DeepSeek V4 Pro:thinking API

DeepSeek's DeepSeek V4 Pro:thinking, through an OpenAI-compatible API. Providers quote it on an open exchange, 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-pro:thinking 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-pro:thinking
Maker: DeepSeek
Context window: 1M tokens
Input price: $0.701 per million tokens
Output price: $1.402 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.701 input and $1.402 output per million tokens, $0.070 cache read per million tokens, 1M tokens of context

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

Questions

What is DeepSeek V4 Pro:thinking?: DeepSeek V4 Pro:thinking is a model from DeepSeek.
How much does DeepSeek V4 Pro:thinking cost?: Offers now ask $0.701 per million input tokens and $1.402 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 Pro: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 Pro: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 Pro:thinking support?: Text → Text.
Which providers serve DeepSeek V4 Pro:thinking?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call DeepSeek V4 Pro:thinking?: Send "deepseek-v4-pro:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V4 Pro:thinking listed?: The exchange first listed it on 10/10/2026. This is not its release date.

DeepSeek V4 Pro:thinking API

Facts

Providers

Request

Questions

Related pages