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 | 2.8T |
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 | 1M |
| 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. | $0.50DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.15DeepInfra | — |
| $208DeepInfra · fp4 | — | |
| These models have no shared benchmark scores. | ||
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. | 8% | — |
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. | 57.6% | — |
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. | 73.3% | — |
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. | 17.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 81% | — |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | May 28 2025 | Oct 23 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528vsClaude Haiku 5.5Kimi K3.1 Pro HighspeedvsClaude Haiku 5.5DeepSeek R1-0528vsGPT-6.1 SolKimi K3.1 Pro HighspeedvsGPT-6.1 SolDeepSeek R1-0528vsGemini 4 ArgonKimi K3.1 Pro HighspeedvsGemini 4 ArgonDeepSeek R1-0528vsMuse Spark OpenKimi K3.1 Pro HighspeedvsMuse Spark OpenDeepSeek R1-0528vsGrok 4.7Kimi K3.1 Pro HighspeedvsGrok 4.7DeepSeek R1-0528vsMistral Large 4Kimi K3.1 Pro HighspeedvsMistral Large 4Frequently asked questions
DeepSeek R1-0528 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek R1-0528 shipped 513 days before Kimi K3.1 Pro Highspeed, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 has 671B parameters, while Kimi K3.1 Pro Highspeed has 2.8T. Context windows are 128k (DeepSeek R1-0528) vs 1M (Kimi K3.1 Pro Highspeed). DeepSeek R1-0528 is open weight, while Kimi K3.1 Pro Highspeed is closed.
Direct benchmark comparisons are unavailable — DeepSeek R1-0528 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks.