DeepSeek · live price
DeepSeek V4 Flash 0423 API pricing
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
- Input
- $0.042
- per 1M tokens
- Output
- $0.084
- per 1M tokens
- Cached input
- $0.0084
- per 1M tokens
- Context
- 1.0M
- 131K max output
List price from OpenRouter, which passes DeepSeek's price through without markup. Refreshed hourly. Released April 24, 2026. Model id deepseek/deepseek-v4-flash.
What DeepSeek V4 Flash 0423 costs in practice
1,000 chat messages
$0.08
1,000 input + 500 output tokens each
1,000 RAG questions
$0.38
8,000 input + 500 output tokens each
100 coding-agent steps
$0.14
30,000 input + 2,000 output tokens each, no caching
DeepSeek V4 Flash 0423 price history
DeepSeek V4 Flash 0423 price by host
- Baidu$0.042 in · $0.084 out · 1.0M ctx · 99.5% uptime 24h
- StreamLake$0.042 in · $0.084 out · 1.0M ctx · 98.7% uptime 24h
- DeepInfra$0.09 in · $0.18 out · 1.0M ctx · 99.8% uptime 24h
- GMICloud$0.091 in · $0.182 out · 1.0M ctx · 100.0% uptime 24h
- Venice$0.097 in · $0.193 out · 1M ctx · 99.7% uptime 24h
- DigitalOcean$0.098 in · $0.196 out · 1.0M ctx · 99.9% uptime 24h
- Alibaba$0.134 in · $0.268 out · 1M ctx · 99.2% uptime 24h
- SiliconFlow$0.13 in · $0.28 out · 1.0M ctx · 99.9% uptime 24h
- Novita$0.14 in · $0.28 out · 1.0M ctx · 100.0% uptime 24h
- AtlasCloud$0.14 in · $0.28 out · 1.0M ctx · 98.6% uptime 24h
- Parasail$0.14 in · $0.28 out · 1.0M ctx · 99.8% uptime 24h
- Mancer 2$0.19 in · $0.5 out · 1.0M ctx · 98.9% uptime 24h
- Azure$0.21 in · $0.56 out · 1.0M ctx · 97.8% uptime 24h
- OpenInference$0.0050 in · $1.25 out · 1.0M ctx · 92.2% uptime 24h
- Relace$0.0045 in · $1.28 out · 1.0M ctx · 99.8% uptime 24h
Where to buy DeepSeek credits for less
Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare
DeepSeek V4 Flash 0423 cost calculator
Cheaper alternatives to DeepSeek V4 Flash 0423
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: gpt-oss-20b | $0.018 | $0.09 |
| Mistral: Mistral Nemo | $0.019 | $0.03 |
| inclusionAI: Ling 3.0 Flash VL | $0.021 | $0.062 |
| Nex AGI: Nex-N2.5-Mini | $0.025 | $0.1 |
| inclusionAI: Ling 3.0 Flash | $0.021 | $0.063 |
| IBM: Granite 4.0 Micro | $0.017 | $0.112 |
Other DeepSeek models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| DeepSeek V4 Pro 0423 | $0.209 | $0.418 |
| DeepSeek V4 Flash 0731 | $0.011 | $1.28 |
| DeepSeek V4 Pro 0813 | $0.66 | $1.98 |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 |
| DeepSeek V4.1 Flash | $0.03 | $0.5 |
| DeepSeek V3.2 | $0.28 | $0.42 |