NVIDIA NIM
HealthyTelemetry updated 26m agoNVIDIA's inference microservice platform providing optimized deployment of LLMs on GPU infrastructure. Offers free endpoints for select models and partner endpoints through Deep Infra, Together AI, Bitdeer, GMI Cloud, and CoreWeave.
API Base URL
Authentication
api-key
Uptime (24h)
100.0%
Uptime (7d)
100.0%
Supported Regions
Latency (TTFT)
Time to first token percentiles
Health History
Uptime over the last 7 days
Current Status
Last Checked
26m ago
Supported Models (13)
Models available through this provider. Click a model to view details.
| Model | Pricing (per 1M) | Rate Limits | Regions |
|---|---|---|---|
DeepSeek V4 Flash deepseek-v4-flash | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
DeepSeek V4 Pro deepseek-v4-pro | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Gemma 4 12B gemma-4-12b | In: $0.00 Out: $0.00 | 200 RPM / 500K TPM | us-east-1us-west-2 |
Gemma 4 31B gemma-4 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
GLM-4.7 glm-4-7 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
GLM-5.1 glm-5-1 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Kimi K2.6 kimi-k2-6 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
MiniMax M2.7 minimax-m2-7 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Mistral Medium 3.5 mistral-medium-3-5 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Mistral Small 4 mistral-small-4 | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Nemotron 3 Super 120B nemotron-3-super-120b | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Nemotron 3 Ultra nemotron-3-ultra | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |
Nemotron Nano 9B v2 nemotron-nano-9b | In: $0.00 Out: $0.00 | 100 RPM / 500K TPM | us-east-1us-west-2global |