API

Base URL and authentication

POST https://api.costplusiq.com/v1/chat/completions
Authorization: Bearer $COSTPLUSIQ_API_KEY
Content-Type: application/json

Keys are issued per caller, so one can be rotated without disturbing anyone else. GET /models and GET /health are public; everything else needs the bearer token.

Video input

Pass a video_url content part — either an https URL we fetch, or the clip inlined as a data: URL. The clip is decoded at the model's native 2 fps across its whole duration, so prompt tokens scale with length (~64 tokens per second of 360p video, ~38,000 for a 10-minute clip).

curl https://api.costplusiq.com/v1/chat/completions \
  -H "Authorization: Bearer $COSTPLUSIQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3.6-27B",
    "stream": true,
    "messages": [{"role": "user", "content": [
      {"type": "video_url", "video_url": {"url": "https://example.com/clip.mp4"}},
      {"type": "text", "text": "Describe every step the operator performs."}
    ]}]
  }'

The same call from the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(base_url="https://api.costplusiq.com/v1",
                api_key=os.environ["COSTPLUSIQ_API_KEY"])

stream = client.chat.completions.create(
    model="Qwen/Qwen3.6-27B", stream=True,
    messages=[{"role": "user", "content": [
        {"type": "video_url", "video_url": {"url": clip_url}},
        {"type": "text", "text": "Describe every step the operator performs."},
    ]}])
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Streaming, and the silence before the first token

Long video is prefill-dominated: on a 10-minute clip the first output token can be tens of seconds away, and until then a normal SSE connection carries nothing at all. Intermediaries drop connections that look idle, so we send SSE comment frames while the prefill runs:

: keep-alive

: keep-alive

data: {"id":"chatcmpl-…","choices":[{"delta":{"content":"The operator"}}]}

If the upstream fails after a stream has started, the error arrives as an SSE frame — data: {"error":{"code":502,…}} followed by data: [DONE] — because the HTTP status was already sent.

Limits

What happens when we are full

We refuse rather than queue. A request that arrives with every slot busy gets 429 with Retry-After immediately, instead of sitting in a queue and returning slowly. A queue would flatter our error rate and wreck the latency you actually experience, and latency is the thing worth optimising for.

Capacity is judged by what the GPUs report running, not by what we happen to have dispatched — so a busy box is never sold as an idle one.

Errors use the OpenAI shape: {"error":{"type":…,"message":…}}.

Zero data retention

Prompts, media and completions are processed in memory and never persisted, never logged, and never trained on. What we keep is the metadata a bill is made of: which key called, when, the model, the status, and token counts.

• The gateway logs no request or response bodies, and its access log is off — a URL query string is caller-controlled, so it is not recorded either.
• The inference engine runs with request and output logging explicitly disabled, rather than relying on its defaults staying that way.
• Nothing on the serving path writes to any datastore.

Discovery endpoints