DeepSeek V3 0324 API

DeepSeek's DeepSeek V3 0324, 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-v3-0324 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-v3-0324
Maker: DeepSeek
Context window: 128K tokens
Input price: $0.200 per million tokens
Output price: $0.770 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.200 input and $0.770 output per million tokens, $0.135 cache read per million tokens, 128K tokens of context

Scores

HLE: 4.7, #209 of 273
GPQA: 65.5, #163 of 250
AA-LCR: 40.7, #184 of 237
SciCode: 39.0, #98 of 123
Terminal-Bench Hard: 15.2, #110 of 166
LiveCodeBench: 40.5, #67 of 130
AIME 2025: 41.0, #58 of 100
MMLU-Pro: 81.9, #36 of 133
τ²-Bench: 47.1, #103 of 169
IFBench: 41.0, #117 of 178

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

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3-0324",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is DeepSeek V3 0324?: DeepSeek V3 0324 is a model from DeepSeek.
How much does DeepSeek V3 0324 cost?: Offers now ask $0.200 per million input tokens and $0.770 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 V3 0324?: The largest offer takes 128,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can DeepSeek V3 0324 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 V3 0324 support?: Text → Text.
Which providers serve DeepSeek V3 0324?: 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 V3 0324?: Send "deepseek-v3-0324" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was DeepSeek V3 0324 listed?: The exchange first listed it on 10/14/2026. This is not its release date.