Model comparison
Kimi K3 vs DeepSeek-V4-Flash
- Input
- $3.00
- Output
- $15.00
- Context
- 1M
- Released
- 2026-07-16
- Input
- $0.22 off-peak · $0.44 peak
- Output
- $0.66 off-peak · $1.32 peak
- Context
- 1M
- Released
- 2026-04-24
Kimi K3 scores higher on 2 of the 2 benchmarks both models report; DeepSeek-V4-Flash is cheaper on input tokens ($0.2 vs $3 per 1M, 13.6×).
Specs and pricing side by side
| Spec | Kimi K3 | DeepSeek-V4-Flash |
|---|---|---|
| Maker | Moonshot AI (Kimi) | DeepSeek |
| Released | 2026-07-16 | 2026-04-24 |
| Context window | 1M | 1Msame |
| Max output | not published | 384K |
| Input price | $3.00 | $0.22 off-peak · $0.44 peak |
| Output price | $15.00 | $0.66 off-peak · $1.32 peak |
| Parameters | 2.8T total · ~16 of 896 experts active per token | 284B total · 13B active |
| License | Kimi K3 License (custom, weights published on Hugging Face 2026-07-26) | MIT |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision, Video | Text |
Not published by either maker: knowledge cutoff.
Benchmarks both models report
| Benchmark | Kimi K3 | DeepSeek-V4-Flash |
|---|---|---|
| Terminal Bench 2.1 | 88.3% | 82.7% |
| GPQA-Diamond | 93.5% | 88.1% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Kimi K3 if…
- You care about Terminal Bench 2.1, GPQA-Diamond (it scores higher on 2 shared benchmarks).
- You need Vision / Video input, which DeepSeek-V4-Flash lacks.
- Your use case is: reach for it for long-horizon agentic coding and browser/tool workflows that need a very long context.
Pick DeepSeek-V4-Flash if…
- Cost matters: input tokens cost 13.6× less ($0.2 vs $3 per 1M).
- Your use case is: high-volume agentic and coding workflows where cost and latency matter more than absolute peak quality.
FAQ
Which is better, Kimi K3 or DeepSeek-V4-Flash?
Kimi K3 scores higher on 2 of the 2 benchmarks both models report; DeepSeek-V4-Flash is cheaper on input tokens ($0.2 vs $3 per 1M, 13.6×). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is DeepSeek-V4-Flash?
Kimi K3: $3.00 input, $15.00 output. DeepSeek-V4-Flash: $0.22 off-peak · $0.44 peak input, $0.66 off-peak · $1.32 peak output (list API prices as published by each maker).
What are the context windows of Kimi K3 and DeepSeek-V4-Flash?
Kimi K3 offers 1M; DeepSeek-V4-Flash offers 1M with up to 384K output.
Is Kimi K3 newer than DeepSeek-V4-Flash?
Kimi K3 was released 2026-07-16; DeepSeek-V4-Flash was released 2026-04-24.