---
id: "recraft/recraft-v3"
also: ["recraft/recraft-v3-20260413", "vercel/recraft/recraft-v3"]
card_usd_per_m: "0.0 in, 0.0 out, at recraft"
context: 65536
max_output: 58982
input: ["text", "image"]
output: ["image"]
released: "2026-05-07"
api: ["/api/v1/images"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 0
retains_prompts: 1
---
# Recraft: Recraft V3

V3 introduced major advances in photorealism and text rendering. It was the first Recraft model to generate mid-size text accurately and, as of 2025, is the only model capable of placing text at specific positions in an image.