Replicate through Squiid

What Replicate is

Replicate hosts open models as callable endpoints. Each model is packaged with Cog, given a versioned API and run on demand, so calling an image generator, an upscaler, a background remover or a fine-tuned LoRA is one HTTP request with a JSON body. Predictions can be synchronous or asynchronous with a webhook, and you can train fine-tunes on the platform and call the result at the same kind of URL. Cold starts depend on how often a model is used, so a popular model responds quickly while an obscure one may spend the first request loading weights.

This is the fastest route from an idea to a working media feature in an AI-coded app. Product photography cleanup, avatar generation, image to video, sticker packs, music stems and voice conversion all exist as models somebody has already published, and an agent can wire one in without knowing anything about GPUs. Because Replicate bills per second of compute rather than per output, cost depends on the model you chose and how long it runs. Most models return a URL to the generated file rather than raw bytes, which keeps the response small but means you should copy the asset into your own storage before the link expires.

Why connect it through Squiid

That per-second billing is easy to misjudge, especially when an agent is trying five models in an afternoon. Squiid meters Replicate against your prepaid credits at the provider's published rates and shows compute spend per model, so an expensive video model is obvious immediately. Calls go to https://api.squiid.io/v1/replicate/... with Authorization: Bearer $SQUIID_API_KEY, the official client libraries work by pointing their base URL at the gateway (gateway convention), and Squiid holds the upstream token so it never lands in a preview build. Everything settles on one monthly invoice.

• One account, one key, one bill, one dashboard. Replicate sits beside every other service your project uses, on the same invoice and the same credit balance.
• Key custody. Squiid holds the Replicate credentials. Your code carries SQUIID_API_KEY, so REPLICATE_API_TOKEN, REPLICATE_BASE_URL never land in a repository, a preview deployment or an agent’s context.
• Metering you can see. Every call is counted per service and per day, so you know what Replicate costs before the month ends.
• Pause on zero. When prepaid credits run out the gateway stops authorizing usage instead of running up a bill you did not fund.
• One rotation. Rotating the Squiid key cuts off every agent, worker and deployment at once, with no provider key to hunt down.

What you get

• Thousands of open image, video and audio models
• Fine-tuned model endpoints on the same key
• Webhook-based async predictions
• Per-second compute spend shown per model
• Replicate list pricing, no markup

How to connect Replicate

One variable replaces the provider credentials this service would normally need. Requests go to the gateway and the official SDKs work by pointing their base URL at it (gateway convention).

# .env
# replaces REPLICATE_API_TOKEN, REPLICATE_BASE_URL
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx

# every request: https://api.squiid.io/v1/replicate/...
# header:       Authorization: Bearer $SQUIID_API_KEY

Pricing through Squiid

Replicate charges per second of GPU or CPU time used by a prediction, at rates that vary by hardware, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of Replicate usage, with no markup and no per-request margin.

Replicate has no subscription attached on Squiid today. If a plan is required for a feature you need, it passes through at the provider’s listed price with no Squiid fee.

Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less. Credits are prepaid, so Replicate usage stops when the balance reaches zero rather than producing an invoice you did not fund. Auto top-up with a cap keeps production running without handing anyone an open-ended card.

If you leave

Nothing to move: Replicate is usage-metered, so leaving means creating your own Replicate key and pointing the client at it. Squiid never owns your code, your schema or your domain, and the gateway speaks Replicate's own API, so the client change is a base URL. The handover page lists what happens for every provider in the catalogue.

Works with every coding agent

Replicate through Squiid is just an HTTP call with a bearer token, so every agentic coding tool can use it with the single key already in your environment:

• Claude Code
• Cursor
• ChatGPT
• Codex
• Grok
• Gemini CLI
• GitHub Copilot
• Windsurf
• Perplexity
• Devin
• Replit
• v0
• Lovable
• Cline

Vibe coding a feature on Replicate usually means asking for it in plain language and letting the agent write the integration. Because the key is Squiid’s rather than the provider’s, it can do that without ever holding a credential that could be leaked, logged or committed.