LLM Comparison
DeepSeek V3.1 Terminus vs Nemotron 3.5 Lightning 30B A3B
Side-by-side specs, pricing & capabilities
Add to comparison
2/6 models| Organization | ||
| OpenTools Score | 19 36.2 | |
| Family | DeepSeek | Nemotron |
| Status | Current | Current |
| Release Date | Sep 2025 | Aug 2026 |
| Context Window | 164K tokens | 1.0M tokens |
| Input Price | $0.21/M tokens | $0.10/M tokens |
| Output Price | $0.79/M tokens | $0.95/M tokens |
| Pricing Notes | Cache read: $0.1300/M tokens | NVIDIA build lists serverless NIM pricing at $0.10 input and $0.95 output per million tokens. Self-hosted weights are also available; infrastructure costs vary. |
| Capabilities | textcode | textreasoningcodingtool-usefunction-callinglong-contextagenticlocal-deploymentopen-weights |
| Training Cutoff | — | May 2026 post-training; September 2025 pre-training |
| Max Output | — | 33K tokens |
| API Identifier | deepseek/deepseek-v3.1-terminus | nvidia/nemotron-3.5-lightning-30b-a3b |
| Benchmarks | ||
| AIME 2025 | 53.7%artificial-analysis | — |
| Artificial Analysis Intelligence Index v4.3 | — | 13.6 indexartificial-analysis |
| Artificial Analysis Intelligence Index v4.3 | — | 14 indexhttps://artificialanalysis.ai/models/nemotron-3-5-lightning |
| GPQA Diamond | 75.1%artificial-analysis | 74.3%artificial-analysis |
| GPQA Diamond | 80.7%deepseek | — |
| HLE | 21.7%deepseek | — |
| MMLU-Pro | 85%deepseek | — |
| SciCode | — | 32.1%artificial-analysis |
| SWE-bench Verified | 68.4%deepseek | — |
| Terminal-Bench 2.1 | — | 24.3%artificial-analysis |
| View DeepSeek V3.1 Terminus | View Nemotron 3.5 Lightning 30B A3B | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3BCheapest | $0.10 | $0.48 | $0.58 | — |
| DeepSeek V3.1 Terminus | $0.21 | $0.40 | $0.61 | +5% |
Compare hosting configurations
Compare two exact setups, including different configurations of the same model. Hardware fit, measured speed and costs are separate decisions.
Add your cost assumptions (optional)
Use hours for the same scenario period. Cloud billing includes idle time; active hours alone do not set the bill. Local electricity uses whole-system attributable power, powered hours and your tariff. Missing inputs remain unknown.
Measured speed needs the same pinned workload protocol, tokenizer, context, batching and cache state.
| Configuration | Run complete DeepSeek V3.1 Terminus hybrid text on an AWS r7i.16xlarge CPU host | Host full native Nemotron 3.5 Lightning reasoning and tools on an owned H100 |
|---|---|---|
| Model | DeepSeek V3.1 Terminus | Nemotron 3.5 Lightning 30B A3B |
| Hardware | AWS r7i.16xlarge, 64 vCPU, 512 GiB RAM | Owned single NVIDIA H100 80 GB GPU host |
| Runtime | Exact DeepSeek V3.1 Terminus main DEEPSEEK2 CPU MLA and native hybrid prompting llama.cpp v0.7.0 source620d222; full MLA/MoE; native Terminus thinking Jinja · CPU | Native Lightning BF16 + embedded MTP1 reader-built vLLM GPU layer vLLM 0.27.1 commit 6e448d0; pinned official amd64 image plus SHA-pinned Transformers 5.8.1 replacement; CUDA 13.0.3 source defaults, reader preflight required · CUDA |
| Artifact | DeepSeek-V3.1-Terminus Q4_K_M, complete nine-file main-model composition · Named Terminus Q4_K_M mixed GGUF; native router correction bias requires F32 · Unsloth Q4_K_M mixed GGUF; separate exact named Terminus derivative, not native FP8 equivalence | Nemotron 3.5 Lightning 30B A3B full native BF16 including embedded MTP · Native BF16 complete publisher weights, including all experts and embedded MTP; no quantization · Unquantized BF16 publisher checkpoint; full experts and embedded MTP retained |
| Context / concurrency | 8,192 tokens / 1 | 8,192 tokens / 1 |
| Required memory | Unknown (unknown) | Unknown (unknown) |
| Evidence | Documented setup | Documented setup |
| Hardware fit | Hardware fit unknown No measured full CPU process peak for all quantized weights, MLA cache, scratch, loading, runtime and OS. Enter available memory per device or unified memory pool. Host RAM: 512 GiB is a planning allocation, not an observed minimum or fit. Free disk space: 600 GiB is planned free disk, not measured setup peak. | Hardware fit unknown No measured GPU/full-process peak for full native BF16/MTP1 / FP32 SSM at 8,192 context. Enter available memory per device or unified memory pool. Host RAM: 256 GiBhost allocation is a planning choice, not a measured minimum. Free disk space: 256 GiB disk allocation and 160 GiB free-space guard are author prescriptions; full image/runtime/model disk requirement is unmeasured. |
| One-time cost | Unknown setup: Initial provisioning/build time and labor cost are unknown. | Unknown hardware: Existing owned GPU/host purchase and incremental cost are unknown. setup: Reader provisioning, image build and labor time/cost are unknown. |
| Recurring scenario cost | Unknown compute: Enter billed hours; active hours alone do not determine the bill. storage: Enter storage in GB. egress: Data transfer price, allowances and traffic volume are unknown. administration: Maintenance labor rate and hours are unknown. One-time setup and recurring costs are separate. Unknown components are not treated as free. No monthly token output is inferred from peak throughput. | Unknown electricity: Actual wall power/rate/poweredhours unknown; no GPU TDP conversion. storage: Incremental local 256 GiB storage cost is unknown. egress: Actual transfer/allowance/traffic cost unknown. administration: Maintenance time/rate unknown. One-time setup and recurring costs are separate. Unknown components are not treated as free. No monthly token output is inferred from peak throughput. |
| Published measurements (unranked) | No compatible measurement available | No compatible measurement available |
Different currencies and incomplete costs are not ranked. Model quality benchmarks remain on the model pages; they do not establish quality or speed for every deployment.
DeepSeek
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.21/M input tokens.
NVIDIA
Nemotron 3.5 Lightning 30B A3B
Nemotron 3.5 Lightning is NVIDIA open-weight 30B-A3B reasoning model for fast, long-running agents. Its hybrid Mamba-2, mixture-of-experts, and attention architecture supports function calling, coding, tool use, long context, and efficient local or serverless deployment.
More Comparisons
Looking for more AI models?
Browse All LLMs