Available DeepSeek Models

Model	Input ($/M)	Output ($/M)	Best For
deepseek-v4	$0.27	$1.10	General purpose, code, Chinese
deepseek-v3	$0.27	$1.10	Similar to V4, alternative
deepseek-r1	$0.50	$2.00	Complex reasoning, math
deepseek-v4-flash	$0.001	$0.001	High volume, simple tasks

Quick Start (30 Seconds)

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-ai-token-hub-key",
    base_url="https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Why Use AI-Token-Hub for DeepSeek?

• One API for all models - Not just DeepSeek, but also Qwen, GLM, Kimi, etc.
• OpenAI compatible - No code changes needed if you're already using OpenAI SDK
• Free trial - 50,000 tokens to test before committing
• Switch models instantly - Change one parameter to use a different model
• Reliable infrastructure - Load balanced, high availability

Framework Integration

Works with all major LLM frameworks:

• ✅ OpenAI Python/Node.js SDK (direct)
• ✅ LangChain (ChatOpenAI with custom base_url)
• ✅ LlamaIndex (OpenAI with custom api_base)
• ✅ LiteLLM (model="openai/deepseek-v4")
• ✅ Semantic Kernel

DeepSeek vs OpenAI: The Numbers

Metric	DeepSeek V4	GPT-4o
Input Price	$0.27/M	$2.50/M
Output Price	$1.10/M	$10.00/M
HumanEval (Code)	90.2%	88.5%
Chinese Understanding	★★★★★	★★★★☆
Context Window	128K	128K

Start Using DeepSeek API Free → Full API Documentation →

← Home | Blog | Cost Calculator