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. | 128k | 400k |
| 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. | $0.2088GMICloud | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.3096GMICloud | — |
| $57.24GMICloud · fp8 | — | |
| Benchmarks | ||
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. | 13% | 32% |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Dec 1 2025 | Nov 13 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2vsClaude Fable 5.2GPT-5.1-CodexvsClaude Fable 5.2DeepSeek-V3.2vsGemini 4 CarbonGPT-5.1-CodexvsGemini 4 CarbonDeepSeek-V3.2vsMuse EmberGPT-5.1-CodexvsMuse EmberDeepSeek-V3.2vsGrok 4.7GPT-5.1-CodexvsGrok 4.7DeepSeek-V3.2vsMistral Large 4GPT-5.1-CodexvsMistral Large 4DeepSeek-V3.2vsKimi K3.1 ProGPT-5.1-CodexvsKimi K3.1 ProFrequently asked questions
GPT-5.1-Codex leads DeepSeek-V3.2 on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5.1-Codex shipped 18 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek-V3.2) vs 400k (GPT-5.1-Codex). DeepSeek-V3.2 is open weight, while GPT-5.1-Codex is closed.
On BullshitBench v2, GPT-5.1-Codex leads at 32% vs DeepSeek-V3.2 at 13%.