@kolisachint/hoocode-ai 0.1.1 → 0.2.0
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/README.md +1 -0
- package/dist/env-api-keys.d.ts.map +1 -1
- package/dist/env-api-keys.js +1 -0
- package/dist/env-api-keys.js.map +1 -1
- package/dist/models.generated.d.ts +953 -34
- package/dist/models.generated.d.ts.map +1 -1
- package/dist/models.generated.js +930 -38
- package/dist/models.generated.js.map +1 -1
- package/dist/types.d.ts +1 -1
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js.map +1 -1
- package/package.json +1 -1
package/dist/models.generated.js
CHANGED
|
@@ -6392,6 +6392,896 @@ export const MODELS = {
|
|
|
6392
6392
|
maxTokens: 262144,
|
|
6393
6393
|
},
|
|
6394
6394
|
},
|
|
6395
|
+
"nvidia": {
|
|
6396
|
+
"abacusai/dracarys-llama-3_1-70b-instruct": {
|
|
6397
|
+
id: "abacusai/dracarys-llama-3_1-70b-instruct",
|
|
6398
|
+
name: "dracarys-llama-3.1-70b-instruct",
|
|
6399
|
+
api: "openai-completions",
|
|
6400
|
+
provider: "nvidia",
|
|
6401
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6402
|
+
reasoning: false,
|
|
6403
|
+
input: ["text"],
|
|
6404
|
+
cost: {
|
|
6405
|
+
input: 0,
|
|
6406
|
+
output: 0,
|
|
6407
|
+
cacheRead: 0,
|
|
6408
|
+
cacheWrite: 0,
|
|
6409
|
+
},
|
|
6410
|
+
contextWindow: 128000,
|
|
6411
|
+
maxTokens: 8192,
|
|
6412
|
+
},
|
|
6413
|
+
"bytedance/seed-oss-36b-instruct": {
|
|
6414
|
+
id: "bytedance/seed-oss-36b-instruct",
|
|
6415
|
+
name: "ByteDance-Seed/Seed-OSS-36B-Instruct",
|
|
6416
|
+
api: "openai-completions",
|
|
6417
|
+
provider: "nvidia",
|
|
6418
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6419
|
+
reasoning: false,
|
|
6420
|
+
input: ["text"],
|
|
6421
|
+
cost: {
|
|
6422
|
+
input: 0,
|
|
6423
|
+
output: 0,
|
|
6424
|
+
cacheRead: 0,
|
|
6425
|
+
cacheWrite: 0,
|
|
6426
|
+
},
|
|
6427
|
+
contextWindow: 262000,
|
|
6428
|
+
maxTokens: 262000,
|
|
6429
|
+
},
|
|
6430
|
+
"deepseek-ai/deepseek-v3.1-terminus": {
|
|
6431
|
+
id: "deepseek-ai/deepseek-v3.1-terminus",
|
|
6432
|
+
name: "DeepSeek V3.1 Terminus",
|
|
6433
|
+
api: "openai-completions",
|
|
6434
|
+
provider: "nvidia",
|
|
6435
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6436
|
+
reasoning: true,
|
|
6437
|
+
input: ["text"],
|
|
6438
|
+
cost: {
|
|
6439
|
+
input: 0,
|
|
6440
|
+
output: 0,
|
|
6441
|
+
cacheRead: 0,
|
|
6442
|
+
cacheWrite: 0,
|
|
6443
|
+
},
|
|
6444
|
+
contextWindow: 128000,
|
|
6445
|
+
maxTokens: 8192,
|
|
6446
|
+
},
|
|
6447
|
+
"deepseek-ai/deepseek-v3.2": {
|
|
6448
|
+
id: "deepseek-ai/deepseek-v3.2",
|
|
6449
|
+
name: "DeepSeek V3.2",
|
|
6450
|
+
api: "openai-completions",
|
|
6451
|
+
provider: "nvidia",
|
|
6452
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6453
|
+
reasoning: true,
|
|
6454
|
+
input: ["text"],
|
|
6455
|
+
cost: {
|
|
6456
|
+
input: 0,
|
|
6457
|
+
output: 0,
|
|
6458
|
+
cacheRead: 0,
|
|
6459
|
+
cacheWrite: 0,
|
|
6460
|
+
},
|
|
6461
|
+
contextWindow: 163840,
|
|
6462
|
+
maxTokens: 65536,
|
|
6463
|
+
},
|
|
6464
|
+
"deepseek-ai/deepseek-v4-flash": {
|
|
6465
|
+
id: "deepseek-ai/deepseek-v4-flash",
|
|
6466
|
+
name: "DeepSeek V4 Flash",
|
|
6467
|
+
api: "openai-completions",
|
|
6468
|
+
provider: "nvidia",
|
|
6469
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6470
|
+
compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
|
|
6471
|
+
reasoning: true,
|
|
6472
|
+
thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
|
|
6473
|
+
input: ["text"],
|
|
6474
|
+
cost: {
|
|
6475
|
+
input: 0.14,
|
|
6476
|
+
output: 0.28,
|
|
6477
|
+
cacheRead: 0.028,
|
|
6478
|
+
cacheWrite: 0,
|
|
6479
|
+
},
|
|
6480
|
+
contextWindow: 1048576,
|
|
6481
|
+
maxTokens: 393216,
|
|
6482
|
+
},
|
|
6483
|
+
"deepseek-ai/deepseek-v4-pro": {
|
|
6484
|
+
id: "deepseek-ai/deepseek-v4-pro",
|
|
6485
|
+
name: "DeepSeek V4 Pro",
|
|
6486
|
+
api: "openai-completions",
|
|
6487
|
+
provider: "nvidia",
|
|
6488
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6489
|
+
compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
|
|
6490
|
+
reasoning: true,
|
|
6491
|
+
thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
|
|
6492
|
+
input: ["text"],
|
|
6493
|
+
cost: {
|
|
6494
|
+
input: 1.74,
|
|
6495
|
+
output: 3.48,
|
|
6496
|
+
cacheRead: 0.145,
|
|
6497
|
+
cacheWrite: 0,
|
|
6498
|
+
},
|
|
6499
|
+
contextWindow: 1048576,
|
|
6500
|
+
maxTokens: 393216,
|
|
6501
|
+
},
|
|
6502
|
+
"google/gemma-2-2b-it": {
|
|
6503
|
+
id: "google/gemma-2-2b-it",
|
|
6504
|
+
name: "Gemma 2 2b It",
|
|
6505
|
+
api: "openai-completions",
|
|
6506
|
+
provider: "nvidia",
|
|
6507
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6508
|
+
reasoning: false,
|
|
6509
|
+
input: ["text"],
|
|
6510
|
+
cost: {
|
|
6511
|
+
input: 0,
|
|
6512
|
+
output: 0,
|
|
6513
|
+
cacheRead: 0,
|
|
6514
|
+
cacheWrite: 0,
|
|
6515
|
+
},
|
|
6516
|
+
contextWindow: 128000,
|
|
6517
|
+
maxTokens: 4096,
|
|
6518
|
+
},
|
|
6519
|
+
"google/gemma-3-27b-it": {
|
|
6520
|
+
id: "google/gemma-3-27b-it",
|
|
6521
|
+
name: "Gemma-3-27B-IT",
|
|
6522
|
+
api: "openai-completions",
|
|
6523
|
+
provider: "nvidia",
|
|
6524
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6525
|
+
reasoning: true,
|
|
6526
|
+
input: ["text", "image"],
|
|
6527
|
+
cost: {
|
|
6528
|
+
input: 0,
|
|
6529
|
+
output: 0,
|
|
6530
|
+
cacheRead: 0,
|
|
6531
|
+
cacheWrite: 0,
|
|
6532
|
+
},
|
|
6533
|
+
contextWindow: 131072,
|
|
6534
|
+
maxTokens: 8192,
|
|
6535
|
+
},
|
|
6536
|
+
"google/gemma-3n-e2b-it": {
|
|
6537
|
+
id: "google/gemma-3n-e2b-it",
|
|
6538
|
+
name: "Gemma 3n E2b It",
|
|
6539
|
+
api: "openai-completions",
|
|
6540
|
+
provider: "nvidia",
|
|
6541
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6542
|
+
reasoning: false,
|
|
6543
|
+
input: ["text", "image"],
|
|
6544
|
+
cost: {
|
|
6545
|
+
input: 0,
|
|
6546
|
+
output: 0,
|
|
6547
|
+
cacheRead: 0,
|
|
6548
|
+
cacheWrite: 0,
|
|
6549
|
+
},
|
|
6550
|
+
contextWindow: 128000,
|
|
6551
|
+
maxTokens: 4096,
|
|
6552
|
+
},
|
|
6553
|
+
"google/gemma-3n-e4b-it": {
|
|
6554
|
+
id: "google/gemma-3n-e4b-it",
|
|
6555
|
+
name: "Gemma 3n E4b It",
|
|
6556
|
+
api: "openai-completions",
|
|
6557
|
+
provider: "nvidia",
|
|
6558
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6559
|
+
reasoning: false,
|
|
6560
|
+
input: ["text", "image"],
|
|
6561
|
+
cost: {
|
|
6562
|
+
input: 0,
|
|
6563
|
+
output: 0,
|
|
6564
|
+
cacheRead: 0,
|
|
6565
|
+
cacheWrite: 0,
|
|
6566
|
+
},
|
|
6567
|
+
contextWindow: 128000,
|
|
6568
|
+
maxTokens: 4096,
|
|
6569
|
+
},
|
|
6570
|
+
"google/gemma-4-31b-it": {
|
|
6571
|
+
id: "google/gemma-4-31b-it",
|
|
6572
|
+
name: "Gemma-4-31B-IT",
|
|
6573
|
+
api: "openai-completions",
|
|
6574
|
+
provider: "nvidia",
|
|
6575
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6576
|
+
reasoning: true,
|
|
6577
|
+
input: ["text", "image"],
|
|
6578
|
+
cost: {
|
|
6579
|
+
input: 0,
|
|
6580
|
+
output: 0,
|
|
6581
|
+
cacheRead: 0,
|
|
6582
|
+
cacheWrite: 0,
|
|
6583
|
+
},
|
|
6584
|
+
contextWindow: 256000,
|
|
6585
|
+
maxTokens: 16384,
|
|
6586
|
+
},
|
|
6587
|
+
"meta/llama-3.1-70b-instruct": {
|
|
6588
|
+
id: "meta/llama-3.1-70b-instruct",
|
|
6589
|
+
name: "Llama 3.1 70b Instruct",
|
|
6590
|
+
api: "openai-completions",
|
|
6591
|
+
provider: "nvidia",
|
|
6592
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6593
|
+
reasoning: false,
|
|
6594
|
+
input: ["text"],
|
|
6595
|
+
cost: {
|
|
6596
|
+
input: 0,
|
|
6597
|
+
output: 0,
|
|
6598
|
+
cacheRead: 0,
|
|
6599
|
+
cacheWrite: 0,
|
|
6600
|
+
},
|
|
6601
|
+
contextWindow: 128000,
|
|
6602
|
+
maxTokens: 4096,
|
|
6603
|
+
},
|
|
6604
|
+
"meta/llama-3.1-8b-instruct": {
|
|
6605
|
+
id: "meta/llama-3.1-8b-instruct",
|
|
6606
|
+
name: "Llama 3.1 8B Instruct",
|
|
6607
|
+
api: "openai-completions",
|
|
6608
|
+
provider: "nvidia",
|
|
6609
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6610
|
+
reasoning: false,
|
|
6611
|
+
input: ["text"],
|
|
6612
|
+
cost: {
|
|
6613
|
+
input: 0,
|
|
6614
|
+
output: 0,
|
|
6615
|
+
cacheRead: 0,
|
|
6616
|
+
cacheWrite: 0,
|
|
6617
|
+
},
|
|
6618
|
+
contextWindow: 16000,
|
|
6619
|
+
maxTokens: 4096,
|
|
6620
|
+
},
|
|
6621
|
+
"meta/llama-3.2-11b-vision-instruct": {
|
|
6622
|
+
id: "meta/llama-3.2-11b-vision-instruct",
|
|
6623
|
+
name: "Llama 3.2 11b Vision Instruct",
|
|
6624
|
+
api: "openai-completions",
|
|
6625
|
+
provider: "nvidia",
|
|
6626
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6627
|
+
reasoning: false,
|
|
6628
|
+
input: ["text", "image"],
|
|
6629
|
+
cost: {
|
|
6630
|
+
input: 0,
|
|
6631
|
+
output: 0,
|
|
6632
|
+
cacheRead: 0,
|
|
6633
|
+
cacheWrite: 0,
|
|
6634
|
+
},
|
|
6635
|
+
contextWindow: 128000,
|
|
6636
|
+
maxTokens: 4096,
|
|
6637
|
+
},
|
|
6638
|
+
"meta/llama-3.2-1b-instruct": {
|
|
6639
|
+
id: "meta/llama-3.2-1b-instruct",
|
|
6640
|
+
name: "Llama 3.2 1b Instruct",
|
|
6641
|
+
api: "openai-completions",
|
|
6642
|
+
provider: "nvidia",
|
|
6643
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6644
|
+
reasoning: false,
|
|
6645
|
+
input: ["text"],
|
|
6646
|
+
cost: {
|
|
6647
|
+
input: 0,
|
|
6648
|
+
output: 0,
|
|
6649
|
+
cacheRead: 0,
|
|
6650
|
+
cacheWrite: 0,
|
|
6651
|
+
},
|
|
6652
|
+
contextWindow: 128000,
|
|
6653
|
+
maxTokens: 4096,
|
|
6654
|
+
},
|
|
6655
|
+
"meta/llama-3.2-90b-vision-instruct": {
|
|
6656
|
+
id: "meta/llama-3.2-90b-vision-instruct",
|
|
6657
|
+
name: "Llama-3.2-90B-Vision-Instruct",
|
|
6658
|
+
api: "openai-completions",
|
|
6659
|
+
provider: "nvidia",
|
|
6660
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6661
|
+
reasoning: false,
|
|
6662
|
+
input: ["text", "image"],
|
|
6663
|
+
cost: {
|
|
6664
|
+
input: 0,
|
|
6665
|
+
output: 0,
|
|
6666
|
+
cacheRead: 0,
|
|
6667
|
+
cacheWrite: 0,
|
|
6668
|
+
},
|
|
6669
|
+
contextWindow: 128000,
|
|
6670
|
+
maxTokens: 8192,
|
|
6671
|
+
},
|
|
6672
|
+
"meta/llama-3.3-70b-instruct": {
|
|
6673
|
+
id: "meta/llama-3.3-70b-instruct",
|
|
6674
|
+
name: "Llama 3.3 70b Instruct",
|
|
6675
|
+
api: "openai-completions",
|
|
6676
|
+
provider: "nvidia",
|
|
6677
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6678
|
+
reasoning: false,
|
|
6679
|
+
input: ["text"],
|
|
6680
|
+
cost: {
|
|
6681
|
+
input: 0,
|
|
6682
|
+
output: 0,
|
|
6683
|
+
cacheRead: 0,
|
|
6684
|
+
cacheWrite: 0,
|
|
6685
|
+
},
|
|
6686
|
+
contextWindow: 128000,
|
|
6687
|
+
maxTokens: 4096,
|
|
6688
|
+
},
|
|
6689
|
+
"meta/llama-4-maverick-17b-128e-instruct": {
|
|
6690
|
+
id: "meta/llama-4-maverick-17b-128e-instruct",
|
|
6691
|
+
name: "Llama 4 Maverick 17b 128e Instruct",
|
|
6692
|
+
api: "openai-completions",
|
|
6693
|
+
provider: "nvidia",
|
|
6694
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6695
|
+
reasoning: false,
|
|
6696
|
+
input: ["text", "image"],
|
|
6697
|
+
cost: {
|
|
6698
|
+
input: 0,
|
|
6699
|
+
output: 0,
|
|
6700
|
+
cacheRead: 0,
|
|
6701
|
+
cacheWrite: 0,
|
|
6702
|
+
},
|
|
6703
|
+
contextWindow: 128000,
|
|
6704
|
+
maxTokens: 4096,
|
|
6705
|
+
},
|
|
6706
|
+
"microsoft/phi-4-mini-instruct": {
|
|
6707
|
+
id: "microsoft/phi-4-mini-instruct",
|
|
6708
|
+
name: "Phi-4-Mini",
|
|
6709
|
+
api: "openai-completions",
|
|
6710
|
+
provider: "nvidia",
|
|
6711
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6712
|
+
reasoning: true,
|
|
6713
|
+
input: ["text", "image"],
|
|
6714
|
+
cost: {
|
|
6715
|
+
input: 0,
|
|
6716
|
+
output: 0,
|
|
6717
|
+
cacheRead: 0,
|
|
6718
|
+
cacheWrite: 0,
|
|
6719
|
+
},
|
|
6720
|
+
contextWindow: 131072,
|
|
6721
|
+
maxTokens: 8192,
|
|
6722
|
+
},
|
|
6723
|
+
"minimaxai/minimax-m2.5": {
|
|
6724
|
+
id: "minimaxai/minimax-m2.5",
|
|
6725
|
+
name: "MiniMax-M2.5",
|
|
6726
|
+
api: "openai-completions",
|
|
6727
|
+
provider: "nvidia",
|
|
6728
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6729
|
+
reasoning: true,
|
|
6730
|
+
input: ["text"],
|
|
6731
|
+
cost: {
|
|
6732
|
+
input: 0,
|
|
6733
|
+
output: 0,
|
|
6734
|
+
cacheRead: 0,
|
|
6735
|
+
cacheWrite: 0,
|
|
6736
|
+
},
|
|
6737
|
+
contextWindow: 204800,
|
|
6738
|
+
maxTokens: 131072,
|
|
6739
|
+
},
|
|
6740
|
+
"minimaxai/minimax-m2.7": {
|
|
6741
|
+
id: "minimaxai/minimax-m2.7",
|
|
6742
|
+
name: "MiniMax-M2.7",
|
|
6743
|
+
api: "openai-completions",
|
|
6744
|
+
provider: "nvidia",
|
|
6745
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6746
|
+
reasoning: true,
|
|
6747
|
+
input: ["text"],
|
|
6748
|
+
cost: {
|
|
6749
|
+
input: 0,
|
|
6750
|
+
output: 0,
|
|
6751
|
+
cacheRead: 0,
|
|
6752
|
+
cacheWrite: 0,
|
|
6753
|
+
},
|
|
6754
|
+
contextWindow: 204800,
|
|
6755
|
+
maxTokens: 131072,
|
|
6756
|
+
},
|
|
6757
|
+
"mistralai/devstral-2-123b-instruct-2512": {
|
|
6758
|
+
id: "mistralai/devstral-2-123b-instruct-2512",
|
|
6759
|
+
name: "Devstral-2-123B-Instruct-2512",
|
|
6760
|
+
api: "openai-completions",
|
|
6761
|
+
provider: "nvidia",
|
|
6762
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6763
|
+
reasoning: true,
|
|
6764
|
+
input: ["text"],
|
|
6765
|
+
cost: {
|
|
6766
|
+
input: 0,
|
|
6767
|
+
output: 0,
|
|
6768
|
+
cacheRead: 0,
|
|
6769
|
+
cacheWrite: 0,
|
|
6770
|
+
},
|
|
6771
|
+
contextWindow: 262144,
|
|
6772
|
+
maxTokens: 262144,
|
|
6773
|
+
},
|
|
6774
|
+
"mistralai/mistral-7b-instruct-v03": {
|
|
6775
|
+
id: "mistralai/mistral-7b-instruct-v03",
|
|
6776
|
+
name: "Mistral-7B-Instruct-v0.3",
|
|
6777
|
+
api: "openai-completions",
|
|
6778
|
+
provider: "nvidia",
|
|
6779
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6780
|
+
reasoning: false,
|
|
6781
|
+
input: ["text"],
|
|
6782
|
+
cost: {
|
|
6783
|
+
input: 0,
|
|
6784
|
+
output: 0,
|
|
6785
|
+
cacheRead: 0,
|
|
6786
|
+
cacheWrite: 0,
|
|
6787
|
+
},
|
|
6788
|
+
contextWindow: 65536,
|
|
6789
|
+
maxTokens: 65536,
|
|
6790
|
+
},
|
|
6791
|
+
"mistralai/mistral-large-3-675b-instruct-2512": {
|
|
6792
|
+
id: "mistralai/mistral-large-3-675b-instruct-2512",
|
|
6793
|
+
name: "Mistral Large 3 675B Instruct 2512",
|
|
6794
|
+
api: "openai-completions",
|
|
6795
|
+
provider: "nvidia",
|
|
6796
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6797
|
+
reasoning: false,
|
|
6798
|
+
input: ["text", "image"],
|
|
6799
|
+
cost: {
|
|
6800
|
+
input: 0,
|
|
6801
|
+
output: 0,
|
|
6802
|
+
cacheRead: 0,
|
|
6803
|
+
cacheWrite: 0,
|
|
6804
|
+
},
|
|
6805
|
+
contextWindow: 262144,
|
|
6806
|
+
maxTokens: 262144,
|
|
6807
|
+
},
|
|
6808
|
+
"mistralai/mistral-nemotron": {
|
|
6809
|
+
id: "mistralai/mistral-nemotron",
|
|
6810
|
+
name: "mistral-nemotron",
|
|
6811
|
+
api: "openai-completions",
|
|
6812
|
+
provider: "nvidia",
|
|
6813
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6814
|
+
reasoning: false,
|
|
6815
|
+
input: ["text"],
|
|
6816
|
+
cost: {
|
|
6817
|
+
input: 0,
|
|
6818
|
+
output: 0,
|
|
6819
|
+
cacheRead: 0,
|
|
6820
|
+
cacheWrite: 0,
|
|
6821
|
+
},
|
|
6822
|
+
contextWindow: 128000,
|
|
6823
|
+
maxTokens: 8192,
|
|
6824
|
+
},
|
|
6825
|
+
"mistralai/mistral-small-4-119b-2603": {
|
|
6826
|
+
id: "mistralai/mistral-small-4-119b-2603",
|
|
6827
|
+
name: "mistral-small-4-119b-2603",
|
|
6828
|
+
api: "openai-completions",
|
|
6829
|
+
provider: "nvidia",
|
|
6830
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6831
|
+
reasoning: false,
|
|
6832
|
+
input: ["text"],
|
|
6833
|
+
cost: {
|
|
6834
|
+
input: 0,
|
|
6835
|
+
output: 0,
|
|
6836
|
+
cacheRead: 0,
|
|
6837
|
+
cacheWrite: 0,
|
|
6838
|
+
},
|
|
6839
|
+
contextWindow: 128000,
|
|
6840
|
+
maxTokens: 8192,
|
|
6841
|
+
},
|
|
6842
|
+
"mistralai/mixtral-8x22b-instruct": {
|
|
6843
|
+
id: "mistralai/mixtral-8x22b-instruct",
|
|
6844
|
+
name: "Mistral: Mixtral 8x22B Instruct",
|
|
6845
|
+
api: "openai-completions",
|
|
6846
|
+
provider: "nvidia",
|
|
6847
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6848
|
+
reasoning: false,
|
|
6849
|
+
input: ["text"],
|
|
6850
|
+
cost: {
|
|
6851
|
+
input: 0,
|
|
6852
|
+
output: 0,
|
|
6853
|
+
cacheRead: 0,
|
|
6854
|
+
cacheWrite: 0,
|
|
6855
|
+
},
|
|
6856
|
+
contextWindow: 65536,
|
|
6857
|
+
maxTokens: 13108,
|
|
6858
|
+
},
|
|
6859
|
+
"mistralai/mixtral-8x7b-instruct": {
|
|
6860
|
+
id: "mistralai/mixtral-8x7b-instruct",
|
|
6861
|
+
name: "Mistral: Mixtral 8x7B Instruct",
|
|
6862
|
+
api: "openai-completions",
|
|
6863
|
+
provider: "nvidia",
|
|
6864
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6865
|
+
reasoning: false,
|
|
6866
|
+
input: ["text"],
|
|
6867
|
+
cost: {
|
|
6868
|
+
input: 0,
|
|
6869
|
+
output: 0,
|
|
6870
|
+
cacheRead: 0,
|
|
6871
|
+
cacheWrite: 0,
|
|
6872
|
+
},
|
|
6873
|
+
contextWindow: 32768,
|
|
6874
|
+
maxTokens: 16384,
|
|
6875
|
+
},
|
|
6876
|
+
"moonshotai/kimi-k2-instruct": {
|
|
6877
|
+
id: "moonshotai/kimi-k2-instruct",
|
|
6878
|
+
name: "Kimi K2 Instruct",
|
|
6879
|
+
api: "openai-completions",
|
|
6880
|
+
provider: "nvidia",
|
|
6881
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6882
|
+
reasoning: true,
|
|
6883
|
+
input: ["text"],
|
|
6884
|
+
cost: {
|
|
6885
|
+
input: 0,
|
|
6886
|
+
output: 0,
|
|
6887
|
+
cacheRead: 0,
|
|
6888
|
+
cacheWrite: 0,
|
|
6889
|
+
},
|
|
6890
|
+
contextWindow: 128000,
|
|
6891
|
+
maxTokens: 8192,
|
|
6892
|
+
},
|
|
6893
|
+
"moonshotai/kimi-k2-instruct-0905": {
|
|
6894
|
+
id: "moonshotai/kimi-k2-instruct-0905",
|
|
6895
|
+
name: "Kimi K2 0905",
|
|
6896
|
+
api: "openai-completions",
|
|
6897
|
+
provider: "nvidia",
|
|
6898
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6899
|
+
reasoning: false,
|
|
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
|
+
"moonshotai/kimi-k2-thinking": {
|
|
6911
|
+
id: "moonshotai/kimi-k2-thinking",
|
|
6912
|
+
name: "Kimi K2 Thinking",
|
|
6913
|
+
api: "openai-completions",
|
|
6914
|
+
provider: "nvidia",
|
|
6915
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6916
|
+
reasoning: true,
|
|
6917
|
+
input: ["text"],
|
|
6918
|
+
cost: {
|
|
6919
|
+
input: 0,
|
|
6920
|
+
output: 0,
|
|
6921
|
+
cacheRead: 0,
|
|
6922
|
+
cacheWrite: 0,
|
|
6923
|
+
},
|
|
6924
|
+
contextWindow: 262144,
|
|
6925
|
+
maxTokens: 262144,
|
|
6926
|
+
},
|
|
6927
|
+
"moonshotai/kimi-k2.6": {
|
|
6928
|
+
id: "moonshotai/kimi-k2.6",
|
|
6929
|
+
name: "Kimi K2.6",
|
|
6930
|
+
api: "openai-completions",
|
|
6931
|
+
provider: "nvidia",
|
|
6932
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6933
|
+
reasoning: true,
|
|
6934
|
+
input: ["text", "image"],
|
|
6935
|
+
cost: {
|
|
6936
|
+
input: 0,
|
|
6937
|
+
output: 0,
|
|
6938
|
+
cacheRead: 0,
|
|
6939
|
+
cacheWrite: 0,
|
|
6940
|
+
},
|
|
6941
|
+
contextWindow: 262144,
|
|
6942
|
+
maxTokens: 262144,
|
|
6943
|
+
},
|
|
6944
|
+
"nvidia/llama-3_3-nemotron-super-49b-v1": {
|
|
6945
|
+
id: "nvidia/llama-3_3-nemotron-super-49b-v1",
|
|
6946
|
+
name: "Llama 3.3 Nemotron Super 49B v1",
|
|
6947
|
+
api: "openai-completions",
|
|
6948
|
+
provider: "nvidia",
|
|
6949
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6950
|
+
reasoning: true,
|
|
6951
|
+
input: ["text"],
|
|
6952
|
+
cost: {
|
|
6953
|
+
input: 0,
|
|
6954
|
+
output: 0,
|
|
6955
|
+
cacheRead: 0,
|
|
6956
|
+
cacheWrite: 0,
|
|
6957
|
+
},
|
|
6958
|
+
contextWindow: 131072,
|
|
6959
|
+
maxTokens: 131072,
|
|
6960
|
+
},
|
|
6961
|
+
"nvidia/llama-3_3-nemotron-super-49b-v1_5": {
|
|
6962
|
+
id: "nvidia/llama-3_3-nemotron-super-49b-v1_5",
|
|
6963
|
+
name: "Llama 3.3 Nemotron Super 49B v1.5",
|
|
6964
|
+
api: "openai-completions",
|
|
6965
|
+
provider: "nvidia",
|
|
6966
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6967
|
+
reasoning: true,
|
|
6968
|
+
input: ["text"],
|
|
6969
|
+
cost: {
|
|
6970
|
+
input: 0,
|
|
6971
|
+
output: 0,
|
|
6972
|
+
cacheRead: 0,
|
|
6973
|
+
cacheWrite: 0,
|
|
6974
|
+
},
|
|
6975
|
+
contextWindow: 131072,
|
|
6976
|
+
maxTokens: 131072,
|
|
6977
|
+
},
|
|
6978
|
+
"nvidia/nemotron-3-nano-30b-a3b": {
|
|
6979
|
+
id: "nvidia/nemotron-3-nano-30b-a3b",
|
|
6980
|
+
name: "nemotron-3-nano-30b-a3b",
|
|
6981
|
+
api: "openai-completions",
|
|
6982
|
+
provider: "nvidia",
|
|
6983
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
6984
|
+
reasoning: true,
|
|
6985
|
+
input: ["text"],
|
|
6986
|
+
cost: {
|
|
6987
|
+
input: 0,
|
|
6988
|
+
output: 0,
|
|
6989
|
+
cacheRead: 0,
|
|
6990
|
+
cacheWrite: 0,
|
|
6991
|
+
},
|
|
6992
|
+
contextWindow: 131072,
|
|
6993
|
+
maxTokens: 131072,
|
|
6994
|
+
},
|
|
6995
|
+
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
|
|
6996
|
+
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
|
|
6997
|
+
name: "Nemotron 3 Nano Omni",
|
|
6998
|
+
api: "openai-completions",
|
|
6999
|
+
provider: "nvidia",
|
|
7000
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7001
|
+
reasoning: true,
|
|
7002
|
+
input: ["text", "image"],
|
|
7003
|
+
cost: {
|
|
7004
|
+
input: 0,
|
|
7005
|
+
output: 0,
|
|
7006
|
+
cacheRead: 0,
|
|
7007
|
+
cacheWrite: 0,
|
|
7008
|
+
},
|
|
7009
|
+
contextWindow: 256000,
|
|
7010
|
+
maxTokens: 65536,
|
|
7011
|
+
},
|
|
7012
|
+
"nvidia/nemotron-3-super-120b-a12b": {
|
|
7013
|
+
id: "nvidia/nemotron-3-super-120b-a12b",
|
|
7014
|
+
name: "Nemotron 3 Super",
|
|
7015
|
+
api: "openai-completions",
|
|
7016
|
+
provider: "nvidia",
|
|
7017
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7018
|
+
reasoning: true,
|
|
7019
|
+
input: ["text"],
|
|
7020
|
+
cost: {
|
|
7021
|
+
input: 0.2,
|
|
7022
|
+
output: 0.8,
|
|
7023
|
+
cacheRead: 0,
|
|
7024
|
+
cacheWrite: 0,
|
|
7025
|
+
},
|
|
7026
|
+
contextWindow: 262144,
|
|
7027
|
+
maxTokens: 262144,
|
|
7028
|
+
},
|
|
7029
|
+
"nvidia/nemotron-mini-4b-instruct": {
|
|
7030
|
+
id: "nvidia/nemotron-mini-4b-instruct",
|
|
7031
|
+
name: "nemotron-mini-4b-instruct",
|
|
7032
|
+
api: "openai-completions",
|
|
7033
|
+
provider: "nvidia",
|
|
7034
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7035
|
+
reasoning: false,
|
|
7036
|
+
input: ["text"],
|
|
7037
|
+
cost: {
|
|
7038
|
+
input: 0,
|
|
7039
|
+
output: 0,
|
|
7040
|
+
cacheRead: 0,
|
|
7041
|
+
cacheWrite: 0,
|
|
7042
|
+
},
|
|
7043
|
+
contextWindow: 128000,
|
|
7044
|
+
maxTokens: 8192,
|
|
7045
|
+
},
|
|
7046
|
+
"nvidia/nemotron-voicechat": {
|
|
7047
|
+
id: "nvidia/nemotron-voicechat",
|
|
7048
|
+
name: "nemotron-voicechat",
|
|
7049
|
+
api: "openai-completions",
|
|
7050
|
+
provider: "nvidia",
|
|
7051
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7052
|
+
reasoning: false,
|
|
7053
|
+
input: ["text"],
|
|
7054
|
+
cost: {
|
|
7055
|
+
input: 0,
|
|
7056
|
+
output: 0,
|
|
7057
|
+
cacheRead: 0,
|
|
7058
|
+
cacheWrite: 0,
|
|
7059
|
+
},
|
|
7060
|
+
contextWindow: 128000,
|
|
7061
|
+
maxTokens: 8192,
|
|
7062
|
+
},
|
|
7063
|
+
"nvidia/nvidia-nemotron-nano-9b-v2": {
|
|
7064
|
+
id: "nvidia/nvidia-nemotron-nano-9b-v2",
|
|
7065
|
+
name: "nvidia-nemotron-nano-9b-v2",
|
|
7066
|
+
api: "openai-completions",
|
|
7067
|
+
provider: "nvidia",
|
|
7068
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7069
|
+
reasoning: true,
|
|
7070
|
+
input: ["text"],
|
|
7071
|
+
cost: {
|
|
7072
|
+
input: 0,
|
|
7073
|
+
output: 0,
|
|
7074
|
+
cacheRead: 0,
|
|
7075
|
+
cacheWrite: 0,
|
|
7076
|
+
},
|
|
7077
|
+
contextWindow: 131072,
|
|
7078
|
+
maxTokens: 131072,
|
|
7079
|
+
},
|
|
7080
|
+
"openai/gpt-oss-20b": {
|
|
7081
|
+
id: "openai/gpt-oss-20b",
|
|
7082
|
+
name: "GPT OSS 20B",
|
|
7083
|
+
api: "openai-completions",
|
|
7084
|
+
provider: "nvidia",
|
|
7085
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7086
|
+
reasoning: true,
|
|
7087
|
+
input: ["text"],
|
|
7088
|
+
cost: {
|
|
7089
|
+
input: 0,
|
|
7090
|
+
output: 0,
|
|
7091
|
+
cacheRead: 0,
|
|
7092
|
+
cacheWrite: 0,
|
|
7093
|
+
},
|
|
7094
|
+
contextWindow: 131072,
|
|
7095
|
+
maxTokens: 32768,
|
|
7096
|
+
},
|
|
7097
|
+
"qwen/qwen2.5-coder-32b-instruct": {
|
|
7098
|
+
id: "qwen/qwen2.5-coder-32b-instruct",
|
|
7099
|
+
name: "Qwen2.5 Coder 32b Instruct",
|
|
7100
|
+
api: "openai-completions",
|
|
7101
|
+
provider: "nvidia",
|
|
7102
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7103
|
+
reasoning: false,
|
|
7104
|
+
input: ["text"],
|
|
7105
|
+
cost: {
|
|
7106
|
+
input: 0,
|
|
7107
|
+
output: 0,
|
|
7108
|
+
cacheRead: 0,
|
|
7109
|
+
cacheWrite: 0,
|
|
7110
|
+
},
|
|
7111
|
+
contextWindow: 128000,
|
|
7112
|
+
maxTokens: 4096,
|
|
7113
|
+
},
|
|
7114
|
+
"qwen/qwen3-coder-480b-a35b-instruct": {
|
|
7115
|
+
id: "qwen/qwen3-coder-480b-a35b-instruct",
|
|
7116
|
+
name: "Qwen3 Coder 480B A35B Instruct",
|
|
7117
|
+
api: "openai-completions",
|
|
7118
|
+
provider: "nvidia",
|
|
7119
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7120
|
+
reasoning: false,
|
|
7121
|
+
input: ["text"],
|
|
7122
|
+
cost: {
|
|
7123
|
+
input: 0,
|
|
7124
|
+
output: 0,
|
|
7125
|
+
cacheRead: 0,
|
|
7126
|
+
cacheWrite: 0,
|
|
7127
|
+
},
|
|
7128
|
+
contextWindow: 262144,
|
|
7129
|
+
maxTokens: 66536,
|
|
7130
|
+
},
|
|
7131
|
+
"qwen/qwen3-next-80b-a3b-instruct": {
|
|
7132
|
+
id: "qwen/qwen3-next-80b-a3b-instruct",
|
|
7133
|
+
name: "Qwen3-Next-80B-A3B-Instruct",
|
|
7134
|
+
api: "openai-completions",
|
|
7135
|
+
provider: "nvidia",
|
|
7136
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7137
|
+
reasoning: false,
|
|
7138
|
+
input: ["text"],
|
|
7139
|
+
cost: {
|
|
7140
|
+
input: 0,
|
|
7141
|
+
output: 0,
|
|
7142
|
+
cacheRead: 0,
|
|
7143
|
+
cacheWrite: 0,
|
|
7144
|
+
},
|
|
7145
|
+
contextWindow: 262144,
|
|
7146
|
+
maxTokens: 16384,
|
|
7147
|
+
},
|
|
7148
|
+
"qwen/qwen3-next-80b-a3b-thinking": {
|
|
7149
|
+
id: "qwen/qwen3-next-80b-a3b-thinking",
|
|
7150
|
+
name: "Qwen3-Next-80B-A3B-Thinking",
|
|
7151
|
+
api: "openai-completions",
|
|
7152
|
+
provider: "nvidia",
|
|
7153
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7154
|
+
reasoning: true,
|
|
7155
|
+
input: ["text"],
|
|
7156
|
+
cost: {
|
|
7157
|
+
input: 0,
|
|
7158
|
+
output: 0,
|
|
7159
|
+
cacheRead: 0,
|
|
7160
|
+
cacheWrite: 0,
|
|
7161
|
+
},
|
|
7162
|
+
contextWindow: 262144,
|
|
7163
|
+
maxTokens: 16384,
|
|
7164
|
+
},
|
|
7165
|
+
"qwen/qwen3.5-122b-a10b": {
|
|
7166
|
+
id: "qwen/qwen3.5-122b-a10b",
|
|
7167
|
+
name: "Qwen3.5 122B-A10B",
|
|
7168
|
+
api: "openai-completions",
|
|
7169
|
+
provider: "nvidia",
|
|
7170
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7171
|
+
reasoning: true,
|
|
7172
|
+
input: ["text", "image"],
|
|
7173
|
+
cost: {
|
|
7174
|
+
input: 0,
|
|
7175
|
+
output: 0,
|
|
7176
|
+
cacheRead: 0,
|
|
7177
|
+
cacheWrite: 0,
|
|
7178
|
+
},
|
|
7179
|
+
contextWindow: 262144,
|
|
7180
|
+
maxTokens: 65536,
|
|
7181
|
+
},
|
|
7182
|
+
"qwen/qwen3.5-397b-a17b": {
|
|
7183
|
+
id: "qwen/qwen3.5-397b-a17b",
|
|
7184
|
+
name: "Qwen3.5-397B-A17B",
|
|
7185
|
+
api: "openai-completions",
|
|
7186
|
+
provider: "nvidia",
|
|
7187
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7188
|
+
reasoning: true,
|
|
7189
|
+
input: ["text", "image"],
|
|
7190
|
+
cost: {
|
|
7191
|
+
input: 0,
|
|
7192
|
+
output: 0,
|
|
7193
|
+
cacheRead: 0,
|
|
7194
|
+
cacheWrite: 0,
|
|
7195
|
+
},
|
|
7196
|
+
contextWindow: 262144,
|
|
7197
|
+
maxTokens: 8192,
|
|
7198
|
+
},
|
|
7199
|
+
"sarvamai/sarvam-m": {
|
|
7200
|
+
id: "sarvamai/sarvam-m",
|
|
7201
|
+
name: "sarvam-m",
|
|
7202
|
+
api: "openai-completions",
|
|
7203
|
+
provider: "nvidia",
|
|
7204
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7205
|
+
reasoning: false,
|
|
7206
|
+
input: ["text"],
|
|
7207
|
+
cost: {
|
|
7208
|
+
input: 0,
|
|
7209
|
+
output: 0,
|
|
7210
|
+
cacheRead: 0,
|
|
7211
|
+
cacheWrite: 0,
|
|
7212
|
+
},
|
|
7213
|
+
contextWindow: 128000,
|
|
7214
|
+
maxTokens: 8192,
|
|
7215
|
+
},
|
|
7216
|
+
"stepfun-ai/step-3.5-flash": {
|
|
7217
|
+
id: "stepfun-ai/step-3.5-flash",
|
|
7218
|
+
name: "Step 3.5 Flash",
|
|
7219
|
+
api: "openai-completions",
|
|
7220
|
+
provider: "nvidia",
|
|
7221
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7222
|
+
reasoning: true,
|
|
7223
|
+
input: ["text"],
|
|
7224
|
+
cost: {
|
|
7225
|
+
input: 0,
|
|
7226
|
+
output: 0,
|
|
7227
|
+
cacheRead: 0,
|
|
7228
|
+
cacheWrite: 0,
|
|
7229
|
+
},
|
|
7230
|
+
contextWindow: 256000,
|
|
7231
|
+
maxTokens: 16384,
|
|
7232
|
+
},
|
|
7233
|
+
"upstage/solar-10_7b-instruct": {
|
|
7234
|
+
id: "upstage/solar-10_7b-instruct",
|
|
7235
|
+
name: "solar-10.7b-instruct",
|
|
7236
|
+
api: "openai-completions",
|
|
7237
|
+
provider: "nvidia",
|
|
7238
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7239
|
+
reasoning: false,
|
|
7240
|
+
input: ["text"],
|
|
7241
|
+
cost: {
|
|
7242
|
+
input: 0,
|
|
7243
|
+
output: 0,
|
|
7244
|
+
cacheRead: 0,
|
|
7245
|
+
cacheWrite: 0,
|
|
7246
|
+
},
|
|
7247
|
+
contextWindow: 128000,
|
|
7248
|
+
maxTokens: 8192,
|
|
7249
|
+
},
|
|
7250
|
+
"z-ai/glm-5.1": {
|
|
7251
|
+
id: "z-ai/glm-5.1",
|
|
7252
|
+
name: "GLM-5.1",
|
|
7253
|
+
api: "openai-completions",
|
|
7254
|
+
provider: "nvidia",
|
|
7255
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7256
|
+
reasoning: true,
|
|
7257
|
+
input: ["text"],
|
|
7258
|
+
cost: {
|
|
7259
|
+
input: 0,
|
|
7260
|
+
output: 0,
|
|
7261
|
+
cacheRead: 0,
|
|
7262
|
+
cacheWrite: 0,
|
|
7263
|
+
},
|
|
7264
|
+
contextWindow: 131072,
|
|
7265
|
+
maxTokens: 131072,
|
|
7266
|
+
},
|
|
7267
|
+
"z-ai/glm4.7": {
|
|
7268
|
+
id: "z-ai/glm4.7",
|
|
7269
|
+
name: "GLM-4.7",
|
|
7270
|
+
api: "openai-completions",
|
|
7271
|
+
provider: "nvidia",
|
|
7272
|
+
baseUrl: "https://integrate.api.nvidia.com/v1",
|
|
7273
|
+
reasoning: true,
|
|
7274
|
+
input: ["text"],
|
|
7275
|
+
cost: {
|
|
7276
|
+
input: 0,
|
|
7277
|
+
output: 0,
|
|
7278
|
+
cacheRead: 0,
|
|
7279
|
+
cacheWrite: 0,
|
|
7280
|
+
},
|
|
7281
|
+
contextWindow: 204800,
|
|
7282
|
+
maxTokens: 131072,
|
|
7283
|
+
},
|
|
7284
|
+
},
|
|
6395
7285
|
"openai": {
|
|
6396
7286
|
"gpt-4": {
|
|
6397
7287
|
id: "gpt-4",
|
|
@@ -7468,6 +8358,25 @@ export const MODELS = {
|
|
|
7468
8358
|
contextWindow: 1000000,
|
|
7469
8359
|
maxTokens: 64000,
|
|
7470
8360
|
},
|
|
8361
|
+
"deepseek-v4-flash-free": {
|
|
8362
|
+
id: "deepseek-v4-flash-free",
|
|
8363
|
+
name: "DeepSeek V4 Flash Free",
|
|
8364
|
+
api: "openai-completions",
|
|
8365
|
+
provider: "opencode",
|
|
8366
|
+
baseUrl: "https://opencode.ai/zen/v1",
|
|
8367
|
+
compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
|
|
8368
|
+
reasoning: true,
|
|
8369
|
+
thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
|
|
8370
|
+
input: ["text"],
|
|
8371
|
+
cost: {
|
|
8372
|
+
input: 0,
|
|
8373
|
+
output: 0,
|
|
8374
|
+
cacheRead: 0,
|
|
8375
|
+
cacheWrite: 0,
|
|
8376
|
+
},
|
|
8377
|
+
contextWindow: 1000000,
|
|
8378
|
+
maxTokens: 384000,
|
|
8379
|
+
},
|
|
7471
8380
|
"gemini-3-flash": {
|
|
7472
8381
|
id: "gemini-3-flash",
|
|
7473
8382
|
name: "Gemini 3 Flash",
|
|
@@ -8346,40 +9255,6 @@ export const MODELS = {
|
|
|
8346
9255
|
contextWindow: 200000,
|
|
8347
9256
|
maxTokens: 8192,
|
|
8348
9257
|
},
|
|
8349
|
-
"anthropic/claude-3.7-sonnet": {
|
|
8350
|
-
id: "anthropic/claude-3.7-sonnet",
|
|
8351
|
-
name: "Anthropic: Claude 3.7 Sonnet",
|
|
8352
|
-
api: "openai-completions",
|
|
8353
|
-
provider: "openrouter",
|
|
8354
|
-
baseUrl: "https://openrouter.ai/api/v1",
|
|
8355
|
-
reasoning: true,
|
|
8356
|
-
input: ["text", "image"],
|
|
8357
|
-
cost: {
|
|
8358
|
-
input: 3,
|
|
8359
|
-
output: 15,
|
|
8360
|
-
cacheRead: 0.3,
|
|
8361
|
-
cacheWrite: 3.75,
|
|
8362
|
-
},
|
|
8363
|
-
contextWindow: 200000,
|
|
8364
|
-
maxTokens: 64000,
|
|
8365
|
-
},
|
|
8366
|
-
"anthropic/claude-3.7-sonnet:thinking": {
|
|
8367
|
-
id: "anthropic/claude-3.7-sonnet:thinking",
|
|
8368
|
-
name: "Anthropic: Claude 3.7 Sonnet (thinking)",
|
|
8369
|
-
api: "openai-completions",
|
|
8370
|
-
provider: "openrouter",
|
|
8371
|
-
baseUrl: "https://openrouter.ai/api/v1",
|
|
8372
|
-
reasoning: true,
|
|
8373
|
-
input: ["text", "image"],
|
|
8374
|
-
cost: {
|
|
8375
|
-
input: 3,
|
|
8376
|
-
output: 15,
|
|
8377
|
-
cacheRead: 0.3,
|
|
8378
|
-
cacheWrite: 3.75,
|
|
8379
|
-
},
|
|
8380
|
-
contextWindow: 200000,
|
|
8381
|
-
maxTokens: 64000,
|
|
8382
|
-
},
|
|
8383
9258
|
"anthropic/claude-haiku-4.5": {
|
|
8384
9259
|
id: "anthropic/claude-haiku-4.5",
|
|
8385
9260
|
name: "Anthropic: Claude Haiku 4.5",
|
|
@@ -8587,6 +9462,23 @@ export const MODELS = {
|
|
|
8587
9462
|
contextWindow: 262144,
|
|
8588
9463
|
maxTokens: 262144,
|
|
8589
9464
|
},
|
|
9465
|
+
"arcee-ai/trinity-large-thinking:free": {
|
|
9466
|
+
id: "arcee-ai/trinity-large-thinking:free",
|
|
9467
|
+
name: "Arcee AI: Trinity Large Thinking (free)",
|
|
9468
|
+
api: "openai-completions",
|
|
9469
|
+
provider: "openrouter",
|
|
9470
|
+
baseUrl: "https://openrouter.ai/api/v1",
|
|
9471
|
+
reasoning: true,
|
|
9472
|
+
input: ["text"],
|
|
9473
|
+
cost: {
|
|
9474
|
+
input: 0,
|
|
9475
|
+
output: 0,
|
|
9476
|
+
cacheRead: 0,
|
|
9477
|
+
cacheWrite: 0,
|
|
9478
|
+
},
|
|
9479
|
+
contextWindow: 262144,
|
|
9480
|
+
maxTokens: 80000,
|
|
9481
|
+
},
|
|
8590
9482
|
"arcee-ai/trinity-mini": {
|
|
8591
9483
|
id: "arcee-ai/trinity-mini",
|
|
8592
9484
|
name: "Arcee AI: Trinity Mini",
|
|
@@ -12709,13 +13601,13 @@ export const MODELS = {
|
|
|
12709
13601
|
reasoning: true,
|
|
12710
13602
|
input: ["text"],
|
|
12711
13603
|
cost: {
|
|
12712
|
-
input:
|
|
12713
|
-
output: 3.
|
|
12714
|
-
cacheRead: 0.
|
|
13604
|
+
input: 0.98,
|
|
13605
|
+
output: 3.08,
|
|
13606
|
+
cacheRead: 0.182,
|
|
12715
13607
|
cacheWrite: 0,
|
|
12716
13608
|
},
|
|
12717
13609
|
contextWindow: 202752,
|
|
12718
|
-
maxTokens:
|
|
13610
|
+
maxTokens: 4096,
|
|
12719
13611
|
},
|
|
12720
13612
|
"z-ai/glm-5v-turbo": {
|
|
12721
13613
|
id: "z-ai/glm-5v-turbo",
|