Rate limits

Rate limits apply per API key — RPM and concurrency — not to your total token volume.

Per-key limits

Embedding and speech models have their own request limits. See Models.

Web search

The web search tool (/v1/search) has its own limits, separate from your chat token budget:

Exceed any of these and the endpoint returns 429 with a Retry-After header. Repeated identical queries within ~15 minutes are served from cache and don’t hit an upstream provider, but still count against your rate and daily quota. See the API Reference for the full request and response shape.

Monthly volume

Efficient open models are unlimited on every plan — the largest frontier-class models count against a monthly quota that scales with your plan:

If you exceed your quota, we contact you before charging for the overage. See Pricing for the full breakdown.

Handling 429

When you exceed a limit, the API returns 429 Too Many Requests. Back off and retry. Most OpenAI SDKs already do this for you with exponential backoff — the Retry-After header tells you how long to wait.

# the OpenAI SDK retries 429s automatically — tune the count if needed
client = OpenAI(
    base_url="https://api.helmcode.com/v1",
    api_key="sk-your-key-here",
    max_retries=5,
)

Need higher limits?

High-demand workloads can get higher RPM and pooled concurrency on request. Dedicated and Enterprise plans also run on hardware reserved for you, with guaranteed throughput. Talk to us.