~deepseek
DeepSeek V4 Flash Latest
Released 2026-08-01
This model always redirects to the latest model in the DeepSeek V4 Flash family.
You send / 1M
$0.048
tokens in
It replies / 1M
$0.157
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0001
1,000 words in, 400 out
Data privacy
No training or retention: Unknown. Check the provider's terms before sending sensitive data.
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 944K tokens
- Repeated text is billed at $0.028 per 1M (prompt caching)
Similar models
- Mercury 2.5Inception · $0.040 in / $0.150 out per 1M
- Laguna S 2.1Poolside · $0.090 in / $0.180 out per 1M
- Solar Mini 4Upstage · $0.050 in / $0.200 out per 1M
- Nemotron 3.5 LightningNVIDIA · $0.070 in / $0.200 out per 1M
- Reka Flash 3Rekaai · $0.100 in / $0.200 out per 1M
- Laguna XS 2.1Poolside · $0.060 in / $0.120 out per 1M