🇺🇸 English
With the default basic models, 1 token is equal to 1 word, image, second. With advanced models, a word, image, or audio will cost more or less tokens.
Basic Model
| Name | Credit |
|---|---|
| Stable Diffusion XL v1.0 | 1 token / image |
| ada v2 (1,536 dimension) | 0.25 token / word |
| Whisper | 1 token / second |
| GPT-4o mini | 1 token / word |
| GPT-4o mini (Jul 2024) | 1 token / word |
| Pebblely | 1 token / image |
Advanced Model
| Name | Credit |
|---|---|
| Claude 3 Haiku (200K token) | 2 token / word |
| Claude 3 Sonnet (200K token) | 25 token / word |
| Claude 3 Opus (200K token) | 125 token / word |
| Claude 2.1 - Legacy Model (200K token) | 40 token / word |
| Claude 2 - Legacy Model (100K token) | 40 token / word |
| Claude Instant 1.2 - Legacy Model (100K token) | 4 token / word |
| Gemini 1.5 Pro (128K tokens) | 7.5 token / word |
| Gemini 1.5 Flash (28K tokens) | 1.75 token / word |
| Gemini 1.0 Pro (28K tokens) | 2.5 token / word |
| Gemini 1.0 Pro Vision (12K tokens) | 2.5 token / word |
| Stable Diffusion v1.6 | 1 token / image |
| Stable Diffusion v2.1 | 1 token / image |
| Stable Diffusion v2.2.2-XL Beta | 1 token / image |
| Esrgan | 0.5 token / image |
| Conservative Upscaler | 25 token / image |
| Creative Upscaler | 25 token / image |
| Stable image edit | 4 token / image |
| Stable Video Diffusion | 20 token / video |
| GPT-4 Omni (128k Token) | 25 token / word |
| GPT-4 Turbo with Vision (128k Token) | 50 token / word |
| GPT-4 Turbo preview model (128k Token) | 50 token / word |
| GPT-4 Turbo preview model (128k Token) | 50 token / word |
| GPT-4 Turbo Vision preview model (128k Token) | 50 token / word |
| GPT-4 model (8,192 Token) | 100 token / word |
| GPT-4 model (32,768 Token) | 200 token / word |
| Updated GPT 3.5 Turbo (16,385 Token) | 2.5 token / word |
| Updated GPT 3.5 Turbo (4,096 Token) | 3.25 token / word |
| Updated GPT 3.5 Turbo (16,385 Token) | 10 token / word |
| GPT base models, davinci base models (16,385 Token) | 20 token / word |
| GPT base models, babbage base models (16,385 Token) | 2.75 token / word |
| Embedding V3 large (3,072 dimension) | 0.25 token / word |
| DALL E 3 Standard Medium | 20 token / image |
| DALL E 3 Standard Large | 40 token / image |
| DALL E 3 HD Medium | 40 token / image |
| DALL E 3 HD Large | 60 token / image |
| DALL E 2 | 10 token / image |
| Text-to-speech 1 | 125 token / word |
| Text-to-speech 1 HD | 250 token / word |
| Plagiarism Checker | 215.75 token / word |
| Neural2 voices | 100 token / word |
| WaveNet voices | 1000 token / word |
| Polyglot voices | 100 token / word |
| WaveNet voices | 100 token / word |
| Standard voices | 25 token / word |
| Speech-to-Text V1 API | 20 token / second |
| Speech-to-Text V2 API | 13.33 token / second |
| Starter | 1041.75 token / word |
| Creator | 687.5 token / word |
| Pro | 1237.5 token / word |
| Scale | 1031.25 token / word |
| Neural voices | 37.5 token / word |
| Synthesis voices | 150 token / word |
| Synthesis voices | 13.89 token / second |
| Llama-3 (70B) | 5.25 token / word |
| Llama-3 (8B) | 2.75 token / word |
| Llama-3 (70B) | 5.25 token / word |
| Llama-2 (13B) | 2.75 token / word |
| Llama-2 (7B) | 0.75 token / word |
| Qwen 2 (72B) | 5.25 token / word |
| Qwen 1.5 (110B) | 5.25 token / word |
| Qwen 1.5 (72B) | 5.25 token / word |
| Qwen 1.5 (32B) | 2.75 token / word |
| Qwen 1.5 (14B) | 2.75 token / word |
| Qwen 1.5 (7B) | 2.75 token / word |
| Qwen 1.5 (4B) | 0.75 token / word |
| Qwen 1.5 (1.8B) | 0.75 token / word |
| Qwen 1.5 (0.5B) | 0.75 token / word |
| gemma (7B) | 2.75 token / word |
| gemma (2B) | 0.75 token / word |
| Clipdrop APIs | 160 token / image |
| ModelsLab | 1.84 token / image |
| AI Image Generator | 3.27 token / image |
| AI Image Editor | 3.27 token / image |
| AI Image Upscaler | 3.27 token / image |
| AI Image Outpainting | 3.27 token / image |
| AuraFlow | 30 token / image |
| FLUX.1 [dev] | 15 token / image |
| FLUX Realism LoRA | 15 token / image |
| FLUX.1 [schnell] | 2 token / image |
| FLUX.1 [pro] | 30 token / image |
| FLUX.1 [dev] with LoRAs | 30 token / image |
| FLUX.1 [dev] with Controlnets and Loras | 30 token / image |
| Stable Diffusion V3 | 17.5 token / image |
| Stable Diffusion XL | 1.25 token / image |
| Stable Diffusion with LoRAs | 17.5 token / image |
| Stable Cascade | 17.5 token / image |
| Stable Diffusion Turbo (v1.5/XL) | 1.25 token / image |
| Latent Consistency Models (v1.5/XL) | 17.5 token / image |
| Stable Diffusion XL Lightning | 1.25 token / image |
| Hyper SDXL | 1.5 token / image |
| Playground v2.5 | 17.5 token / image |
| Kolors | 17.5 token / image |
| Birefnet Background Removal | 30 token / image |
| Remove Background | 30 token / image |
| Remove Background | 30 token / image |
| AuraFlow | 30 token / image |
| FLUX.1 [dev] | 15 token / image |
| FLUX Realism LoRA | 15 token / image |
| FLUX.1 [schnell] | 2 token / image |
| FLUX.1 [pro] | 30 token / image |
| FLUX.1 [dev] with LoRAs | 30 token / image |
| FLUX.1 [dev] with Controlnets and Loras | 30 token / image |
| Stable Diffusion V3 | 17.5 token / image |
| Stable Diffusion XL | 1.25 token / image |
| Stable Diffusion with LoRAs | 17.5 token / image |
| Stable Cascade | 17.5 token / image |
| Stable Diffusion Turbo (v1.5/XL) | 1.25 token / image |
| Latent Consistency Models (v1.5/XL) | 17.5 token / image |
| Stable Diffusion XL Lightning | 1.25 token / image |
| Hyper SDXL | 1.5 token / image |
| Playground v2.5 | 17.5 token / image |
| Kolors | 17.5 token / image |
| Birefnet Background Removal | 30 token / image |
| Remove Background | 30 token / image |
| Remove Background | 30 token / image |
| PuLID | |
| Face Retoucher | 30 token / image |
| Face to Sticker | 30 token / image |
| T2V Turbo - Video Crafter | 37.5 token / video |
| AnimateDiff | 37.5 token / video |
| High Quality Stable Video Diffusion | 37.5 token / video |
| Live Portrait | 37.5 token / video |
| Erase Object | 3 token / image |
| Inpaint | 3 token / image |
| Outpaint | 4 token / image |
| Remove Background | 2 token / image |
| Search and Recolor | 5 token / image |
| Search and Replace | 4 token / image |
| Structure | 3 token / image |
| Sketch | 3 token / image |
| Style | 4 token / image |
| Outpaint | 4.15 token / image |
| Blip Diffusion | 4.15 token / image |
| Magic Mix | 4.15 token / image |
| Depth to Image | 4.15 token / image |
| Image Mixer | 4.15 token / image |
| Image Guided Editing | 4.15 token / image |
| Background Removal | 4.15 token / image |
| Multiview | 4.15 token / image |
| Fashion | 4.15 token / image |
| Object Removal | 4.15 token / image |
| Face Generator | 4.15 token / image |
| Inpainting | 4.15 token / image |
| Head shot | 4.15 token / image |
| Avatar Generator | 4.15 token / image |
| Wifu Diffusion | 4.15 token / image |
| Arcane Diffusion | 4.15 token / image |
| Robo Diffusion | 4.15 token / image |
| Mo Di Diffusion | 4.15 token / image |
| Vintedois | 4.15 token / image |
| Vintedois | 4.15 token / image |
| Firewatch Diffusion | 4.15 token / image |
| Double Exposure | 4.15 token / image |
| Anything V4 | 4.15 token / image |
| hc-anything-v3-vae | 4.15 token / image |
| Edge of Realism | 4.15 token / image |
| Realistic Vision V1.3 | 4.15 token / image |
| animefull | 4.15 token / image |
| Dark Sushi Mix | 4.15 token / image |
| kakigori | 4.15 token / image |
| meinapastelv6 | 4.15 token / image |
| DisillusionMix | 4.15 token / image |
| MidJourney V4 | 4.15 token / image |
| MidJourney PaperCut | 4.15 token / image |
| MidJourney V4 (OpenJourney) | 4.15 token / image |
| Midjourney-v4-PaintArt | 4.15 token / image |
| Graffity Midjourney | 4.15 token / image |
| Colorful portraits Midjourney | 4.15 token / image |
| Midjourney-Flux | 4.15 token / image |
| DreamShaper V8 | 4.15 token / image |
| DreamShaper V7 | 4.15 token / image |
| DreamShaper V6 | 4.15 token / image |
| DreamShaper V6 | 4.15 token / image |
| DreamShaper XL | 4.15 token / image |
| DreamShaper SD XL 1.0 | 4.15 token / image |
| DreamShaper111 | 4.15 token / image |
| Dream Shaper 8797 | 4.15 token / image |
| Midjourney-Flux | 4.15 token / image |
| Yae Miko Genshin | 4.15 token / image |
| Ganyu Lora | 4.15 token / image |
| noiseoffset | 4.15 token / image |
| noiseoffset | 4.15 token / image |
| u58hvdfu4q | 4.15 token / image |
| DetailTweakerLoRA | 4.15 token / image |
🍪 This website uses cookies to improve your web experience.