All models
ModelFold exposes 188 models through one OpenAI-style API. Pick a modality below, or jump straight to a model reference page.
| Modality | Models | Endpoint |
|---|---|---|
| Video Generation | 80 | POST /v1/videos/generations |
| Image Generation | 63 | POST /v1/images/generations |
| Chat Models | 35 | POST /v1/chat/completions |
| Audio & Speech | 10 | n/a |
Video Generation
Text-to-video, image-to-video, reference-to-video, video editing and restoration models.
bytedance/seedance-1.5-pro— 14 credits / call (upstream 1.75 / (按描述匹配) × 1.5)bytedance/seedance-2— 87 credits / call (upstream 11.5 / per second × 1.5)bytedance/seedance-2-5— 54 credits / callbytedance/seedance-2-5-draft— 54 credits / callbytedance/seedance-2-fast— 51 credits / call (upstream 6.8 / per second × 1.5)bytedance/seedance-2-mini— 18 credits / call (upstream 2.4 / (按描述匹配) × 1.5)bytedance/v1-lite-image-to-video— 15 credits / call (upstream 2 / per second × 1.5)bytedance/v1-lite-text-to-video— 15 credits / call (upstream 2 / per second × 1.5)bytedance/v1-pro-fast-image-to-video— 24 credits / call (upstream 16 / per video × 1.5)bytedance/v1-pro-image-to-video— 21 credits / call (upstream 2.8 / per second × 1.5)bytedance/v1-pro-text-to-video— 21 credits / call (upstream 2.8 / per second × 1.5)google/gemini-omni-flash-1-1— 95 credits / call (upstream 63 / per video × 1.5)grok-imagine-video-1-5-preview— 18 credits / call (upstream 2.4 / (按描述匹配) × 1.5)grok-imagine/image-to-video— 18 credits / call (upstream 2.4 / per second × 1.5)grok-imagine/text-to-video— 18 credits / call (upstream 2.4 / per second × 1.5)hailuo/02-image-to-video-pro— 86 credits / call (upstream 57 / per video × 1.5)hailuo/02-image-to-video-standard— 18 credits / call (upstream 12 / per video × 1.5)hailuo/02-text-to-video-pro— 86 credits / call (upstream 57 / per video × 1.5)hailuo/02-text-to-video-standard— 45 credits / call (upstream 30 / per video × 1.5)hailuo/2-3-image-to-video-pro— 68 credits / call (upstream 45 / per video × 1.5)hailuo/2-3-image-to-video-standard— 45 credits / call (upstream 30 / per video × 1.5)happyhorse-1-1/image-to-video— 169 credits / call (upstream 22.5 / per second × 1.5)happyhorse-1-1/reference-to-video— 169 credits / call (upstream 22.5 / per second × 1.5)happyhorse-1-1/text-to-video— 169 credits / call (upstream 22.5 / per second × 1.5)happyhorse/image-to-video— 210 credits / call (upstream 28 / per second × 1.5)happyhorse/reference-to-video— 210 credits / call (upstream 28 / per second × 1.5)happyhorse/text-to-video— 210 credits / call (upstream 28 / per second × 1.5)happyhorse/video-edit— 210 credits / call (upstream 28 / per second × 1.5)kling-2.6/image-to-video— 165 credits / call (upstream 110 / per video × 1.5)kling-2.6/motion-control— 83 credits / call (upstream 11 / (按描述匹配) × 1.5)kling-2.6/text-to-video— 83 credits / call (upstream 55 / per video × 1.5)kling-3.0-omni/image-to-video— 105 credits / call (upstream 14 / per second × 1.5)kling-3.0-omni/reference-to-video— 105 credits / call (upstream 14 / per second × 1.5)kling-3.0-omni/text-to-video— 105 credits / call (upstream 14 / per second × 1.5)kling-3.0-omni/transformation— 150 credits / call (upstream 20 / per second × 1.5)kling-3.0/motion-control— 150 credits / call (upstream 20 / (按描述匹配) × 1.5)kling-3.0/video— 54 credits / callkling-4.0/keyframe-to-video— 214 credits / call (upstream 28.5 / per second × 1.5)kling-4.0/reference-to-video— 214 credits / call (upstream 28.5 / per second × 1.5)kling/ai-avatar-pro— 120 credits / call (upstream 16 / per second × 1.5)kling/ai-avatar-standard— 60 credits / call (upstream 8 / per second × 1.5)kling/v2-1-master-image-to-video— 240 credits / call (upstream 160 / per video × 1.5)kling/v2-1-master-text-to-video— 240 credits / call (upstream 160 / per video × 1.5)kling/v2-1-pro— 75 credits / call (upstream 50 / per video × 1.5)kling/v2-1-standard— 38 credits / call (upstream 25 / per video × 1.5)kling/v2-5-turbo-image-to-video-pro— 63 credits / call (upstream 42 / per video × 1.5)kling/v2-5-turbo-text-to-video-pro— 63 credits / call (upstream 42 / per video × 1.5)kling/v3-turbo-image-to-video— 54 credits / callkling/v3-turbo-text-to-video— 54 credits / callminimax-h3/image-to-video— 60 credits / call (upstream 8 / per second × 1.5)minimax-h3/reference-to-video— 60 credits / call (upstream 8 / per second × 1.5)minimax-h3/text-to-video— 60 credits / call (upstream 8 / per second × 1.5)omnihuman-1-5— 203 credits / call (upstream 27 / per second × 1.5)omnihuman-1-5/human-identification— 0 credits / call (upstream 0 / per request × 1.5)omnihuman-1-5/subject-detection— 0 credits / call (upstream 0 / per request × 1.5)pixverse-v6/image-to-video— 30 credits / call (upstream 4 / per second × 1.5)pixverse-v6/reference-to-video— 30 credits / call (upstream 4 / per second × 1.5)pixverse-v6/text-to-video— 54 credits / callpixverse-v6/transition— 30 credits / call (upstream 4 / per second × 1.5)topaz/video-upscale— 54 credits / callvidu-q4/image-to-video— 54 credits / call (upstream 7.2 / per second × 1.5)vidu-q4/reference-to-video— 54 credits / call (upstream 7.2 / per second × 1.5)volcengine/video-to-video-lip-sync— 60 credits / call (upstream 8 / (按描述匹配) × 1.5)wan/2-2-a14b-image-to-video-turbo— 60 credits / call (upstream 8 / per second × 1.5)wan/2-2-a14b-text-to-video-turbo— 60 credits / call (upstream 8 / per second × 1.5)wan/2-2-animate-move— 54 credits / callwan/2-2-animate-replace— 54 credits / callwan/2-5-image-to-video— 90 credits / call (upstream 60 / per video × 1.5)wan/2-5-text-to-video— 90 credits / call (upstream 60 / per video × 1.5)wan/2-6-flash-image-to-video— 30 credits / call (upstream 20 / per video × 1.5)wan/2-6-flash-video-to-video— 30 credits / call (upstream 20 / per video × 1.5)wan/2-6-image-to-video— 105 credits / call (upstream 70 / per video × 1.5)wan/2-6-text-to-video— 105 credits / call (upstream 70 / per video × 1.5)wan/2-6-video-to-video— 105 credits / call (upstream 70 / per video × 1.5)wan/2-7-image-to-video— 120 credits / call (upstream 16 / per second × 1.5)wan/2-7-r2v— 120 credits / call (upstream 16 / per second × 1.5)wan/2-7-text-to-video— 120 credits / call (upstream 16 / per second × 1.5)wan/2-7-videoedit— 120 credits / call (upstream 16 / per second × 1.5)wan/3-0-video— 54 credits / callwan/3-0-video-prime— 54 credits / call
Image Generation
Text-to-image, image-to-image, inpainting, upscaling and background-removal models.
bytedance/seedream— 12 credits / callbytedance/seedream-v4-edit— 8 credits / call (upstream 5 / per image × 1.5)bytedance/seedream-v4-text-to-image— 8 credits / call (upstream 5 / per image × 1.5)flux-2/flex-image-to-image— 21 credits / call (upstream 14 / per image × 1.5)flux-2/flex-text-to-image— 21 credits / call (upstream 14 / per image × 1.5)flux-2/pro-image-to-image— 8 credits / call (upstream 5 / per image × 1.5)flux-2/pro-text-to-image— 8 credits / call (upstream 5 / per image × 1.5)gemini-omni-character— 12 credits / callgoogle/imagen4— 12 credits / call (upstream 8 / per request × 1.5)google/imagen4-fast— 6 credits / call (upstream 4 / per request × 1.5)google/imagen4-ultra— 18 credits / call (upstream 12 / per image × 1.5)google/nano-banana— 12 credits / callgoogle/nano-banana-edit— 6 credits / call (upstream 4 / per image × 1.5)gpt-image-2-5-flare-image-to-image— 12 credits / callgpt-image-2-5-flare-text-to-image— 12 credits / callgpt-image-2-5-sunburst-image-to-image— 9 credits / call (upstream 6 / per image × 1.5)gpt-image-2-5-sunburst-text-to-image— 9 credits / call (upstream 6 / per image × 1.5)gpt-image-2-image-to-image— 9 credits / call (upstream 6 / per image × 1.5)gpt-image-2-text-to-image— 9 credits / call (upstream 6 / per image × 1.5)gpt-image/1.5-image-to-image— 6 credits / call (upstream 4 / per image × 1.5)gpt-image/1.5-text-to-image— 6 credits / call (upstream 4 / per image × 1.5)grok-imagine-image-2-0/image-edit— 6 credits / call (upstream 4 / per image × 1.5)grok-imagine-image-2-0/segment-edit— 6 credits / call (upstream 4 / per image × 1.5)grok-imagine-image-2-0/segment-map— 12 credits / callgrok-imagine-image-2-0/text-to-image— 6 credits / call (upstream 4 / per image × 1.5)grok-imagine/image-to-image— 6 credits / call (upstream 4 / per generation × 1.5)grok-imagine/text-to-image— 6 credits / call (upstream 4 / per 2 images × 1.5)ideogram/character— 18 credits / call (upstream 12 / per image × 1.5)ideogram/character-edit— 18 credits / call (upstream 12 / per image × 1.5)ideogram/character-remix— 18 credits / call (upstream 12 / per image × 1.5)ideogram/v3-edit— 6 credits / call (upstream 3.5 / per image × 1.5)ideogram/v3-remix— 6 credits / call (upstream 3.5 / per image × 1.5)ideogram/v3-text-to-image— 6 credits / call (upstream 3.5 / per image × 1.5)nano-banana-2-1— 6 credits / call (upstream 4 / (按描述匹配) × 1.5)nano-banana-2-lite— 6 credits / call (upstream 4 / (按描述匹配) × 1.5)nano-banana-pro— 12 credits / callqwen/image-edit— 8 credits / call (upstream 5 / (按描述匹配) × 1.5)qwen/image-to-image— 12 credits / callqwen/text-to-image— 12 credits / callqwen2-1/image-to-image— 6 credits / call (upstream 4 / per image × 1.5)qwen2-1/text-to-image— 12 credits / callqwen2/image-edit— 9 credits / call (upstream 5.6 / per image × 1.5)qwen2/text-to-image— 9 credits / call (upstream 5.6 / per image × 1.5)qwen3/image-to-image— 1 credits / call (upstream 0.5 / per image × 1.5)qwen3/pro-image-to-image— 1 credits / call (upstream 0.5 / per image × 1.5)qwen3/pro-text-to-image— 10 credits / call (upstream 6.4 / per image × 1.5)qwen3/text-to-image— 8 credits / call (upstream 4.8 / per image × 1.5)recraft/crisp-upscale— 1 credits / call (upstream 0.5 / (按描述匹配) × 1.5)recraft/remove-background— 2 credits / call (upstream 1 / (按描述匹配) × 1.5)seedream/4.5-edit— 10 credits / call (upstream 6.5 / per image × 1.5)seedream/4.5-text-to-image— 10 credits / call (upstream 6.5 / per image × 1.5)seedream/5-flash-image-to-image— 5 credits / call (upstream 3.24 / per image × 1.5)seedream/5-flash-layer-decomposition— 5 credits / call (upstream 3.24 / per image × 1.5)seedream/5-flash-text-to-image— 5 credits / call (upstream 3.24 / per image × 1.5)seedream/5-lite-image-to-image— 9 credits / call (upstream 5.5 / per image × 1.5)seedream/5-lite-text-to-image— 9 credits / call (upstream 5.5 / per image × 1.5)seedream/5-pro-image-to-image— 1 credits / call (upstream 0.5 / per image × 1.5)seedream/5-pro-layer-decomposition— 11 credits / call (upstream 7 / per image × 1.5)seedream/5-pro-text-to-image— 11 credits / call (upstream 7 / per image × 1.5)topaz/image-upscale— 12 credits / callwan/2-7-image— 54 credits / callwan/2-7-image-pro— 18 credits / call (upstream 12 / per image × 1.5)z-image— 12 credits / call
Chat Models
OpenAI-compatible chat completions, billed per token.
claude-fable-5— Input 1200 credits / 1M tokens; output 6000 credits / 1M tokensclaude-haiku-4-5— Input 82.5 credits / 1M tokens; output 427.5 credits / 1M tokensclaude-haiku-5-5— Input 18 credits / 1M tokens; output 90 credits / 1M tokensclaude-opus-4-5— Input 427.5 credits / 1M tokens; output 2145 credits / 1M tokensclaude-opus-4-6— Input 427.5 credits / 1M tokens; output 2145 credits / 1M tokensclaude-opus-4-7— Input 427.5 credits / 1M tokens; output 2145 credits / 1M tokensclaude-opus-4-8— Input 600 credits / 1M tokens; output 3000 credits / 1M tokensclaude-opus-5— Input 600 credits / 1M tokens; output 3000 credits / 1M tokensclaude-opus-5-5— Input 480 credits / 1M tokens; output 2400 credits / 1M tokensclaude-sonnet-4-5— Input 255 credits / 1M tokens; output 1282.5 credits / 1M tokensclaude-sonnet-4-6— Input 255 credits / 1M tokens; output 1282.5 credits / 1M tokensclaude-sonnet-5— Input 255 credits / 1M tokens; output 1282.5 credits / 1M tokensclaude-sonnet-5-5— Input 240 credits / 1M tokens; output 1200 credits / 1M tokensdeepseek-v4-1-flash— Input 36 credits / 1M tokens; output 142.5 credits / 1M tokensgemini-3-6-flash— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-6-flash-openai— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-7-flash— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-7-flash-openai— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-8-flash— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-8-flash-openai— Input 67.5 credits / 1M tokens; output 337.5 credits / 1M tokensgemini-3-pro— Input 150 credits / 1M tokens; output 1050 credits / 1M tokensgemini-3.1-pro— Input 150 credits / 1M tokens; output 1050 credits / 1M tokensgemini-4-argon— Input 240 credits / 1M tokens; output 1200 credits / 1M tokensgemini-4-argon-openai— Input 240 credits / 1M tokens; output 1200 credits / 1M tokensgpt-5-2— Input 131.256 credits / 1M tokens; output 1050 credits / 1M tokensgpt-5-6-luna— Input 16.8 credits / 1M tokens; output 100.8 credits / 1M tokensgpt-5-6-sol— Input 420 credits / 1M tokens; output 2520 credits / 1M tokensgpt-5-6-terra— Input 168 credits / 1M tokens; output 1008 credits / 1M tokensgpt-6-1-sol— Input 180 credits / 1M tokens; output 900 credits / 1M tokensgpt-6-astra— Input 840 credits / 1M tokens; output 4200 credits / 1M tokensgpt-6-luna— Input 9 credits / 1M tokens; output 45 credits / 1M tokensgpt-6-sol— Input 180 credits / 1M tokens; output 900 credits / 1M tokensgrok-4-6— Input 240 credits / 1M tokens; output 720 credits / 1M tokensgrok-4-7— Input 240 credits / 1M tokens; output 720 credits / 1M tokenskimi-k3— Input 720 credits / 1M tokens; output 3600 credits / 1M tokens
Audio & Speech
Text-to-speech, voice cloning and audio generation models.
elevenlabs/text-to-dialogue-v3— 10 credits / callelevenlabs/text-to-speech-multilingual-v2— 18 credits / call (upstream 12 / per 1000 characters × 1.5)elevenlabs/text-to-speech-turbo-2-5— 9 credits / call (upstream 6 / per 1000 characters × 1.5)gemini-omni-audio— 10 credits / callgoogle/gemini-2-5-pro-tts— 10 credits / callgoogle/gemini-3-1-flash-tts— 10 credits / callgoogle/gemini-3-8-flash-lite-tts— 10 credits / callgoogle/gemini-3-8-flash-tts— 10 credits / callinfinitalk/from-audio— 10 credits / callwan/2-2-a14b-speech-to-video-turbo— 10 credits / call