1vy — One Key, Every Model · AI API Gateway
Access 100+ AI models with a single API key. OpenAI GPT-4o, GPT-5, Anthropic Claude (Opus 4.7, Sonnet 4.6, Haiku 4.5), Google Gemini 3 / 2.5, DeepSeek V3, Alibaba Qwen, Meta Llama, xAI Grok, and more — all through one OpenAI-compatible endpoint. Pay per token, no subscriptions, flat 15% markup over upstream list prices, $1 free credit on signup.
Why developers choose 1vy
- One key, every model — no separate accounts for OpenAI, Anthropic, Google, DeepSeek, Qwen, xAI, Mistral, or Meta. Sign up once, get them all.
- OpenAI SDK drop-in compatibility — change
base_urltohttps://api.1vy.ai/v1in any OpenAI client (Python, Node.js, Go, Rust, etc.) and your existing code works without changes. - Transparent pricing — flat 15% markup over upstream list prices, no hidden fees. Full per-model price catalog published at /models.
- Pay per token — no subscription, no monthly minimum, no seat fees. Balance never expires. Top up any amount, use it forever.
- Streaming + tool calling + reasoning effort — full OpenAI-compatible feature parity including SSE streaming, function calling, vision input, and reasoning_effort control for o-series and GPT-5 thinking models.
- Multi-provider failover — 1vy automatically retries on upstream errors and routes to backup providers, so single-provider outages don't break your app.
Featured models
- Claude Opus 4.7 — Anthropic, $5.75 in / $28.75 out per 1M tokens
- GPT-5 — OpenAI, $1.44 in / $11.50 out per 1M tokens
- Gemini 3 Pro — Google, $2.88 in / $11.50 out per 1M tokens
- Claude Sonnet 4.6 — Anthropic, $3.45 in / $17.25 out per 1M tokens
- GPT-4o — OpenAI, $2.88 in / $11.50 out per 1M tokens
- DeepSeek V3 — DeepSeek, $0.322 in / $0.483 out per 1M tokens
- Kimi K2 — Moonshot, $0.6394 in / $2.56 out per 1M tokens
- Qwen3 Max — Alibaba, $1.84 in / $7.36 out per 1M tokens
See the full model catalog for prices on all 100+ supported models including Llama 4, Grok 4, Mistral Large, Cohere Command R+, and many more.
Quick start
Sign up at 1vy.ai/register for $1 free credit. Generate an API key in your dashboard, then call any supported model with the OpenAI SDK:
from openai import OpenAI
client = OpenAI(base_url="https://api.1vy.ai/v1", api_key="sk-1vy-...")
resp = client.chat.completions.create(
model="claude-opus-4-7",
messages=[{"role": "user", "content": "Hello"}],
)Common questions
Is 1vy compatible with my existing OpenAI code?
Yes. 1vy exposes a fully OpenAI-compatible /v1/chat/completions endpoint. Use the official OpenAI SDK in any language — Python, Node.js, Go, Java, Rust, Ruby, PHP — and only change the base_url and API key. Your prompts, function definitions, streaming code, and response handling all work unchanged.
How is 1vy different from OpenRouter?
Both 1vy and OpenRouter aggregate AI models behind one OpenAI-compatible API. 1vy applies a transparent flat 15% markup over upstream list prices, prioritizes first-party access to major providers, and offers $1 free starter credit. See the full side-by-side comparison.
Which models does 1vy support?
OpenAI (GPT-4o, GPT-5, o1, o3, o4-mini), Anthropic Claude (Opus 4.7/4.6, Sonnet 4.6, Haiku 4.5), Google Gemini (3 Pro/Flash, 2.5 Pro/Flash), DeepSeek (V3, R1), Alibaba Qwen (Max, Plus, Turbo, 3-Max), Moonshot Kimi (K2, K2.5), xAI Grok, Meta Llama, Mistral, and more. Full list at /models.