@elyracode/ai 0.9.1 → 0.9.2

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.
@@ -1086,6 +1086,59 @@ export const MODELS = {
1086
1086
  contextWindow: 262144,
1087
1087
  maxTokens: 131072,
1088
1088
  },
1089
+ "openai.gpt-5.4": {
1090
+ id: "openai.gpt-5.4",
1091
+ name: "GPT-5.4",
1092
+ api: "bedrock-converse-stream",
1093
+ provider: "amazon-bedrock",
1094
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1095
+ reasoning: true,
1096
+ thinkingLevelMap: { "xhigh": "xhigh" },
1097
+ input: ["text", "image"],
1098
+ cost: {
1099
+ input: 2.75,
1100
+ output: 16.5,
1101
+ cacheRead: 0.275,
1102
+ cacheWrite: 0,
1103
+ },
1104
+ contextWindow: 272000,
1105
+ maxTokens: 128000,
1106
+ },
1107
+ "openai.gpt-5.5": {
1108
+ id: "openai.gpt-5.5",
1109
+ name: "GPT-5.5",
1110
+ api: "bedrock-converse-stream",
1111
+ provider: "amazon-bedrock",
1112
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1113
+ reasoning: true,
1114
+ thinkingLevelMap: { "xhigh": "xhigh" },
1115
+ input: ["text", "image"],
1116
+ cost: {
1117
+ input: 5.5,
1118
+ output: 33,
1119
+ cacheRead: 0.55,
1120
+ cacheWrite: 0,
1121
+ },
1122
+ contextWindow: 272000,
1123
+ maxTokens: 128000,
1124
+ },
1125
+ "openai.gpt-oss-120b": {
1126
+ id: "openai.gpt-oss-120b",
1127
+ name: "gpt-oss-120b",
1128
+ api: "bedrock-converse-stream",
1129
+ provider: "amazon-bedrock",
1130
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1131
+ reasoning: false,
1132
+ input: ["text"],
1133
+ cost: {
1134
+ input: 0.15,
1135
+ output: 0.6,
1136
+ cacheRead: 0,
1137
+ cacheWrite: 0,
1138
+ },
1139
+ contextWindow: 128000,
1140
+ maxTokens: 16384,
1141
+ },
1089
1142
  "openai.gpt-oss-120b-1:0": {
1090
1143
  id: "openai.gpt-oss-120b-1:0",
1091
1144
  name: "gpt-oss-120b",
@@ -1103,6 +1156,23 @@ export const MODELS = {
1103
1156
  contextWindow: 128000,
1104
1157
  maxTokens: 16384,
1105
1158
  },
1159
+ "openai.gpt-oss-20b": {
1160
+ id: "openai.gpt-oss-20b",
1161
+ name: "gpt-oss-20b",
1162
+ api: "bedrock-converse-stream",
1163
+ provider: "amazon-bedrock",
1164
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1165
+ reasoning: false,
1166
+ input: ["text"],
1167
+ cost: {
1168
+ input: 0.07,
1169
+ output: 0.3,
1170
+ cacheRead: 0,
1171
+ cacheWrite: 0,
1172
+ },
1173
+ contextWindow: 128000,
1174
+ maxTokens: 16384,
1175
+ },
1106
1176
  "openai.gpt-oss-20b-1:0": {
1107
1177
  id: "openai.gpt-oss-20b-1:0",
1108
1178
  name: "gpt-oss-20b",
@@ -3638,8 +3708,8 @@ export const MODELS = {
3638
3708
  cacheRead: 0.1,
3639
3709
  cacheWrite: 0,
3640
3710
  },
3641
- contextWindow: 128000,
3642
- maxTokens: 8192,
3711
+ contextWindow: 262144,
3712
+ maxTokens: 65536,
3643
3713
  },
3644
3714
  "accounts/fireworks/routers/glm-5p1-fast": {
3645
3715
  id: "accounts/fireworks/routers/glm-5p1-fast",
@@ -3658,6 +3728,23 @@ export const MODELS = {
3658
3728
  contextWindow: 202800,
3659
3729
  maxTokens: 131072,
3660
3730
  },
3731
+ "accounts/fireworks/routers/kimi-k2p6-fast": {
3732
+ id: "accounts/fireworks/routers/kimi-k2p6-fast",
3733
+ name: "Kimi K2.6 Fast",
3734
+ api: "anthropic-messages",
3735
+ provider: "fireworks",
3736
+ baseUrl: "https://api.fireworks.ai/inference",
3737
+ reasoning: true,
3738
+ input: ["text", "image"],
3739
+ cost: {
3740
+ input: 2,
3741
+ output: 8,
3742
+ cacheRead: 0.3,
3743
+ cacheWrite: 0,
3744
+ },
3745
+ contextWindow: 262000,
3746
+ maxTokens: 262000,
3747
+ },
3661
3748
  "accounts/fireworks/routers/kimi-k2p6-turbo": {
3662
3749
  id: "accounts/fireworks/routers/kimi-k2p6-turbo",
3663
3750
  name: "Kimi K2.6 Turbo",
@@ -3679,7 +3766,7 @@ export const MODELS = {
3679
3766
  "github-copilot": {
3680
3767
  "claude-haiku-4.5": {
3681
3768
  id: "claude-haiku-4.5",
3682
- name: "Claude Haiku 4.5",
3769
+ name: "Claude Haiku 4.5 (latest)",
3683
3770
  api: "anthropic-messages",
3684
3771
  provider: "github-copilot",
3685
3772
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3688,17 +3775,17 @@ export const MODELS = {
3688
3775
  reasoning: true,
3689
3776
  input: ["text", "image"],
3690
3777
  cost: {
3691
- input: 0,
3692
- output: 0,
3693
- cacheRead: 0,
3694
- cacheWrite: 0,
3778
+ input: 1,
3779
+ output: 5,
3780
+ cacheRead: 0.1,
3781
+ cacheWrite: 1.25,
3695
3782
  },
3696
3783
  contextWindow: 200000,
3697
3784
  maxTokens: 64000,
3698
3785
  },
3699
3786
  "claude-opus-4.5": {
3700
3787
  id: "claude-opus-4.5",
3701
- name: "Claude Opus 4.5",
3788
+ name: "Claude Opus 4.5 (latest)",
3702
3789
  api: "anthropic-messages",
3703
3790
  provider: "github-copilot",
3704
3791
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3706,10 +3793,10 @@ export const MODELS = {
3706
3793
  reasoning: true,
3707
3794
  input: ["text", "image"],
3708
3795
  cost: {
3709
- input: 0,
3710
- output: 0,
3711
- cacheRead: 0,
3712
- cacheWrite: 0,
3796
+ input: 5,
3797
+ output: 25,
3798
+ cacheRead: 0.5,
3799
+ cacheWrite: 6.25,
3713
3800
  },
3714
3801
  contextWindow: 200000,
3715
3802
  maxTokens: 32000,
@@ -3725,10 +3812,10 @@ export const MODELS = {
3725
3812
  thinkingLevelMap: { "xhigh": "max" },
3726
3813
  input: ["text", "image"],
3727
3814
  cost: {
3728
- input: 0,
3729
- output: 0,
3730
- cacheRead: 0,
3731
- cacheWrite: 0,
3815
+ input: 5,
3816
+ output: 25,
3817
+ cacheRead: 0.5,
3818
+ cacheWrite: 6.25,
3732
3819
  },
3733
3820
  contextWindow: 1000000,
3734
3821
  maxTokens: 32000,
@@ -3744,10 +3831,10 @@ export const MODELS = {
3744
3831
  thinkingLevelMap: { "xhigh": "xhigh" },
3745
3832
  input: ["text", "image"],
3746
3833
  cost: {
3747
- input: 0,
3748
- output: 0,
3749
- cacheRead: 0,
3750
- cacheWrite: 0,
3834
+ input: 5,
3835
+ output: 25,
3836
+ cacheRead: 0.5,
3837
+ cacheWrite: 6.25,
3751
3838
  },
3752
3839
  contextWindow: 200000,
3753
3840
  maxTokens: 32000,
@@ -3763,17 +3850,36 @@ export const MODELS = {
3763
3850
  thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
3764
3851
  input: ["text", "image"],
3765
3852
  cost: {
3766
- input: 0,
3767
- output: 0,
3768
- cacheRead: 0,
3769
- cacheWrite: 0,
3853
+ input: 5,
3854
+ output: 25,
3855
+ cacheRead: 0.5,
3856
+ cacheWrite: 6.25,
3770
3857
  },
3771
3858
  contextWindow: 200000,
3772
3859
  maxTokens: 64000,
3773
3860
  },
3861
+ "claude-sonnet-4": {
3862
+ id: "claude-sonnet-4",
3863
+ name: "Claude Sonnet 4 (latest)",
3864
+ api: "anthropic-messages",
3865
+ provider: "github-copilot",
3866
+ baseUrl: "https://api.individual.githubcopilot.com",
3867
+ 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" },
3868
+ compat: { "supportsEagerToolInputStreaming": false },
3869
+ reasoning: true,
3870
+ input: ["text", "image"],
3871
+ cost: {
3872
+ input: 3,
3873
+ output: 15,
3874
+ cacheRead: 0.3,
3875
+ cacheWrite: 3.75,
3876
+ },
3877
+ contextWindow: 216000,
3878
+ maxTokens: 16000,
3879
+ },
3774
3880
  "claude-sonnet-4.5": {
3775
3881
  id: "claude-sonnet-4.5",
3776
- name: "Claude Sonnet 4.5",
3882
+ name: "Claude Sonnet 4.5 (latest)",
3777
3883
  api: "anthropic-messages",
3778
3884
  provider: "github-copilot",
3779
3885
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3782,10 +3888,10 @@ export const MODELS = {
3782
3888
  reasoning: true,
3783
3889
  input: ["text", "image"],
3784
3890
  cost: {
3785
- input: 0,
3786
- output: 0,
3787
- cacheRead: 0,
3788
- cacheWrite: 0,
3891
+ input: 3,
3892
+ output: 15,
3893
+ cacheRead: 0.3,
3894
+ cacheWrite: 3.75,
3789
3895
  },
3790
3896
  contextWindow: 200000,
3791
3897
  maxTokens: 32000,
@@ -3800,10 +3906,10 @@ export const MODELS = {
3800
3906
  reasoning: true,
3801
3907
  input: ["text", "image"],
3802
3908
  cost: {
3803
- input: 0,
3804
- output: 0,
3805
- cacheRead: 0,
3806
- cacheWrite: 0,
3909
+ input: 3,
3910
+ output: 15,
3911
+ cacheRead: 0.3,
3912
+ cacheWrite: 3.75,
3807
3913
  },
3808
3914
  contextWindow: 1000000,
3809
3915
  maxTokens: 32000,
@@ -3816,12 +3922,12 @@ export const MODELS = {
3816
3922
  baseUrl: "https://api.individual.githubcopilot.com",
3817
3923
  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" },
3818
3924
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3819
- reasoning: false,
3925
+ reasoning: true,
3820
3926
  input: ["text", "image"],
3821
3927
  cost: {
3822
- input: 0,
3823
- output: 0,
3824
- cacheRead: 0,
3928
+ input: 1.25,
3929
+ output: 10,
3930
+ cacheRead: 0.125,
3825
3931
  cacheWrite: 0,
3826
3932
  },
3827
3933
  contextWindow: 128000,
@@ -3829,7 +3935,7 @@ export const MODELS = {
3829
3935
  },
3830
3936
  "gemini-3-flash-preview": {
3831
3937
  id: "gemini-3-flash-preview",
3832
- name: "Gemini 3 Flash",
3938
+ name: "Gemini 3 Flash Preview",
3833
3939
  api: "openai-completions",
3834
3940
  provider: "github-copilot",
3835
3941
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3838,9 +3944,9 @@ export const MODELS = {
3838
3944
  reasoning: true,
3839
3945
  input: ["text", "image"],
3840
3946
  cost: {
3841
- input: 0,
3842
- output: 0,
3843
- cacheRead: 0,
3947
+ input: 0.5,
3948
+ output: 3,
3949
+ cacheRead: 0.05,
3844
3950
  cacheWrite: 0,
3845
3951
  },
3846
3952
  contextWindow: 128000,
@@ -3857,9 +3963,9 @@ export const MODELS = {
3857
3963
  reasoning: true,
3858
3964
  input: ["text", "image"],
3859
3965
  cost: {
3860
- input: 0,
3861
- output: 0,
3862
- cacheRead: 0,
3966
+ input: 2,
3967
+ output: 12,
3968
+ cacheRead: 0.2,
3863
3969
  cacheWrite: 0,
3864
3970
  },
3865
3971
  contextWindow: 200000,
@@ -3876,9 +3982,9 @@ export const MODELS = {
3876
3982
  reasoning: true,
3877
3983
  input: ["text", "image"],
3878
3984
  cost: {
3879
- input: 0,
3880
- output: 0,
3881
- cacheRead: 0,
3985
+ input: 1.5,
3986
+ output: 9,
3987
+ cacheRead: 0.15,
3882
3988
  cacheWrite: 0,
3883
3989
  },
3884
3990
  contextWindow: 200000,
@@ -3895,36 +4001,17 @@ export const MODELS = {
3895
4001
  reasoning: false,
3896
4002
  input: ["text", "image"],
3897
4003
  cost: {
3898
- input: 0,
3899
- output: 0,
3900
- cacheRead: 0,
4004
+ input: 2,
4005
+ output: 8,
4006
+ cacheRead: 0.5,
3901
4007
  cacheWrite: 0,
3902
4008
  },
3903
4009
  contextWindow: 128000,
3904
4010
  maxTokens: 16384,
3905
4011
  },
3906
- "gpt-4o": {
3907
- id: "gpt-4o",
3908
- name: "GPT-4o",
3909
- api: "openai-completions",
3910
- provider: "github-copilot",
3911
- baseUrl: "https://api.individual.githubcopilot.com",
3912
- 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" },
3913
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3914
- reasoning: false,
3915
- input: ["text", "image"],
3916
- cost: {
3917
- input: 0,
3918
- output: 0,
3919
- cacheRead: 0,
3920
- cacheWrite: 0,
3921
- },
3922
- contextWindow: 128000,
3923
- maxTokens: 4096,
3924
- },
3925
4012
  "gpt-5-mini": {
3926
4013
  id: "gpt-5-mini",
3927
- name: "GPT-5-mini",
4014
+ name: "GPT-5 Mini",
3928
4015
  api: "openai-responses",
3929
4016
  provider: "github-copilot",
3930
4017
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3933,9 +4020,9 @@ export const MODELS = {
3933
4020
  thinkingLevelMap: { "off": null },
3934
4021
  input: ["text", "image"],
3935
4022
  cost: {
3936
- input: 0,
3937
- output: 0,
3938
- cacheRead: 0,
4023
+ input: 0.25,
4024
+ output: 2,
4025
+ cacheRead: 0.025,
3939
4026
  cacheWrite: 0,
3940
4027
  },
3941
4028
  contextWindow: 264000,
@@ -3952,9 +4039,9 @@ export const MODELS = {
3952
4039
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3953
4040
  input: ["text", "image"],
3954
4041
  cost: {
3955
- input: 0,
3956
- output: 0,
3957
- cacheRead: 0,
4042
+ input: 1.75,
4043
+ output: 14,
4044
+ cacheRead: 0.175,
3958
4045
  cacheWrite: 0,
3959
4046
  },
3960
4047
  contextWindow: 400000,
@@ -3962,7 +4049,7 @@ export const MODELS = {
3962
4049
  },
3963
4050
  "gpt-5.2-codex": {
3964
4051
  id: "gpt-5.2-codex",
3965
- name: "GPT-5.2-Codex",
4052
+ name: "GPT-5.2 Codex",
3966
4053
  api: "openai-responses",
3967
4054
  provider: "github-copilot",
3968
4055
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3971,9 +4058,9 @@ export const MODELS = {
3971
4058
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3972
4059
  input: ["text", "image"],
3973
4060
  cost: {
3974
- input: 0,
3975
- output: 0,
3976
- cacheRead: 0,
4061
+ input: 1.75,
4062
+ output: 14,
4063
+ cacheRead: 0.175,
3977
4064
  cacheWrite: 0,
3978
4065
  },
3979
4066
  contextWindow: 400000,
@@ -3981,7 +4068,7 @@ export const MODELS = {
3981
4068
  },
3982
4069
  "gpt-5.3-codex": {
3983
4070
  id: "gpt-5.3-codex",
3984
- name: "GPT-5.3-Codex",
4071
+ name: "GPT-5.3 Codex",
3985
4072
  api: "openai-responses",
3986
4073
  provider: "github-copilot",
3987
4074
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3990,9 +4077,9 @@ export const MODELS = {
3990
4077
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3991
4078
  input: ["text", "image"],
3992
4079
  cost: {
3993
- input: 0,
3994
- output: 0,
3995
- cacheRead: 0,
4080
+ input: 1.75,
4081
+ output: 14,
4082
+ cacheRead: 0.175,
3996
4083
  cacheWrite: 0,
3997
4084
  },
3998
4085
  contextWindow: 400000,
@@ -4009,9 +4096,9 @@ export const MODELS = {
4009
4096
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4010
4097
  input: ["text", "image"],
4011
4098
  cost: {
4012
- input: 0,
4013
- output: 0,
4014
- cacheRead: 0,
4099
+ input: 2.5,
4100
+ output: 15,
4101
+ cacheRead: 0.25,
4015
4102
  cacheWrite: 0,
4016
4103
  },
4017
4104
  contextWindow: 400000,
@@ -4019,7 +4106,7 @@ export const MODELS = {
4019
4106
  },
4020
4107
  "gpt-5.4-mini": {
4021
4108
  id: "gpt-5.4-mini",
4022
- name: "GPT-5.4 Mini",
4109
+ name: "GPT-5.4 mini",
4023
4110
  api: "openai-responses",
4024
4111
  provider: "github-copilot",
4025
4112
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -4028,9 +4115,28 @@ export const MODELS = {
4028
4115
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4029
4116
  input: ["text", "image"],
4030
4117
  cost: {
4031
- input: 0,
4032
- output: 0,
4033
- cacheRead: 0,
4118
+ input: 0.75,
4119
+ output: 4.5,
4120
+ cacheRead: 0.075,
4121
+ cacheWrite: 0,
4122
+ },
4123
+ contextWindow: 400000,
4124
+ maxTokens: 128000,
4125
+ },
4126
+ "gpt-5.4-nano": {
4127
+ id: "gpt-5.4-nano",
4128
+ name: "GPT-5.4 nano",
4129
+ api: "openai-responses",
4130
+ provider: "github-copilot",
4131
+ baseUrl: "https://api.individual.githubcopilot.com",
4132
+ 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" },
4133
+ reasoning: true,
4134
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4135
+ input: ["text", "image"],
4136
+ cost: {
4137
+ input: 0.2,
4138
+ output: 1.25,
4139
+ cacheRead: 0.02,
4034
4140
  cacheWrite: 0,
4035
4141
  },
4036
4142
  contextWindow: 400000,
@@ -4047,32 +4153,32 @@ export const MODELS = {
4047
4153
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4048
4154
  input: ["text", "image"],
4049
4155
  cost: {
4050
- input: 0,
4051
- output: 0,
4052
- cacheRead: 0,
4156
+ input: 5,
4157
+ output: 30,
4158
+ cacheRead: 0.5,
4053
4159
  cacheWrite: 0,
4054
4160
  },
4055
4161
  contextWindow: 400000,
4056
4162
  maxTokens: 128000,
4057
4163
  },
4058
- "grok-code-fast-1": {
4059
- id: "grok-code-fast-1",
4060
- name: "Grok Code Fast 1",
4164
+ "raptor-mini": {
4165
+ id: "raptor-mini",
4166
+ name: "Raptor mini",
4061
4167
  api: "openai-completions",
4062
4168
  provider: "github-copilot",
4063
4169
  baseUrl: "https://api.individual.githubcopilot.com",
4064
4170
  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" },
4065
4171
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4066
4172
  reasoning: true,
4067
- input: ["text"],
4173
+ input: ["text", "image"],
4068
4174
  cost: {
4069
- input: 0,
4070
- output: 0,
4071
- cacheRead: 0,
4175
+ input: 0.25,
4176
+ output: 2,
4177
+ cacheRead: 0.025,
4072
4178
  cacheWrite: 0,
4073
4179
  },
4074
- contextWindow: 128000,
4075
- maxTokens: 64000,
4180
+ contextWindow: 400000,
4181
+ maxTokens: 128000,
4076
4182
  },
4077
4183
  },
4078
4184
  "google": {
@@ -5419,6 +5525,23 @@ export const MODELS = {
5419
5525
  contextWindow: 262144,
5420
5526
  maxTokens: 262144,
5421
5527
  },
5528
+ "devstral-latest": {
5529
+ id: "devstral-latest",
5530
+ name: "Devstral 2",
5531
+ api: "mistral-conversations",
5532
+ provider: "mistral",
5533
+ baseUrl: "https://api.mistral.ai",
5534
+ reasoning: false,
5535
+ input: ["text"],
5536
+ cost: {
5537
+ input: 0.4,
5538
+ output: 2,
5539
+ cacheRead: 0,
5540
+ cacheWrite: 0,
5541
+ },
5542
+ contextWindow: 262144,
5543
+ maxTokens: 262144,
5544
+ },
5422
5545
  "devstral-medium-2507": {
5423
5546
  id: "devstral-medium-2507",
5424
5547
  name: "Devstral Medium",
@@ -5697,11 +5820,11 @@ export const MODELS = {
5697
5820
  api: "mistral-conversations",
5698
5821
  provider: "mistral",
5699
5822
  baseUrl: "https://api.mistral.ai",
5700
- reasoning: true,
5823
+ reasoning: false,
5701
5824
  input: ["text", "image"],
5702
5825
  cost: {
5703
- input: 1.5,
5704
- output: 7.5,
5826
+ input: 0.4,
5827
+ output: 2,
5705
5828
  cacheRead: 0,
5706
5829
  cacheWrite: 0,
5707
5830
  },
@@ -5793,6 +5916,23 @@ export const MODELS = {
5793
5916
  contextWindow: 8000,
5794
5917
  maxTokens: 8000,
5795
5918
  },
5919
+ "open-mistral-nemo": {
5920
+ id: "open-mistral-nemo",
5921
+ name: "Open Mistral Nemo",
5922
+ api: "mistral-conversations",
5923
+ provider: "mistral",
5924
+ baseUrl: "https://api.mistral.ai",
5925
+ reasoning: false,
5926
+ input: ["text"],
5927
+ cost: {
5928
+ input: 0.15,
5929
+ output: 0.15,
5930
+ cacheRead: 0,
5931
+ cacheWrite: 0,
5932
+ },
5933
+ contextWindow: 128000,
5934
+ maxTokens: 128000,
5935
+ },
5796
5936
  "open-mixtral-8x22b": {
5797
5937
  id: "open-mixtral-8x22b",
5798
5938
  name: "Mixtral 8x22B",
@@ -7677,9 +7817,9 @@ export const MODELS = {
7677
7817
  contextWindow: 200000,
7678
7818
  maxTokens: 32000,
7679
7819
  },
7680
- "nemotron-3-super-free": {
7681
- id: "nemotron-3-super-free",
7682
- name: "Nemotron 3 Super Free",
7820
+ "nemotron-3-ultra-free": {
7821
+ id: "nemotron-3-ultra-free",
7822
+ name: "Nemotron 3 Ultra Free",
7683
7823
  api: "openai-completions",
7684
7824
  provider: "opencode",
7685
7825
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7691,7 +7831,7 @@ export const MODELS = {
7691
7831
  cacheRead: 0,
7692
7832
  cacheWrite: 0,
7693
7833
  },
7694
- contextWindow: 204800,
7834
+ contextWindow: 1000000,
7695
7835
  maxTokens: 128000,
7696
7836
  },
7697
7837
  "qwen3.5-plus": {
@@ -7936,7 +8076,7 @@ export const MODELS = {
7936
8076
  cacheRead: 0.05,
7937
8077
  cacheWrite: 0.625,
7938
8078
  },
7939
- contextWindow: 262144,
8079
+ contextWindow: 1000000,
7940
8080
  maxTokens: 65536,
7941
8081
  },
7942
8082
  "qwen3.7-max": {
@@ -7956,6 +8096,23 @@ export const MODELS = {
7956
8096
  contextWindow: 1000000,
7957
8097
  maxTokens: 65536,
7958
8098
  },
8099
+ "qwen3.7-plus": {
8100
+ id: "qwen3.7-plus",
8101
+ name: "Qwen3.7 Plus",
8102
+ api: "anthropic-messages",
8103
+ provider: "opencode-go",
8104
+ baseUrl: "https://opencode.ai/zen/go",
8105
+ reasoning: true,
8106
+ input: ["text", "image"],
8107
+ cost: {
8108
+ input: 0.4,
8109
+ output: 1.6,
8110
+ cacheRead: 0.04,
8111
+ cacheWrite: 0.5,
8112
+ },
8113
+ contextWindow: 1000000,
8114
+ maxTokens: 65536,
8115
+ },
7959
8116
  },
7960
8117
  "openrouter": {
7961
8118
  "ai21/jamba-large-1.7": {
@@ -8500,8 +8657,8 @@ export const MODELS = {
8500
8657
  reasoning: false,
8501
8658
  input: ["text"],
8502
8659
  cost: {
8503
- input: 0.2288,
8504
- output: 0.9144,
8660
+ input: 0.20020000000000002,
8661
+ output: 0.8000999999999999,
8505
8662
  cacheRead: 0,
8506
8663
  cacheWrite: 0,
8507
8664
  },
@@ -8602,13 +8759,13 @@ export const MODELS = {
8602
8759
  reasoning: true,
8603
8760
  input: ["text"],
8604
8761
  cost: {
8605
- input: 0.252,
8606
- output: 0.378,
8607
- cacheRead: 0.0252,
8762
+ input: 0.2288,
8763
+ output: 0.3432,
8764
+ cacheRead: 0,
8608
8765
  cacheWrite: 0,
8609
8766
  },
8610
8767
  contextWindow: 131072,
8611
- maxTokens: 65536,
8768
+ maxTokens: 64000,
8612
8769
  },
8613
8770
  "deepseek/deepseek-v3.2-exp": {
8614
8771
  id: "deepseek/deepseek-v3.2-exp",
@@ -8682,40 +8839,6 @@ export const MODELS = {
8682
8839
  contextWindow: 32768,
8683
8840
  maxTokens: 4096,
8684
8841
  },
8685
- "google/gemini-2.0-flash-001": {
8686
- id: "google/gemini-2.0-flash-001",
8687
- name: "Google: Gemini 2.0 Flash",
8688
- api: "openai-completions",
8689
- provider: "openrouter",
8690
- baseUrl: "https://openrouter.ai/api/v1",
8691
- reasoning: false,
8692
- input: ["text", "image"],
8693
- cost: {
8694
- input: 0.09999999999999999,
8695
- output: 0.39999999999999997,
8696
- cacheRead: 0.024999999999999998,
8697
- cacheWrite: 0.08333333333333334,
8698
- },
8699
- contextWindow: 1048576,
8700
- maxTokens: 8192,
8701
- },
8702
- "google/gemini-2.0-flash-lite-001": {
8703
- id: "google/gemini-2.0-flash-lite-001",
8704
- name: "Google: Gemini 2.0 Flash Lite",
8705
- api: "openai-completions",
8706
- provider: "openrouter",
8707
- baseUrl: "https://openrouter.ai/api/v1",
8708
- reasoning: false,
8709
- input: ["text", "image"],
8710
- cost: {
8711
- input: 0.075,
8712
- output: 0.3,
8713
- cacheRead: 0,
8714
- cacheWrite: 0,
8715
- },
8716
- contextWindow: 1048576,
8717
- maxTokens: 8192,
8718
- },
8719
8842
  "google/gemini-2.5-flash": {
8720
8843
  id: "google/gemini-2.5-flash",
8721
8844
  name: "Google: Gemini 2.5 Flash",
@@ -8998,12 +9121,12 @@ export const MODELS = {
8998
9121
  input: ["text", "image"],
8999
9122
  cost: {
9000
9123
  input: 0.12,
9001
- output: 0.37,
9002
- cacheRead: 0,
9124
+ output: 0.36,
9125
+ cacheRead: 0.09,
9003
9126
  cacheWrite: 0,
9004
9127
  },
9005
9128
  contextWindow: 262144,
9006
- maxTokens: 16384,
9129
+ maxTokens: 8192,
9007
9130
  },
9008
9131
  "google/gemma-4-31b-it:free": {
9009
9132
  id: "google/gemma-4-31b-it:free",
@@ -9099,9 +9222,9 @@ export const MODELS = {
9099
9222
  reasoning: true,
9100
9223
  input: ["text"],
9101
9224
  cost: {
9102
- input: 0.3,
9103
- output: 2.5,
9104
- cacheRead: 0.06,
9225
+ input: 0.075,
9226
+ output: 0.625,
9227
+ cacheRead: 0.015,
9105
9228
  cacheWrite: 0,
9106
9229
  },
9107
9230
  contextWindow: 262144,
@@ -9151,7 +9274,7 @@ export const MODELS = {
9151
9274
  input: ["text"],
9152
9275
  cost: {
9153
9276
  input: 0.02,
9154
- output: 0.049999999999999996,
9277
+ output: 0.03,
9155
9278
  cacheRead: 0,
9156
9279
  cacheWrite: 0,
9157
9280
  },
@@ -9303,13 +9426,13 @@ export const MODELS = {
9303
9426
  reasoning: true,
9304
9427
  input: ["text"],
9305
9428
  cost: {
9306
- input: 0.26,
9429
+ input: 0.27899999999999997,
9307
9430
  output: 1.2,
9308
9431
  cacheRead: 0,
9309
9432
  cacheWrite: 0,
9310
9433
  },
9311
9434
  contextWindow: 204800,
9312
- maxTokens: 4096,
9435
+ maxTokens: 196608,
9313
9436
  },
9314
9437
  "minimax/minimax-m3": {
9315
9438
  id: "minimax/minimax-m3",
@@ -9838,6 +9961,40 @@ export const MODELS = {
9838
9961
  contextWindow: 1000000,
9839
9962
  maxTokens: 262144,
9840
9963
  },
9964
+ "nvidia/nemotron-3-ultra-550b-a55b": {
9965
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
9966
+ name: "NVIDIA: Nemotron 3 Ultra",
9967
+ api: "openai-completions",
9968
+ provider: "openrouter",
9969
+ baseUrl: "https://openrouter.ai/api/v1",
9970
+ reasoning: true,
9971
+ input: ["text"],
9972
+ cost: {
9973
+ input: 0.5,
9974
+ output: 2.5,
9975
+ cacheRead: 0.15,
9976
+ cacheWrite: 0,
9977
+ },
9978
+ contextWindow: 1000000,
9979
+ maxTokens: 16384,
9980
+ },
9981
+ "nvidia/nemotron-3-ultra-550b-a55b:free": {
9982
+ id: "nvidia/nemotron-3-ultra-550b-a55b:free",
9983
+ name: "NVIDIA: Nemotron 3 Ultra (free)",
9984
+ api: "openai-completions",
9985
+ provider: "openrouter",
9986
+ baseUrl: "https://openrouter.ai/api/v1",
9987
+ reasoning: true,
9988
+ input: ["text"],
9989
+ cost: {
9990
+ input: 0,
9991
+ output: 0,
9992
+ cacheRead: 0,
9993
+ cacheWrite: 0,
9994
+ },
9995
+ contextWindow: 1000000,
9996
+ maxTokens: 65536,
9997
+ },
9841
9998
  "nvidia/nemotron-nano-12b-v2-vl:free": {
9842
9999
  id: "nvidia/nemotron-nano-12b-v2-vl:free",
9843
10000
  name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -9957,23 +10114,6 @@ export const MODELS = {
9957
10114
  contextWindow: 8191,
9958
10115
  maxTokens: 4096,
9959
10116
  },
9960
- "openai/gpt-4-0314": {
9961
- id: "openai/gpt-4-0314",
9962
- name: "OpenAI: GPT-4 (older v0314)",
9963
- api: "openai-completions",
9964
- provider: "openrouter",
9965
- baseUrl: "https://openrouter.ai/api/v1",
9966
- reasoning: false,
9967
- input: ["text"],
9968
- cost: {
9969
- input: 30,
9970
- output: 60,
9971
- cacheRead: 0,
9972
- cacheWrite: 0,
9973
- },
9974
- contextWindow: 8191,
9975
- maxTokens: 4096,
9976
- },
9977
10117
  "openai/gpt-4-1106-preview": {
9978
10118
  id: "openai/gpt-4-1106-preview",
9979
10119
  name: "OpenAI: GPT-4 Turbo (older v1106)",
@@ -11004,7 +11144,7 @@ export const MODELS = {
11004
11144
  cacheWrite: 0,
11005
11145
  },
11006
11146
  contextWindow: 131072,
11007
- maxTokens: 20000,
11147
+ maxTokens: 16384,
11008
11148
  },
11009
11149
  "qwen/qwen3-30b-a3b-instruct-2507": {
11010
11150
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -11015,13 +11155,13 @@ export const MODELS = {
11015
11155
  reasoning: false,
11016
11156
  input: ["text"],
11017
11157
  cost: {
11018
- input: 0.09,
11019
- output: 0.3,
11158
+ input: 0.04815,
11159
+ output: 0.19305,
11020
11160
  cacheRead: 0,
11021
11161
  cacheWrite: 0,
11022
11162
  },
11023
- contextWindow: 262144,
11024
- maxTokens: 262144,
11163
+ contextWindow: 131072,
11164
+ maxTokens: 32000,
11025
11165
  },
11026
11166
  "qwen/qwen3-30b-a3b-thinking-2507": {
11027
11167
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -11618,6 +11758,23 @@ export const MODELS = {
11618
11758
  contextWindow: 1000000,
11619
11759
  maxTokens: 65536,
11620
11760
  },
11761
+ "qwen/qwen3.7-plus": {
11762
+ id: "qwen/qwen3.7-plus",
11763
+ name: "Qwen: Qwen3.7 Plus",
11764
+ api: "openai-completions",
11765
+ provider: "openrouter",
11766
+ baseUrl: "https://openrouter.ai/api/v1",
11767
+ reasoning: true,
11768
+ input: ["text", "image"],
11769
+ cost: {
11770
+ input: 0.39999999999999997,
11771
+ output: 1.5999999999999999,
11772
+ cacheRead: 0.08,
11773
+ cacheWrite: 0.5,
11774
+ },
11775
+ contextWindow: 1000000,
11776
+ maxTokens: 65536,
11777
+ },
11621
11778
  "rekaai/reka-edge": {
11622
11779
  id: "rekaai/reka-edge",
11623
11780
  name: "Reka Edge",
@@ -11652,23 +11809,6 @@ export const MODELS = {
11652
11809
  contextWindow: 256000,
11653
11810
  maxTokens: 128000,
11654
11811
  },
11655
- "sao10k/l3-euryale-70b": {
11656
- id: "sao10k/l3-euryale-70b",
11657
- name: "Sao10k: Llama 3 Euryale 70B v2.1",
11658
- api: "openai-completions",
11659
- provider: "openrouter",
11660
- baseUrl: "https://openrouter.ai/api/v1",
11661
- reasoning: false,
11662
- input: ["text"],
11663
- cost: {
11664
- input: 1.48,
11665
- output: 1.48,
11666
- cacheRead: 0,
11667
- cacheWrite: 0,
11668
- },
11669
- contextWindow: 8192,
11670
- maxTokens: 8192,
11671
- },
11672
11812
  "sao10k/l3.1-euryale-70b": {
11673
11813
  id: "sao10k/l3.1-euryale-70b",
11674
11814
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -12024,7 +12164,7 @@ export const MODELS = {
12024
12164
  cacheWrite: 0,
12025
12165
  },
12026
12166
  contextWindow: 202752,
12027
- maxTokens: 16384,
12167
+ maxTokens: 4096,
12028
12168
  },
12029
12169
  "z-ai/glm-5-turbo": {
12030
12170
  id: "z-ai/glm-5-turbo",
@@ -12058,7 +12198,7 @@ export const MODELS = {
12058
12198
  cacheWrite: 0,
12059
12199
  },
12060
12200
  contextWindow: 202752,
12061
- maxTokens: 131072,
12201
+ maxTokens: 4096,
12062
12202
  },
12063
12203
  "z-ai/glm-5v-turbo": {
12064
12204
  id: "z-ai/glm-5v-turbo",
@@ -12368,7 +12508,7 @@ export const MODELS = {
12368
12508
  },
12369
12509
  "deepseek-ai/DeepSeek-V3": {
12370
12510
  id: "deepseek-ai/DeepSeek-V3",
12371
- name: "DeepSeek V3",
12511
+ name: "DeepSeek-V3",
12372
12512
  api: "openai-completions",
12373
12513
  provider: "together",
12374
12514
  baseUrl: "https://api.together.ai/v1",
@@ -12516,6 +12656,25 @@ export const MODELS = {
12516
12656
  contextWindow: 262144,
12517
12657
  maxTokens: 131000,
12518
12658
  },
12659
+ "nvidia/nemotron-3-ultra-550b-a55b": {
12660
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
12661
+ name: "Nemotron 3 Ultra 550B A55B",
12662
+ api: "openai-completions",
12663
+ provider: "together",
12664
+ baseUrl: "https://api.together.ai/v1",
12665
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12666
+ reasoning: true,
12667
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12668
+ input: ["text"],
12669
+ cost: {
12670
+ input: 0.6,
12671
+ output: 3.6,
12672
+ cacheRead: 0.2,
12673
+ cacheWrite: 0,
12674
+ },
12675
+ contextWindow: 512300,
12676
+ maxTokens: 512300,
12677
+ },
12519
12678
  "openai/gpt-oss-120b": {
12520
12679
  id: "openai/gpt-oss-120b",
12521
12680
  name: "GPT OSS 120B",
@@ -12631,7 +12790,7 @@ export const MODELS = {
12631
12790
  provider: "vercel-ai-gateway",
12632
12791
  baseUrl: "https://ai-gateway.vercel.sh",
12633
12792
  reasoning: true,
12634
- input: ["text", "image"],
12793
+ input: ["text"],
12635
12794
  cost: {
12636
12795
  input: 1.3,
12637
12796
  output: 7.8,
@@ -12903,7 +13062,7 @@ export const MODELS = {
12903
13062
  provider: "vercel-ai-gateway",
12904
13063
  baseUrl: "https://ai-gateway.vercel.sh",
12905
13064
  reasoning: true,
12906
- input: ["text", "image"],
13065
+ input: ["text"],
12907
13066
  cost: {
12908
13067
  input: 1.25,
12909
13068
  output: 3.75,
@@ -12913,6 +13072,23 @@ export const MODELS = {
12913
13072
  contextWindow: 991000,
12914
13073
  maxTokens: 64000,
12915
13074
  },
13075
+ "alibaba/qwen3.7-plus": {
13076
+ id: "alibaba/qwen3.7-plus",
13077
+ name: "Qwen 3.7 Plus",
13078
+ api: "anthropic-messages",
13079
+ provider: "vercel-ai-gateway",
13080
+ baseUrl: "https://ai-gateway.vercel.sh",
13081
+ reasoning: true,
13082
+ input: ["text", "image"],
13083
+ cost: {
13084
+ input: 0.39999999999999997,
13085
+ output: 1.5999999999999999,
13086
+ cacheRead: 0.08,
13087
+ cacheWrite: 0.5,
13088
+ },
13089
+ contextWindow: 1000000,
13090
+ maxTokens: 64000,
13091
+ },
12916
13092
  "anthropic/claude-3-haiku": {
12917
13093
  id: "anthropic/claude-3-haiku",
12918
13094
  name: "Claude 3 Haiku",
@@ -13297,7 +13473,7 @@ export const MODELS = {
13297
13473
  provider: "vercel-ai-gateway",
13298
13474
  baseUrl: "https://ai-gateway.vercel.sh",
13299
13475
  reasoning: true,
13300
- input: ["text", "image"],
13476
+ input: ["text"],
13301
13477
  cost: {
13302
13478
  input: 0.435,
13303
13479
  output: 0.87,
@@ -13500,12 +13676,12 @@ export const MODELS = {
13500
13676
  api: "anthropic-messages",
13501
13677
  provider: "vercel-ai-gateway",
13502
13678
  baseUrl: "https://ai-gateway.vercel.sh",
13503
- reasoning: false,
13679
+ reasoning: true,
13504
13680
  input: ["text", "image"],
13505
13681
  cost: {
13506
- input: 0.13,
13507
- output: 0.39999999999999997,
13508
- cacheRead: 0,
13682
+ input: 0.15,
13683
+ output: 0.6,
13684
+ cacheRead: 0.015,
13509
13685
  cacheWrite: 0,
13510
13686
  },
13511
13687
  contextWindow: 262144,
@@ -13790,7 +13966,7 @@ export const MODELS = {
13790
13966
  provider: "vercel-ai-gateway",
13791
13967
  baseUrl: "https://ai-gateway.vercel.sh",
13792
13968
  reasoning: true,
13793
- input: ["text", "image"],
13969
+ input: ["text"],
13794
13970
  cost: {
13795
13971
  input: 0.6,
13796
13972
  output: 2.4,
@@ -13807,7 +13983,7 @@ export const MODELS = {
13807
13983
  provider: "vercel-ai-gateway",
13808
13984
  baseUrl: "https://ai-gateway.vercel.sh",
13809
13985
  reasoning: true,
13810
- input: ["text", "image"],
13986
+ input: ["text"],
13811
13987
  cost: {
13812
13988
  input: 0.3,
13813
13989
  output: 1.2,
@@ -13824,7 +14000,7 @@ export const MODELS = {
13824
14000
  provider: "vercel-ai-gateway",
13825
14001
  baseUrl: "https://ai-gateway.vercel.sh",
13826
14002
  reasoning: true,
13827
- input: ["text", "image"],
14003
+ input: ["text"],
13828
14004
  cost: {
13829
14005
  input: 0.6,
13830
14006
  output: 2.4,
@@ -14174,6 +14350,23 @@ export const MODELS = {
14174
14350
  contextWindow: 256000,
14175
14351
  maxTokens: 32000,
14176
14352
  },
14353
+ "nvidia/nemotron-3-ultra-550b-a55b": {
14354
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
14355
+ name: "Nemotron 3 Ultra",
14356
+ api: "anthropic-messages",
14357
+ provider: "vercel-ai-gateway",
14358
+ baseUrl: "https://ai-gateway.vercel.sh",
14359
+ reasoning: true,
14360
+ input: ["text"],
14361
+ cost: {
14362
+ input: 0.6,
14363
+ output: 2.4,
14364
+ cacheRead: 0.12,
14365
+ cacheWrite: 0,
14366
+ },
14367
+ contextWindow: 1000000,
14368
+ maxTokens: 65000,
14369
+ },
14177
14370
  "nvidia/nemotron-nano-12b-v2-vl": {
14178
14371
  id: "nvidia/nemotron-nano-12b-v2-vl",
14179
14372
  name: "Nvidia Nemotron Nano 12B V2 VL",