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. | 7B/13B/70B | — |
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. | 4k | 200k |
| 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. | — | $1.10OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $4.40OpenAI |
| — | $440OpenAI | |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Jul 18 2023 | Apr 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
LLaMA 2vsClaude Haiku 5.5o4-mini-highvsClaude Haiku 5.5LLaMA 2vsGemini 4 Argono4-mini-highvsGemini 4 ArgonLLaMA 2vsGrok 4.7o4-mini-highvsGrok 4.7LLaMA 2vsDeepSeek-V4.1-Flash-1017o4-mini-highvsDeepSeek-V4.1-Flash-1017LLaMA 2vsMistral Large 4o4-mini-highvsMistral Large 4LLaMA 2vsKimi K3o4-mini-highvsKimi K3Frequently asked questions
LLaMA 2 and o4-mini-high don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 2 shipped 638 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.
Context windows are 4k (LLaMA 2) vs 200k (o4-mini-high). LLaMA 2 is open weight, while o4-mini-high is closed.
Direct benchmark comparisons are unavailable — LLaMA 2 and o4-mini-high don't publish scores on any of the same benchmarks.