AI

One SDK, one key, every model. Usually cheaper than running the same open models elsewhere.

Pricing: Model prices pass through; OpenRouter adds 5.5% on credit purchases. Example: DeepSeek V4 Pro at $0.66 / $1.98 per million tokens vs $1.32 / $3.96 on Cloudflare Workers AI. The Business plan's fee is 8%. Bring your own provider key (BYOK): the first $25,000 of list-price usage a month carries no fee, then 5%.

Embeddings next to the data they describe, for when a user is waiting for the answer.

Pricing: Mostly the storage on a Postgres you already pay for: about $5 a month for 1M vectors on an existing Neon database.

Vectors at S3 prices, for huge, cold or per-client collections where 100 ms is fine.

Pricing: Sydney storage $0.066/GB-month; about $2.50 a month for 1M vectors, $15–154 for 10M, $76–473 for 100M (vs $2,000–12,000 to hold 100M in Postgres). No servers to size.

Where an AI product runs code nobody reviewed: an isolated container per session, started and driven from a Worker, billed only for the CPU it actually uses.

Pricing: On Workers Paid ($5 a month): active CPU at $0.000020 per vCPU-second, with 375 vCPU-minutes, 25 GiB-hours of memory and 200 GB-hours of disk included each month. Egress from Oceania $0.05/GB after 500 GB.

Give agents safe, scoped access to client systems. I've started hosting my own.

Pricing: The protocol is free. You pay for whatever hosts the server: a Worker or a Lambda function, like any other small API.

Free caching, rate limits, spend caps and model fallback in front of OpenRouter. Works even from Lambda.

Pricing: Core features free (analytics, caching, rate limiting). Logs: 20M events a month included on Workers Paid, then $0.60 per million, for accounts whose first gateway dates from 24 September 2026 or later; older accounts keep 10M stored logs per gateway (pricing changes 1 December 2026). Unified Billing credits carry a 5% fee; your own provider keys carry none.

Too expensive for production features in client systems. OpenAI models give better cost per intelligence.

Pricing: Per million tokens: Haiku 5.5 $0.10 / $0.50 (prompts up to 100,000 tokens; $0.50 / $2.50 above), Sonnet 5.5 $2 / $10, Opus 5.5 $4 / $20. The Batch API halves those, and cache reads cost 0.05x the input price on Sonnet and Opus 5.5. On Amazon Bedrock, the Australian (AU) regional endpoint adds 10% over global routing.

Instead: OpenRouter, picking the model by cost per intelligence.

Many of the same open models cost up to twice as much as on OpenRouter, and the newest frontier models are capped at 20 requests a minute.

Pricing: $0.011 per 1,000 neurons, with 10,000 neurons a day free. DeepSeek V4 Pro: $1.32 / $3.96 per million tokens vs $0.66 / $1.98 on OpenRouter; DeepSeek V4.1 Flash (1017) costs the same on both, $0.30 / $1.20. Embeddings from $0.012 per million tokens (bge-m3); Whisper $0.0005 per audio minute.

Instead: OpenRouter: the same open models, often for half the price, and far more of them.