Model comparison
DeepSeek V4.1 Flash vs Hunyuan Hy4 preview
- Input
- $0.15
- Output
- $0.60
- Context
- 1M tokens
- Released
- 2026-09-10
- Input
- $0.834
- Output
- $2.501
- Context
- 1M
- Released
- 2026-08-28
Hunyuan Hy4 preview scores higher on 2 of the 3 benchmarks both models report (the other leads on 1); DeepSeek V4.1 Flash is cheaper on input tokens ($0.2 vs $0.8 per 1M, 5.6×).
Specs and pricing side by side
| Spec | DeepSeek V4.1 Flash | Hunyuan Hy4 preview |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Released | 2026-09-10 | 2026-08-28 |
| Context window | 1M tokens | 1M |
| Input price | $0.15 | $0.834 |
| Output price | $0.60 | $2.501 |
| Parameters | 552B backbone + 196B Engram · 8B active on prefill, 16B on decode | 770B total · 49B active |
| License | MIT | Apache-2.0 |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision | Text |
Not published by either maker: max output, knowledge cutoff.
Benchmarks both models report
| Benchmark | DeepSeek V4.1 Flash | Hunyuan Hy4 preview |
|---|---|---|
| Terminal-Bench 2.1 | 90.6% | 85.4% |
| GPQA Diamond | 90.9% | 92.3% |
| HLE | 36.8% | 43.4% |
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 DeepSeek V4.1 Flash if…
- You care about Terminal-Bench 2.1 (it scores higher on 1 shared benchmark).
- Cost matters: input tokens cost 5.6× less ($0.2 vs $0.8 per 1M).
- You need Vision input, which Hunyuan Hy4 preview lacks.
- Your use case is: agentic coding and terminal work where the published Terminal-Bench and DeepSWE scores matter.
Pick Hunyuan Hy4 preview if…
- You care about GPQA Diamond, HLE (it scores higher on 2 shared benchmarks).
- Your use case is: self-hosted agentic coding and long-horizon software engineering via vLLM or SGLang.
FAQ
Which is better, DeepSeek V4.1 Flash or Hunyuan Hy4 preview?
Hunyuan Hy4 preview scores higher on 2 of the 3 benchmarks both models report (the other leads on 1); DeepSeek V4.1 Flash is cheaper on input tokens ($0.2 vs $0.8 per 1M, 5.6×). 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 V4.1 Flash?
DeepSeek V4.1 Flash: $0.15 input, $0.60 output. Hunyuan Hy4 preview: $0.834 input, $2.501 output (list API prices as published by each maker).
What are the context windows of DeepSeek V4.1 Flash and Hunyuan Hy4 preview?
DeepSeek V4.1 Flash offers 1M tokens; Hunyuan Hy4 preview offers 1M.
Is DeepSeek V4.1 Flash newer than Hunyuan Hy4 preview?
DeepSeek V4.1 Flash was released 2026-09-10; Hunyuan Hy4 preview was released 2026-08-28.
Go deeper
- DeepSeek V4.1 Flash: full specs, pricing and benchmarks
- Hunyuan Hy4 preview: full specs, pricing and benchmarks
- hunyuan hy4 preview vs hunyuan hy3
- deepseek v4 1 flash vs deepseek v4 flash vision exp
- hunyuan hy4 preview vs laguna s 2 1
- hunyuan hy4 preview vs glm 5 2
- deepseek v4 1 flash vs nemotron 3 5 lightning
- deepseek v4 1 flash vs kimi k3
- All model comparisons