OpenRouter

ship

One API for every major model — unified billing, fallbacks and routing.

journal entry · observed by @whysanesanders · verified 2026-08-15

The single most useful piece of AI infra for small teams: swap models by changing a string, compare costs on one bill, get automatic fallbacks. The model-agnostic insurance policy.

Known limitations

Small markup over direct API pricing.
Adds a network hop and latency.
Provider-specific features arrive later than direct APIs.

Facts

pricing: freemium
price note: pay-per-token pass-through plus a small fee
free tier: yes
open source: no
api: yes
self-host: no
category: dev-infra

Models used

gpt-5 claude-sonnet-4-5 gemini-2-5-pro deepseek-v3 qwen3 llama-4 mistral-large grok-4

Receipts

openrouter.ai

Edit this page on GitHub

Same sector — dev-infra

Fireworks AI

Fast inference platform for open models — serverless and on-demand GPUs.

dev-infra

freemium · free credits; pay-per-token from ~$0.10/1M (small models)

APIFREE TIER

situationalverified 2026-08-15

Groq

Ultra-fast inference on custom LPU hardware — open models at 500+ tok/s.

dev-infra

freemium · free tier; from $0.05/1M tokens (small models)

APIFREE TIER

shipverified 2026-08-15

Hugging Face

The GitHub of AI — models, datasets, Spaces and inference endpoints.

dev-infra

freemium · free; PRO $9/mo; inference pay-as-you-go

APIFREE TIER

shipverified 2026-08-15