DeepSeek-V3 API

deepseek/deepseek-chat-v3-0324
DeepSeek-V3 is a Mixture-of-Experts language model that rivals the best closed-source systems in the world, trained at a fraction of the cost, and fully open to the research community.
Context
128K tokens
Input
$0.398866 / 1M tokens
Output
$1.567956 / 1M tokens
Released
Aug 28, 2025

How to use DeepSeek-V3 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to deepseek/deepseek-chat-v3-0324.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "deepseek/deepseek-chat-v3-0324",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-chat-v3-0324",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-chat-v3-0324","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

DeepSeek-V3 API Pricing

TypePrice
Input
$0.398866 / 1M tokens
Output
$1.567956 / 1M tokens
Cached input
$0.192556 / 1M tokens

DeepSeek-V3 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
LiveCodeBench
49.2%
Contamination-free competitive programming problemsSourceJuly 12, 2026
MMLU-Pro
81.2%
Multi-discipline knowledge + reasoning (harder MMLU)SourceJuly 12, 2026
Intelligence
8.5
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
23
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
26
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

DeepSeek-V3 vs other models

ModelInputOutputContextBest for
DeepSeek-V3
This page
$0.398866 / 1M tokens
$1.567956 / 1M tokens
128K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$1.95 / 1M tokens
$11.7 / 1M tokens
1M tokens
Reasoning + agents

Frequently asked questions

DeepSeek-V3 has a 128,000 tokens context window and can return up to 124,000 tokens.

DeepSeek-V3 takes text as input and returns text.

Use deepseek/deepseek-chat-v3-0324 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

DeepSeek-V3 became available on August 28, 2025.

DeepSeek-V3 is priced at input $0.398866 / 1M tokens, output $1.567956 / 1M tokens, cached input $0.192556 / 1M tokens.

Yes, DeepSeek-V3 can stream responses as they are generated.

DeepSeek-V3 was built by DeepSeek.

DeepSeek-V3 is classified as a chat model, not a dedicated reasoning model.

Yes, it supports function calling, parallel tool calls, and structured outputs.

Start building with DeepSeek-V3

Get API Key
1000+ models, one API.