DeepSeek · live price
DeepSeek V4 Flash 0731 API pricing
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
- Input
- $0.011
- per 1M tokens
- Output
- $1.28
- per 1M tokens
- Cached input
- $0.011
- per 1M tokens
- Context
- 1.0M
- 944K max output
List price from OpenRouter, which passes DeepSeek's price through without markup. Refreshed hourly. Released July 31, 2026. Model id deepseek/deepseek-v4-flash-0731.
What DeepSeek V4 Flash 0731 costs in practice
1,000 chat messages
$0.65
1,000 input + 500 output tokens each
1,000 RAG questions
$0.73
8,000 input + 500 output tokens each
100 coding-agent steps
$0.29
30,000 input + 2,000 output tokens each, no caching
DeepSeek V4 Flash 0731 price history
DeepSeek V4 Flash 0731 price by host
- StreamLake$0.044 in · $0.132 out · 1.0M ctx · 99.4% uptime 24h
- DeepInfra$0.06 in · $0.18 out · 1.0M ctx · 99.9% uptime 24h
- Makora$0.09 in · $0.195 out · 1M ctx · 97.6% uptime 24h
- Sail Research$0.019 in · $0.3 out · 1.0M ctx · 98.2% uptime 24h
- DigitalOcean$0.119 in · $0.238 out · 1.0M ctx · 99.9% uptime 24h
- BaseTen$0.13 in · $0.26 out · 1.0M ctx · 99.6% uptime 24h
- CoreWeave$0.13 in · $0.28 out · 262K ctx · 100.0% uptime 24h
- Cohere$0.14 in · $0.28 out · 1.0M ctx · 99.8% uptime 24h
- Together$0.14 in · $0.28 out · 1.0M ctx · 99.6% uptime 24h
- Parasail$0.14 in · $0.28 out · 1.0M ctx · 99.3% uptime 24h
- Venice$0.175 in · $0.35 out · 1M ctx · 99.7% uptime 24h
- Morph$0.142 in · $0.4 out · 1.0M ctx · 95.9% uptime 24h
- Reka$0.021 in · $0.528 out · 262K ctx · 99.8% uptime 24h
- Inceptron$0.05 in · $0.65 out · 1.0M ctx · 99.9% uptime 24h
- Mancer 2$0.2 in · $0.6 out · 1.0M ctx · 98.8% uptime 24h
- Wafer$0.12 in · $0.7 out · 1.0M ctx · 100.0% uptime 24h
- SiliconFlow$0.22 in · $0.66 out · 1.0M ctx · 99.5% uptime 24h
- GMICloud$0.286 in · $0.858 out · 1.0M ctx · 100.0% uptime 24h
- Phala$0.308 in · $0.924 out · 1.0M ctx · 99.8% uptime 24h
- OpenInference$0.012 in · $1.25 out · 1.0M ctx · 93.4% uptime 24h
- Relace$0.011 in · $1.28 out · 1.0M ctx · 99.8% uptime 24h
- NextBit$0.352 in · $1.06 out · 1.0M ctx · 100.0% uptime 24h
- Alibaba$0.352 in · $1.06 out · 1M ctx · 99.3% uptime 24h
- Novita$0.409 in · $1.23 out · 1.0M ctx · 100.0% uptime 24h
- Baidu$0.44 in · $1.32 out · 1.0M ctx · 99.6% uptime 24h
- AtlasCloud$0.44 in · $1.32 out · 1.0M ctx · 99.8% uptime 24h
- Cloudflare$0.44 in · $1.32 out · 1.0M ctx · 100.0% 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 0731 cost calculator
Cheaper alternatives to DeepSeek V4 Flash 0731
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.5 |
| Qwen: Qwen3.7 Flash | $0.03 | $0.13 |
Other DeepSeek models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| 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 V4 Pro 0423 | $0.209 | $0.418 |
| DeepSeek V4 Flash 0423 | $0.042 | $0.084 |
| DeepSeek V3.2 | $0.28 | $0.42 |