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 | 4B |
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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $4.00 | — |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $20.00 | — |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.20 | — |
| $1,800Moonshot AI list price | — | |
| These models have no shared benchmark scores. | ||
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 96.2% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 46.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 55.1% |
| Overview | ||
| Company | Moonshot AI | NVIDIA |
| Release date | Oct 23 2026 | May 20 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K3.1 Pro HighspeedvsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Kimi K3.1 Pro HighspeedvsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGPT-6.2 AstraKimi K3.1 Pro HighspeedvsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsGemini 4 NeonKimi K3.1 Pro HighspeedvsMuse EmberLlama Nemotron Nano 4B v1.1vsMuse EmberKimi K3.1 Pro HighspeedvsGrok 4.7Llama Nemotron Nano 4B v1.1vsGrok 4.7Kimi K3.1 Pro HighspeedvsDeepSeek-V4.1-Flash-1017Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K3.1 Pro Highspeed and Llama Nemotron Nano 4B v1.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Kimi K3.1 Pro Highspeed has a verified first-party price for an available API: $4.00 per million input tokens and $20.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Llama Nemotron Nano 4B v1.1. Llama Nemotron Nano 4B v1.1 shipped 521 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 Llama Nemotron Nano 4B v1.1 has 4B. Context windows are 1M (Kimi K3.1 Pro Highspeed) vs 128k (Llama Nemotron Nano 4B v1.1). Kimi K3.1 Pro Highspeed is closed, while Llama Nemotron Nano 4B v1.1 is open weight.
Direct benchmark comparisons are unavailable — Kimi K3.1 Pro Highspeed and Llama Nemotron Nano 4B v1.1 don't publish scores on any of the same benchmarks.