DeepSeek: DeepSeek-V3

Open DeepSeek MoE chat model for coding, math, and general reasoning

Model lab: DeepSeek
Model family: deepseek

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output8,192

InputUSD 0.256 / 1M tokens

OutputUSD 0.712 / 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.

import os
import requests

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

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 API Pricing

Type	Price information
Input	USD 0.256 / 1M tokens
Output	USD 0.712 / 1M tokens

Benchmarks

Intelligence Index · v4.38.5

Coding Index23

Agentic Index0.8

Performance

Output speed44.37 tokens/s

Time to first token1.08 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput44.37 tok/sCurrent

Time to first token1.08 sCurrent

End-to-end latency8.0 sCurrent

Throughput

Current44.37 tok/s

Window average44.2 tok/s

Time to first token

Current1.08 s

Window average1.3 s

End-to-end latency

Current8.0 s

Window average7.5 s

Tail latency (P99)

Current17.0 s

Window average16.7 s

Prompt cache hit rate

Current18.4%

Window average24.7%

Error rate

Current0.0%

Window average0.2%

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 Compare models

Model	Input price	Output price	Context window	Capabilities
DeepSeek-V3This page	USD 0.256 / 1M tokens	USD 0.712 / 1M tokens	131,072	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: 131,072
Maximum output: 8,192
Release date: 2024-12-26
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is DeepSeek-V3 for?

Open DeepSeek MoE chat model for coding, math, and general reasoning

What inputs and outputs does DeepSeek-V3 support?

Recorded inputs: text; outputs: text.

How is DeepSeek-V3 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.256 / 1M tokens; Output USD 0.712 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for DeepSeek-V3?

Current model records list Context window 131,072 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses deepseek/deepseek-v3. 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.