■ Docs

Quickstart.

Conduit exposes an OpenAI-compatible API, so any OpenAI SDK or tool works out of the box. Point it at our base URL and you're done.

Base URLhttps://api.conduit.enverth.ai/v1

1. Get an API key

Create an account in the Conduit console and generate a key under API keys. Store the key in an environment variable:

export CONDUIT_API_KEY="sk-conduit-..."

2. Install an SDK

Use the official OpenAI client libraries — no Conduit-specific SDK required.

pip install openai

3. Make your first request

Pass any model ID from the models page as the model parameter.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.conduit.enverth.ai/v1",
    api_key="CONDUIT_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Explain MoE in one sentence."}],
)

print(response.choices[0].message.content)

Streaming

Set stream: true to receive tokens as server-sent events as soon as they're generated.

stream = client.chat.completions.create(
    model="zai/glm-5.3-flash",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
    stream=True,
)

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

List models

Retrieve every model available to your key with GET /models.

curl https://api.conduit.enverth.ai/v1/models \
  -H "Authorization: Bearer $CONDUIT_API_KEY"

Next steps