Hugging Face Inference Endpoints Pricing
Every Hugging Face Inference Endpoints plan with its monthly and annual price, what it costs for common team sizes, and a calculator to estimate your own monthly cost before you buy.
Compare Hugging Face Inference Endpoints alternatives by priceRead our Hugging Face Inference Endpoints reviewCompare AI Software pricing
Plans and prices
| Plan | Monthly billing | Annual billing (per month) | Per user or flat | Users | Free tier |
|---|---|---|---|---|---|
| PRO | $9/mo | Not listed | Flat | 1 users | No |
| Enterprise | $50/user/mo | Not listed | Per user | No limit listed | No |
| Pay-as-you-go compute | Contact sales | Contact sales | — | No limit listed | No |
| Team | $20/user/mo | Not listed | Per user | No limit listed | No |
Prices last updated November 2026.
What each Hugging Face Inference Endpoints plan includes
PRO
- 8x ZeroGPU quota
- Personal account
- More private storage
- $2 of monthly inference credits
Enterprise
- GDPR DPA
- Dedicated support
- Everything in Team
- Contract invoicing and prepaid credits
Pay-as-you-go compute
- A100 at $2.50 per hour
- B200 at $9.25 per hour
- H100 at $4.50 per hour
- NVIDIA T4 at $0.50 per hour
- CPU from about $0.03 per hour
- Billed per instance hour while the endpoint runs
Team
- SSO
- Audit logs
- Resource groups
- Higher GPU quotas
What Hugging Face Inference Endpoints costs by team size
| Team size | 1 user | 5 users | 10 users | 25 users | 50 users |
|---|---|---|---|---|---|
| Monthly cost | $9/moPRO | $250/moEnterprise | $500/moEnterprise | $1,250/moEnterprise | $2,500/moEnterprise |
The plan that fits each team size, billed monthly, before add-ons and usage charges.
Usage pricing
| Metric | Plan | Included per month | Price after that |
|---|---|---|---|
| 1 vCPU CPU instance | All plans | None | $0.03 per hour |
| NVIDIA A100 GPU instance | All plans | None | $2.50 per hour |
| NVIDIA B200 GPU instance | All plans | None | $9.25 per hour |
| NVIDIA H100 GPU instance | All plans | None | $4.50 per hour |
| NVIDIA T4 GPU instance | All plans | None | $0.50 per hour |
Hugging Face Inference Endpoints Pricing Calculator
Estimate your team's real monthly and annual cost based on seats, billing cycle, and add-ons.
Cost breakdown
Estimated from the vendor's published prices, last updated November 2026. Actual costs may vary based on negotiated contracts. How we collect prices
Ready to try Hugging Face Inference Endpoints?
Use this estimate to align with your team, then start a trial or subscription.
Visit Hugging Face Inference EndpointsBetter value alternatives
See what similar tools would cost for the same team size.
Hugging Face Inference Endpoints pricing FAQs
No, Hugging Face Inference Endpoints does not list a free plan. Its cheapest paid plan is PRO, at $9/mo billed monthly.
Hugging Face Inference Endpoints lists 4 plans. The cheapest paid plan is PRO, at $9/mo billed monthly.
Hugging Face Inference Endpoints's PRO plan, at $9/mo billed monthly, includes 8x ZeroGPU quota, Personal account, More private storage and $2 of monthly inference credits.
Hugging Face Inference Endpoints costs about $500/mo for 10 users on its Enterprise plan, billed monthly, before add-ons and usage charges.
Partly. Enterprise and Team charge per user. PRO charges a flat monthly price.
Yes. Hugging Face Inference Endpoints charges by usage for 1 vCPU CPU instance, NVIDIA A100 GPU instance, NVIDIA B200 GPU instance and 2 more, past what the plan includes.