Fireworks AI

Open-model inference host

Free tier + paidModel APIs, routers & observabilityfireworks.ai

What it is

A speed-focused inference host for open-weight models, offering serverless token endpoints, per-second on-demand GPU deployments and managed fine-tuning. It competes with Together and Groq on throughput and cold-start behaviour rather than on proprietary models.

Why it earns a slot

Good when you need a specific open model served reliably with tunable speed and price tiers, or want LoRA fine-tunes deployed without managing GPUs. Serverless has no cold starts, which suits bursty consumer traffic.

Know before you commit

Only $1 in free credit, on-demand GPU rates are scheduled to rise on 1 September, and region-restricted deployments carry a 1.5x premium. Dedicated deployments bill while idle.

Getting started

pip install fireworks-ai

Field notes

0 from the community

Loading notes…

Field check

Unverified

Pricing snapshot

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.

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

Drop into your Lovable chat

Evaluate Fireworks AI (https://fireworks.ai) for this project, then use it only if it fits what we are already building.
Context: Open-model inference host. A speed-focused inference host for open-weight models, offering serverless token endpoints, per-second on-demand GPU deployments and managed fine-tuning. It competes with Together and Groq on throughput and cold-start behaviour rather than on proprietary models.
Reviewer notes (general, not written for this codebase): Good when you need a specific open model served reliably with tunable speed and price tiers, or want LoRA fine-tunes deployed without managing GPUs. Serverless has no cold starts, which suits bursty consumer traffic.
Watch out for: Only $1 in free credit, on-demand GPU rates are scheduled to rise on 1 September, and region-restricted deployments carry a 1.5x premium. Dedicated deployments bill while idle.
Pricing: 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.
Setup: pip install fireworks-ai
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/fireworks-ai

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

Google AI Studio / Gemini API

ai.google.dev

Model provider API with free tier

Free tier + paidModel APIs, routers & observability

Free tier in AI Studio with rate limits. Paid: Gemini 3.7 Flash $0.75/$3.75 per M in/out; Gemini 3.5 Flash-Lite $0.30/$2.50; Gemini 2.5 Pro $1.25/$10.

Open dossier