# Recraft V3 (Recraft) — API pricing and providers

> Image & vector generation. Model id `recraft/recraft-v3`. Image model by Recraft.

- Page: https://infro.io/models/recraft/recraft-v3
- Vendor: Recraft (https://infro.io/models/recraft)
- Modality: Image
- Endpoint through INFRO: `POST /v1/images/generations` at https://api.infro.io/v1
- List rate: $0.04 per image
- Rates checked: 2026-10-05

Rates are Recraft's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| OpenRouter | `recraft/recraft-v3` |
| fal.ai | `recraft-v3` |
| Replicate | `recraft-ai/recraft-v3` |

## Questions

### How much does the Recraft V3 API cost?

Recraft's published list rate for Recraft V3 is $0.04 per image (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Recraft V3?

In INFRO's provider registry, Recraft V3 can be served by OpenRouter, fal.ai and Replicate. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Recraft V3 model ID?

Request it from INFRO as "recraft/recraft-v3". INFRO sends each provider its own id: OpenRouter "recraft/recraft-v3", fal.ai "recraft-v3", Replicate "recraft-ai/recraft-v3".

### How do I call Recraft V3 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "recraft/recraft-v3" to POST /v1/images/generations. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Recraft V3 usage?

No. Recraft or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.