@elyracode/ai 0.6.2 → 0.6.4

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.
@@ -908,8 +908,8 @@ export const MODELS = {
908
908
  cacheRead: 0,
909
909
  cacheWrite: 0,
910
910
  },
911
- contextWindow: 256000,
912
- maxTokens: 256000,
911
+ contextWindow: 262143,
912
+ maxTokens: 16000,
913
913
  },
914
914
  "moonshotai.kimi-k2.5": {
915
915
  id: "moonshotai.kimi-k2.5",
@@ -925,8 +925,8 @@ export const MODELS = {
925
925
  cacheRead: 0,
926
926
  cacheWrite: 0,
927
927
  },
928
- contextWindow: 256000,
929
- maxTokens: 256000,
928
+ contextWindow: 262143,
929
+ maxTokens: 16000,
930
930
  },
931
931
  "nvidia.nemotron-nano-12b-v2": {
932
932
  id: "nvidia.nemotron-nano-12b-v2",
@@ -3477,6 +3477,23 @@ export const MODELS = {
3477
3477
  contextWindow: 160000,
3478
3478
  maxTokens: 160000,
3479
3479
  },
3480
+ "accounts/fireworks/models/deepseek-v4-flash": {
3481
+ id: "accounts/fireworks/models/deepseek-v4-flash",
3482
+ name: "DeepSeek V4 Flash",
3483
+ api: "anthropic-messages",
3484
+ provider: "fireworks",
3485
+ baseUrl: "https://api.fireworks.ai/inference",
3486
+ reasoning: true,
3487
+ input: ["text"],
3488
+ cost: {
3489
+ input: 0.14,
3490
+ output: 0.28,
3491
+ cacheRead: 0.03,
3492
+ cacheWrite: 0,
3493
+ },
3494
+ contextWindow: 1000000,
3495
+ maxTokens: 384000,
3496
+ },
3480
3497
  "accounts/fireworks/models/deepseek-v4-pro": {
3481
3498
  id: "accounts/fireworks/models/deepseek-v4-pro",
3482
3499
  name: "DeepSeek V4 Pro",
@@ -4492,6 +4509,24 @@ export const MODELS = {
4492
4509
  contextWindow: 1048576,
4493
4510
  maxTokens: 65536,
4494
4511
  },
4512
+ "gemini-3.5-flash": {
4513
+ id: "gemini-3.5-flash",
4514
+ name: "Gemini 3.5 Flash",
4515
+ api: "google-generative-ai",
4516
+ provider: "google",
4517
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4518
+ reasoning: true,
4519
+ thinkingLevelMap: { "off": null },
4520
+ input: ["text", "image"],
4521
+ cost: {
4522
+ input: 1.5,
4523
+ output: 9,
4524
+ cacheRead: 0.15,
4525
+ cacheWrite: 0,
4526
+ },
4527
+ contextWindow: 1048576,
4528
+ maxTokens: 65536,
4529
+ },
4495
4530
  "gemini-flash-latest": {
4496
4531
  id: "gemini-flash-latest",
4497
4532
  name: "Gemini Flash Latest",
@@ -7523,6 +7558,24 @@ export const MODELS = {
7523
7558
  contextWindow: 1048576,
7524
7559
  maxTokens: 65536,
7525
7560
  },
7561
+ "gemini-3.5-flash": {
7562
+ id: "gemini-3.5-flash",
7563
+ name: "Gemini 3.5 Flash",
7564
+ api: "google-generative-ai",
7565
+ provider: "opencode",
7566
+ baseUrl: "https://opencode.ai/zen/v1",
7567
+ reasoning: true,
7568
+ thinkingLevelMap: { "off": null },
7569
+ input: ["text", "image"],
7570
+ cost: {
7571
+ input: 1.5,
7572
+ output: 9,
7573
+ cacheRead: 0.15,
7574
+ cacheWrite: 0,
7575
+ },
7576
+ contextWindow: 1048576,
7577
+ maxTokens: 65536,
7578
+ },
7526
7579
  "glm-5": {
7527
7580
  id: "glm-5",
7528
7581
  name: "GLM-5",
@@ -9242,6 +9295,23 @@ export const MODELS = {
9242
9295
  contextWindow: 1048756,
9243
9296
  maxTokens: 65536,
9244
9297
  },
9298
+ "google/gemini-3.5-flash": {
9299
+ id: "google/gemini-3.5-flash",
9300
+ name: "Google: Gemini 3.5 Flash",
9301
+ api: "openai-completions",
9302
+ provider: "openrouter",
9303
+ baseUrl: "https://openrouter.ai/api/v1",
9304
+ reasoning: true,
9305
+ input: ["text", "image"],
9306
+ cost: {
9307
+ input: 1.5,
9308
+ output: 9,
9309
+ cacheRead: 0.15,
9310
+ cacheWrite: 0.08333333333333334,
9311
+ },
9312
+ contextWindow: 1048576,
9313
+ maxTokens: 65536,
9314
+ },
9245
9315
  "google/gemma-3-12b-it": {
9246
9316
  id: "google/gemma-3-12b-it",
9247
9317
  name: "Google: Gemma 3 12B",
@@ -9285,13 +9355,13 @@ export const MODELS = {
9285
9355
  reasoning: true,
9286
9356
  input: ["text", "image"],
9287
9357
  cost: {
9288
- input: 0.07,
9289
- output: 0.33999999999999997,
9358
+ input: 0.06,
9359
+ output: 0.33,
9290
9360
  cacheRead: 0,
9291
9361
  cacheWrite: 0,
9292
9362
  },
9293
9363
  contextWindow: 262144,
9294
- maxTokens: 16384,
9364
+ maxTokens: 4096,
9295
9365
  },
9296
9366
  "google/gemma-4-26b-a4b-it:free": {
9297
9367
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9881,12 +9951,12 @@ export const MODELS = {
9881
9951
  input: ["text"],
9882
9952
  cost: {
9883
9953
  input: 0.02,
9884
- output: 0.04,
9954
+ output: 0.03,
9885
9955
  cacheRead: 0,
9886
9956
  cacheWrite: 0,
9887
9957
  },
9888
9958
  contextWindow: 131072,
9889
- maxTokens: 16384,
9959
+ maxTokens: 4096,
9890
9960
  },
9891
9961
  "mistralai/mistral-saba": {
9892
9962
  id: "mistralai/mistral-saba",
@@ -10169,13 +10239,13 @@ export const MODELS = {
10169
10239
  reasoning: true,
10170
10240
  input: ["text"],
10171
10241
  cost: {
10172
- input: 0.09999999999999999,
10173
- output: 0.5,
10242
+ input: 0.09,
10243
+ output: 0.44999999999999996,
10174
10244
  cacheRead: 0,
10175
10245
  cacheWrite: 0,
10176
10246
  },
10177
10247
  contextWindow: 1000000,
10178
- maxTokens: 16384,
10248
+ maxTokens: 4096,
10179
10249
  },
10180
10250
  "nvidia/nemotron-3-super-120b-a12b:free": {
10181
10251
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -10998,12 +11068,12 @@ export const MODELS = {
10998
11068
  input: ["text"],
10999
11069
  cost: {
11000
11070
  input: 0.039,
11001
- output: 0.19,
11071
+ output: 0.18,
11002
11072
  cacheRead: 0,
11003
11073
  cacheWrite: 0,
11004
11074
  },
11005
11075
  contextWindow: 131072,
11006
- maxTokens: 131072,
11076
+ maxTokens: 4096,
11007
11077
  },
11008
11078
  "openai/gpt-oss-120b:free": {
11009
11079
  id: "openai/gpt-oss-120b:free",
@@ -11915,13 +11985,13 @@ export const MODELS = {
11915
11985
  reasoning: true,
11916
11986
  input: ["text", "image"],
11917
11987
  cost: {
11918
- input: 0.14,
11988
+ input: 0.13899999999999998,
11919
11989
  output: 1,
11920
- cacheRead: 0.049999999999999996,
11990
+ cacheRead: 0,
11921
11991
  cacheWrite: 0,
11922
11992
  },
11923
11993
  contextWindow: 262144,
11924
- maxTokens: 81920,
11994
+ maxTokens: 4096,
11925
11995
  },
11926
11996
  "qwen/qwen3.5-397b-a17b": {
11927
11997
  id: "qwen/qwen3.5-397b-a17b",
@@ -12034,13 +12104,13 @@ export const MODELS = {
12034
12104
  reasoning: true,
12035
12105
  input: ["text", "image"],
12036
12106
  cost: {
12037
- input: 0.15,
12107
+ input: 0.149,
12038
12108
  output: 1,
12039
- cacheRead: 0.049999999999999996,
12109
+ cacheRead: 0,
12040
12110
  cacheWrite: 0,
12041
12111
  },
12042
12112
  contextWindow: 262144,
12043
- maxTokens: 262144,
12113
+ maxTokens: 4096,
12044
12114
  },
12045
12115
  "qwen/qwen3.6-flash": {
12046
12116
  id: "qwen/qwen3.6-flash",
@@ -12561,13 +12631,13 @@ export const MODELS = {
12561
12631
  reasoning: true,
12562
12632
  input: ["text"],
12563
12633
  cost: {
12564
- input: 0.98,
12565
- output: 3.08,
12566
- cacheRead: 0.182,
12634
+ input: 0,
12635
+ output: 0,
12636
+ cacheRead: 0,
12567
12637
  cacheWrite: 0,
12568
12638
  },
12569
- contextWindow: 202752,
12570
- maxTokens: 4096,
12639
+ contextWindow: 202800,
12640
+ maxTokens: 202800,
12571
12641
  },
12572
12642
  "z-ai/glm-5v-turbo": {
12573
12643
  id: "z-ai/glm-5v-turbo",
@@ -12646,9 +12716,9 @@ export const MODELS = {
12646
12716
  reasoning: true,
12647
12717
  input: ["text", "image"],
12648
12718
  cost: {
12649
- input: 0.5,
12650
- output: 3,
12651
- cacheRead: 0.049999999999999996,
12719
+ input: 1.5,
12720
+ output: 9,
12721
+ cacheRead: 0.15,
12652
12722
  cacheWrite: 0.08333333333333334,
12653
12723
  },
12654
12724
  contextWindow: 1048576,
@@ -13915,6 +13985,23 @@ export const MODELS = {
13915
13985
  contextWindow: 1000000,
13916
13986
  maxTokens: 64000,
13917
13987
  },
13988
+ "google/gemini-3.5-flash": {
13989
+ id: "google/gemini-3.5-flash",
13990
+ name: "Gemini 3.5 Flash",
13991
+ api: "anthropic-messages",
13992
+ provider: "vercel-ai-gateway",
13993
+ baseUrl: "https://ai-gateway.vercel.sh",
13994
+ reasoning: true,
13995
+ input: ["text", "image"],
13996
+ cost: {
13997
+ input: 1.5,
13998
+ output: 9,
13999
+ cacheRead: 0.15,
14000
+ cacheWrite: 0,
14001
+ },
14002
+ contextWindow: 1000000,
14003
+ maxTokens: 64000,
14004
+ },
13918
14005
  "google/gemma-4-26b-a4b-it": {
13919
14006
  id: "google/gemma-4-26b-a4b-it",
13920
14007
  name: "Gemma 4 26B A4B IT",
@@ -14374,6 +14461,23 @@ export const MODELS = {
14374
14461
  contextWindow: 128000,
14375
14462
  maxTokens: 64000,
14376
14463
  },
14464
+ "mistral/mistral-medium-3.5": {
14465
+ id: "mistral/mistral-medium-3.5",
14466
+ name: "Mistral Medium Latest",
14467
+ api: "anthropic-messages",
14468
+ provider: "vercel-ai-gateway",
14469
+ baseUrl: "https://ai-gateway.vercel.sh",
14470
+ reasoning: true,
14471
+ input: ["text"],
14472
+ cost: {
14473
+ input: 1.5,
14474
+ output: 7.5,
14475
+ cacheRead: 0,
14476
+ cacheWrite: 0,
14477
+ },
14478
+ contextWindow: 256000,
14479
+ maxTokens: 256000,
14480
+ },
14377
14481
  "mistral/mistral-small": {
14378
14482
  id: "mistral/mistral-small",
14379
14483
  name: "Mistral Small",