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/67B | 9B/27B |
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 | 8k |
| 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. | — | $0.65NextBit |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.65NextBit |
| — | $163NextBit · int4 | |
| Overview | ||
| Company | DeepSeek | |
| Release date | Nov 29 2023 | Jun 27 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Frequently asked questions
DeepSeek-LLM and Gemma 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-LLM shipped 211 days before Gemma 2, so benchmark comparisons should account for the intervening progress.
DeepSeek-LLM has 7B/67B parameters, while Gemma 2 has 9B/27B. Context windows are 4k (DeepSeek-LLM) vs 8k (Gemma 2).
Direct benchmark comparisons are unavailable — DeepSeek-LLM and Gemma 2 don't publish scores on any of the same benchmarks.