Rate limits
Rate limits apply per API key — RPM and concurrency — not to your total token volume.
Per-key limits
| Limit | Value |
|---|---|
| Requests per minute | 100 rpm |
| Concurrency | 5 concurrent requests |
| Tokens per minute | 2M tpm (language models) |
Embedding and speech models have their own request limits. See Models.
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:
| Plan | Monthly quota |
|---|---|
| Starter | 2.5B tokens |
| Growth | 7.5B tokens |
| Scale | 20B tokens |
| Enterprise | Custom |
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.