DeepSeek V4 Flash 0423:thinking API

DeepSeek's DeepSeek V4 Flash 0423:thinking costs $0.14 per million input tokens and $0.28 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.

About DeepSeek V4 Flash 0423:thinking

DeepSeek V4 Flash 0423:thinking is a language model from DeepSeek. Its release date is 23 April 2026. Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads. Its weights are open. Its licence is MIT. Its training data ends in May 2025. It takes text and gives text. The largest offer takes 1,048,576 input tokens. It has 1 supplier on this exchange now.

Description, release date and licence: models.dev (https://models.dev/)

Facts

Model name
deepseek-v4-flash-0423:thinking
Maker
DeepSeek
Context window
1M tokens
Input price
$0.14 per million tokens
Output price
$0.28 per million tokens
Suppliers
1 supplier
Regions
us

Providers

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-0423:thinking",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is DeepSeek V4 Flash 0423:thinking?
DeepSeek V4 Flash 0423:thinking is a language model from DeepSeek. Its release date is 23 April 2026. Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads. Its weights are open. Its licence is MIT. Its training data ends in May 2025.
How much does DeepSeek V4 Flash 0423:thinking cost?
Offers now ask $0.14 per million input tokens and $0.28 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 0423:thinking?
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 0423:thinking do?
Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does DeepSeek V4 Flash 0423:thinking support?
Text → Text.
Which providers serve DeepSeek V4 Flash 0423:thinking?
It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
How do I call DeepSeek V4 Flash 0423:thinking?
Send "deepseek-v4-flash-0423:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V4 Flash 0423:thinking released?
Its creator released it on 23 April 2026.
When was DeepSeek V4 Flash 0423:thinking listed?
The exchange first listed it on 10/17/2026. This is not its release date.

Related pages