@elyracode/ai 0.6.1 → 0.6.3

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",
@@ -9242,6 +9277,23 @@ export const MODELS = {
9242
9277
  contextWindow: 1048756,
9243
9278
  maxTokens: 65536,
9244
9279
  },
9280
+ "google/gemini-3.5-flash": {
9281
+ id: "google/gemini-3.5-flash",
9282
+ name: "Google: Gemini 3.5 Flash",
9283
+ api: "openai-completions",
9284
+ provider: "openrouter",
9285
+ baseUrl: "https://openrouter.ai/api/v1",
9286
+ reasoning: true,
9287
+ input: ["text", "image"],
9288
+ cost: {
9289
+ input: 1.5,
9290
+ output: 9,
9291
+ cacheRead: 0.15,
9292
+ cacheWrite: 0.08333333333333334,
9293
+ },
9294
+ contextWindow: 1048576,
9295
+ maxTokens: 65536,
9296
+ },
9245
9297
  "google/gemma-3-12b-it": {
9246
9298
  id: "google/gemma-3-12b-it",
9247
9299
  name: "Google: Gemma 3 12B",
@@ -9285,13 +9337,13 @@ export const MODELS = {
9285
9337
  reasoning: true,
9286
9338
  input: ["text", "image"],
9287
9339
  cost: {
9288
- input: 0.07,
9289
- output: 0.33999999999999997,
9340
+ input: 0.06,
9341
+ output: 0.33,
9290
9342
  cacheRead: 0,
9291
9343
  cacheWrite: 0,
9292
9344
  },
9293
9345
  contextWindow: 262144,
9294
- maxTokens: 16384,
9346
+ maxTokens: 4096,
9295
9347
  },
9296
9348
  "google/gemma-4-26b-a4b-it:free": {
9297
9349
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9881,12 +9933,12 @@ export const MODELS = {
9881
9933
  input: ["text"],
9882
9934
  cost: {
9883
9935
  input: 0.02,
9884
- output: 0.04,
9936
+ output: 0.03,
9885
9937
  cacheRead: 0,
9886
9938
  cacheWrite: 0,
9887
9939
  },
9888
9940
  contextWindow: 131072,
9889
- maxTokens: 16384,
9941
+ maxTokens: 4096,
9890
9942
  },
9891
9943
  "mistralai/mistral-saba": {
9892
9944
  id: "mistralai/mistral-saba",
@@ -10169,13 +10221,13 @@ export const MODELS = {
10169
10221
  reasoning: true,
10170
10222
  input: ["text"],
10171
10223
  cost: {
10172
- input: 0.09999999999999999,
10173
- output: 0.5,
10224
+ input: 0.09,
10225
+ output: 0.44999999999999996,
10174
10226
  cacheRead: 0,
10175
10227
  cacheWrite: 0,
10176
10228
  },
10177
10229
  contextWindow: 1000000,
10178
- maxTokens: 16384,
10230
+ maxTokens: 4096,
10179
10231
  },
10180
10232
  "nvidia/nemotron-3-super-120b-a12b:free": {
10181
10233
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -10998,12 +11050,12 @@ export const MODELS = {
10998
11050
  input: ["text"],
10999
11051
  cost: {
11000
11052
  input: 0.039,
11001
- output: 0.19,
11053
+ output: 0.18,
11002
11054
  cacheRead: 0,
11003
11055
  cacheWrite: 0,
11004
11056
  },
11005
11057
  contextWindow: 131072,
11006
- maxTokens: 131072,
11058
+ maxTokens: 4096,
11007
11059
  },
11008
11060
  "openai/gpt-oss-120b:free": {
11009
11061
  id: "openai/gpt-oss-120b:free",
@@ -11915,13 +11967,13 @@ export const MODELS = {
11915
11967
  reasoning: true,
11916
11968
  input: ["text", "image"],
11917
11969
  cost: {
11918
- input: 0.14,
11970
+ input: 0.13899999999999998,
11919
11971
  output: 1,
11920
- cacheRead: 0.049999999999999996,
11972
+ cacheRead: 0,
11921
11973
  cacheWrite: 0,
11922
11974
  },
11923
11975
  contextWindow: 262144,
11924
- maxTokens: 81920,
11976
+ maxTokens: 4096,
11925
11977
  },
11926
11978
  "qwen/qwen3.5-397b-a17b": {
11927
11979
  id: "qwen/qwen3.5-397b-a17b",
@@ -12561,13 +12613,13 @@ export const MODELS = {
12561
12613
  reasoning: true,
12562
12614
  input: ["text"],
12563
12615
  cost: {
12564
- input: 0.98,
12565
- output: 3.08,
12566
- cacheRead: 0.182,
12616
+ input: 0,
12617
+ output: 0,
12618
+ cacheRead: 0,
12567
12619
  cacheWrite: 0,
12568
12620
  },
12569
- contextWindow: 202752,
12570
- maxTokens: 4096,
12621
+ contextWindow: 202800,
12622
+ maxTokens: 202800,
12571
12623
  },
12572
12624
  "z-ai/glm-5v-turbo": {
12573
12625
  id: "z-ai/glm-5v-turbo",
@@ -12646,9 +12698,9 @@ export const MODELS = {
12646
12698
  reasoning: true,
12647
12699
  input: ["text", "image"],
12648
12700
  cost: {
12649
- input: 0.5,
12650
- output: 3,
12651
- cacheRead: 0.049999999999999996,
12701
+ input: 1.5,
12702
+ output: 9,
12703
+ cacheRead: 0.15,
12652
12704
  cacheWrite: 0.08333333333333334,
12653
12705
  },
12654
12706
  contextWindow: 1048576,
@@ -13915,6 +13967,23 @@ export const MODELS = {
13915
13967
  contextWindow: 1000000,
13916
13968
  maxTokens: 64000,
13917
13969
  },
13970
+ "google/gemini-3.5-flash": {
13971
+ id: "google/gemini-3.5-flash",
13972
+ name: "Gemini 3.5 Flash",
13973
+ api: "anthropic-messages",
13974
+ provider: "vercel-ai-gateway",
13975
+ baseUrl: "https://ai-gateway.vercel.sh",
13976
+ reasoning: true,
13977
+ input: ["text", "image"],
13978
+ cost: {
13979
+ input: 1.5,
13980
+ output: 9,
13981
+ cacheRead: 0.15,
13982
+ cacheWrite: 0,
13983
+ },
13984
+ contextWindow: 1000000,
13985
+ maxTokens: 64000,
13986
+ },
13918
13987
  "google/gemma-4-26b-a4b-it": {
13919
13988
  id: "google/gemma-4-26b-a4b-it",
13920
13989
  name: "Gemma 4 26B A4B IT",