Model comparison
DeepSeek V4 Flash and Kimi K3 compared on price, context window, capabilities and published benchmarks. Data comes from the OpenModels registry.
| Specification | DeepSeek V4 Flash | Kimi K3 |
|---|---|---|
| Developer | Deepseek | Kimi |
| Released | Apr 24, 2026 | Jul 15, 2026 |
| Context window | 1M tokens | 1M tokens |
| Input price / 1M | $0.07via Deep Infra | $3.00via Moonshot AI |
| Output price / 1M | $0.14via Deep Infra | $15.00via Moonshot AI |
| Providers | 3 | 2 |
| License | mit | other |
| Input modalities | code, text | code, image, text, video |
| Capabilities | chat, completion, function-calling, code-generation | chat, completion, function-calling, vision, code-generation, reasoning |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
Only benchmarks with a published score for at least one of the two models are shown. Published scores with their sources. Vendor-reported results use the vendor's own evaluation settings and are not directly comparable across vendors.
| Benchmark | DeepSeek V4 Flash | Kimi K3 |
|---|---|---|
| Artificial Analysis Intelligence Index | — | 44Artificial Analysis · Independent |