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. | 2.8T | 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. | 1M | 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. | — | $0.05Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.20Novita |
| — | $20.00Novita · fp4 | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 28% |
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. | — | 68.3% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 10.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 73% |
| Overview | ||
| Company | Moonshot AI | NVIDIA |
| Release date | Oct 23 2026 | Dec 15 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K3.1 Pro HighspeedvsClaude Haiku 5.5Nemotron 3 NanovsClaude Haiku 5.5Kimi K3.1 Pro HighspeedvsGPT-6.1 SolNemotron 3 NanovsGPT-6.1 SolKimi K3.1 Pro HighspeedvsGemini 4 ArgonNemotron 3 NanovsGemini 4 ArgonKimi K3.1 Pro HighspeedvsMuse Spark OpenNemotron 3 NanovsMuse Spark OpenKimi K3.1 Pro HighspeedvsGrok 4.7Nemotron 3 NanovsGrok 4.7Kimi K3.1 Pro HighspeedvsDeepSeek-V4.1-Flash-1017Nemotron 3 NanovsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K3.1 Pro Highspeed and Nemotron 3 Nano don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Nemotron 3 Nano shipped 312 days before Kimi K3.1 Pro Highspeed, so benchmark comparisons should account for the intervening progress.
Kimi K3.1 Pro Highspeed has 2.8T parameters, while Nemotron 3 Nano has 30B. Context windows are 1M (Kimi K3.1 Pro Highspeed) vs 1M (Nemotron 3 Nano). Kimi K3.1 Pro Highspeed is closed, while Nemotron 3 Nano is open weight.
Direct benchmark comparisons are unavailable — Kimi K3.1 Pro Highspeed and Nemotron 3 Nano don't publish scores on any of the same benchmarks.