DeepSeek V4 Flash API

DeepSeek's DeepSeek V4 Flash, through an OpenAI-compatible API. 2 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send deepseek-v4-flash as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: deepseek-v4-flash
Maker: DeepSeek
Context window: 920.6K · 1M tokens
Input price: $0.050 to $0.140 per million tokens
Output price: $0.0050 to $0.280 per million tokens
Providers: 2 independent providers
Regions: asia, us

Providers

engy: asia, $0.050 input and $0.0050 output per million tokens, $0.010 cache read per million tokens, 920.6K tokens of context
Pera: us, $0.140 input and $0.280 output per million tokens, $0.140 cache read per million tokens, $0.00057 fee for each request, 1M tokens of context

Scores

HLE: 38.6, #54 of 273
GPQA: 90.8, #36 of 250
AA-LCR: 79.7, #47 of 237
SciCode: 50.3, #55 of 123
SimpleQA Verified: 33.6, #64 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is DeepSeek V4 Flash?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does DeepSeek V4 Flash cost?: Offers now ask $0.050 to $0.140 per million input tokens and $0.0050 to $0.280 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of DeepSeek V4 Flash?: The largest offer takes 1,000,000 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can DeepSeek V4 Flash do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does DeepSeek V4 Flash support?: Text → Text.
Which providers serve DeepSeek V4 Flash?: 2 independent providers quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call DeepSeek V4 Flash?: Send "deepseek-v4-flash" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V4 Flash listed?: The exchange first listed it on 10/8/2026. This is not its release date.