SiliconFlow

Use SiliconFlow’s AI inference platform through Portkey for fast, cost-effective model deployment.

Quick Start

Get started with SiliconFlow in under 2 minutes:

Python

from portkey_ai import Portkey

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

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
    model="@siliconflow/deepseek-ai/DeepSeek-V2-Chat",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

Add Provider in Model Catalog

Before making requests, add SiliconFlow to your Model Catalog:

1. Go to Model Catalog → Add Provider
2. Select SiliconFlow
3. Enter your SiliconFlow API key
4. Name your provider (e.g., siliconflow)

Complete Setup Guide

See all setup options and detailed configuration instructions

---

Supported Models

SiliconFlow provides cost-effective inference for various models:

Check SiliconFlow’s documentation for the complete model list.

---

Next Steps

Gateway Configs

Add fallbacks, load balancing, and more

Observability

Monitor and trace your SiliconFlow requests

Prompt Library

Manage and version your prompts

Metadata

Add custom metadata to requests

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation