NVIDIA NIM
Explore NVIDIA NIM models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
NVIDIA NIMnvidia-nim
These privacy labels describe NVIDIA NIM, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | NVIDIA NIM |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://build.nvidia.com/ |
| Models | 14 public models |
| Credits routes | 14 |
| Zero data retention | no |
| Verified confidential inference | Not verified |
| Policy note | NVIDIA's hosted NIM API Catalog endpoints are preview services for development and prototyping. TrustedRouter exposes chat-capable models from its configured API Catalog key as Standard routes. NVIDIA requires an NVIDIA AI Enterprise entitlement for production deployments. NVIDIA does not publish hosted preview token rates, so TrustedRouter uses a conservative fallback price and excludes these routes from price indexing. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
19 samplesContinuously sampled across NVIDIA NIM's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1135 ms |
|---|---|
| Effective throughput | 43 tok/s n=1 |
| Uptime | 78.95% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| openai/gpt-oss-20b | 762 ms | — | 100.00% | — | 4 |
| nvidia/nemotron-3.5-lightning-30b-a3b | 831 ms | — | 100.00% | — | 1 |
| poolside/laguna-xs-2.1 | 1096 ms | — | 50.00% | — | 2 |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | 1135 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.2-11b-vision-instruct | 1138 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-super-120b-a12b | 2122 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 4396 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3-flash | 40094 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | — | — | 0.00% | — | 1 |
| google/gemma-4-31b-it | — | 43 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k3 | — | — | 0.00% | — | 2 |
NVIDIA NIM performance history · Full provider & model leaderboard.
Models served by NVIDIA NIM.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#21 | 1,048,576 | $2.11/1M | Not published | $10.55/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#110 | 262,144 | $2.11/1M | Not published | $10.55/1M |
meta-llama/llama-3.2-11b-vision-instruct@cf/meta/llama-3.2-11b-vision-instruct |
— | 128,000 | $2.11/1M | Not published | $10.55/1M |
meta-llama/llama-3.2-90b-vision-instructmeta/llama-3.2-90b-vision-instruct |
— | 0 | $2.11/1M | Not published | $10.55/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#20 | 1,048,576 | $2.11/1M | Not published | $10.55/1M |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
— | 0 | $2.11/1M | Not published | $10.55/1M |
nvidia/nemotron-3-super-120b-a12bNVIDIA: Nemotron 3 Super |
— | 262,144 | $2.11/1M | Not published | $10.55/1M |
nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra |
— | 262,144 | $2.11/1M | Not published | $10.55/1M |
nvidia/nemotron-3.5-lightning-30b-a3bnvidia/Nemotron-3.5-Lightning-30B-A3B |
— | 262,144 | $2.11/1M | Not published | $10.55/1M |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 94#140 | 131,072 | $2.11/1M | Not published | $10.55/1M |
poolside/laguna-xs-2.1poolside/laguna-xs-2.1 |
— | 0 | $2.11/1M | Not published | $10.55/1M |
stepfun-ai/step-5-previewstepfun-ai/Step-5-Preview |
— | 1,048,576 | $2.11/1M | Not published | $10.55/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 125#24 | 1,048,576 | $2.11/1M | Not published | $10.55/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 120#42 | 1,048,576 | $2.11/1M | Not published | $10.55/1M |
Questions
Does NVIDIA NIM have zero data retention?
TrustedRouter does not currently mark NVIDIA NIM as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is NVIDIA NIM end-to-end encrypted?
TrustedRouter does not currently mark NVIDIA NIM as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which NVIDIA NIM models are available through TrustedRouter?
This page currently lists 14 public NVIDIA NIM models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.