@elyracode/ai 0.7.3 → 0.7.5

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.
@@ -3515,40 +3515,6 @@ export const MODELS = {
3515
3515
  },
3516
3516
  },
3517
3517
  "fireworks": {
3518
- "accounts/fireworks/models/deepseek-v3p1": {
3519
- id: "accounts/fireworks/models/deepseek-v3p1",
3520
- name: "DeepSeek V3.1",
3521
- api: "anthropic-messages",
3522
- provider: "fireworks",
3523
- baseUrl: "https://api.fireworks.ai/inference",
3524
- reasoning: true,
3525
- input: ["text"],
3526
- cost: {
3527
- input: 0.56,
3528
- output: 1.68,
3529
- cacheRead: 0,
3530
- cacheWrite: 0,
3531
- },
3532
- contextWindow: 163840,
3533
- maxTokens: 163840,
3534
- },
3535
- "accounts/fireworks/models/deepseek-v3p2": {
3536
- id: "accounts/fireworks/models/deepseek-v3p2",
3537
- name: "DeepSeek V3.2",
3538
- api: "anthropic-messages",
3539
- provider: "fireworks",
3540
- baseUrl: "https://api.fireworks.ai/inference",
3541
- reasoning: true,
3542
- input: ["text"],
3543
- cost: {
3544
- input: 0.56,
3545
- output: 1.68,
3546
- cacheRead: 0.28,
3547
- cacheWrite: 0,
3548
- },
3549
- contextWindow: 160000,
3550
- maxTokens: 160000,
3551
- },
3552
3518
  "accounts/fireworks/models/deepseek-v4-flash": {
3553
3519
  id: "accounts/fireworks/models/deepseek-v4-flash",
3554
3520
  name: "DeepSeek V4 Flash",
@@ -3577,80 +3543,12 @@ export const MODELS = {
3577
3543
  cost: {
3578
3544
  input: 1.74,
3579
3545
  output: 3.48,
3580
- cacheRead: 0.15,
3546
+ cacheRead: 0.145,
3581
3547
  cacheWrite: 0,
3582
3548
  },
3583
3549
  contextWindow: 1000000,
3584
3550
  maxTokens: 384000,
3585
3551
  },
3586
- "accounts/fireworks/models/glm-4p5": {
3587
- id: "accounts/fireworks/models/glm-4p5",
3588
- name: "GLM 4.5",
3589
- api: "anthropic-messages",
3590
- provider: "fireworks",
3591
- baseUrl: "https://api.fireworks.ai/inference",
3592
- reasoning: true,
3593
- input: ["text"],
3594
- cost: {
3595
- input: 0.55,
3596
- output: 2.19,
3597
- cacheRead: 0,
3598
- cacheWrite: 0,
3599
- },
3600
- contextWindow: 131072,
3601
- maxTokens: 131072,
3602
- },
3603
- "accounts/fireworks/models/glm-4p5-air": {
3604
- id: "accounts/fireworks/models/glm-4p5-air",
3605
- name: "GLM 4.5 Air",
3606
- api: "anthropic-messages",
3607
- provider: "fireworks",
3608
- baseUrl: "https://api.fireworks.ai/inference",
3609
- reasoning: true,
3610
- input: ["text"],
3611
- cost: {
3612
- input: 0.22,
3613
- output: 0.88,
3614
- cacheRead: 0,
3615
- cacheWrite: 0,
3616
- },
3617
- contextWindow: 131072,
3618
- maxTokens: 131072,
3619
- },
3620
- "accounts/fireworks/models/glm-4p7": {
3621
- id: "accounts/fireworks/models/glm-4p7",
3622
- name: "GLM 4.7",
3623
- api: "anthropic-messages",
3624
- provider: "fireworks",
3625
- baseUrl: "https://api.fireworks.ai/inference",
3626
- reasoning: true,
3627
- input: ["text"],
3628
- cost: {
3629
- input: 0.6,
3630
- output: 2.2,
3631
- cacheRead: 0.3,
3632
- cacheWrite: 0,
3633
- },
3634
- contextWindow: 198000,
3635
- maxTokens: 198000,
3636
- },
3637
- "accounts/fireworks/models/glm-5": {
3638
- id: "accounts/fireworks/models/glm-5",
3639
- name: "GLM 5",
3640
- api: "anthropic-messages",
3641
- provider: "fireworks",
3642
- baseUrl: "https://api.fireworks.ai/inference",
3643
- reasoning: true,
3644
- input: ["text"],
3645
- cost: {
3646
- input: 1,
3647
- output: 3.2,
3648
- cacheRead: 0.5,
3649
- cacheWrite: 0,
3650
- },
3651
- contextWindow: 202752,
3652
- maxTokens: 131072,
3653
- },
3654
3552
  "accounts/fireworks/models/glm-5p1": {
3655
3553
  id: "accounts/fireworks/models/glm-5p1",
3656
3554
  name: "GLM 5.1",
@@ -3679,7 +3577,7 @@ export const MODELS = {
3679
3577
  cost: {
3680
3578
  input: 0.15,
3681
3579
  output: 0.6,
3682
- cacheRead: 0,
3580
+ cacheRead: 0.015,
3683
3581
  cacheWrite: 0,
3684
3582
  },
3685
3583
  contextWindow: 131072,
@@ -3694,48 +3592,14 @@ export const MODELS = {
3694
3592
  reasoning: true,
3695
3593
  input: ["text"],
3696
3594
  cost: {
3697
- input: 0.05,
3698
- output: 0.2,
3699
- cacheRead: 0,
3595
+ input: 0.07,
3596
+ output: 0.3,
3597
+ cacheRead: 0.035,
3700
3598
  cacheWrite: 0,
3701
3599
  },
3702
3600
  contextWindow: 131072,
3703
3601
  maxTokens: 32768,
3704
3602
  },
3705
- "accounts/fireworks/models/kimi-k2-instruct": {
3706
- id: "accounts/fireworks/models/kimi-k2-instruct",
3707
- name: "Kimi K2 Instruct",
3708
- api: "anthropic-messages",
3709
- provider: "fireworks",
3710
- baseUrl: "https://api.fireworks.ai/inference",
3711
- reasoning: false,
3712
- input: ["text"],
3713
- cost: {
3714
- input: 1,
3715
- output: 3,
3716
- cacheRead: 0,
3717
- cacheWrite: 0,
3718
- },
3719
- contextWindow: 128000,
3720
- maxTokens: 16384,
3721
- },
3722
- "accounts/fireworks/models/kimi-k2-thinking": {
3723
- id: "accounts/fireworks/models/kimi-k2-thinking",
3724
- name: "Kimi K2 Thinking",
3725
- api: "anthropic-messages",
3726
- provider: "fireworks",
3727
- baseUrl: "https://api.fireworks.ai/inference",
3728
- reasoning: true,
3729
- input: ["text"],
3730
- cost: {
3731
- input: 0.6,
3732
- output: 2.5,
3733
- cacheRead: 0.3,
3734
- cacheWrite: 0,
3735
- },
3736
- contextWindow: 256000,
3737
- maxTokens: 256000,
3738
- },
3739
3603
  "accounts/fireworks/models/kimi-k2p5": {
3740
3604
  id: "accounts/fireworks/models/kimi-k2p5",
3741
3605
  name: "Kimi K2.5",
@@ -3770,23 +3634,6 @@ export const MODELS = {
3770
3634
  contextWindow: 262000,
3771
3635
  maxTokens: 262000,
3772
3636
  },
3773
- "accounts/fireworks/models/minimax-m2p1": {
3774
- id: "accounts/fireworks/models/minimax-m2p1",
3775
- name: "MiniMax-M2.1",
3776
- api: "anthropic-messages",
3777
- provider: "fireworks",
3778
- baseUrl: "https://api.fireworks.ai/inference",
3779
- reasoning: true,
3780
- input: ["text"],
3781
- cost: {
3782
- input: 0.3,
3783
- output: 1.2,
3784
- cacheRead: 0.03,
3785
- cacheWrite: 0,
3786
- },
3787
- contextWindow: 200000,
3788
- maxTokens: 200000,
3789
- },
3790
3637
  "accounts/fireworks/models/minimax-m2p5": {
3791
3638
  id: "accounts/fireworks/models/minimax-m2p5",
3792
3639
  name: "MiniMax-M2.5",
@@ -3815,7 +3662,7 @@ export const MODELS = {
3815
3662
  cost: {
3816
3663
  input: 0.3,
3817
3664
  output: 1.2,
3818
- cacheRead: 0.03,
3665
+ cacheRead: 0.06,
3819
3666
  cacheWrite: 0,
3820
3667
  },
3821
3668
  contextWindow: 196608,
@@ -3838,22 +3685,39 @@ export const MODELS = {
3838
3685
  contextWindow: 128000,
3839
3686
  maxTokens: 8192,
3840
3687
  },
3841
- "accounts/fireworks/routers/kimi-k2p5-turbo": {
3842
- id: "accounts/fireworks/routers/kimi-k2p5-turbo",
3843
- name: "Kimi K2.5 Turbo",
3688
+ "accounts/fireworks/routers/glm-5p1-fast": {
3689
+ id: "accounts/fireworks/routers/glm-5p1-fast",
3690
+ name: "GLM 5.1 Fast",
3691
+ api: "anthropic-messages",
3692
+ provider: "fireworks",
3693
+ baseUrl: "https://api.fireworks.ai/inference",
3694
+ reasoning: true,
3695
+ input: ["text"],
3696
+ cost: {
3697
+ input: 2.8,
3698
+ output: 8.8,
3699
+ cacheRead: 0.52,
3700
+ cacheWrite: 0,
3701
+ },
3702
+ contextWindow: 202800,
3703
+ maxTokens: 131072,
3704
+ },
3705
+ "accounts/fireworks/routers/kimi-k2p6-turbo": {
3706
+ id: "accounts/fireworks/routers/kimi-k2p6-turbo",
3707
+ name: "Kimi K2.6 Turbo",
3844
3708
  api: "anthropic-messages",
3845
3709
  provider: "fireworks",
3846
3710
  baseUrl: "https://api.fireworks.ai/inference",
3847
3711
  reasoning: true,
3848
3712
  input: ["text", "image"],
3849
3713
  cost: {
3850
- input: 0,
3851
- output: 0,
3852
- cacheRead: 0,
3714
+ input: 2,
3715
+ output: 8,
3716
+ cacheRead: 0.3,
3853
3717
  cacheWrite: 0,
3854
3718
  },
3855
- contextWindow: 256000,
3856
- maxTokens: 256000,
3719
+ contextWindow: 262000,
3720
+ maxTokens: 262000,
3857
3721
  },
3858
3722
  },
3859
3723
  "github-copilot": {
@@ -4026,6 +3890,25 @@ export const MODELS = {
4026
3890
  contextWindow: 128000,
4027
3891
  maxTokens: 64000,
4028
3892
  },
3893
+ "gemini-3.5-flash": {
3894
+ id: "gemini-3.5-flash",
3895
+ name: "Gemini 3.5 Flash",
3896
+ api: "openai-completions",
3897
+ provider: "github-copilot",
3898
+ baseUrl: "https://api.individual.githubcopilot.com",
3899
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3900
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3901
+ reasoning: true,
3902
+ input: ["text", "image"],
3903
+ cost: {
3904
+ input: 0,
3905
+ output: 0,
3906
+ cacheRead: 0,
3907
+ cacheWrite: 0,
3908
+ },
3909
+ contextWindow: 128000,
3910
+ maxTokens: 64000,
3911
+ },
4029
3912
  "gpt-4.1": {
4030
3913
  id: "gpt-4.1",
4031
3914
  name: "GPT-4.1",
@@ -8828,13 +8711,13 @@ export const MODELS = {
8828
8711
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8829
8712
  input: ["text"],
8830
8713
  cost: {
8831
- input: 0.112,
8832
- output: 0.224,
8833
- cacheRead: 0.022,
8714
+ input: 0.09999999999999999,
8715
+ output: 0.19999999999999998,
8716
+ cacheRead: 0.02,
8834
8717
  cacheWrite: 0,
8835
8718
  },
8836
8719
  contextWindow: 1048576,
8837
- maxTokens: 4096,
8720
+ maxTokens: 16384,
8838
8721
  },
8839
8722
  "deepseek/deepseek-v4-flash:free": {
8840
8723
  id: "deepseek/deepseek-v4-flash:free",
@@ -11923,11 +11806,11 @@ export const MODELS = {
11923
11806
  cost: {
11924
11807
  input: 0.15,
11925
11808
  output: 1,
11926
- cacheRead: 0.049999999999999996,
11809
+ cacheRead: 0,
11927
11810
  cacheWrite: 0,
11928
11811
  },
11929
11812
  contextWindow: 262144,
11930
- maxTokens: 262144,
11813
+ maxTokens: 262140,
11931
11814
  },
11932
11815
  "qwen/qwen3.6-flash": {
11933
11816
  id: "qwen/qwen3.6-flash",
@@ -11938,10 +11821,10 @@ export const MODELS = {
11938
11821
  reasoning: true,
11939
11822
  input: ["text", "image"],
11940
11823
  cost: {
11941
- input: 0.12375000000000001,
11942
- output: 0.7424999999999999,
11824
+ input: 0.1875,
11825
+ output: 1.125,
11943
11826
  cacheRead: 0,
11944
- cacheWrite: 0.1545,
11827
+ cacheWrite: 0.234375,
11945
11828
  },
11946
11829
  contextWindow: 1000000,
11947
11830
  maxTokens: 65536,
@@ -11972,10 +11855,10 @@ export const MODELS = {
11972
11855
  reasoning: true,
11973
11856
  input: ["text", "image"],
11974
11857
  cost: {
11975
- input: 0.1794,
11976
- output: 1.07315,
11858
+ input: 0.325,
11859
+ output: 1.95,
11977
11860
  cacheRead: 0,
11978
- cacheWrite: 0.2236,
11861
+ cacheWrite: 0.40625,
11979
11862
  },
11980
11863
  contextWindow: 1000000,
11981
11864
  maxTokens: 65536,