DeepSeek: DeepSeek V3 0324

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

Model lab: DeepSeek
Model family: deepseek

Model resources

Model weights

Modalitiestext → text

Context window163,840

Maximum output163,840

InputUSD 0.192 / 1M tokens

OutputUSD 0.72 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to deepseek/deepseek-v3-0324.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "deepseek/deepseek-v3-0324"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

DeepSeek V3 0324 API Pricing

Type	Price information
Input	USD 0.192 / 1M tokens
Output	USD 0.72 / 1M tokens
Cached input	USD 0.108 / 1M tokens

Benchmarks

Intelligence Index · v4.39.7

Coding Index21.2

Agentic Index0.8

Performance

Output speed91.61 tokens/s

Time to first token0.68 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput91.61 tok/sCurrent

Time to first token0.68 sCurrent

End-to-end latency7.8 sCurrent

Throughput

Current91.61 tok/s

Window average92.8 tok/s

Time to first token

Current0.68 s

Window average0.8 s

End-to-end latency

Current7.8 s

Window average7.5 s

Tail latency (P99)

Current14.2 s

Window average16.8 s

Prompt cache hit rate

Current26.1%

Window average24.4%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

DeepSeek V3 0324 Compare models

Model	Input price	Output price	Context window	Capabilities
DeepSeek V3 0324This page	USD 0.192 / 1M tokens	USD 0.72 / 1M tokens	163,840	Text output · Tool calling
DeepSeek Chat	USD 0.1176 / 1M tokens	USD 0.236 / 1M tokens	1,000,000	Text output · Tool calling
DeepSeek V3.2	USD 0.16704 / 1M tokens	USD 0.24768 / 1M tokens	128,000	Text output · Reasoning · Tool calling
DeepSeek-V3.1	USD 0.152 / 1M tokens	USD 0.568 / 1M tokens	131,072	Text output · Reasoning · Tool calling
DeepSeek V3.1	USD 0.2 / 1M tokens	USD 0.76 / 1M tokens	163,840	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 163,840
Maximum output: 163,840
Release date: 2025-03-24
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is DeepSeek V3 0324 for?

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

What inputs and outputs does DeepSeek V3 0324 support?

Recorded inputs: text; outputs: text.

How is DeepSeek V3 0324 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.192 / 1M tokens; Output USD 0.72 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for DeepSeek V3 0324?

Current model records list Context window 163,840 tokens; Maximum output 163,840 tokens.

What model parameter does the Quickstart use?

The example uses deepseek/deepseek-v3-0324. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.