Supported Providers - Lava Documentation

Overview

Lava supports 27 AI service providers out of the box, enabling you to route requests to dozens of different AI APIs through a single, unified billing system. Each provider is fully integrated with Lava’s metering and pricing infrastructure.

All providers are accessible through Lava’s /v1/forward endpoint with automatic usage tracking, billing, and cost calculation.

How Provider Integration Works

When you send a request through Lava:

Automatic Routing: Lava identifies the provider from your target URL
Authentication: Lava adds the appropriate provider API key
Request Forwarding: Your request is sent to the provider unchanged
Usage Tracking: Lava extracts usage metrics (tokens, characters, duration, etc.)
Cost Calculation: Costs are calculated based on provider pricing + your configured fees

Lava handles provider-specific authentication formats, response parsing, and usage extraction automatically - you only need to provide the target URL.

Supported Providers by Category

Large Language Models (LLMs)

These providers offer chat completion, text generation, and conversational AI capabilities:

OpenAI

GPT-4, GPT-3.5, GPT-4o

Chat completions
Embeddings
Streaming support

Anthropic

Claude 3 (Opus, Sonnet, Haiku)

Long context windows
Function calling
Vision support

Google

Gemini Pro, Gemini Flash

Multimodal inputs
Large context
Code generation

xAI

Grok models

Real-time data
Advanced reasoning

Mistral

Mistral Large, Medium, Small

Efficient inference
Multilingual

DeepSeek

DeepSeek models

Cost-effective
High performance

Cohere

Command, Embed models

Enterprise features
RAG support

Groq

Ultra-fast LLM inference

Low latency
High throughput

together.ai

Open-source LLMs

Llama, Mixtral, more
Custom models

AI Infrastructure & Hosting

Platforms that host and serve AI models at scale:

Fireworks

Fast LLM inference platform

DeepInfra

Serverless AI inference

Hyperbolic

GPU compute for AI

Cerebras

Wafer-scale AI compute

SambaNova

Enterprise AI platform

Nebius AI Studio

Cloud AI infrastructure

GMI Cloud

AI compute cloud

Inference.net

Decentralized AI inference

Baseten

Model deployment platform

Voice & Audio

Providers specializing in speech synthesis, recognition, and voice AI:

ElevenLabs

Text-to-Speech & Speech-to-Text

Natural voice synthesis
Voice cloning
Multilingual support
Character-based metering

Retell

Voice AI Phone Calls

Conversational AI calls
Real-time responses
Duration-based billing

Developer Platforms

AI development and deployment platforms:

Vercel

Vercel AI SDK integration

Novita AI

AI model marketplace

Specialized AI Services

kluster.ai

AI workflow automation

Parasail

AI-powered services

Chutes

AI infrastructure

Targon

Specialized AI models

Pearch

AI search & retrieval

Provider Authentication Methods

Lava automatically handles different authentication formats for each provider:

Authentication Type	Providers	Header Format
Bearer Token	OpenAI, Anthropic, DeepSeek, Mistral, xAI, and most LLM providers	`Authorization: Bearer <key>`
x-api-key	Standard API key header	`x-api-key: <key>`
x-goog-api-key	Google Gemini	`x-goog-api-key: <key>`
xi-api-key	ElevenLabs	`xi-api-key: <key>`
Query Parameter	Google (alternative)	`?key=<key>`

You don’t need to manage provider API keys yourself - Lava uses managed keys for all providers. Your forward token handles authentication on the Lava side.

Metering by Provider Type

Different AI services are metered in different ways:

Token-Based Metering

Providers: OpenAI, Anthropic, Google, Mistral, xAI, Groq, Cohere, and most LLM providers Metrics Tracked:

Input tokens (prompt)
Output tokens (completion)
Cached tokens (where supported)
Audio tokens (multimodal models)

Pricing Basis: Per million tokens (1M)

Character-Based Metering

Providers: ElevenLabs (text-to-speech) Metrics Tracked:

Character count of input text

Pricing Basis: Per million characters (1M)

Duration-Based Metering

Providers: Retell (voice calls), ElevenLabs (speech-to-text) Metrics Tracked:

Audio duration in seconds
Call duration

Pricing Basis: Per minute or per second

Request-Based Metering

Providers: Image generation services Metrics Tracked:

Number of API requests

Pricing Basis: Per request

Streaming Support

Lava fully supports Server-Sent Events (SSE) for real-time streaming responses:

Supported Streaming Providers

All major LLM providers support streaming:

OpenAI (GPT models)
Anthropic (Claude models)
Google (Gemini models)
Mistral, xAI, DeepSeek
Groq, Fireworks, together.ai
And all other LLM platforms

How Streaming Works Through Lava

Your request includes "stream": true in the body
Lava detects streaming and forwards the request
Lava streams the response back to you in real-time
Usage data is extracted from the final SSE message
Billing happens after the stream completes

Streaming Response Headers

Lava adds the request tracking header:

x-lava-request-id: req_01234567890abcdef

Usage data comes from the response body’s final SSE message, not headers.

Using Providers in Your Application

Basic Example (OpenAI)

const response = await fetch('https://api.lavapayments.com/v1/forward?u=https://api.openai.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${forwardToken}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'gpt-4',
    messages: [
      { role: 'user', content: 'Hello!' }
    ]
  })
});

Switching Providers

Changing providers is as simple as updating the target URL:

// OpenAI
const openaiUrl = 'https://api.openai.com/v1/chat/completions';

// Anthropic
const anthropicUrl = 'https://api.anthropic.com/v1/messages';

// Google
const googleUrl = 'https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent';

// Use any provider with the same forward token
const url = `https://api.lavapayments.com/v1/forward?u=${encodeURIComponent(targetUrl)}`;

Multi-Provider Support

Your users can use their Lava wallet credits across all providers:

// User's wallet has $50 credit
// They can use it for:
- OpenAI GPT-4 completions
- Anthropic Claude conversations
- ElevenLabs text-to-speech
- Google Gemini API calls
// All from the same prepaid balance

Provider-Specific Features

OpenAI

Function Calling: Fully supported with usage tracking
Vision: Image inputs metered separately
DALL-E: Image generation per-request pricing
Embeddings: Token-based metering

Anthropic

Long Context: Up to 200K tokens supported
Vision: Claude 3 image understanding
Tool Use: Native function calling support

ElevenLabs

Voice Cloning: Character-based billing
Multilingual: 29+ languages supported
Real-time: Streaming audio generation

Retell

Phone Calls: Duration + cost metering
Webhooks: Call status notifications
Real-time: Live conversation AI

Adding Custom Providers

If you need to use a provider not listed here, you can use the “Other” provider category:

Set your product to use unmanaged provider keys
Your users include their own API keys in requests
Lava tracks usage and bills based on your configured fees
Works with any REST API endpoint

Custom providers require users to bring their own API keys. Lava can still meter and bill for usage, but cannot manage authentication automatically.

Provider Availability

All providers are available on Lava’s production infrastructure with:

✅ Global edge deployment - Requests routed to nearest region
✅ Less than 20ms latency overhead - Minimal proxy delay
✅ 99.9% uptime SLA - Enterprise-grade reliability
✅ Automatic failover - Provider outages handled gracefully
✅ Real-time monitoring - Usage tracking and error logs

Pricing Transparency

For each provider, Lava:

Passes through base costs - You pay provider’s standard rates
Adds your configured fees - Fixed or percentage markups
Applies service charge - 1.9% platform fee
Shows complete breakdown - Full cost visibility in dashboard

See Pricing Configuration for details on setting up pricing.

Next Steps

Architecture Overview

Learn about Lava’s proxy architecture and request flow

Getting Started

Integration Guides

Core Concepts

Provider Reference

SDK Reference

​Overview

​How Provider Integration Works

​Supported Providers by Category

​Large Language Models (LLMs)

OpenAI

Anthropic

Google

xAI

Mistral

DeepSeek

Cohere

Groq

together.ai

​AI Infrastructure & Hosting

Fireworks

DeepInfra

Hyperbolic

Cerebras

SambaNova

Nebius AI Studio

GMI Cloud

Inference.net

Baseten

​Voice & Audio

ElevenLabs

Retell

​Developer Platforms

Vercel

Novita AI

​Specialized AI Services

kluster.ai

Parasail

Chutes

Targon

Pearch

​Provider Authentication Methods

​Metering by Provider Type

​Token-Based Metering

​Character-Based Metering

​Duration-Based Metering

​Request-Based Metering

​Streaming Support

​Using Providers in Your Application

​Basic Example (OpenAI)

​Switching Providers

​Multi-Provider Support

​Provider-Specific Features

​OpenAI

​Anthropic

​ElevenLabs

​Retell

​Adding Custom Providers

​Provider Availability

​Pricing Transparency

​Next Steps

Architecture Overview

Get Started

Overview

How Provider Integration Works

Supported Providers by Category

Large Language Models (LLMs)

AI Infrastructure & Hosting

Voice & Audio

Developer Platforms

Specialized AI Services

Provider Authentication Methods

Metering by Provider Type

Token-Based Metering

Character-Based Metering

Duration-Based Metering

Request-Based Metering

Streaming Support

Using Providers in Your Application

Basic Example (OpenAI)

Switching Providers

Multi-Provider Support

Provider-Specific Features

OpenAI

Anthropic

ElevenLabs

Retell

Adding Custom Providers

Provider Availability

Pricing Transparency

Next Steps