token.app › Compare › DeepSeek V3.1 vs DeepSeek V4 Flash Latest
DeepSeek V3.1 vs DeepSeek V4 Flash Latest
DeepSeek V4 Flash Latest is 3.8× cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash Latest accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| DeepSeek V3.1 | DeepSeek V4 Flash Latest | |
|---|---|---|
| Provider | DeepSeek | ~deepseek |
| Input $/1M | $0.250 | $0.090 |
| Output $/1M | $0.950 | $0.180 |
| Blended $/1M | $0.425 | $0.113 |
| Context window | 164K | 1.0M |
| Max output | 33K | 384K |
| Released | Aug 2025 | Aug 2026 |
| Licence | Open weights | Proprietary |
Choose DeepSeek V3.1 if…
- Open weights — self-hostable
Choose DeepSeek V4 Flash Latest if…
- Costs less per token — $0.113 vs $0.425 blended
- Larger context window (1.0M)
- Newer model (released Aug 2026)
FAQ
Which is better, DeepSeek V3.1 or DeepSeek V4 Flash Latest?
We do not hold independently-run benchmark scores covering both DeepSeek V3.1 and DeepSeek V4 Flash Latest, so we make no quality claim. Their pricing and specifications are compared on this page.
Is DeepSeek V3.1 cheaper than DeepSeek V4 Flash Latest?
DeepSeek V4 Flash Latest is cheaper: $0.113 versus $0.425 per million tokens blended at 3:1 input:output. Input alone: $0.250 vs $0.090. Output alone: $0.950 vs $0.180.
What context windows do DeepSeek V3.1 and DeepSeek V4 Flash Latest have?
DeepSeek V3.1: 163,840 tokens. DeepSeek V4 Flash Latest: 1,048,576 tokens.
Who makes DeepSeek V3.1 and DeepSeek V4 Flash Latest?
DeepSeek V3.1 is made by DeepSeek. DeepSeek V4 Flash Latest is made by ~deepseek.