# Hugging Face

Rate-limited free · API key · code · last checked 30 Aug 2026

Create a key at https://huggingface.co/docs/inference-providers and call it from your harness.

Two products: Serverless API (free, rate-limited) and Inference Providers gateway. Cold starts 10-30s on unpopular models. Limits not published as fixed numbers.

Source: https://huggingface.co/docs/inference-providers/index

| Model | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Llama 3.2 8B (Serverless) | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-08-30 |
| Qwen 2.5 7B (Serverless) | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-08-30 |
| Mistral 7B (Serverless) | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-08-30 |
| Inference Providers gateway (15+ partners) | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-08-30 |

Machine-readable: /data/hugging-face.json

Numbers cross-checked against official docs and third-party trackers as of 2026-08-30. Limits change without notice — this is a map, not a contract.