Every active model, one transparent rate.

ByteDance: Seedance 1.5 Pro on DeepInfra.

Black Forest Labs: FLUX 2 Klein 4b on DeepInfra.

Wan2.2 T2V A14B on DeepInfra.

Black Forest Labs: FLUX 1 Redux Dev on DeepInfra.

Black Forest Labs: FLUX 2 Dev on DeepInfra.

Qwen3 TTS VoiceDesign on DeepInfra.

Qwen3 TTS on DeepInfra.

Bria: Fibo on DeepInfra.

Qwen Image Max on DeepInfra.

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Pixverse 6 T2V on DeepInfra.

Inworld Ai: Realtime Tts 1.5 Max on DeepInfra.

Bria 3.2 on DeepInfra.

Black Forest Labs: FLUX 1 Schnell on DeepInfra.

Pixverse T2V HD on DeepInfra.

XiaomiMiMo: MiMo V2.5 Tts on DeepInfra.

Wan2.6 T2V on DeepInfra.

Qwen Image Edit on DeepInfra.

Bosonai: HiggsAudioV2.5 on DeepInfra.

Black Forest Labs: FLUX 1 Dev on DeepInfra.

Wan2.6 T2I on DeepInfra.

Inworld Ai: Realtime Tts 1.5 Mini on DeepInfra.

XiaomiMiMo: MiMo V2.5 Tts Voicedesign on DeepInfra.

Bria 3.2 Vector on DeepInfra.

Google: Nano Banana 2 on DeepInfra.

ResembleAI: Chatterbox Turbo on DeepInfra.

Stabilityai: Sdxl Turbo on DeepInfra.

Black Forest Labs: FLUX 1.1 Pro on DeepInfra.

Google: Nano Banana Pro on DeepInfra.

Inworld Ai: Realtime Tts 2 on DeepInfra.

Black Forest Labs: FLUX 2 Max on DeepInfra.

Black Forest Labs: FLUX 2 Klein 9b on DeepInfra.

Black Forest Labs: FLUX 2 Pro on DeepInfra.

Pixverse T2V on DeepInfra.

Sesame: Csm 1b on DeepInfra.

Black Forest Labs: FLUX.1 Kontext Dev on DeepInfra.

ByteDance: Seedream 4 on DeepInfra.

PrunaAI: P Video on DeepInfra.

Google: Nano Banana 2 Lite on DeepInfra.

FLUX.2 is a completely new base model trained for visual intelligence, not just pixel generation, setting a new standard for both image generation and image editing. With FLUX.2 models you can expect the highest quality, higher resolutions (up to 4MP), and new capabilities like multi-ref images. FLUX.2 [flex] supports customizable image generation and editing with adjustable steps and guidance. It's better at typography and text rendering. It supports up to 10 reference images (up to 14 MP total input). This provider gives the option to change the moderation level for inputs and outputs. The control is under safety tolerance and is by default 2 on a range from 0 (more strict) through 6 (more permissive).

FLUX.2 [klein] is Black Forest Labs' fastest image model yet - it unifies image generation and editing in a single, compact model. Delivering state-of-the-art quality with end-to-end inference in less than a second. Enabling interactive workflows, real-time previews, and latency-critical applications.

FLUX.2 [klein] is Black Forest Labs' fastest image model yet - it unifies image generation and editing in a single, compact model. Delivering state-of-the-art quality with end-to-end inference in less than a second. Enabling interactive workflows, real-time previews, and latency-critical applications.

FLUX.2 [max] offers image generation and image editing with the highest quality available. It delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency. Built for professional use, FLUX.2 [max] produces production-ready outputs for marketing teams, creatives, filmmakers, and creators around the world.

FLUX.2 is a completely new base model trained for visual intelligence, not just pixel generation, setting a new standard for both image generation and image editing. With FLUX.2 models you can expect the highest quality, higher resolutions (up to 4MP), and new capabilities like multi-ref images. FLUX.2 [pro] supports generation, editing, and multiple reference images (up to 9 MP total input). This provider gives the option to change the moderation level for inputs and outputs. The control is under safety tolerance and is by default 2 on a range from 0 (more strict) through 6 (more permissive).

FLUX 3 is a new multimodal foundation model that learns from images, videos, and audio within a unified architecture.

Seedance 2.5 is a next-generation audio-video joint generation model, built for 30-second storytelling with precise reference control and powerful editing capabilities.

Kling Video 3.0 Omni: Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control

GPT Image 1 is OpenAI's new state-of-the-art image generation model. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

Lightning-fast image generation

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.

Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.

Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.

Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4.1, with higher resolution for print-ready and large-scale work.

A faster, lighter Recraft image generation model optimized for high-volume and production pipelines. Same design taste as V4.1, built for speed and throughput.

A faster, lighter Recraft image generation model at ~2048px resolution, optimized for high-volume production. Design taste and prompt accuracy at high resolution with better throughput.

An adjustable image NSFW filter based on the Stable Diffusion v1.5 safety checker. Supports a configurable threshold offset while preserving the original special-care behavior.

Prunaai: P-Image-Ideogram on Together AI.

Image generation model from Reve

Image generation model from Reve which handles multiple input reference images

ByteDance's flagship text-to-image and image editing model, generating sharp 1K and 2K images from text or up to 10 reference images

Realistic image generation.

VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video

A lower-cost variant of Seedance 2.0 for high-volume video generation with multimodal inputs and native audio.

For image generation, check out p-image here: https://replicate.com/prunaai/p-image

Google's fast, expressive text-to-speech model with 30 voices and 70+ language support

A sub 1 second text-to-image model built for production use cases.

Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model

Extend videos with xAI's Grok Imagine Video model. Provide a source video and describe what happens next.

Generate videos guided by reference images using xAI's Grok Imagine Video model

Top-quality agentic image model with multi-step reasoning, candidate scoring, and adjustable thinking effort

Luma's reasoning video model. Generates cinematic 5s or 10s video from text or images, with native HDR and EXR export for professional production pipelines.

p-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.

Krea's flagship foundation image model. Larger and more flexible than Krea 2 Medium, with particular strength in photorealism and expressive artistic styles.

Foundation image model from Krea, tuned for expressive illustration, anime, and painterly styles. Fast and consistent across artistic directions.

A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution

Train subjects or styles faster than ever

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

xAI's higher-quality image model with sharper details, better text rendering, and 2k output

Most expressive text-to-speech model from Inworld, with natural-language steering, real-time latency, and multilingual support across 100+ languages.

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Max-quality image generation and editing with support for ten reference images

Convert text to natural-sounding speech with xAI's Grok TTS. 5 voices, 20 languages, expressive speech tags, and high-fidelity MP3 / WAV / telephony audio output.

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.

MiniMax Speech 2.6 HD delivers studio-quality multilingual text-to-audio on Replicate with nuanced prosody, subtitle export, and premium voices

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency

Minimax Speech 2.8 HD focuses on high-fidelity audio generation with features like studio-grade quality, flexible emotion control, multilingual support, and voice cloning capabilities

Low‑latency MiniMax Speech 2.6 Turbo brings multilingual, emotional text-to-speech to Replicate with 300+ voices and real-time friendly pricing

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

Generate videos from reference images or clips while preserving subject identity using Alibaba's Wan 2.7 reference-to-video model

Generate videos from images, with support for first-and-last-frame control, clip continuation, and audio synchronization using Alibaba's Wan 2.7 model

Highest-quality realtime text-to-speech with <200ms latency, emotion control, and 15-language support

Ultra-fast, cost-efficient realtime text-to-speech with ~120ms latency and 15-language support

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

Prunaai: Sdxl Cheetah.

High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

Fast video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.

Generate videos with audio from text prompts using Alibaba's Wan 2.7 model. 1080p, up to 15 seconds, with audio synchronization.

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation

High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.