Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 1T | — |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 256k | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.15 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.60 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.075 |
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. | $0.60Novita | $0.15Azure |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.50Novita | $0.60Azure |
| $245Novita · fp8 | $60.00OpenAI list price | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.1% | 40.2% |
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. | — | 2% |
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% | — |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Sep 5 2025 | Jul 18 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2 (0905)vsClaude Haiku 5.5GPT-4o minivsClaude Haiku 5.5Kimi K2 (0905)vsGemini 4 ArgonGPT-4o minivsGemini 4 ArgonKimi K2 (0905)vsMuse WonderGPT-4o minivsMuse WonderKimi K2 (0905)vsGrok 4.7GPT-4o minivsGrok 4.7Kimi K2 (0905)vsDeepSeek-V4.1-FlashGPT-4o minivsDeepSeek-V4.1-FlashKimi K2 (0905)vsMistral Large 4GPT-4o minivsMistral Large 4Frequently asked questions
Kimi K2 (0905) leads GPT-4o mini on 1 of the 1 benchmark they both report (GPQA Diamond). Only GPT-4o mini has a verified first-party API price: $0.15 per million input tokens and $0.60 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2 (0905). GPT-4o mini shipped 414 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2 (0905)) vs 128k (GPT-4o mini). Kimi K2 (0905) is open weight, while GPT-4o mini is closed.
On GPQA Diamond, Kimi K2 (0905) leads at 75.1% vs GPT-4o mini at 40.2%.