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 | 8B |
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 | — |
| 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 | — |
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 | — |
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 | — |
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 | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $3.00StreamLake | — |
| $293StreamLake | — | |
| These models have no shared benchmark scores. | ||
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 | NVIDIA |
| Release date | Jun 12 2026 | Oct 23 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K2.7 CodevsClaude Haiku 5.5Nemotron 3.5 Bolt E4B 4GBvsClaude Haiku 5.5Kimi K2.7 CodevsGPT-6.1 SolNemotron 3.5 Bolt E4B 4GBvsGPT-6.1 SolKimi K2.7 CodevsGemini 4 ArgonNemotron 3.5 Bolt E4B 4GBvsGemini 4 ArgonKimi K2.7 CodevsMuse Spark OpenNemotron 3.5 Bolt E4B 4GBvsMuse Spark OpenKimi K2.7 CodevsGrok 4.7Nemotron 3.5 Bolt E4B 4GBvsGrok 4.7Kimi K2.7 CodevsDeepSeek-V4.1-Flash-1017Nemotron 3.5 Bolt E4B 4GBvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2.7 Code and Nemotron 3.5 Bolt E4B 4GB don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Kimi K2.7 Code has a verified first-party API price: $0.95 per million input tokens and $4.00 per million output tokens. No pay-as-you-go API rate is tracked for Nemotron 3.5 Bolt E4B 4GB. Kimi K2.7 Code shipped 133 days before Nemotron 3.5 Bolt E4B 4GB, so benchmark comparisons should account for the intervening progress.
Kimi K2.7 Code has 1T parameters, while Nemotron 3.5 Bolt E4B 4GB has 8B.
Direct benchmark comparisons are unavailable — Kimi K2.7 Code and Nemotron 3.5 Bolt E4B 4GB don't publish scores on any of the same benchmarks.