Skip to main content
Obsidian AI Providers supports many additional AI providers through OpenAI-compatible APIs. This page covers setup instructions for all remaining supported providers and generic OpenAI-compatible endpoints.

Supported Providers

The following providers are supported through OpenAI-compatible APIs:
  • Mistral AI
  • Together AI
  • Fireworks AI
  • Perplexity AI
  • DeepSeek
  • xAI (Grok)
  • Cerebras
  • Z.AI
  • 302.AI
  • Novita AI
  • DeepInfra
  • SambaNova
  • Any other OpenAI-compatible API

Generic Setup Process

All OpenAI-compatible providers follow the same setup pattern:
1

Select provider type

In the AI Providers settings, click Create AI provider and select OpenAI compatible API as the provider type.
2

Configure provider URL

Enter the provider’s API endpoint URL (see provider-specific details below).
3

Enter API key

Paste your API key from the provider’s dashboard.
4

Select or enter model name

Click refresh to fetch models (if supported) or manually enter the model name.
5

Test the provider

Click Test to verify everything is configured correctly.

Provider-Specific Details

Mistral AI

Overview:
  • High-performance European AI provider
  • Strong multilingual support
  • Competitive pricing
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.mistral.ai/v1
  • API Key: Get from console.mistral.ai
  • Popular Models: mistral-large-latest, mistral-small-latest, codestral-latest
Official Website: mistral.ai

Together AI

Overview:
  • Access to many open-source models
  • Fast inference
  • Developer-friendly
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.together.xyz/v1
  • API Key: Get from api.together.xyz
  • Popular Models: Various Llama, Mixtral, and Qwen models
Official Website: together.ai

Fireworks AI

Overview:
  • Optimized for speed
  • Wide model selection
  • Function calling support
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.fireworks.ai/inference/v1
  • API Key: Get from fireworks.ai
  • Popular Models: accounts/fireworks/models/llama-v3p1-70b-instruct
Official Website: fireworks.ai

Perplexity AI

Overview:
  • Online models with web search
  • Real-time information access
  • Citation support
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.perplexity.ai
  • API Key: Get from perplexity.ai
  • Popular Models: llama-3.1-sonar-large-128k-online, llama-3.1-sonar-small-128k-online
Official Website: perplexity.ai
Perplexity’s “online” models can search the web in real-time, providing up-to-date information beyond their training data.

DeepSeek

Overview:
  • Chinese AI provider
  • Strong coding capabilities
  • Cost-effective pricing
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.deepseek.com/v1
  • API Key: Get from platform.deepseek.com
  • Popular Models: deepseek-chat, deepseek-coder
Official Website: deepseek.com

xAI (Grok)

Overview:
  • Created by xAI (Elon Musk’s AI company)
  • Real-time information access
  • Long context windows
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.x.ai/v1
  • API Key: Get from x.ai console
  • Popular Models: grok-beta, grok-vision-beta
Official Website: x.ai

Cerebras

Overview:
  • Ultra-fast inference
  • Wafer-scale AI acceleration
  • Free tier available
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.cerebras.ai/v1
  • API Key: Get from cloud.cerebras.ai
  • Popular Models: llama3.1-8b, llama3.1-70b
Official Website: cerebras.ai

Z.AI

Overview:
  • AI inference platform
  • Multiple model support
  • Competitive pricing
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.z.ai/v1
  • API Key: Get from Z.AI dashboard
  • Popular Models: Check Z.AI documentation

302.AI

Overview:
  • Chinese AI platform
  • Multiple models aggregated
  • Pay-as-you-go pricing
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: Check 302.AI documentation
  • API Key: Get from 302.AI dashboard
  • Popular Models: Various models from different providers
Official Website: 302.ai

Novita AI

Overview:
  • GPU cloud platform
  • Flexible model deployment
  • Developer-focused
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.novita.ai/v1
  • API Key: Get from novita.ai
  • Popular Models: Various open-source models
Official Website: novita.ai

DeepInfra

Overview:
  • Serverless inference platform
  • Wide model selection
  • Pay-per-use pricing
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.deepinfra.com/v1/openai
  • API Key: Get from deepinfra.com
  • Popular Models: Various Llama, Mixtral, and other open models
Official Website: deepinfra.com

SambaNova

Overview:
  • AI inference optimization
  • High-performance hardware
  • Enterprise-focused
Setup:
  • Provider Type: OpenAI compatible API
  • Provider URL: https://api.sambanova.ai/v1
  • API Key: Get from SambaNova Cloud
  • Popular Models: Optimized Llama and other models
Official Website: sambanova.ai

Custom OpenAI-Compatible APIs

You can connect to any OpenAI-compatible API endpoint:

Local Servers

Many tools provide OpenAI-compatible endpoints:
  • llama.cpp: http://localhost:8080/v1
  • llama-cpp-python: http://localhost:8000/v1
  • LocalAI: http://localhost:8080/v1
  • text-generation-webui (Oobabooga): Configure in extensions
  • vLLM: http://localhost:8000/v1

Cloud Deployments

Connect to your own deployed models:
  • Self-hosted OpenAI-compatible APIs
  • Custom model endpoints
  • Private cloud deployments

Setup for Custom Endpoints

1

Select OpenAI compatible API

Choose OpenAI compatible API as the provider type.
2

Enter your endpoint URL

Use the full URL including /v1 (e.g., http://localhost:8080/v1).
3

Add API key if required

Some endpoints don’t require authentication. Leave blank if not needed.
4

Enter model name manually

Type the exact model name as configured in your server.

Troubleshooting

Connection Issues

Common connection problems:
  • Incorrect endpoint URL (missing /v1 or wrong protocol)
  • Firewall blocking the connection
  • Server not running (for local endpoints)
  • Invalid API key

Model Not Found

If models don’t load:
  1. Try entering the model name manually
  2. Check provider documentation for exact model names
  3. Verify your API key has access to the model
  4. Some providers don’t support model listing

API Key Issues

If authentication fails:
  1. Verify the API key is copied correctly
  2. Check the key hasn’t expired or been revoked
  3. Ensure you’re using the right key type (some providers have different key types)
  4. Confirm your account has sufficient credits

Unsupported Features

Not all providers support all features:
  • Embeddings: Not all providers offer embedding models
  • Vision: Image support varies by provider and model
  • Streaming: Most support streaming, but some don’t
  • Function calling: Advanced feature not universally supported

Choosing a Provider

Consider these factors:
FactorBest Providers
SpeedGroq, Cerebras, Fireworks AI
CostDeepSeek, Together AI, Groq (free tier)
QualityMistral AI, xAI, OpenAI
PrivacyLocal servers (llama.cpp, LM Studio, Ollama)
Web accessPerplexity AI, xAI
MultilingualMistral AI, DeepSeek, Qwen models
CodingDeepSeek Coder, Codestral, specialized code models

Best Practices

  1. Start with free tiers: Test providers before committing
  2. Compare pricing: Costs vary significantly between providers
  3. Check model availability: Not all models available on all providers
  4. Monitor usage: Track spending and rate limits
  5. Have fallbacks: Configure multiple providers for reliability
  6. Read documentation: Each provider has specific features and limits
Many developers use multiple providers: local models for privacy-sensitive work, cloud models for complex tasks, and fast providers for real-time interactions.

Build docs developers (and LLMs) love