Build with anything.
Run on open standards.
OpenAI-compatible and Anthropic-compatible out of the box. Your SDKs, frameworks, IDE assistants, and coding agents keep working. Only the base URL changes.
Drop-in SDKs
Use the OpenAI or Anthropic SDK. Change the base URL and key.
Streaming everywhere
Server-sent events on every chat format, across providers.
Tool calling and JSON
Function calling, structured output, and reasoning controls.
Batch and files
Upload inputs and run large jobs asynchronously.
First call
in minutes.
- 01
Create an API key
Sign in to the platform, open API keys, and create one. Give it a spend limit if you like.
- 02
Change the base URL
Point the OpenAI or Anthropic SDK at https://api.aivene.com/v1 and pass your Aivene key.
- 03
Pick any model
Use any model id from the catalogue. Switching later is a one-line change.
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://api.aivene.com/v1',
apiKey: process.env.AIVENE_API_KEY,
})
const res = await client.chat.completions.create({
model: 'gpt-5-mini',
messages: [{ role: 'user', content: 'Hello' }],
})import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.aivene.com/v1",
api_key=os.environ["AIVENE_API_KEY"],
)
res = client.chat.completions.create(
model="claude-opus-4-8",
messages=[{"role": "user", "content": "Hello"}],
)curl https://api.aivene.com/v1/chat/completions \
-H "Authorization: Bearer $AIVENE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5-mini",
"messages": [{ "role": "user", "content": "Hello" }]
}'export ANTHROPIC_BASE_URL="https://api.aivene.com/v1"
export ANTHROPIC_AUTH_TOKEN="$AIVENE_API_KEY"
export ANTHROPIC_API_KEY=""
claudeEvery modality,
one base URL.
Text, images, video, audio, embeddings, batches, and tools all live under the same API and the same key.
| Endpoint | Use it for |
|---|---|
| POST /v1/chat/completions | Chat, tools, vision, structured output |
| POST /v1/responses | OpenAI Responses format |
| POST /v1/messages | Anthropic Messages format |
| POST /v1/embeddings | Vector embeddings for search and RAG |
| POST /v1/images | Image generation |
| POST /v1/videos | Video generation |
| POST /v1/audio/speech | Text to speech |
| POST /v1/audio/transcriptions | Speech to text |
| POST /v1/audio/translations | Speech to English text |
| POST /v1/batches | Asynchronous batch jobs |
| POST /v1/files | Upload files for batches and documents |
| POST /v1/tools/:id | Standalone tools like web_scrape |
| GET /v1/models | Every available model and its pricing |
Bring your
favorite agent.
Each integration has a one-click setup script in the platform that configures the environment for you.
Claude Code
Anthropic's terminal coding agent, running any Aivene model through the Messages API.
Codex
OpenAI's coding agent with sandboxed execution, pointed at Aivene instead of OpenAI.
OpenCode
Terminal-based AI coding with multi-model support, using one Aivene key for every model.
Hermes Agent
The autonomous coding agent from Nous Research, configured in one step.
OpenClaw
An AI agent for WhatsApp, Telegram, and email automation, backed by Aivene models.
Anything OpenAI-compatible
If a tool lets you set a base URL and key, it works with Aivene.
Try before
you code.
Every modality has a playground in the platform, billed at the same rates as the API.
Chat
Talk to any text model, with tools and file attachments.
Images
Generate and iterate on images across image models.
Speech
Turn text into speech and pick a voice.
Transcriptions
Upload audio and get text back.
Embeddings
Embed text and inspect the vectors.
Token counter
Count tokens before you send a prompt.
Questions from developers.
Design and manage
AI apps and agents.
Create, customize, and scale AI apps and agents on every major model. Get an API key and make your first call in minutes.
Pay as you go. No monthly minimum.

