Simple, transparent pricing. Pay only for what you use with our credit-based system. All models include parameters and example payloads.
Model Categories
1 credit = $0.01 USD. Credits are deducted when you submit a job.
ai-avatar-i2v
sora-2-pro-i2v
sora-2-i2v
sora-2-t2v
Text-to-video generation powered by OpenAI Sora 2
sora-2-pro-t2v
Premium text-to-video with higher resolution support using OpenAI Sora 2 Pro
wan-2-6-i2v
Alibaba WAN 2.6 image-to-video generation with enhanced quality
virtual-tryon
Virtual try-on video generation - upload a person image and garment image to generate a video of the person wearing the garment
kling-2-6-i2v-pro
kling-2-6-motion-control
Kling V2.6 Pro motion control - transfer motion from a reference video to a subject image
kling-2-5-i2v
Kling V2.5 Turbo Pro image-to-video with smooth visual transformation
kling-2-5-t2v
Kling V2.5 Turbo Pro text-to-video generation
seedance-1-5-t2v
ByteDance Seedance 1.5 Pro text-to-video with optional audio generation
seedance-1-5-i2v
ByteDance Seedance 1.5 Pro image-to-video with optional audio generation
veo-3-1-i2v
Google Veo 3.1 Fast image-to-video with synchronized audio generation
veo-3-1-t2v
Google Veo 3.1 Fast text-to-video with synchronized audio generation
veo-3-1-quality-i2v
Google Veo 3.1 Quality image-to-video with highest quality output and synchronized audio
veo-3-1-quality-t2v
Google Veo 3.1 Quality text-to-video with highest quality output and synchronized audio
hailuo-02-i2v
MiniMax Hailuo 02 image-to-video generation with high quality output
hailuo-02-t2v
MiniMax Hailuo 02 text-to-video generation with high quality output
nano-banana-t2i
Fast text-to-image generation with natural language prompts
nano-banana-pro-t2i
High-quality text-to-image with resolution options up to 4K
nano-banana-pro-4k-t2i
Premium 4K text-to-image generation with ultra-high resolution output
seedream-4-5-t2i
ByteDance SeeDream V4.5 text-to-image with up to 4K resolution support
qwen-image-t2i
flux-2-dev-t2i
Fast, high-quality text-to-image generation powered by Flux 2 Dev architecture
flux-2-max-t2i
Premium text-to-image generation with highest quality output using Flux 2 Max
nano-banana-edit
Fast image editing with natural language instructions
nano-banana-pro-edit
Advanced image editing with resolution options up to 4K
seedream-4-edit
qwen-image-edit
Advanced image editing with natural language instructions using Qwen 2511 LoRA
flux-kontext
minimax-voice-clone
Clone any voice from an audio sample and generate speech with that voice
minimax-speech-02
Fast text-to-speech synthesis with emotion control and multiple voice options
minimax-music-02
AI music generation with vocals from text prompts and lyrics
audio-tts
High-quality text-to-speech synthesis with natural intonation and multiple output formats
qwen3-tts-flash
Low-latency text-to-speech with 49+ expressive voices, 10 languages, and Chinese dialects. Optimized for real-time conversations.
audio-clone
Clone any voice from an audio sample and generate speech with zero-shot voice cloning
audio-asr
Automatic speech recognition to transcribe audio to text with timestamps
tripo3d-2-5-i3d
Convert images to 3D models using Tripo3D V2.5. Outputs GLB format.
tripo3d-multiview-to-3d
Convert 4 orthogonal images to high-quality 3D assets using Tripo3D V2.5.
hunyuan3d-v2-base
Convert a single image to high-fidelity 3D model with 4K textures using Hunyuan3D V2.
hunyuan3d-v2-multiview
Convert 3 view images (front, back, left) to 3D model with 4K textures. Fast ~30s generation.
meshy6-text-to-3d
Generate high-quality 3D models from text descriptions using Meshy6. Outputs GLB, FBX, OBJ, USDZ formats.
meshy6-image-to-3d
Convert images to high-quality 3D models using Meshy6. Outputs GLB, FBX, OBJ, USDZ formats.
