Hugging Face Inference Providers

Inference provider router

Free tier + paidModel APIs, routers & observabilityhuggingface.co

What it is

A routing layer on the Hugging Face Hub that fans a single API out to 18+ inference providers including Groq, Together, Fireworks, Replicate, Cerebras and fal. It covers chat, vision, embeddings, image, video and speech, with :fastest and :cheapest routing suffixes.

Why it earns a slot

You are already browsing models on the Hub, so calling one is a token away — no separate signup per provider. The :cheapest suffix auto-picks the lowest-cost host for the same open weights.

Know before you commit

The free monthly credit is only $0.10 — enough for a handful of calls, not a demo. Provider capability varies, so a model may support tool calling on one backend and not another.

Getting started

pip install huggingface_hub

Field notes

0 from the community

Loading notes…

Field check

Unverified

Pricing snapshot

Pass-through provider rates with no HF markup. Monthly credits: free accounts $0.10, PRO $2, Team and Enterprise $2 per seat, then pay-as-you-go. Bringing your own provider key bills that provider directly.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Hugging Face Inference Providers (https://huggingface.co/docs/inference-providers) for this project, then use it only if it fits what we are already building.
Context: Inference provider router. A routing layer on the Hugging Face Hub that fans a single API out to 18+ inference providers including Groq, Together, Fireworks, Replicate, Cerebras and fal. It covers chat, vision, embeddings, image, video and speech, with :fastest and :cheapest routing suffixes.
Reviewer notes (general, not written for this codebase): You are already browsing models on the Hub, so calling one is a token away — no separate signup per provider. The :cheapest suffix auto-picks the lowest-cost host for the same open weights.
Watch out for: The free monthly credit is only $0.10 — enough for a handful of calls, not a demo. Provider capability varies, so a model may support tool calling on one backend and not another.
Pricing: Pass-through provider rates with no HF markup. Monthly credits: free accounts $0.10, PRO $2, Team and Enterprise $2 per seat, then pay-as-you-go. Bringing your own provider key bills that provider directly.
Setup: pip install huggingface_hub
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/hugging-face-inference-providers

Neighbourhood

How Hugging Face Inference Providers sits against the rest of the atlas — swaps, companions and the tools builders actually save alongside it.

Instead of thisVercel AI SDK Anthropic API / Claude Platform Braintrust Fal.ai Fireworks AI Google AI Studio / Gemini API Groq Helicone LangChain

Named in the wiringReplicate

Also in Model APIs, routers & observability

Anthropic API / Claude Platform

platform.claude.com

Frontier model provider API

PaidModel APIs, routers & observability

Per token. Opus 5 $5/$25 per M in/out; Sonnet 5 $2/$10; Haiku 4.5 $1/$5; Fable 5 and Mythos 5 $10/$50. Batch API 50% off; cache reads 0.1x input.

Open dossier

Braintrust

braintrust.dev

LLM eval and experiment platform

Free tier + paidModel APIs, routers & observability

Starter free ($10/mo model credits, 1GB data, 10k scores, 14-day retention), Pro $249/mo ($249 credits, 5GB, 50k scores), Enterprise custom. Overage $3-4/GB and $1.50-$2.50 per 1k scores.

Open dossier

Fal.ai

fal.ai

Generative media inference host

PaidModel APIs, routers & observability

Per output or per second for media models: images ~$0.02-$0.04 at 1MP, video $0.05-$0.40 per second. Serverless GPU rates $1.10-$8.50/hr with committed-use discounts.

Open dossier

Fireworks AI

fireworks.ai

Open-model inference host

Free tier + paidModel APIs, routers & observability

Per token serverless across Standard/Priority/Fast tiers; embeddings $0.008-$0.10/M. On-demand GPUs billed per second: H100/H200 ~$7-8/hr, B200 ~$10-13/hr. Fine-tuning $0.50-$40 per M training tokens. $1 free credit.

Open dossier