Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 671B | 30B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.27SiliconFlow | $0.025Darkbloom |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | $0.12Darkbloom |
| $104SiliconFlow · fp8 | $11.00Darkbloom · int4 | |
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 68.4% | 51.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.7% | 75.4% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 57.8% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 74.9% | — |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Sep 22 2025 | Aug 11 2026 |
| Access | Open Weight | Open Source |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Haiku 5.5Nemotron 3.5 LightningvsClaude Haiku 5.5DeepSeek V3.1 TerminusvsGPT-6.1 SolNemotron 3.5 LightningvsGPT-6.1 SolDeepSeek V3.1 TerminusvsGemini 4 ArgonNemotron 3.5 LightningvsGemini 4 ArgonDeepSeek V3.1 TerminusvsMuse Spark OpenNemotron 3.5 LightningvsMuse Spark OpenDeepSeek V3.1 TerminusvsGrok 4.7Nemotron 3.5 LightningvsGrok 4.7DeepSeek V3.1 TerminusvsMistral Large 4Nemotron 3.5 LightningvsMistral Large 4Frequently asked questions
DeepSeek V3.1 Terminus leads Nemotron 3.5 Lightning on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek V3.1 Terminus shipped 323 days before Nemotron 3.5 Lightning, so benchmark comparisons should account for the intervening progress.
DeepSeek V3.1 Terminus has 671B parameters, while Nemotron 3.5 Lightning has 30B. Context windows are 128k (DeepSeek V3.1 Terminus) vs 1M (Nemotron 3.5 Lightning). DeepSeek V3.1 Terminus is open weight, while Nemotron 3.5 Lightning is open source.
On SWE-Bench Verified, DeepSeek V3.1 Terminus leads at 68.4% vs Nemotron 3.5 Lightning at 51.6%. On GPQA Diamond, DeepSeek V3.1 Terminus leads at 80.7% vs Nemotron 3.5 Lightning at 75.4%.