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. | — | 72B |
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 · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.25 | — |
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. | $0.125 | — |
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. | $0.625Google AI Studio | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $5.00Google AI Studio | — |
| $750Google list price | — | |
| Benchmarks | ||
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. | 59.6% | 60.4% |
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. | 20% | — |
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. | 18.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | Moonshot AI | |
| Release date | Mar 25 2025 | Jun 17 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 ProvsClaude Haiku 5.5Kimi-DevvsClaude Haiku 5.5Gemini 2.5 ProvsGPT-6.1 SolKimi-DevvsGPT-6.1 SolGemini 2.5 ProvsMuse Spark OpenKimi-DevvsMuse Spark OpenGemini 2.5 ProvsGrok 4.7Kimi-DevvsGrok 4.7Gemini 2.5 ProvsDeepSeek-V4.1-Flash-1017Kimi-DevvsDeepSeek-V4.1-Flash-1017Gemini 2.5 ProvsMistral Large 4Kimi-DevvsMistral Large 4Frequently asked questions
Kimi-Dev leads Gemini 2.5 Pro on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only Gemini 2.5 Pro has a verified first-party API price: $1.25 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Kimi-Dev. Gemini 2.5 Pro shipped 84 days before Kimi-Dev, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.5 Pro) vs 128k (Kimi-Dev). Gemini 2.5 Pro is closed, while Kimi-Dev is open weight.
On SWE-Bench Verified, Kimi-Dev leads at 60.4% vs Gemini 2.5 Pro at 59.6%.