Introduction

AnyGpu provides unified access to 200+ AI models from multiple providers through a single, standardized API. Built for developers who want flexibility without vendor lock-in.

📦 Unified API

One API to access models from OpenAI, Anthropic, Google, Meta, DeepSeek, and more.

⚡ Low Latency

Optimized routing ensures minimal latency for your production workloads.

💰 Cost Effective

Competitive pricing with token-level cost tracking and spending limits.

Quick Start

Get up and running with AnyGpu in under 5 minutes.

1

Create an Account

Sign up for free and receive your API key instantly.

2

Get Your API Key

Navigate to the Console to copy your API key.

3

Make Your First Request

curl https://api.anygpu.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}]}'

Authentication

AnyGpu uses API key authentication. Include your API key in the Authorization header of every request.

Authorization: Bearer sk-anygpu-xxxxxxxxxxxx

⚠️ Security Note: Never expose your API key in client-side code or public repositories. Use environment variables.

Models

AnyGpu supports 200+ models across all major providers. Browse the full catalog at the Models page.

Model	Provider	Context	Best For
GPT-4o	OpenAI	128K	General purpose
Claude 3.5 Sonnet	Anthropic	200K	Long context tasks
Gemini 2.0 Flash	Google	1M	High volume, low cost
Llama 4	Meta	128K	Open source projects
DeepSeek V3	DeepSeek	64K	Coding tasks

Chat Completion

The Chat Completion API follows the OpenAI format, making it easy to switch from any provider.

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is AnyGpu?"}
  ],
  "max_tokens": 512,
  "temperature": 0.7
}

Streaming

Enable streaming for real-time responses in chat interfaces.

curl https://api.anygpu.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}], "stream": true}'

Endpoints

POST /v1/chat/completions Chat completion

GET /v1/models List available models

GET /v1/models/{id} Get model info

GET /v1/me Current user info

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Model identifier
messages	array	Yes	Array of message objects
max_tokens	integer	No	Max tokens to generate
temperature	float	No	Sampling temperature (0–2)
stream	boolean	No	Enable streaming

Error Codes

Code	Message	Description
401	Invalid API key	Check your API key format and validity
429	Rate limit exceeded	Slow down requests or upgrade plan
500	Internal server error	Retry with backoff
503	Model unavailable	Try a different model or wait

Pricing

Pay per token. No subscriptions, no commitments. View real-time pricing on the Models page.

Free Tier

$0

1,000 tokens/day
5 models
Community support

Pro

$0.002/1K tokens

Unlimited tokens
All 200+ models
Priority support
Usage analytics

Enterprise

Custom

Dedicated capacity
SLA guarantee
Custom models
Dedicated support

Billing

Billing is calculated per token with granular cost tracking per model. Set spending limits to control costs.