What it is

A single OpenAI-compatible endpoint that fronts 500+ models from OpenAI, Anthropic, Google, Meta and dozens of inference hosts. It is a router, not a model provider — it resells other people's inference at list price and picks a backend by price, latency or uptime.

Why it earns a slot

One API key and one billing relationship for every model, so you can swap anthropic/claude-opus-5 for google/gemini-3.7-flash in a string and A/B the cost. Free models let you prototype at zero spend.

Know before you commit

Routing is opaque by default — the same model slug can land on providers with different quantization, context limits and data-retention policies. Pin providers explicitly for production.

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

No inference markup; 5.5% (min $0.80) fee on credit top-ups, 5% via crypto. BYOK 5% above a $25k/mo free allowance. Free models capped at 50 req/day, 1,000 with $10 credit.

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

Drop into your Lovable chat

Evaluate OpenRouter (https://openrouter.ai) for this project, then use it only if it fits what we are already building.
Context: Multi-provider LLM router. A single OpenAI-compatible endpoint that fronts 500+ models from OpenAI, Anthropic, Google, Meta and dozens of inference hosts. It is a router, not a model provider — it resells other people's inference at list price and picks a backend by price, latency or uptime.
Reviewer notes (general, not written for this codebase): One API key and one billing relationship for every model, so you can swap anthropic/claude-opus-5 for google/gemini-3.7-flash in a string and A/B the cost. Free models let you prototype at zero spend.
Watch out for: Routing is opaque by default — the same model slug can land on providers with different quantization, context limits and data-retention policies. Pin providers explicitly for production.
Pricing: No inference markup; 5.5% (min $0.80) fee on credit top-ups, 5% via crypto. BYOK 5% above a $25k/mo free allowance. Free models capped at 50 req/day, 1,000 with $10 credit.
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/openrouter

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