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—
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.
128k128k
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.
$0.25DeepInfra—
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input.
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
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.
74.8%74.8%
Overview
CompanyDeepSeekSpaceXSI
Release dateAug 21 2025Feb 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.1 and Grok 3 mini are evenly matched across the 1 benchmark they both report (LiveCodeBench). Grok 3 mini shipped 185 days before DeepSeek V3.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3.1) vs 128k (Grok 3 mini). DeepSeek V3.1 is open weight, while Grok 3 mini is closed.

On LiveCodeBench, both models score 74.8%.