Credit services
See what each service costs in credits and how options combine when you upload documents, chat with PDFs, transcribe audio, generate music, generate images, or generate video.
Document
Document extractor
Choose a processing tier and optional field highlighting when uploading files.
| Service | Description | Unit | Credits |
|---|---|---|---|
| Standard extraction | Standard AI extraction — fast and budget-friendly for everyday documents. | Per page | 2credits |
| High-quality extraction | Premium extraction with our most accurate AI model. Best for important or complex documents. | Per page | 10credits |
| Field highlighting | Highlights every extracted field right on the page, so you can verify each value at a glance. | Per page | 19credits |
Document extractor combinations
Total credits charged per document page when you combine options at upload time.
| Option | Credits / page |
|---|---|
| Standard | 2credits |
| Standard + field highlighting | 21credits |
| High quality | 10credits |
| High quality + field highlighting | 29credits |
Document chat
Upload a PDF for AI Q&A. Billed per page for document context and per 10 user messages with AI replies.
| Service | Description | Unit | Credits |
|---|---|---|---|
| Document chat (per page) | Load a PDF for AI Q&A — 2 credits per page for document context. | Per page | 2credits |
| Document chat (messages) | Ask questions about your document — 2 credits per 10 messages and replies. | Per 10 messages | 2credits |
Audio
Audio transcription
Speech-to-text with optional speaker labels and translation. Billed per minute of audio (minimum 1 minute).
| Service | Description | Unit | Credits |
|---|---|---|---|
| Audio transcription | Convert audio to text with timestamps — 2 credits per minute. | Per minute | 2credits |
| Speaker diarization | Label each segment with a speaker — +2 credits per minute. | Per minute | 2credits |
| Transcript translation | Translate each segment to your chosen language — +3 credits per minute. | Per minute | 3credits |
Audio combinations
Total credits charged per minute when you combine options at upload time.
| Option | Credits / minute |
|---|---|
| Transcription | 2credits |
| Transcription + speaker diarization | 4credits |
| Transcription + translation | 5credits |
| Transcription + diarization + translation | 7credits |
Text to speech
Natural speech synthesis with gpt-4o-mini-tts — billed per minute of output audio.
| Service | Description | Unit | Credits |
|---|---|---|---|
| Text-to-Speech (gpt-4o-mini-tts) | Natural text-to-speech with gpt-4o-mini-tts — 4 credits per minute of audio. | Per minute | 4credits |
Music generation
Full songs with Google Lyria 3 Pro — instrumental or with vocals. Billed per generated song. Optional AI lyrics draft is billed separately.
| Service | Description | Unit | Credits |
|---|---|---|---|
| Lyria 3 Pro | Google Lyria 3 Pro — full songs with optional vocals and lyrics. Billed per song. | Per song | 20credits |
| Song lyrics | Generate song lyrics from your prompt — use them in Custom lyrics before creating the track. | Per song | 2credits |
| MiniMax Music 2.0 | MiniMax Music 2.0 — vocal tracks steered by a reference song. Flat per generation. | Per song | 9credits |
| MiniMax Music 2.6 | MiniMax Music 2.6 — strong vocals from your lyrics. Flat per generation. | Per song | 46credits |
| Sonilo v1.1 | Sonilo v1.1 — long tracks (up to 10 min). Billed per second. | Per second | 1credits |
Image
Image generation
Text-to-image with GPT Image 2 and Google Nano Banana models. Standard or high quality per model; credits scale with the number of images per request.
| Service | Description | Unit | Credits |
|---|---|---|---|
| GPT Image 2 (standard) | Generate an image from a text prompt — standard quality, great for everyday visuals. | Per image | 13credits |
| GPT Image 2 (high) | Generate an image from a text prompt — high quality with sharper detail. | Per image | 45credits |
| Nano Banana (standard) | Fast, affordable image generation with Google Nano Banana — standard quality. | Per image | 9credits |
| GPT Image 2.5 Flare (standard) | GPT Image 2.5 Flare — fast everyday generation, standard quality. | Per image | 4credits |
| Nano Banana (high) | Google Nano Banana image generation — high quality. | Per image | 9credits |
| GPT Image 2.5 Flare (high) | GPT Image 2.5 Flare — fast everyday generation, high quality. | Per image | 13credits |
| Nano Banana 2 (standard) | Google Nano Banana 2 image generation — sharper detail, standard quality. | Per image | 16credits |
| GPT Image 2.5 Sunburst (standard) | GPT Image 2.5 Sunburst — precise edits and detailed creative work, standard quality. | Per image | 13credits |
| Nano Banana 2 (high) | Google Nano Banana 2 image generation — high quality with 2K output. | Per image | 24credits |
| GPT Image 2.5 Sunburst (high) | GPT Image 2.5 Sunburst — precise edits and detailed creative work, high quality. | Per image | 45credits |
| Nano Banana Pro (standard) | Google Nano Banana Pro — studio-grade image generation, standard quality. | Per image | 33credits |
| Nano Banana Pro (high) | Google Nano Banana Pro — studio-grade image generation, high quality with 2K output. | Per image | 35credits |
| Grok Imagine (standard) | Fast, affordable image generation with xAI Grok Imagine — standard quality. | Per image | 5credits |
| Grok Imagine (high) | xAI Grok Imagine image generation — high quality with 2K output. | Per image | 12credits |
| FLUX.1 Pro (standard) | Black Forest Labs FLUX.1 Pro — fast, high-quality image generation. | Per image | 9credits |
| FLUX.1 Pro (high) | Black Forest Labs FLUX.1 Pro — ultra resolution and max-quality edits. | Per image | 19credits |
| FLUX.2 Pro (standard) | Black Forest Labs FLUX.2 Pro — latest generation, fast and affordable. | Per image | 11credits |
| FLUX.2 Pro (high) | Black Forest Labs FLUX.2 Pro — maximum quality with FLUX.2 [max]. | Per image | 24credits |
| Nano Banana 2 Lite (standard) | Google Nano Banana 2 Lite — fastest Nano Banana tier, 1K output. | Per image | 8credits |
| Nano Banana 2 Lite (high) | Google Nano Banana 2 Lite — 1K only; high quality uses the same resolution. | Per image | 8credits |
| Grok Imagine 2.0 (standard) | xAI Grok Imagine Image 2.0 — next-gen Imagine quality at 1K. | Per image | 9credits |
| Grok Imagine 2.0 (high) | xAI Grok Imagine Image 2.0 — 2K output at the same per-image rate. | Per image | 9credits |
Video
Video generation
Text or image to video with xAI Grok Imagine and Google Veo 3.1. Native audio included. Credits are charged per second of generated video.
| Service | Description | Unit | Credits |
|---|---|---|---|
| Grok Imagine Video | xAI Grok Imagine Video — text or image to video with native audio. Billed per second of output. | Per second | 12credits |
| Grok Imagine Video 1.5 | xAI Grok Imagine Video 1.5 — higher-fidelity image-to-video with native audio. Billed per second. | Per second | 19credits |
| Veo 3.1 Lite (720p) | Google Veo 3.1 Lite at 720p — affordable video with native audio. Billed per second. | Per second | 12credits |
| Veo 3.1 Lite (1080p) | Google Veo 3.1 Lite at 1080p — native audio. 1080p requires 8s duration. Billed per second. | Per second | 19credits |
| Veo 3.1 Fast (720p) | Google Veo 3.1 Fast at 720p — balanced speed and quality with native audio. Billed per second. | Per second | 24credits |
| Veo 3.1 Fast (1080p) | Google Veo 3.1 Fast at 1080p — native audio. 1080p requires 8s duration. Billed per second. | Per second | 28credits |
| Veo 3.1 Fast (4K) | Google Veo 3.1 Fast at 4K — native audio. 4K requires 8s duration. Billed per second. | Per second | 64credits |
| Veo 3.1 Standard (720p / 1080p) | Google Veo 3.1 Standard at 720p or 1080p — highest quality with native audio. Billed per second. | Per second | 85credits |
| Veo 3.1 Standard (4K) | Google Veo 3.1 Standard at 4K — native audio. 4K requires 8s duration. Billed per second. | Per second | 128credits |
| FLUX 3 Video (HD) | Black Forest Labs FLUX 3 Video at HD — clips 5–20s with native audio. Billed per second. | Per second | 36credits |
| FLUX 3 Video (FHD) | Black Forest Labs FLUX 3 Video at FHD — clips 5–20s with native audio. Billed per second. | Per second | 62credits |