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. | 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. | 256k | 200k |
| 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. | $0.95 | $1.10 |
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. | $4.00 | $4.40 |
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. | $0.19 | $0.275 |
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. | $0.6712Inceptron | $1.10OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $3.00StreamLake | $4.40OpenAI |
| $293StreamLake | $440OpenAI 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. | — | 8% |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 31% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 74% | — |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jun 12 2026 | Apr 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2.7 CodevsClaude Haiku 5.5o4-minivsClaude Haiku 5.5Kimi K2.7 CodevsGemini 4 Argono4-minivsGemini 4 ArgonKimi K2.7 CodevsMuse Spark Openo4-minivsMuse Spark OpenKimi K2.7 CodevsGrok 4.7o4-minivsGrok 4.7Kimi K2.7 CodevsDeepSeek-V4.1-Flash-1017o4-minivsDeepSeek-V4.1-Flash-1017Kimi K2.7 CodevsMistral Large 4o4-minivsMistral Large 4Frequently asked questions
Kimi K2.7 Code and o4-mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2.7 Code is cheaper on both input and output: $0.95 vs $1.10 per million input tokens, and $4.00 vs $4.40 per million output tokens. o4-mini shipped 422 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2.7 Code) vs 200k (o4-mini). Kimi K2.7 Code is open weight, while o4-mini is closed.
Direct benchmark comparisons are unavailable — Kimi K2.7 Code and o4-mini don't publish scores on any of the same benchmarks.