Three wire formats
/v1/chat/completions, /v1/responses and /v1/messages. Use the SDK you already have.
Pay per token · no minimums
The model behind the Excession agent, for your own tools and pipelines. Drop-in for OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, with one key and one balance.
curl https://api.excessionlabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EXCESSION_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "excession-1",
"messages": [{"role": "user",
"content": "Review this nginx config for SSRF paths."}]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.excessionlabs.ai/v1",
api_key=os.environ["EXCESSION_API_KEY"],
)
r = client.chat.completions.create(
model="excession-1",
messages=[{"role": "user", "content": "Triage this crash log."}],
)
print(r.choices[0].message.content)
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.excessionlabs.ai",
apiKey: process.env.EXCESSION_API_KEY,
});
const msg = await client.messages.create({
model: "excession-1",
max_tokens: 2048,
messages: [{ role: "user", content: "Explain this decompiled function." }],
});
/v1/chat/completions, /v1/responses and /v1/messages. Use the SDK you already have.
Server-sent events, parallel tool calls, JSON output and images, in every format.
Whole repositories, long captures and large disassembly in one request.
The same model the Excession agent runs on, for recon, audit, exploit development and analysis.
Every response carries a request id and its cost. Per-request history in your dashboard.
The API and the agent share one key system and one credit balance. Plans and top-ups cover both.
Verify your email, add a card for a $0 check, and accept the Acceptable Use Policy. Most people are approved on the spot.