/mistral-medium-3.5": {
17051
17000
  id: "mistral/mistral-medium-3.5",
17052
17001
  name: "Mistral Medium Latest",
@@ -17058,10 +17007,10 @@ export const MODELS = {
17058
17007
  cost: {
17059
17008
  input: 1.5,
17060
17009
  output: 7.5,
17061
- cacheRead: 0,
17010
+ cacheRead: 0.15,
17062
17011
  cacheWrite: 0,
17063
17012
  },
17064
- contextWindow: 256000,
17013
+ contextWindow: 262144,
17065
17014
  maxTokens: 256000,
17066
17015
  },
17067
17016
  "mistral/mistral-nemo": {
@@ -17071,15 +17020,15 @@ export const MODELS = {
17071
17020
  provider: "vercel-ai-gateway",
17072
17021
  baseUrl: "https://ai-gateway.vercel.sh",
17073
17022
  reasoning: false,
17074
- input: ["text", "image"],
17023
+ input: ["text"],
17075
17024
  cost: {
17076
- input: 0.15,
17077
- output: 0.15,
17025
+ input: 0.04,
17026
+ output: 0.16999999999999998,
17078
17027
  cacheRead: 0,
17079
17028
  cacheWrite: 0,
17080
17029
  },
17081
- contextWindow: 128000,
17082
- maxTokens: 128000,
17030
+ contextWindow: 60288,
17031
+ maxTokens: 16000,
17083
17032
  },
17084
17033
  "mistral/mistral-small": {
17085
17034
  id: "mistral/mistral-small",
@@ -17089,30 +17038,13 @@ export const MODELS = {
17089
17038
  baseUrl: "https://ai-gateway.vercel.sh",
17090
17039
  reasoning: false,
17091
17040
  input: ["text", "image"],
17092
- cost: {
17093
- input: 0.09999999999999999,
17094
- output: 0.3,
17095
- cacheRead: 0,
17096
- cacheWrite: 0,
17097
- },
17098
- contextWindow: 32000,
17099
- maxTokens: 4000,
17100
- },
17101
- "mistral/pixtral-12b": {
17102
- id: "mistral/pixtral-12b",
17103
- name: "Pixtral 12B 2409",
17104
- api: "anthropic-messages",
17105
- provider: "vercel-ai-gateway",
17106
- baseUrl: "https://ai-gateway.vercel.sh",
17107
- reasoning: false,
17108
- input: ["text", "image"],
17109
17041
  cost: {
17110
17042
  input: 0.15,
17111
- output: 0.15,
17112
- cacheRead: 0,
17043
+ output: 0.6,
17044
+ cacheRead: 0.015,
17113
17045
  cacheWrite: 0,
17114
17046
  },
17115
- contextWindow: 128000,
17047
+ contextWindow: 262144,
17116
17048
  maxTokens: 4000,
17117
17049
  },
17118
17050
  "moonshotai/kimi-k2": {
@@ -17261,8 +17193,8 @@ export const MODELS = {
17261
17193
  input: ["text"],
17262
17194
  cost: {
17263
17195
  input: 0.049999999999999996,
17264
- output: 0.24,
17265
- cacheRead: 0,
17196
+ output: 0.19999999999999998,
17197
+ cacheRead: 0.024999999999999998,
17266
17198
  cacheWrite: 0,
17267
17199
  },
17268
17200
  contextWindow: 262144,