SU8 Codes
All models
DeepSeek

DeepSeek-v4-flash API

DeepSeek-v4-flash

deepseek-v4-flash
Lowest landed discount
49.3% off

Inside the SU500 plan on the Volcengine channel, the landed discount is 49.3% off.

Official input
$0.05 / 1M
Official output
$0.16 / 1M
Cache read
$0.007 / 1M
Cache write
—

About DeepSeek-v4-flash

DeepSeek-v4-flash

Tool calling
Supported, parallel
Prompt caching
Supported
Reasoning effort
Supported

Time-based pricing

This model uses time-of-day pricing (Beijing time): during the periods below the list price is multiplied by the factor shown, and other times are billed at the list price.

PeriodDaysBeijing timeOfficial price ×
峰时Mon–Fri09:00–12:00×2
峰时Mon–Fri14:00–18:00×2

Pay-as-you-go discounts by channel

The same model can run through different channels at different landed discounts. Shorter bars cost less.

ChannelFinal discountQuota multiplierBilling unit
Volcengine Lowest
28.5% off
4.8× USD / 1M

Cache hits are billed at the cache read price. Cache writes use the cache write price, and the Console usage detail shows the final cost breakdown.

Plans that include this model

On a plan, calls are deducted from the daily quota at the plan channel's discount.

PackageFinal discountChannelQuota multiplierBilling unit
SU500
49.3% off
Volcengine 3.8× USD / 1M
SU750
49.3% off
Volcengine 3.8× USD / 1M
SU1000
49.3% off
Volcengine 3.8× USD / 1M
Super Ultra
46.2% off
Volcengine 3.8× USD / 1M
Ultra
45.1% off
Volcengine 3.8× USD / 1M
Max
34.1% off
Volcengine 3.8× USD / 1M
Pro
23.1% off
Volcengine 3.8× USD / 1M

Example call

curl https://www.su8.codes/v1/chat/completions \
  -H "Authorization: Bearer $SU8_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-flash",
       "messages": [{"role": "user", "content": "Hello"}]}'

Frequently asked questions

How much does the DeepSeek-v4-flash API cost?

DeepSeek list price: Input $0.05/1M, Output $0.16/1M, Cache read $0.007/1M. On SU8 Codes, each channel has its own landed discount; the current pay-as-you-go and package discounts are in the channel and package tables on this page, refreshed live.

How do I call DeepSeek-v4-flash?

Create an API key in the SU8 Codes console, point your client at this site's base URL, and use the model ID deepseek-v4-flash. The example call above has copy-ready cURL and Python code.

Can I use DeepSeek-v4-flash with Codex CLI?

Yes. In ~/.codex/config.toml, set the base URL to this site, add your SU8 API key, and set the model to deepseek-v4-flash. The Codex CLI tab in the example call above has the full config, and the integration docs walk through each step.

Integration guides

More from DeepSeek

ModelOfficial inputOfficial outputLanded discount
DeepSeek V4.1 Flash 1017
deepseek-flash
$0.3/ 1M $1.2/ 1M
40% offDeepSeek-API
deepseek-v4-1-flash-261017
deepseek-v4-1-flash-261017
$0.15/ 1M $0.6/ 1M
28.5% offVolcengine
DeepSeek-v4.1-flash
deepseek-v4.1-flash
$0.15/ 1M $0.6/ 1M
28.5% offVolcengine
DeepSeek-v4-pro
deepseek-v4-pro
$0.87/ 1M $1.74/ 1M
40% offDeepSeek-API