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. | 1.6T | 1T |
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 | ||
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. | $0.90Relace | $0.57Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.50Relace | $2.30Novita |
| $255Relace · fp4 | $229Novita · 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. | 14% | 10% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | 75.1% |
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | 75.1% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 65.8% |
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. | 93.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 4.7% |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | Apr 24 2026 | Jul 11 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-ProvsClaude Haiku 5.5Kimi K2vsClaude Haiku 5.5DeepSeek-V4-ProvsGPT-6.1 SolKimi K2vsGPT-6.1 SolDeepSeek-V4-ProvsGemini 4 ArgonKimi K2vsGemini 4 ArgonDeepSeek-V4-ProvsMuse Spark OpenKimi K2vsMuse Spark OpenDeepSeek-V4-ProvsGrok 4.7Kimi K2vsGrok 4.7DeepSeek-V4-ProvsMistral Large 4Kimi K2vsMistral Large 4Frequently asked questions
DeepSeek-V4-Pro leads Kimi K2 on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Kimi K2 shipped 287 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro has 1.6T parameters, while Kimi K2 has 1T. Context windows are 1M (DeepSeek-V4-Pro) vs 128k (Kimi K2).
On BullshitBench v2, DeepSeek-V4-Pro leads at 14% vs Kimi K2 at 10%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Kimi K2 at 75.1%.