DeepSeek

Integrate DeepSeek models with Portkey’s AI Gateway

Portkey provides a robust and secure gateway to integrate various Large Language Models (LLMs) into applications, including DeepSeek’s models.

With Portkey, take advantage of features like fast AI gateway access, observability, prompt management, and more, while securely managing API keys through Model Catalog.

Quick Start

Get DeepSeek working in 3 steps:

Python

from portkey_ai import Portkey

# 1. Install: pip install portkey-ai
# 2. Add @deepseek provider in model catalog
# 3. Use it:

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
    model="@deepseek/deepseek-chat",
    messages=[{"role": "user", "content": "Say this is a test"}]
)

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

import Portkey from 'portkey-ai'

// 1. Install: npm install portkey-ai
// 2. Add @deepseek provider in model catalog
// 3. Use it:

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY"
})

const response = await portkey.chat.completions.create({
    model: "@deepseek/deepseek-chat",
    messages: [{ role: "user", content: "Say this is a test" }]
})

console.log(response.choices[0].message.content)

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL

# 1. Install: pip install openai portkey-ai
# 2. Add @deepseek provider in model catalog
# 3. Use it:

client = OpenAI(
    api_key="PORTKEY_API_KEY",  # Portkey API key
    base_url=PORTKEY_GATEWAY_URL
)

response = client.chat.completions.create(
    model="@deepseek/deepseek-chat",
    messages=[{"role": "user", "content": "Say this is a test"}]
)

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

import OpenAI from "openai"
import { PORTKEY_GATEWAY_URL } from "portkey-ai"

// 1. Install: npm install openai portkey-ai
// 2. Add @deepseek provider in model catalog
// 3. Use it:

const client = new OpenAI({
    apiKey: "PORTKEY_API_KEY",  // Portkey API key
    baseURL: PORTKEY_GATEWAY_URL
})

const response = await client.chat.completions.create({
    model: "@deepseek/deepseek-chat",
    messages: [{ role: "user", content: "Say this is a test" }]
})

console.log(response.choices[0].message.content)

# 1. Add @deepseek provider in model catalog
# 2. Use it:

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "model": "@deepseek/deepseek-chat",
    "messages": [
      { "role": "user", "content": "Say this is a test" }
    ]
  }'

Tip: You can also set provider="@deepseek" in Portkey() and use just model="deepseek-chat" in the request.

Add Provider in Model Catalog

1. Go to Model Catalog → Add Provider
2. Select DeepSeek
3. Choose existing credentials or create new by entering your DeepSeek API key
4. Name your provider (e.g., deepseek-prod)

Complete Setup Guide →

See all setup options, code examples, and detailed instructions

Advanced Features

Multi-round Conversations

DeepSeek supports multi-turn conversations where context is maintained across messages:

Python

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@deepseek"
)

# Round 1
messages = [{"role": "user", "content": "What's the highest mountain in the world?"}]
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=messages
)

messages.append(response.choices[0].message)
print(f"Messages Round 1: {messages}")

# Round 2
messages.append({"role": "user", "content": "What is the second?"})
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=messages
)

messages.append(response.choices[0].message)
print(f"Messages Round 2: {messages}")

import Portkey from 'portkey-ai'

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    provider: "@deepseek"
})

// Round 1
let messages = [{ role: "user", content: "What's the highest mountain in the world?" }]

let response = await client.chat.completions.create({
    model: "deepseek-chat",
    messages: messages
})

messages.push(response.choices[0].message)
console.log(`Messages Round 1: ${JSON.stringify(messages, null, 2)}`)

// Round 2
messages.push({ role: "user", content: "What is the second?" })
response = await client.chat.completions.create({
    model: "deepseek-chat",
    messages: messages
})

messages.push(response.choices[0].message)
console.log(`Messages Round 2: ${JSON.stringify(messages, null, 2)}`)

JSON Output

Force structured JSON responses from DeepSeek models:

Python

import json
from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@deepseek"
)

system_prompt = """
The user will provide some exam text. Please parse the "question" and "answer" and output them in JSON format.

EXAMPLE INPUT:
Which is the highest mountain in the world? Mount Everest.

EXAMPLE JSON OUTPUT:
{
    "question": "Which is the highest mountain in the world?",
    "answer": "Mount Everest"
}
"""

user_prompt = "Which is the longest river in the world? The Nile River."

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": user_prompt}
]

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=messages,
    response_format={"type": "json_object"}
)

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

import Portkey from 'portkey-ai'

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    provider: "@deepseek"
})

const systemPrompt = `
The user will provide some exam text. Please parse the "question" and "answer" and output them in JSON format.

EXAMPLE INPUT:
Which is the highest mountain in the world? Mount Everest.

EXAMPLE JSON OUTPUT:
{
    "question": "Which is the highest mountain in the world?",
    "answer": "Mount Everest"
}
`

const userPrompt = "Which is the longest river in the world? The Nile River."

const messages = [
    { role: "system", content: systemPrompt },
    { role: "user", content: userPrompt }
]

const response = await client.chat.completions.create({
    model: "deepseek-chat",
    messages: messages,
    responseFormat: { type: "json_object" }
})

console.log(JSON.parse(response.choices[0].message.content))

Tool Calling

DeepSeek supports tool calling (function calling) on the deepseek-chat model. Pass tools and optionally tool_choice in your request:

Python

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@deepseek"
)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City name"}
            },
            "required": ["location"]
        }
    }
}]

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools
)

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

import Portkey from 'portkey-ai'

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    provider: "@deepseek"
})

const tools = [{
    type: "function",
    function: {
        name: "get_weather",
        description: "Get the current weather for a location",
        parameters: {
            type: "object",
            properties: {
                location: { type: "string", description: "City name" }
            },
            required: ["location"]
        }
    }
}]

const response = await client.chat.completions.create({
    model: "deepseek-chat",
    messages: [{ role: "user", content: "What's the weather in Tokyo?" }],
    tools: tools
})

console.log(response.choices[0].message.tool_calls)

Reasoning (deepseek-reasoner)

The deepseek-reasoner model supports chain-of-thought reasoning. Use the reasoning_effort parameter to control reasoning behavior:

Python

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@deepseek"
)

response = client.chat.completions.create(
    model="deepseek-reasoner",
    messages=[{"role": "user", "content": "Solve: If 3x + 7 = 22, what is x?"}],
    reasoning_effort="high"
)

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

import Portkey from 'portkey-ai'

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    provider: "@deepseek"
})

const response = await client.chat.completions.create({
    model: "deepseek-reasoner",
    messages: [{ role: "user", content: "Solve: If 3x + 7 = 22, what is x?" }],
    reasoning_effort: "high"
})

console.log(response.choices[0].message.content)

When streaming, reasoning_content is included in the delta for deepseek-reasoner responses.

Managing DeepSeek Prompts

Manage all prompt templates to DeepSeek in the Prompt Library. All current DeepSeek models are supported, and you can easily test different prompts.

Use the portkey.prompts.completions.create interface to use the prompt in an application.

Supported Endpoints

• Chat Completions
• Streaming Chat Completions

Next Steps

Add Metadata

Add metadata to your DeepSeek requests

Gateway Configs

Add gateway configs to your DeepSeek requests

Tracing

Trace your DeepSeek requests

Fallbacks

Setup fallback from OpenAI to DeepSeek

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation