@openachieve/ai 0.79.0 → 0.79.1
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.
package/dist/models.generated.js
CHANGED
|
@@ -6546,6 +6546,82 @@ export const MODELS = {
|
|
|
6546
6546
|
},
|
|
6547
6547
|
},
|
|
6548
6548
|
"nvidia": {
|
|
6549
|
+
"abacusai/dracarys-llama-3_1-70b-instruct": {
|
|
6550
|
+
id: "abacusai/dracarys-llama-3_1-70b-instruct",
|
|
6551
|
+
name: "dracarys-llama-3.1-70b-instruct",
|
|
6552
|
+
api: "openai-completions",
|
|
6553
|
+
provider: "nvidia",
|
|
6554
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6555
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6556
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6557
|
+
reasoning: false,
|
|
6558
|
+
input: ["text"],
|
|
6559
|
+
cost: {
|
|
6560
|
+
input: 0,
|
|
6561
|
+
output: 0,
|
|
6562
|
+
cacheRead: 0,
|
|
6563
|
+
cacheWrite: 0,
|
|
6564
|
+
},
|
|
6565
|
+
contextWindow: 128000,
|
|
6566
|
+
maxTokens: 8192,
|
|
6567
|
+
},
|
|
6568
|
+
"deepseek-ai/deepseek-v3.1-terminus": {
|
|
6569
|
+
id: "deepseek-ai/deepseek-v3.1-terminus",
|
|
6570
|
+
name: "DeepSeek V3.1 Terminus",
|
|
6571
|
+
api: "openai-completions",
|
|
6572
|
+
provider: "nvidia",
|
|
6573
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6574
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6575
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6576
|
+
reasoning: true,
|
|
6577
|
+
input: ["text"],
|
|
6578
|
+
cost: {
|
|
6579
|
+
input: 0,
|
|
6580
|
+
output: 0,
|
|
6581
|
+
cacheRead: 0,
|
|
6582
|
+
cacheWrite: 0,
|
|
6583
|
+
},
|
|
6584
|
+
contextWindow: 128000,
|
|
6585
|
+
maxTokens: 8192,
|
|
6586
|
+
},
|
|
6587
|
+
"deepseek-ai/deepseek-v3.2": {
|
|
6588
|
+
id: "deepseek-ai/deepseek-v3.2",
|
|
6589
|
+
name: "DeepSeek V3.2",
|
|
6590
|
+
api: "openai-completions",
|
|
6591
|
+
provider: "nvidia",
|
|
6592
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6593
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6594
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6595
|
+
reasoning: true,
|
|
6596
|
+
input: ["text"],
|
|
6597
|
+
cost: {
|
|
6598
|
+
input: 0,
|
|
6599
|
+
output: 0,
|
|
6600
|
+
cacheRead: 0,
|
|
6601
|
+
cacheWrite: 0,
|
|
6602
|
+
},
|
|
6603
|
+
contextWindow: 163840,
|
|
6604
|
+
maxTokens: 65536,
|
|
6605
|
+
},
|
|
6606
|
+
"google/gemma-3-27b-it": {
|
|
6607
|
+
id: "google/gemma-3-27b-it",
|
|
6608
|
+
name: "Gemma-3-27B-IT",
|
|
6609
|
+
api: "openai-completions",
|
|
6610
|
+
provider: "nvidia",
|
|
6611
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6612
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6613
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6614
|
+
reasoning: true,
|
|
6615
|
+
input: ["text", "image"],
|
|
6616
|
+
cost: {
|
|
6617
|
+
input: 0,
|
|
6618
|
+
output: 0,
|
|
6619
|
+
cacheRead: 0,
|
|
6620
|
+
cacheWrite: 0,
|
|
6621
|
+
},
|
|
6622
|
+
contextWindow: 131072,
|
|
6623
|
+
maxTokens: 8192,
|
|
6624
|
+
},
|
|
6549
6625
|
"meta/llama-3.1-70b-instruct": {
|
|
6550
6626
|
id: "meta/llama-3.1-70b-instruct",
|
|
6551
6627
|
name: "Llama 3.1 70b Instruct",
|
|
@@ -6641,6 +6717,63 @@ export const MODELS = {
|
|
|
6641
6717
|
contextWindow: 128000,
|
|
6642
6718
|
maxTokens: 4096,
|
|
6643
6719
|
},
|
|
6720
|
+
"minimaxai/minimax-m2.5": {
|
|
6721
|
+
id: "minimaxai/minimax-m2.5",
|
|
6722
|
+
name: "MiniMax-M2.5",
|
|
6723
|
+
api: "openai-completions",
|
|
6724
|
+
provider: "nvidia",
|
|
6725
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6726
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6727
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6728
|
+
reasoning: true,
|
|
6729
|
+
input: ["text"],
|
|
6730
|
+
cost: {
|
|
6731
|
+
input: 0,
|
|
6732
|
+
output: 0,
|
|
6733
|
+
cacheRead: 0,
|
|
6734
|
+
cacheWrite: 0,
|
|
6735
|
+
},
|
|
6736
|
+
contextWindow: 204800,
|
|
6737
|
+
maxTokens: 131072,
|
|
6738
|
+
},
|
|
6739
|
+
"mistralai/devstral-2-123b-instruct-2512": {
|
|
6740
|
+
id: "mistralai/devstral-2-123b-instruct-2512",
|
|
6741
|
+
name: "Devstral-2-123B-Instruct-2512",
|
|
6742
|
+
api: "openai-completions",
|
|
6743
|
+
provider: "nvidia",
|
|
6744
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6745
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6746
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6747
|
+
reasoning: true,
|
|
6748
|
+
input: ["text"],
|
|
6749
|
+
cost: {
|
|
6750
|
+
input: 0,
|
|
6751
|
+
output: 0,
|
|
6752
|
+
cacheRead: 0,
|
|
6753
|
+
cacheWrite: 0,
|
|
6754
|
+
},
|
|
6755
|
+
contextWindow: 262144,
|
|
6756
|
+
maxTokens: 262144,
|
|
6757
|
+
},
|
|
6758
|
+
"mistralai/mistral-7b-instruct-v03": {
|
|
6759
|
+
id: "mistralai/mistral-7b-instruct-v03",
|
|
6760
|
+
name: "Mistral-7B-Instruct-v0.3",
|
|
6761
|
+
api: "openai-completions",
|
|
6762
|
+
provider: "nvidia",
|
|
6763
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6764
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6765
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6766
|
+
reasoning: false,
|
|
6767
|
+
input: ["text"],
|
|
6768
|
+
cost: {
|
|
6769
|
+
input: 0,
|
|
6770
|
+
output: 0,
|
|
6771
|
+
cacheRead: 0,
|
|
6772
|
+
cacheWrite: 0,
|
|
6773
|
+
},
|
|
6774
|
+
contextWindow: 65536,
|
|
6775
|
+
maxTokens: 65536,
|
|
6776
|
+
},
|
|
6644
6777
|
"mistralai/mistral-large-3-675b-instruct-2512": {
|
|
6645
6778
|
id: "mistralai/mistral-large-3-675b-instruct-2512",
|
|
6646
6779
|
name: "Mistral Large 3 675B Instruct 2512",
|
|
@@ -6679,6 +6812,101 @@ export const MODELS = {
|
|
|
6679
6812
|
contextWindow: 128000,
|
|
6680
6813
|
maxTokens: 8192,
|
|
6681
6814
|
},
|
|
6815
|
+
"mistralai/mixtral-8x22b-instruct": {
|
|
6816
|
+
id: "mistralai/mixtral-8x22b-instruct",
|
|
6817
|
+
name: "Mistral: Mixtral 8x22B Instruct",
|
|
6818
|
+
api: "openai-completions",
|
|
6819
|
+
provider: "nvidia",
|
|
6820
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6821
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6822
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6823
|
+
reasoning: false,
|
|
6824
|
+
input: ["text"],
|
|
6825
|
+
cost: {
|
|
6826
|
+
input: 0,
|
|
6827
|
+
output: 0,
|
|
6828
|
+
cacheRead: 0,
|
|
6829
|
+
cacheWrite: 0,
|
|
6830
|
+
},
|
|
6831
|
+
contextWindow: 65536,
|
|
6832
|
+
maxTokens: 13108,
|
|
6833
|
+
},
|
|
6834
|
+
"mistralai/mixtral-8x7b-instruct": {
|
|
6835
|
+
id: "mistralai/mixtral-8x7b-instruct",
|
|
6836
|
+
name: "Mistral: Mixtral 8x7B Instruct",
|
|
6837
|
+
api: "openai-completions",
|
|
6838
|
+
provider: "nvidia",
|
|
6839
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6840
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6841
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6842
|
+
reasoning: false,
|
|
6843
|
+
input: ["text"],
|
|
6844
|
+
cost: {
|
|
6845
|
+
input: 0,
|
|
6846
|
+
output: 0,
|
|
6847
|
+
cacheRead: 0,
|
|
6848
|
+
cacheWrite: 0,
|
|
6849
|
+
},
|
|
6850
|
+
contextWindow: 32768,
|
|
6851
|
+
maxTokens: 16384,
|
|
6852
|
+
},
|
|
6853
|
+
"moonshotai/kimi-k2-instruct": {
|
|
6854
|
+
id: "moonshotai/kimi-k2-instruct",
|
|
6855
|
+
name: "Kimi K2 Instruct",
|
|
6856
|
+
api: "openai-completions",
|
|
6857
|
+
provider: "nvidia",
|
|
6858
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6859
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6860
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6861
|
+
reasoning: true,
|
|
6862
|
+
input: ["text"],
|
|
6863
|
+
cost: {
|
|
6864
|
+
input: 0,
|
|
6865
|
+
output: 0,
|
|
6866
|
+
cacheRead: 0,
|
|
6867
|
+
cacheWrite: 0,
|
|
6868
|
+
},
|
|
6869
|
+
contextWindow: 128000,
|
|
6870
|
+
maxTokens: 8192,
|
|
6871
|
+
},
|
|
6872
|
+
"moonshotai/kimi-k2-instruct-0905": {
|
|
6873
|
+
id: "moonshotai/kimi-k2-instruct-0905",
|
|
6874
|
+
name: "Kimi K2 0905",
|
|
6875
|
+
api: "openai-completions",
|
|
6876
|
+
provider: "nvidia",
|
|
6877
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6878
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6879
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6880
|
+
reasoning: false,
|
|
6881
|
+
input: ["text"],
|
|
6882
|
+
cost: {
|
|
6883
|
+
input: 0,
|
|
6884
|
+
output: 0,
|
|
6885
|
+
cacheRead: 0,
|
|
6886
|
+
cacheWrite: 0,
|
|
6887
|
+
},
|
|
6888
|
+
contextWindow: 262144,
|
|
6889
|
+
maxTokens: 262144,
|
|
6890
|
+
},
|
|
6891
|
+
"moonshotai/kimi-k2-thinking": {
|
|
6892
|
+
id: "moonshotai/kimi-k2-thinking",
|
|
6893
|
+
name: "Kimi K2 Thinking",
|
|
6894
|
+
api: "openai-completions",
|
|
6895
|
+
provider: "nvidia",
|
|
6896
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6897
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
6898
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
6899
|
+
reasoning: true,
|
|
6900
|
+
input: ["text"],
|
|
6901
|
+
cost: {
|
|
6902
|
+
input: 0,
|
|
6903
|
+
output: 0,
|
|
6904
|
+
cacheRead: 0,
|
|
6905
|
+
cacheWrite: 0,
|
|
6906
|
+
},
|
|
6907
|
+
contextWindow: 262144,
|
|
6908
|
+
maxTokens: 262144,
|
|
6909
|
+
},
|
|
6682
6910
|
"moonshotai/kimi-k2.6": {
|
|
6683
6911
|
id: "moonshotai/kimi-k2.6",
|
|
6684
6912
|
name: "Kimi K2.6",
|
|
@@ -6698,8 +6926,8 @@ export const MODELS = {
|
|
|
6698
6926
|
contextWindow: 262144,
|
|
6699
6927
|
maxTokens: 262144,
|
|
6700
6928
|
},
|
|
6701
|
-
"nvidia/llama-
|
|
6702
|
-
id: "nvidia/llama-
|
|
6929
|
+
"nvidia/llama-3_3-nemotron-super-49b-v1": {
|
|
6930
|
+
id: "nvidia/llama-3_3-nemotron-super-49b-v1",
|
|
6703
6931
|
name: "Llama 3.3 Nemotron Super 49B v1",
|
|
6704
6932
|
api: "openai-completions",
|
|
6705
6933
|
provider: "nvidia",
|
|
@@ -6717,8 +6945,8 @@ export const MODELS = {
|
|
|
6717
6945
|
contextWindow: 131072,
|
|
6718
6946
|
maxTokens: 131072,
|
|
6719
6947
|
},
|
|
6720
|
-
"nvidia/llama-
|
|
6721
|
-
id: "nvidia/llama-
|
|
6948
|
+
"nvidia/llama-3_3-nemotron-super-49b-v1_5": {
|
|
6949
|
+
id: "nvidia/llama-3_3-nemotron-super-49b-v1_5",
|
|
6722
6950
|
name: "Llama 3.3 Nemotron Super 49B v1.5",
|
|
6723
6951
|
api: "openai-completions",
|
|
6724
6952
|
provider: "nvidia",
|
|
@@ -6793,6 +7021,25 @@ export const MODELS = {
|
|
|
6793
7021
|
contextWindow: 262144,
|
|
6794
7022
|
maxTokens: 262144,
|
|
6795
7023
|
},
|
|
7024
|
+
"nvidia/nemotron-voicechat": {
|
|
7025
|
+
id: "nvidia/nemotron-voicechat",
|
|
7026
|
+
name: "nemotron-voicechat",
|
|
7027
|
+
api: "openai-completions",
|
|
7028
|
+
provider: "nvidia",
|
|
7029
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7030
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
7031
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
7032
|
+
reasoning: false,
|
|
7033
|
+
input: ["text"],
|
|
7034
|
+
cost: {
|
|
7035
|
+
input: 0,
|
|
7036
|
+
output: 0,
|
|
7037
|
+
cacheRead: 0,
|
|
7038
|
+
cacheWrite: 0,
|
|
7039
|
+
},
|
|
7040
|
+
contextWindow: 128000,
|
|
7041
|
+
maxTokens: 8192,
|
|
7042
|
+
},
|
|
6796
7043
|
"nvidia/nvidia-nemotron-nano-9b-v2": {
|
|
6797
7044
|
id: "nvidia/nvidia-nemotron-nano-9b-v2",
|
|
6798
7045
|
name: "nvidia-nemotron-nano-9b-v2",
|
|
@@ -6831,6 +7078,25 @@ export const MODELS = {
|
|
|
6831
7078
|
contextWindow: 131072,
|
|
6832
7079
|
maxTokens: 32768,
|
|
6833
7080
|
},
|
|
7081
|
+
"qwen/qwen2.5-coder-32b-instruct": {
|
|
7082
|
+
id: "qwen/qwen2.5-coder-32b-instruct",
|
|
7083
|
+
name: "Qwen2.5 Coder 32b Instruct",
|
|
7084
|
+
api: "openai-completions",
|
|
7085
|
+
provider: "nvidia",
|
|
7086
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7087
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
7088
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
7089
|
+
reasoning: false,
|
|
7090
|
+
input: ["text"],
|
|
7091
|
+
cost: {
|
|
7092
|
+
input: 0,
|
|
7093
|
+
output: 0,
|
|
7094
|
+
cacheRead: 0,
|
|
7095
|
+
cacheWrite: 0,
|
|
7096
|
+
},
|
|
7097
|
+
contextWindow: 128000,
|
|
7098
|
+
maxTokens: 4096,
|
|
7099
|
+
},
|
|
6834
7100
|
"qwen/qwen3-coder-480b-a35b-instruct": {
|
|
6835
7101
|
id: "qwen/qwen3-coder-480b-a35b-instruct",
|
|
6836
7102
|
name: "Qwen3 Coder 480B A35B Instruct",
|
|
@@ -6850,6 +7116,25 @@ export const MODELS = {
|
|
|
6850
7116
|
contextWindow: 262144,
|
|
6851
7117
|
maxTokens: 66536,
|
|
6852
7118
|
},
|
|
7119
|
+
"qwen/qwen3-next-80b-a3b-thinking": {
|
|
7120
|
+
id: "qwen/qwen3-next-80b-a3b-thinking",
|
|
7121
|
+
name: "Qwen3-Next-80B-A3B-Thinking",
|
|
7122
|
+
api: "openai-completions",
|
|
7123
|
+
provider: "nvidia",
|
|
7124
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7125
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
7126
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
7127
|
+
reasoning: true,
|
|
7128
|
+
input: ["text"],
|
|
7129
|
+
cost: {
|
|
7130
|
+
input: 0,
|
|
7131
|
+
output: 0,
|
|
7132
|
+
cacheRead: 0,
|
|
7133
|
+
cacheWrite: 0,
|
|
7134
|
+
},
|
|
7135
|
+
contextWindow: 262144,
|
|
7136
|
+
maxTokens: 16384,
|
|
7137
|
+
},
|
|
6853
7138
|
"qwen/qwen3.5-122b-a10b": {
|
|
6854
7139
|
id: "qwen/qwen3.5-122b-a10b",
|
|
6855
7140
|
name: "Qwen3.5 122B-A10B",
|
|
@@ -6907,6 +7192,25 @@ export const MODELS = {
|
|
|
6907
7192
|
contextWindow: 256000,
|
|
6908
7193
|
maxTokens: 16384,
|
|
6909
7194
|
},
|
|
7195
|
+
"upstage/solar-10_7b-instruct": {
|
|
7196
|
+
id: "upstage/solar-10_7b-instruct",
|
|
7197
|
+
name: "solar-10.7b-instruct",
|
|
7198
|
+
api: "openai-completions",
|
|
7199
|
+
provider: "nvidia",
|
|
7200
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7201
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
7202
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
7203
|
+
reasoning: false,
|
|
7204
|
+
input: ["text"],
|
|
7205
|
+
cost: {
|
|
7206
|
+
input: 0,
|
|
7207
|
+
output: 0,
|
|
7208
|
+
cacheRead: 0,
|
|
7209
|
+
cacheWrite: 0,
|
|
7210
|
+
},
|
|
7211
|
+
contextWindow: 128000,
|
|
7212
|
+
maxTokens: 8192,
|
|
7213
|
+
},
|
|
6910
7214
|
"z-ai/glm-5.1": {
|
|
6911
7215
|
id: "z-ai/glm-5.1",
|
|
6912
7216
|
name: "GLM-5.1",
|
|
@@ -6926,6 +7230,25 @@ export const MODELS = {
|
|
|
6926
7230
|
contextWindow: 131072,
|
|
6927
7231
|
maxTokens: 131072,
|
|
6928
7232
|
},
|
|
7233
|
+
"z-ai/glm4.7": {
|
|
7234
|
+
id: "z-ai/glm4.7",
|
|
7235
|
+
name: "GLM-4.7",
|
|
7236
|
+
api: "openai-completions",
|
|
7237
|
+
provider: "nvidia",
|
|
7238
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7239
|
+
headers: { "NVCF-POLL-SECONDS": "3600" },
|
|
7240
|
+
compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
|
|
7241
|
+
reasoning: true,
|
|
7242
|
+
input: ["text"],
|
|
7243
|
+
cost: {
|
|
7244
|
+
input: 0,
|
|
7245
|
+
output: 0,
|
|
7246
|
+
cacheRead: 0,
|
|
7247
|
+
cacheWrite: 0,
|
|
7248
|
+
},
|
|
7249
|
+
contextWindow: 204800,
|
|
7250
|
+
maxTokens: 131072,
|
|
7251
|
+
},
|
|
6929
7252
|
},
|
|
6930
7253
|
"openai": {
|
|
6931
7254
|
"gpt-4": {
|
|
@@ -9778,12 +10101,12 @@ export const MODELS = {
|
|
|
9778
10101
|
input: ["text", "image"],
|
|
9779
10102
|
cost: {
|
|
9780
10103
|
input: 0.12,
|
|
9781
|
-
output: 0.
|
|
9782
|
-
cacheRead: 0,
|
|
10104
|
+
output: 0.36,
|
|
10105
|
+
cacheRead: 0.09,
|
|
9783
10106
|
cacheWrite: 0,
|
|
9784
10107
|
},
|
|
9785
10108
|
contextWindow: 262144,
|
|
9786
|
-
maxTokens:
|
|
10109
|
+
maxTokens: 8192,
|
|
9787
10110
|
},
|
|
9788
10111
|
"google/gemma-4-31b-it:free": {
|
|
9789
10112
|
id: "google/gemma-4-31b-it:free",
|