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. | — | $2.50 |
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. | — | $10.00 |
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. | — | $1.25 |
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. | $0.60Google | $2.50Azure |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.50Google | $10.00Azure |
| $245Novita · bf16 | $1,000OpenAI list price | |
| 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. | — | 12% |
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. | 71.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 49.9% |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Nov 6 2025 | May 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2 ThinkingvsClaude Haiku 5.5GPT-4ovsClaude Haiku 5.5Kimi K2 ThinkingvsGemini 4 ArgonGPT-4ovsGemini 4 ArgonKimi K2 ThinkingvsMuse WonderGPT-4ovsMuse WonderKimi K2 ThinkingvsGrok 4.7GPT-4ovsGrok 4.7Kimi K2 ThinkingvsDeepSeek-V4.1-FlashGPT-4ovsDeepSeek-V4.1-FlashKimi K2 ThinkingvsMistral Large 4GPT-4ovsMistral Large 4Frequently asked questions
Kimi K2 Thinking and GPT-4o don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only GPT-4o has a verified first-party API price: $2.50 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2 Thinking. GPT-4o shipped 542 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2 Thinking) vs 128k (GPT-4o). Kimi K2 Thinking is open weight, while GPT-4o is closed.
Direct benchmark comparisons are unavailable — Kimi K2 Thinking and GPT-4o don't publish scores on any of the same benchmarks.