DeepSeek V4.1 Flash API

DeepSeek's DeepSeek V4.1 Flash, through an OpenAI-compatible API. 6 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-v4.1-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-v4.1-flash
Maker: DeepSeek
Context window: 262.1K · 1M tokens
Input price: $0.027 to $0.300 per million tokens
Output price: $0.0084 to $1.200 per million tokens
Providers: 6 independent providers
Regions: ap-southeast, asia, global, us

Providers

engy: asia, $0.028 input and $0.090 output per million tokens, $0.010 cache read per million tokens, 262.1K tokens of context
Munito AI: global, $0.027 input and $0.101 output per million tokens, $0.00055 cache read per million tokens, 1M tokens of context
Boundless: us, $0.060 input and $0.200 output per million tokens, $0.0030 cache read per million tokens, 1M tokens of context
deeprelay: ap-southeast, $0.068 input and $0.270 output per million tokens, $0.0014 cache read per million tokens, 1M tokens of context
Pera: us, $0.140 input and $0.0084 output per million tokens, $0.140 cache read per million tokens, $0.000058 fee for each request, 1M tokens of context
zro: us, $0.300 input and $1.200 output per million tokens, $0.0060 cache read per million tokens, 1M tokens of context

Scores

HLE: 39.2, #50 of 273
AA-LCR: 84.0, #7 of 237
SciCode: 51.9, #43 of 123
SimpleQA Verified: 42.9, #46 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-v4.1-flash",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is DeepSeek V4.1 Flash?: DeepSeek V4.1 Flash is a model from DeepSeek.
How much does DeepSeek V4.1 Flash cost?: Offers now ask $0.027 to $0.300 per million input tokens and $0.0084 to $1.200 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 V4.1 Flash?: 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 V4.1 Flash do?: Its providers list Vision, 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 V4.1 Flash support?: Text · Images → Text.
Which providers serve DeepSeek V4.1 Flash?: 6 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 V4.1 Flash?: Send "deepseek-v4.1-flash" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V4.1 Flash listed?: The exchange first listed it on 9/29/2026. This is not its release date.