Gemini 3.7 Flash vs Kimi K3
Gemini 3.7 Flash vs Kimi K3: compare language model API prices, specs and cited scores side by side. Every figure links to its source.
| Gemini 3.7 Flash Google | Kimi K3 Moonshot AI | |
|---|---|---|
| Overview | ||
| Released | Aug 13, 2026 | Jul 2026 |
| Open weights | — | |
| Knowledge cutoff | Mar 2026 | — |
| Specs | ||
| Context | 1.05M | 1.05M |
| Max input | 1M | Not stated |
| Max output | 65.54K | 1.05M |
| Input modalities | Text, Image, Video, Audio, PDF | Text, Image, Video |
| Output modalities | Text | Text |
| Reasoning | ||
| Reasoning efforts | low, medium, high | low, high, max |
| Reasoning can be off | — | |
| Tool use | ||
| Structured output | ||
| Built-in tools | Code execution | Not stated |
| Pricing · per 1M tokens | ||
| Input price | $0.75 | $3.00 |
| Output price | $3.75 | $15.00 |
| Cache read price | $0.075 | $0.30 |
| Blended price (3 input : 1 output) | $1.50 | $6.00 |
| Cited scores | ||
| Epoch Capabilities Index | 157.3 | 157.5 |
| LMArena Text | 1,488 high effort | 1,488 max effort |
| LMArena Text · Coding | 1,518 high effort | 1,541 max effort |
| LMArena Vision | 1,315 high effort | — |
| LMArena Text · Chinese | 1,546 high effort | 1,540 max effort |
| Epoch AI · GPQA Diamond | 94.8% high effort | 93.1% max effort |
| Epoch AI · FrontierMath Tiers 1–3 | 71.6% high effort | 72.2% max effort |
Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.
Cited scores
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · Epoch AI Benchmarking Hub data · CC BY 4.0 · as of Oct 7, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · LMArena leaderboard dataset (Hugging Face) · CC BY 4.0 · as of Oct 2, 2026