DeepSeek · Chat / text model
deepseek-v4-flash API
deepseek-v4-flash is a model from DeepSeek that you can call through Ezkielyna API in the OpenAI-compatible format.
DeepSeek V4 Flash — fast and affordable. Vision: yes — accepts image input (tested).
Price
Standard price · per 1M input tokens
$0.04 ≈ Rp727
Standard ×1
- Input
- $0.04
Rp727 - Output
- $0.16
Rp2,909 - Cached input
- $0.0054
Rp98
Rupiah is an estimate at the store's current rate (Rp18,182 per USD). The live price is always at api.ezkielyna.store/pricing.
Key group availability: Standard. Create your key in the Auto group (it covers Standard, Premium, Hemat and Media, but not Pro). A Standard key cannot call Premium, Pro or Media models.
Capabilities
- Type
- Chat / text model
- Reads images
- Yes (tested)
- API formats
- POST /v1/chat/completions (OpenAI)
- POST /v1/responses (OpenAI Responses)
- POST /v1/messages (Anthropic)
- POST /v1beta/models/{model}:generateContent (Gemini)
Code example
Base URL https://api.ezkielyna.store/v1. Replace YOUR_EZKIELYNA_API_KEY with your key.
curl https://api.ezkielyna.store/v1/chat/completions \
-H "Authorization: Bearer $EZKIELYNA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello! Explain what an API is in 2 sentences."}]
}'Live performance
Numbers for deepseek-v4-flash from real requests through Ezkielyna API, not synthetic tests. A failure counts only when the error came from Ezkielyna or the provider (5xx).
- Success, 24 h
- 100%
- 48 requests
- Uptime, 7 days
- 92.69%
- 957 requests
- Uptime, 30 days
- 96.7%
- 4,337 requests
- First token (median)
- 4.2 s
- p90 8.4 s
- Output speed
- 208 tokens/s
- median, estimate
- Answer time (median)
- 7 s
- includes answer length
Updated 12 Nov 2026 04:10 WIB · raw data: models.json
Live status
Status is built from real requests, not synthetic tests.
View status · deepseek-v4-flash ↗Embed a live status badge for deepseek-v4-flash on your site or README
Get started
FAQ
How much does the deepseek-v4-flash API cost per 1M tokens?
Standard: $0.04 per 1M input tokens (about Rp727) and $0.16 per 1M output tokens (about Rp2,909). Prices follow the live catalog and can change; the rupiah figure is an estimate at the store's rate today. Full list: api.ezkielyna.store/pricing.
Which API key group can call deepseek-v4-flash?
deepseek-v4-flash is available in the Standard group(s). When you create a key at api.ezkielyna.store, pick the Auto group (it covers Standard, Premium, Hemat and Media, but not Pro) or a matching group. A Standard key cannot call Premium, Pro or Media models.
How do I use deepseek-v4-flash with the OpenAI SDK?
Set base_url to https://api.ezkielyna.store/v1, use your Ezkielyna key as api_key and call the model "deepseek-v4-flash". curl and Python examples are on this page.
Can deepseek-v4-flash read images?
Yes. The catalog records that this model accepts image input (tested).
How can I tell whether deepseek-v4-flash is working right now?
The status page at api.ezkielyna.store/status is built from real requests (not synthetic tests). Only server-side failures count, and models without traffic are shown as such.
How do I buy credit and pay?
Buy Ezkielyna API Credit in the store (QRIS, store balance, USDT or Binance Pay), redeem the code in Wallet at api.ezkielyna.store, then create a key under API Keys. The balance is charged per token used.
How fast and reliable is deepseek-v4-flash on Ezkielyna?
From real requests (updated 12 Nov 2026 04:10 WIB): 7-day uptime 92.69%, median time to first token 4.2 s, output speed about 208 tokens per second. Live numbers are in the Live performance section and at https://api.ezkielyna.store/status.
More DeepSeek models
All models & prices →DeepSeek API prices in IDR →Estimate and compare the cost of deepseek-v4-flash →