LLM Reference

GPT-4 Turbo (older v1106) vs Nemotron 3 Super-120B-A12B

GPT-4 Turbo (older v1106) (2023) and Nemotron 3 Super-120B-A12B (2026) are compact production models from OpenAI and NVIDIA AI. GPT-4 Turbo (older v1106) ships a 128k-token context window, while Nemotron 3 Super-120B-A12B ships a 1.05m-token context window. On pricing, Nemotron 3 Super-120B-A12B costs $0.09/1M input tokens versus $10/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Nemotron 3 Super-120B-A12B is ~11011% cheaper at $0.09/1M; pay for GPT-4 Turbo (older v1106) only for provider fit.

Decision scorecard

Local evidence first
SignalGPT-4 Turbo (older v1106)Nemotron 3 Super-120B-A12B
Best forgeneral production evaluationlong-context analysis and provider-routed production
Decision fitRAG, Long context, and ClassificationCoding, RAG, and Agents
Context window128k1.05m
Cheapest output$30/1M tokens$0.45/1M tokens
Provider routes1 tracked6 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose GPT-4 Turbo (older v1106) when...
  • Local decision data tags GPT-4 Turbo (older v1106) for RAG, Long context, and Classification.
Choose Nemotron 3 Super-120B-A12B when...
  • Nemotron 3 Super-120B-A12B has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Nemotron 3 Super-120B-A12B has the lower cheapest tracked output price at $0.45/1M tokens.
  • Nemotron 3 Super-120B-A12B has broader tracked provider coverage for fallback and procurement flexibility.
  • Local decision data tags Nemotron 3 Super-120B-A12B for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Nemotron 3 Super-120B-A12B

GPT-4 Turbo (older v1106)

$15,500

Cheapest tracked route/tier: OpenRouter

Nemotron 3 Super-120B-A12B

$185

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $15,316. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

GPT-4 Turbo (older v1106) -> Nemotron 3 Super-120B-A12B
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Nemotron 3 Super-120B-A12B is $29.55/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
Nemotron 3 Super-120B-A12B -> GPT-4 Turbo (older v1106)
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • GPT-4 Turbo (older v1106) is $29.55/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.

Specs

Specification
Released2023-11-062026-03-11
Context window128k1.05m
Parameters120B
ArchitectureDecoder OnlyDecoder Only
LicenseProprietaryNVIDIA Open Model
OpennessProprietaryOpen weights
Commercial useCommercial use: conditionalCommercial use: permitted
Knowledge cutoff2023-04-

Pricing and availability

Pricing attributeGPT-4 Turbo (older v1106)Nemotron 3 Super-120B-A12B
Input price$10/1M tokens$0.09/1M tokens
Output price$30/1M tokens$0.45/1M tokens
Providers

Capabilities

CapabilityGPT-4 Turbo (older v1106)Nemotron 3 Super-120B-A12B
VisionNoNo
MultimodalNoNo
ReasoningNoNo
Function callingNoNo
Tool useNoNo
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Deep dive

The capability footprint is close: both models cover structured outputs. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.

For cost, GPT-4 Turbo (older v1106) lists $10/1M input and $30/1M output tokens on the cheapest tracked provider, while Nemotron 3 Super-120B-A12B lists $0.09/1M input and $0.45/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Nemotron 3 Super-120B-A12B lower by about $15.80 per million blended tokens. Availability is 1 providers versus 6, so concentration risk also matters.

Choose GPT-4 Turbo (older v1106) when provider fit are central to the workload. Choose Nemotron 3 Super-120B-A12B when long-context analysis, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency.

FAQ

Which has a larger context window, GPT-4 Turbo (older v1106) or Nemotron 3 Super-120B-A12B?

Nemotron 3 Super-120B-A12B supports 1.05m tokens, while GPT-4 Turbo (older v1106) supports 128k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, GPT-4 Turbo (older v1106) or Nemotron 3 Super-120B-A12B?

Nemotron 3 Super-120B-A12B is cheaper on tracked token pricing. GPT-4 Turbo (older v1106) costs $10/1M input and $30/1M output tokens. Nemotron 3 Super-120B-A12B costs $0.09/1M input and $0.45/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is GPT-4 Turbo (older v1106) or Nemotron 3 Super-120B-A12B open source?

GPT-4 Turbo (older v1106) is listed under Proprietary. Nemotron 3 Super-120B-A12B is listed under NVIDIA Open Model. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for structured outputs, GPT-4 Turbo (older v1106) or Nemotron 3 Super-120B-A12B?

Both GPT-4 Turbo (older v1106) and Nemotron 3 Super-120B-A12B expose structured outputs. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run GPT-4 Turbo (older v1106) and Nemotron 3 Super-120B-A12B?

GPT-4 Turbo (older v1106) is available on OpenRouter. Nemotron 3 Super-120B-A12B is available on Cloudflare Workers AI, DeepInfra, NVIDIA NIM, OpenRouter, and Fireworks AI. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

When should I pick GPT-4 Turbo (older v1106) over Nemotron 3 Super-120B-A12B?

Nemotron 3 Super-120B-A12B is ~11011% cheaper at $0.09/1M; pay for GPT-4 Turbo (older v1106) only for provider fit. If your workload also depends on provider fit, start with GPT-4 Turbo (older v1106); if it depends on long-context analysis, run the same evaluation with Nemotron 3 Super-120B-A12B.

Continue comparing

Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.