Hugging Face Inference Providers pricing
One OpenAI-compatible router on the Hugging Face Hub that forwards requests to partner hosts at their own prices, with no markup.
Go to Hugging Face Inference Providers Compare with DeepInfra, CoreWeave, OpenRouter Request a quote
Every field, sourced
Marker opens the source- Status Whether the provider's public inference API is live.
- Active 1
- Hardware Chips that serve requests: GPUs, the vendor's own custom silicon, or both.
- Not published
- Hardware detail Published chip types (e.g. LPU, wafer-scale engine, RDU, NVIDIA H100/B200).
- None of its own; routes to partner providers 1
- OpenAI API Accepts OpenAI Chat Completions-style requests, per vendor docs.
- Yes 2
- Serverless Pay-per-use API billed per token or per second, with no GPU to manage.
- Yes 2
- Dedicated Single-tenant deployments or reserved capacity.
- Yes 2
- Fine-tuning Hosted fine-tuning or LoRA adapters offered.
- Not published
- Models (published) models Model count as published or counted from the official model list on the verified date.
- 126 1
- Flagship models Notable models served, from the official list.
- gpt-oss-120b, Llama 3.3 70B Instruct, DeepSeek, Qwen, GLM 1
- Serves gpt-oss-120b Offers the reference model gpt-oss-120b pay-per-token.
- Yes 1
- gpt-oss-120b in $/1M tok Standard serverless input price for the reference model gpt-oss-120b, per 1M tokens.
- $0.037 1
- gpt-oss-120b out $/1M tok Standard serverless output price for the reference model gpt-oss-120b, per 1M tokens.
- $0.17 1
- Llama 3.3 70B in $/1M tok Secondary reference: Llama 3.3 70B Instruct input price per 1M tokens, where still listed.
- $0.135 1
- Llama 3.3 70B out $/1M tok Secondary reference: Llama 3.3 70B Instruct output price per 1M tokens, where still listed.
- $0.40 1
- Vendor speed tok/s Vendor-stated output speed on gpt-oss-120b, linked to the vendor’s own page.
- Not published
- Speed source Who published the speed figure and when.
- Not published
- Dedicated H100 $/GPU-hr On-demand price of one H100 for dedicated deployments.
- Not published
- Regions Published serving or data regions.
- Not published
- SOC 2 SOC 2 status as stated by the vendor.
- Type 2 3
- HIPAA Vendor states HIPAA support or offers a BAA.
- Yes 4
- ZDR Zero data retention: the vendor states prompts and outputs are not stored, by default or as a setting.
- Yes 3
- Free tier Free credits or free rate-limited access, as published.
- $2.00 monthly credits on PRO and per Team/Enterprise seat; Free accounts buy credits 2
Pricing detail
Cheapest gpt-oss-120b host on the router: DeepInfra $0.037 in / $0.17 out (also Novita $0.05 / $0.25, OVHcloud $0.09 / $0.47, Baseten $0.10 / $0.50). Llama 3.3 70B from $0.135 / $0.40 (Novita). Provider rates passed through with no Hugging Face fee. Request and response bodies not stored; debug logs kept up to 30 days. Dedicated = Inference Endpoints. BAA through the Enterprise plan.
Sources
- Hugging Face router model list accessed 2026-11-09
- Inference Providers pricing and billing accessed 2026-11-09
- Inference Providers security accessed 2026-11-09
- Hub security accessed 2026-11-09
Get dedicated or volume pricing from Hugging Face Inference Providers and similar providers
Tell us what you need once. We send it to matching providers and they reply to you directly.