DeepSeek V4 Flash 0731 API

DeepSeek's DeepSeek V4 Flash 0731, through an OpenAI-compatible API. 5 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-0731 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-0731
Maker: DeepSeek
Context window: 1M tokens
Input price: $0.015 to $0.424 per million tokens
Output price: $0.0018 to $1.272 per million tokens
Providers: 5 independent providers
Regions: eu, global, us

Providers

Munito AI: global, $0.019 input and $0.048 output per million tokens, $0.0037 cache read per million tokens, 1M tokens of context
blackfuel: global, $0.015 input and $0.177 output per million tokens, $0.0030 cache read per million tokens, 1M tokens of context
Pera: us, $0.038 input and $0.0018 output per million tokens, $0.038 cache read per million tokens, 1M tokens of context
Boundless: us, $0.060 input and $0.180 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
blackfuel: eu, $0.140 input and $0.280 output per million tokens, $0.028 cache read per million tokens, 1M tokens of context
EmpirioLabs AI: global, $0.424 input and $1.272 output per million tokens, $0.424 cache read per million tokens, 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-0731",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is DeepSeek V4 Flash 0731?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does DeepSeek V4 Flash 0731 cost?: Offers now ask $0.015 to $0.424 per million input tokens and $0.0018 to $1.272 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 0731?: The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can DeepSeek V4 Flash 0731 do?: Its providers list Reasoning budget, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does DeepSeek V4 Flash 0731 support?: Text → Text.
Which providers serve DeepSeek V4 Flash 0731?: 5 independent providers quote it now, with 6 offers. The table above ranks them by the cost of a typical job.
How do I call DeepSeek V4 Flash 0731?: Send "deepseek-v4-flash-0731" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V4 Flash 0731 listed?: The exchange first listed it on 10/8/2026. This is not its release date.