@openachieve/ai 0.79.1 → 0.79.2

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.
@@ -6546,82 +6546,6 @@ 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
- },
6625
6549
  "meta/llama-3.1-70b-instruct": {
6626
6550
  id: "meta/llama-3.1-70b-instruct",
6627
6551
  name: "Llama 3.1 70b Instruct",
@@ -6717,63 +6641,6 @@ export const MODELS = {
6717
6641
  contextWindow: 128000,
6718
6642
  maxTokens: 4096,
6719
6643
  },
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
- },
6777
6644
  "mistralai/mistral-large-3-675b-instruct-2512": {
6778
6645
  id: "mistralai/mistral-large-3-675b-instruct-2512",
6779
6646
  name: "Mistral Large 3 675B Instruct 2512",
@@ -6812,101 +6679,6 @@ export const MODELS = {
6812
6679
  contextWindow: 128000,
6813
6680
  maxTokens: 8192,
6814
6681
  },
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
- },
6910
6682
  "moonshotai/kimi-k2.6": {
6911
6683
  id: "moonshotai/kimi-k2.6",
6912
6684
  name: "Kimi K2.6",
@@ -6926,8 +6698,8 @@ export const MODELS = {
6926
6698
  contextWindow: 262144,
6927
6699
  maxTokens: 262144,
6928
6700
  },
6929
- "nvidia/llama-3_3-nemotron-super-49b-v1": {
6930
- id: "nvidia/llama-3_3-nemotron-super-49b-v1",
6701
+ "nvidia/llama-3.3-nemotron-super-49b-v1": {
6702
+ id: "nvidia/llama-3.3-nemotron-super-49b-v1",
6931
6703
  name: "Llama 3.3 Nemotron Super 49B v1",
6932
6704
  api: "openai-completions",
6933
6705
  provider: "nvidia",
@@ -6945,8 +6717,8 @@ export const MODELS = {
6945
6717
  contextWindow: 131072,
6946
6718
  maxTokens: 131072,
6947
6719
  },
6948
- "nvidia/llama-3_3-nemotron-super-49b-v1_5": {
6949
- id: "nvidia/llama-3_3-nemotron-super-49b-v1_5",
6720
+ "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
6721
+ id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
6950
6722
  name: "Llama 3.3 Nemotron Super 49B v1.5",
6951
6723
  api: "openai-completions",
6952
6724
  provider: "nvidia",
@@ -7021,25 +6793,6 @@ export const MODELS = {
7021
6793
  contextWindow: 262144,
7022
6794
  maxTokens: 262144,
7023
6795
  },
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
- },
7043
6796
  "nvidia/nvidia-nemotron-nano-9b-v2": {
7044
6797
  id: "nvidia/nvidia-nemotron-nano-9b-v2",
7045
6798
  name: "nvidia-nemotron-nano-9b-v2",
@@ -7078,25 +6831,6 @@ export const MODELS = {
7078
6831
  contextWindow: 131072,
7079
6832
  maxTokens: 32768,
7080
6833
  },
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
- },
7100
6834
  "qwen/qwen3-coder-480b-a35b-instruct": {
7101
6835
  id: "qwen/qwen3-coder-480b-a35b-instruct",
7102
6836
  name: "Qwen3 Coder 480B A35B Instruct",
@@ -7116,25 +6850,6 @@ export const MODELS = {
7116
6850
  contextWindow: 262144,
7117
6851
  maxTokens: 66536,
7118
6852
  },
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
- },
7138
6853
  "qwen/qwen3.5-122b-a10b": {
7139
6854
  id: "qwen/qwen3.5-122b-a10b",
7140
6855
  name: "Qwen3.5 122B-A10B",
@@ -7192,25 +6907,6 @@ export const MODELS = {
7192
6907
  contextWindow: 256000,
7193
6908
  maxTokens: 16384,
7194
6909
  },
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
- },
7214
6910
  "z-ai/glm-5.1": {
7215
6911
  id: "z-ai/glm-5.1",
7216
6912
  name: "GLM-5.1",
@@ -7230,25 +6926,6 @@ export const MODELS = {
7230
6926
  contextWindow: 131072,
7231
6927
  maxTokens: 131072,
7232
6928
  },
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
- },
7252
6929
  },
7253
6930
  "openai": {
7254
6931
  "gpt-4": {
@@ -9509,23 +9186,6 @@ export const MODELS = {
9509
9186
  contextWindow: 2000000,
9510
9187
  maxTokens: 30000,
9511
9188
  },
9512
- "baidu/ernie-4.5-vl-28b-a3b": {
9513
- id: "baidu/ernie-4.5-vl-28b-a3b",
9514
- name: "Baidu: ERNIE 4.5 VL 28B A3B",
9515
- api: "openai-completions",
9516
- provider: "openrouter",
9517
- baseUrl: "https://openrouter.ai/api/v1",
9518
- reasoning: true,
9519
- input: ["text", "image"],
9520
- cost: {
9521
- input: 0.14,
9522
- output: 0.56,
9523
- cacheRead: 0,
9524
- cacheWrite: 0,
9525
- },
9526
- contextWindow: 131072,
9527
- maxTokens: 8000,
9528
- },
9529
9189
  "bytedance-seed/seed-1.6": {
9530
9190
  id: "bytedance-seed/seed-1.6",
9531
9191
  name: "ByteDance Seed: Seed 1.6",
@@ -10413,7 +10073,7 @@ export const MODELS = {
10413
10073
  cacheWrite: 0,
10414
10074
  },
10415
10075
  contextWindow: 204800,
10416
- maxTokens: 131072,
10076
+ maxTokens: 196608,
10417
10077
  },
10418
10078
  "minimax/minimax-m3": {
10419
10079
  id: "minimax/minimax-m3",
@@ -11097,23 +10757,6 @@ export const MODELS = {
11097
10757
  contextWindow: 8191,
11098
10758
  maxTokens: 4096,
11099
10759
  },
11100
- "openai/gpt-4-1106-preview": {
11101
- id: "openai/gpt-4-1106-preview",
11102
- name: "OpenAI: GPT-4 Turbo (older v1106)",
11103
- api: "openai-completions",
11104
- provider: "openrouter",
11105
- baseUrl: "https://openrouter.ai/api/v1",
11106
- reasoning: false,
11107
- input: ["text"],
11108
- cost: {
11109
- input: 10,
11110
- output: 30,
11111
- cacheRead: 0,
11112
- cacheWrite: 0,
11113
- },
11114
- contextWindow: 128000,
11115
- maxTokens: 4096,
11116
- },
11117
10760
  "openai/gpt-4-turbo": {
11118
10761
  id: "openai/gpt-4-turbo",
11119
10762
  name: "OpenAI: GPT-4 Turbo",