Free to start

NVIDIA: Nemotron 3 Ultra

Try Nemotron 3 Ultra on us. Starter credit covers your first requests, then one key reaches all 5 provider routes with automatic failover.

`nvidia/nemotron-3-ultra-550b-a55b`

open weights US providers EU-focused NVIDIA

All models

Publisher	NVIDIA
AI IQ	No AI IQ profile matched yet.
Context	262,144 tokens
Providers	Baseten ZDR Fireworks AI Weights & Biases DeepInfra NVIDIA NIM
Credits routes	5 provider routes
Modes	chat open weights US providers EU-focused
Billing	Credits

Current route evidence

Live leaderboard

$0.5275/1MLowest Credits input price

$2.26825/1MLowest Credits output price

904 msFastest measured p50 TTFT via baseten

not enough dataHighest measured throughput

Recent provider-route uptime spans 100.00% across 5 routes and 5 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

All route prices All providers

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture. Company country is separate from inference location. Weight formats are source-backed declarations, not per-request proofs.

Provider	Input	Cached input	Output	Weight format	Provider policy	Company / inference location	Measured speed
Weights & Biaseswandb	$0.5275/1M	$0.1055/1M	$2.26825/1M	Unknown	no verified privacy claim Retention details W&B Serverless Inference runs on CoreWeave infrastructure. W&B does not publish a zero-retention, confidential-compute, or end-to-end-encryption commitment for this service, so these routes use the Standard privacy tier. TrustedRouter does not enable W&B Weave tracing for provider calls. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T03:15:35.372Z
DeepInfradeepinfra	$0.5275/1M	$0.1055/1M	$2.321/1M	Unknown	no verified privacy claim Retention details Tracked as no-store, not strict ZDR. DeepInfra documents memory-only handling and no training for ordinary inference, but reserves the right to log a small portion of requests for debugging or security. Google- and Anthropic-backed routes also inherit those vendors' terms. Provider policy source	Operator country: US Location details Headquarters / registered office: Palo Alto, California, United States. Company location source (reviewed 2026-09-27). Inference: US infrastructure plus announced Canadian capacity; model-specific residency unconfirmed. DeepInfra describes US infrastructure and announced its first international data center in Toronto on July 8, 2026. This is a provider footprint, not an exhaustive or model-specific placement list. DeepSeek V4.1 Flash placement has not been confirmed; do not declare this route US-only. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. DeepInfra infrastructure statement DeepInfra Toronto announcement Full location evidence	TTFT: insufficient data Speed: insufficient data
Basetenbaseten	$0.633/1M	$0.1266/1M	$2.532/1M	Unknown	ZDR Retention details Baseten states that it does not store synchronous Model API inputs or outputs by default. TrustedRouter uses the synchronous Model API path; Baseten documents separate temporary input storage for async inference. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: 0.90 s Speed: insufficient data Last sample: 2026-10-31T07:27:40.000Z
Fireworks AIfireworks	$0.633/1M	$0.1266/1M	$2.532/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. Fireworks publishes security, privacy, and zero-retention documentation; enable a contracted ZDR posture before marking this provider as ZDR. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T05:40:42.000Z
NVIDIA NIMnvidia-nim	$2.11/1M	Not published	$10.55/1M	Unknown	no verified privacy claim Retention details 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. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T07:57:49.000Z

Speed is the median (p50) from TR's recent measured requests for this exact model and provider, refreshed from the cached leaderboard. At least two timing samples are required; workload and network conditions affect results. Performance details

Compare NVIDIA: Nemotron 3 Ultra

All comparisons

NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 5.338 combined provider routes
NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 5.237 combined provider routes
NVIDIA: Nemotron 3 Ultra vs Z.ai: GLM 5.3 Flash37 combined provider routes
MoonshotAI: Kimi K3 vs NVIDIA: Nemotron 3 Ultra33 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs NVIDIA: Nemotron 3 Ultra31 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs NVIDIA: Nemotron 3 Ultra29 combined provider routes

Questions

What model ID should I use for NVIDIA: Nemotron 3 Ultra?

Use nvidia/nemotron-3-ultra-550b-a55b as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve NVIDIA: Nemotron 3 Ultra?

TrustedRouter currently lists Baseten, Fireworks AI, Weights & Biases, DeepInfra, and NVIDIA NIM for NVIDIA: Nemotron 3 Ultra. Provider availability and routing eligibility can change as catalog and health data update.

How much does NVIDIA: Nemotron 3 Ultra cost through TrustedRouter?

The current lowest Credits input price is $0.5275/1M and the lowest Credits output price is $2.26825/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for NVIDIA: Nemotron 3 Ultra?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.