NVIDIA NIM

NVIDIA NIM

meta

Access NVIDIA NIM models through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

https://integrate.api.nvidia.com/v1
Models
18
Max context
1.0M
Input range
- - $5.00
Discovery
static

Activity

Managed-cloud usage across this serving provider.

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

NVIDIA NIM models

18 shown
NVIDIA NIM: Nemotron 3.5 Lightning 30B A3B (NVIDIA NIM)stable

Nemotron 3.5 Lightning 30B A3B (NVIDIA NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nimAug 11, 2026262.1K context- input- output
ChatFunction CallingReasoning
NVIDIA NIM: Muse Glimmer 30B (NVIDIA NIM)stable

Muse Glimmer 30B (NVIDIA NIM) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by nvidia-nimAug 10, 2026131.1K context- input- output
ChatFunction CallingVision
NVIDIA NIM: DeepSeek V4 Flash 0731 (NVIDIA NIM)stable

DeepSeek V4 Flash 0731 (NVIDIA NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nimJul 31, 20261M context- input- output
ChatFunction CallingReasoning
NVIDIA NIM: Kimi K3 (NVIDIA NIM)stable

Kimi K3 (NVIDIA NIM) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by nvidia-nimJul 16, 20261.0M context- input- output
ChatFunction CallingVision
NVIDIA NIM: Inkling (NVIDIA NIM)stable

Inkling (NVIDIA NIM) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by nvidia-nimJul 15, 20261.0M context- input- output
ChatFunction CallingVision
NVIDIA NIM: GLM-5.2 (NVIDIA NIM)stable

GLM-5.2 (NVIDIA NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nimJun 13, 20261M context- input- output
ChatFunction CallingReasoning
NVIDIA NIM: Nemotron 3 Ultra 550B A55B (NVIDIA NIM)stable

Nemotron 3 Ultra 550B A55B (NVIDIA NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nimJun 4, 20261M context$0.50 input$2.50 output
ChatFunction CallingReasoning
NVIDIA NIM: MiniMax-M3 (NVIDIA NIM)stable

MiniMax-M3 (NVIDIA NIM) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by nvidia-nimJun 1, 20261M context- input- output
ChatFunction CallingVision
NVIDIA NIM: Step 3.7 Flash (NVIDIA NIM)stable

Step 3.7 Flash (NVIDIA NIM) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by nvidia-nimMay 28, 2026256K context- input- output
ChatFunction CallingVision
NVIDIA NIM: DeepSeek V4 Pro (NIM)stable

DeepSeek V4 Pro (NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nimApr 24, 20261.0M context$0.43 input$0.87 output
ChatFunction CallingReasoning
NVIDIA NIM: Nemotron 70B Instructstable

Nemotron 70B Instruct supports Chat, Function Calling workloads through Everstack.

by nvidia-nimApr 15, 2025128K context- input- output
ChatFunction Calling
NVIDIA NIM: Llama 4 Maverick 17B 128Estable

Llama 4 Maverick 17B 128E supports Chat, Function Calling, Vision workloads through Everstack.

by nvidia-nimApr 1, 2025128K context- input- output
ChatFunction CallingVision
NVIDIA NIM: Llama 3.3 70B Instructstable

Llama 3.3 70B Instruct supports Chat, Function Calling workloads through Everstack.

by nvidia-nimNov 26, 2024128K context- input- output
ChatFunction Calling
NVIDIA NIM: Llama 3.1 70B Instructstable

Llama 3.1 70B Instruct supports Chat, Function Calling workloads through Everstack.

by nvidia-nimJul 16, 2024128K context- input- output
ChatFunction Calling
NVIDIA NIM: DeepSeek V3.2 (NIM)stable

DeepSeek V3.2 (NIM) supports Chat, Function Calling, Reasoning workloads through Everstack.

by nvidia-nim163.8K context- input- output
ChatFunction CallingReasoning
NVIDIA NIM: Llama 3.1 405B Instructstable

Llama 3.1 405B Instruct supports Chat, Function Calling workloads through Everstack.

by nvidia-nim131.1K context$5.00 input$5.00 output
ChatFunction Calling
NVIDIA NIM: Llama 4 Scout 17B 16Estable

Llama 4 Scout 17B 16E supports Chat, Function Calling, Vision workloads through Everstack.

by nvidia-nim128K context- input- output
ChatFunction CallingVision
NVIDIA NIM: NV EmbedQA E5 v5stable

NV EmbedQA E5 v5 supports Embeddings workloads through Everstack.

by nvidia-nim8.2K context$0.080 input- output
Embeddings