
Nemotron 3 Super
Model ranking
Not matched to the current verified ranking snapshot.
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
Cloudflare Workers AInemotron-3-120b-a12b | Input$0.5 Output$1.5 USD / 1M tokensUpdated 2026-10-20 | @cf/nvidia/nemotron-3-120b-a12b | Catalog-listedConditionsPublic catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine. | Context tokens 256000 | Official source ↗2026-10-20 |
Nemotron 3 Super is NVIDIA’s hybrid mixture-of-experts reasoning model, associated with the 120B total and 12B active configuration. It is a different checkpoint from Nemotron 3 Ultra.
Nemotron 3 Super: suitable applications
Consider multi-agent text workflows and tool-assisted reasoning where the Super checkpoint is an appropriate deployment size.
Capabilities and technical details
The architecture combines selectively activated experts with hybrid sequence-modeling components. NVIDIA publishes model documentation and a dedicated weight license.
Nemotron 3 Super accepts text and returns text. The recorded input reference is 262,144 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are NVIDIA Nemotron Open Model License; the linked source explains their scope.
Nemotron 3 Super limitations and selection
The Cloudflare endpoint has its own context limit. Reasoning modes use documented template options and should not be assumed to follow every generic API reasoning field.
Check the provider’s reasoning configuration and compare completed task quality with Ultra or a smaller model using the same tools and context.
Nemotron 3 Super API pricing
Nemotron 3 Super pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.
Review the Cloudflare Nemotron 3 Super endpoint reference and the NVIDIA model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.
Specifications
- Catalog model ID
- nvidia/nemotron-3-super-120b-a12b
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- textCloudflare Workers AI endpoint; route-specific capabilities ↗
- Output modalities
- textCloudflare Workers AI endpoint; route-specific capabilities ↗
- Context / input token limit
- 262,144Developer model card / documentation ↗
- Maximum output tokens
- Not verified in cited sources
- Tool calling
- SupportedCloudflare Workers AI endpoint; route-specific capabilities ↗
- Structured output
- Not verified in cited sources
- API parameters (source-specific)
- Not verified in cited sources
- Weight access
- Open weightsDeveloper model card / documentation ↗
- Weight license / access terms
- NVIDIA Nemotron Open Model LicenseDeveloper weight license / hosted access terms ↗
- Total parameters (billions)
- 120Developer model card / documentation ↗
- Active parameters (billions)
- 12Developer model card / documentation ↗
- Parameter-count details
- Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- Not verified in cited sources
- Notes
- Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the publisher configuration; provider caps can be lower. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.
