DeepSeek V4 Flash API
160K context · Released May 21, 2026 · By DeepSeek · MIT
DeepSeek V4 Flash costs $0.09 per million input tokens and $0.18 per million output tokens, against an official rate of $0.14 and $0.28 — 36% below official pricing. It is a DeepSeek model under the MIT licence, with a 160K context window, callable through an OpenAI-compatible endpoint with the model id `deepseek/deepseek-v4-flash`.
Input
$0.090/M
$0.14/M
Output
$0.18/M
$0.28/M
Savings
36%
off official
- No markup
- OpenAI SDK compatible
- No minimum spend
- MIT
The cheapest capable model on the platform. Fast enough for interactive use and priced for workloads measured in billions of tokens per month.
Copy this and go
The model id is already filled in. Nothing in this snippet needs editing except your key.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://router.xark.io/api/v1" # ← the only line that changes
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello"}]
)
DeepSeek V4 Flash pricing across providers
Rates as published by each provider. We update these when they change; if you spot one that's stale, tell us and we'll fix it.
| Provider | Input | Output |
|---|---|---|
| AI Token Router | $0.090/M | $0.18/M |
| Official (DeepSeek) | $0.14/M | $0.28/M |
| OpenRouter | $0.14/M | $0.27/M |
| DeepInfra | $0.10/M | $0.20/M |
| Together AI | $0.13/M | $0.26/M |
Cached input on DeepSeek V4 Flash is billed at $0.018/M — roughly 80% below the standard input rate. For agent loops with a large fixed system prompt this is usually the number that matters most.
What it's good at
- Billion-token-scale batch jobs
- Summarisation and reranking
- Cheap first-pass filtering before an expensive model