Back to CodeSlick

AI Provider Configuration Guide

CodeSlick works with ANY OpenAI-compatible API. Choose your preferred provider below and follow the setup instructions.

Quick Start

  1. Choose a provider from the list below
  2. Create an account and get your API key
  3. Copy the Provider URL and Model Name
  4. Go back to CodeSlick and click "Use My API Key"
  5. Paste your configuration and click "Validate" then "Save"

OpenAI

Industry-leading models including GPT-4o, GPT-4 Turbo, and GPT-3.5 Turbo

💰 From $0.50/1M tokensGet API Key
https://api.openai.com/v1
gpt-4o
gpt-4-turbo
sk-...

Setup Steps:

  1. Go to OpenAI Platform
  2. Create an account or sign in
  3. Navigate to API Keys
  4. Click "Create new secret key"
  5. Copy your API key (starts with sk-)

Anthropic

Claude models - excellent for code analysis and following complex instructions

💰 From $3/1M tokensGet API Key
https://api.anthropic.com/v1
claude-3-5-sonnet-20241022
claude-3-opus-20240229
sk-ant-...

Setup Steps:

  1. Go to Anthropic Console
  2. Create an account or sign in
  3. Navigate to API Keys
  4. Click "Create Key"
  5. Copy your API key (starts with sk-ant-)

OpenRouter

Access 100+ models from multiple providers with a single API key (recommended)

💰 Pay-per-use across providersGet API Key

Note: Recommended: Access multiple providers with a single API key. Great for trying different models without separate accounts.

https://openrouter.ai/api/v1
openai/gpt-4o
anthropic/claude-3.5-sonnet
sk-or-...

Setup Steps:

  1. Go to OpenRouter
  2. Sign up with GitHub or Google
  3. Navigate to Keys
  4. Click "Create Key"
  5. Copy your API key (starts with sk-or-)
  6. Add credits to your account

Groq

Ultra-fast inference for Llama and other open-source models

💰 Free tier availableGet API Key
https://api.groq.com/openai/v1
llama-3.1-70b-versatile
llama-3.1-8b-instant
gsk_...

Setup Steps:

  1. Go to Groq Console
  2. Create an account or sign in
  3. Navigate to API Keys
  4. Click "Create API Key"
  5. Copy your API key (starts with gsk_)

Together AI

Open-source models including Qwen, Llama, and DeepSeek

💰 From $0.20/1M tokensGet API Key
https://api.together.xyz/v1
Qwen/Qwen2.5-Coder-32B-Instruct
meta-llama/Llama-3-70b-chat-hf
random string

Setup Steps:

  1. Go to Together AI
  2. Create an account or sign in
  3. Navigate to API Keys
  4. Click "Create new API key"
  5. Copy your API key

DeepSeek

Specialized code models with excellent performance at low cost

💰 From $0.14/1M tokensGet API Key
https://api.deepseek.com/v1
deepseek-coder
deepseek-chat
sk-...

Setup Steps:

  1. Go to DeepSeek Platform
  2. Create an account or sign in
  3. Navigate to API Keys
  4. Click "Create API Key"
  5. Copy your API key

Self-Hosted / Custom

Use any OpenAI-compatible API including Ollama, LM Studio, or vLLM

💰 Free (your hardware)Get API Key

Note: Perfect for privacy-sensitive code or offline usage. Works with Ollama, LM Studio, vLLM, and any OpenAI-compatible server.

http://localhost:11434/v1 (Ollama example)
llama3:70b
codellama:34b
Not required for local

Setup Steps:

  1. Install Ollama or your preferred server
  2. Start the server (e.g., ollama serve)
  3. Pull a model (e.g., ollama pull llama3:70b)
  4. Use http://localhost:11434/v1 as Provider URL
  5. Model name matches your pulled model
  6. API key can be left as "none" or any placeholder

Frequently Asked Questions

Which provider should I choose?

For beginners: OpenRouter (access 100+ models with one API key)
For best quality: OpenAI GPT-4o or Anthropic Claude 3.5 Sonnet
For lowest cost: Groq (free tier) or DeepSeek
For privacy: Self-hosted with Ollama

Is my API key secure?

Yes. Your API key is stored only in your browser's localStorage and is never sent to CodeSlick servers. It is used directly in requests from your browser to your chosen AI provider.

Can I use multiple providers?

You can save one configuration at a time. To switch providers, simply configure a new API key. OpenRouter is recommended if you want to try different models without changing your configuration.

What if my provider isn't listed?

Any provider with an OpenAI-compatible API will work! Just enter their base URL, model name, and API key. Examples include Replicate, Hugging Face Inference, Azure OpenAI, and many others.

How much will it cost?

Costs vary by provider and model. Most code analysis requests use 500-2000 tokens (~$0.001-0.005 per request). Check your provider's pricing page for exact rates. Many providers offer free credits to get started.

Need help? Contact us at support@codeslick.dev