RivenGet started

Search docs

Find a page across the Riven documentation

Quickstart

Copy-paste working code. Set a key, pick a base URL, and send a request — in curl, Python, or JavaScript.

Set your key#

shell
export RIVEN_API_KEY="rvn_..."
export RIVEN_BASE_URL="https://api.rivenai.io/v1"

Need a key? Getting started walks through it, or mint one programmatically per Authentication & keys.

Chat completion#

curl
curl https://api.rivenai.io/v1/chat/completions \
  -H "Authorization: Bearer $RIVEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "riven-best", "messages": [{"role": "user", "content": "Hello"}]}'
python
from openai import OpenAI

client = OpenAI(base_url="https://api.rivenai.io/v1", api_key=os.environ["RIVEN_API_KEY"])

resp = client.chat.completions.create(
    model="riven-best",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.rivenai.io/v1",
  apiKey: process.env.RIVEN_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "riven-best",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Streaming#

python
stream = client.chat.completions.create(
    model="riven-core",
    messages=[{"role": "user", "content": "Count to five."}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Embeddings#

curl
curl https://api.rivenai.io/v1/embeddings \
  -H "Authorization: Bearer $RIVEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "riven-embed", "input": ["first text", "second text"]}'

Vectors are 768-dimensional. input accepts a string or an array of strings.

Check your quota#

curl
curl https://api.rivenai.io/billing/quota -H "Authorization: Bearer $RIVEN_API_KEY"

Every response carries an x-riven-upstream header naming the pool that served it. An onprem- prefix means the request never left Riven infrastructure — see the on-prem fleet.