DeepSeek

DeepSeek V3 API

DeepSeek V3 is a general-purpose open model with strong code and chat performance — and pricing that is hard to beat. A great default for high-volume open-model workloads.

Input
$0.27
/ 1M tokens
Output
$1.10
/ 1M tokens
Context
128K
tokens
Vision
Text only

Top use cases

  • Cheap general chat and Q&A
  • Code completion at scale
  • Bulk content generation
  • Open-model production workloads

Use DeepSeek V3 in 30 seconds

ModelServer is OpenAI-compatible. Point your existing OpenAI SDK at modelserver.dev/v1 and set the model name to deepseek-v3.

deepseek-v3.py
from openai import OpenAI

client = OpenAI(
    api_key="sk-modelserver-...",
    base_url="https://modelserver.dev/v1",
)

response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "user", "content": "Hello, DeepSeek V3!"}
    ],
)

print(response.choices[0].message.content)

Frequently asked questions

How much does DeepSeek V3 cost?
DeepSeek V3 is priced at $0.27 per 1M input tokens and $1.10 per 1M output tokens via ModelServer. ModelServer adds a flat 5.5% platform fee on top — no markups on individual tokens, no monthly minimum.
What is the DeepSeek V3 context window?
DeepSeek V3 supports a 128K token context window. You can put roughly 96,000 words in a single prompt.
Is DeepSeek V3 OpenAI-compatible via ModelServer?
Yes. Point your OpenAI SDK base_url to https://modelserver.dev/v1 and set model="deepseek-v3". Existing OpenAI-SDK code works without modification.
Who is DeepSeek V3 best for?
High-volume general-purpose open-model workloads.
Does DeepSeek V3 support vision input?
No. DeepSeek V3 is text-only. For multimodal use cases consider Claude Sonnet 4, GPT-4o, or Gemini 2.5 Pro.

Other DeepSeek models

DeepSeek V3 API — Pricing & Access — ModelServer