Why use a unified AI API
One API for any model
Reach every major model through a single endpoint. The OpenAI, Anthropic and Gemini SDKs all work unchanged — point the base URL at Oxyy and keep your existing code.
Read the docsHigher availability
Requests route across multiple upstream providers. When one degrades or rate-limits you, traffic fails over automatically instead of erroring back to your users.
View statusPrice and performance
Each request goes to a healthy provider in the order set for that model, and fails over automatically when one degrades. You pay the model’s listed price whichever provider serves it, with no fallback list to maintain.
See pricingUsage-based, no lock-in
Pay for the tokens you use. Tiers unlock higher rate limits automatically as you top up — no seats, no monthly minimum, no contract.
Compare tiersAI providers
Every model below is reachable through one Oxyy key. Browse a provider to compare its models and prices.
Get started in three steps
- 1
Create an account
Sign up with email, Google or GitHub. A free starting balance is applied automatically.
- 2
Add funds
Top up once. Your balance works with every model and provider, and never expires.
- 3
Get your API key
Generate a key and send your first request. Fully OpenAI-compatible.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.oxyy.ai/v1",
api_key=os.environ["OXYY_API_KEY"],
)
response = client.chat.completions.create(
model="claude-opus-5",
messages=[
{"role": "user", "content": "Explain unified AI APIs in one sentence."},
],
)
print(response.choices[0].message.content)Model Pricing
Compare context windows and per-million-token pricing
| Model | Provider | Context | Standard price / 1M | Our price / 1M | You save | ||
|---|---|---|---|---|---|---|---|
| Input | Output | Input | Output | ||||
| GPT-5.5gpt-5.5 | OpenAI | 1050K | $5.00 | $30.00 | $2.00 | $12.00 | 60% |
| Claude Opus 5claude-opus-5 | Anthropic | 1000K | $5.00 | $25.00 | $2.00 | $10.00 | 60% |
| Gemini 3.8 Flashgemini-3.8-flash | 1049K | $0.750 | $3.75 | $0.300 | $1.50 | 60% | |
| Grok 4.6grok-4.6 | xAI | 500K | $2.00 | $6.00 | $0.800 | $2.40 | 60% |
| DeepSeek-V4-Pro-0813deepseek-v4-pro | DeepSeek | 1000K | $0.660 | $1.98 | $0.264 | $0.792 | 60% |
| GLM-5.3glm-5.3 | Z.ai | 1049K | $1.40 | $4.40 | $0.560 | $1.76 | 60% |
| GPT-5.4 minigpt-5.4-mini | OpenAI | 400K | $0.750 | $4.50 | $0.300 | $1.80 | 60% |
| Claude Sonnet 5claude-sonnet-5 | Anthropic | 1000K | $2.00 | $10.00 | $0.800 | $4.00 | 60% |
| Gemini 3.6 Flashgemini-3.6-flash | 1049K | $0.750 | $3.75 | $0.300 | $1.50 | 60% | |
| Grok 4.5grok-4.5 | xAI | 500K | $2.00 | $6.00 | $0.800 | $2.40 | 60% |
Recent Blog Posts
Guides and notes from the team building Oxyy
Perplexity Sonar & FLUX 3 API Pricing 2026: Per-Search & Per-Image
October 21, 202611 min readRead
Gemini & Claude API Rate Limits 2026: Fix 429 Errors (RPM/TPM)
October 21, 202611 min readRead
Claude Opus 5.5 & Sonnet 5.5 API Pricing 2026 (+ Save 60%)
October 21, 20269 min readRead
Fish Audio vs ElevenLabs API (2026): Latency, Quality & Cost
October 21, 20269 min readRead
OpenRouter vs LiteLLM vs Oxyy (2026): Managed API vs Self-Hosted
October 21, 20269 min readReadStart building in minutes
A free starting balance on signup. No card required to try it.