Simple, Transparent Pricing
Get exactly what you need with one-time credits. Zero subscriptions, zero hassle.
Show currency in
USDIDR
Need more credits? Purchase additional credit packs starting at just $5. These credit packs provide flexibility for your usage needs. Credits are valid for a whole year from purchase!
Key Platform Features
- Flexible Credit System: Utilize credits for various features, available through plans or purchased separately.
- Subtitle Translation: Translate subtitles (SRT, VTT, ASS) using all available AI models for over 100+ languages.
- Extract Context Feature: Analyze content to extract characters, settings, plot, and relationships.
- Audio Transcription: Convert audio into subtitle text. Supports large files and background processing.
- Batch Translation: Translate multiple files simultaneously to improve workflow efficiency and save time.
- Project Management & Backup: Efficiently manage, organize, backup, and transfer your translation projects, subtitles, and related assets.
- Access to All Models: Select from a wide range of AI models available on the platform.
- Support Options: Access Discord community and email support resources.
How Credits Work
Discover how credits work and how they provide flexible access to our powerful AI tools.
What are Credits?
Credits are used for features like Translation, Transcription, and Context Extraction. Using these features will deduct credits from your balance. See "Credit Usage" below for details.
You can receive credits by purchasing credit packs as needed.
Where Can I See My Credits?
You can see your remaining credit balance and usage history in User Information page.
Credit Usage
Credit costs vary based on the specific AI model used. Costs are typically calculated based on the number of input and output tokens processed. More models will be added in the future. Prices are aligned to original API prices with a 0.2 service fee. See the estimated costs below.
| Model | Credit per Input Token |
Credit per Output Token |
Credit Usage | Context Length | Max Completion |
|---|---|---|---|---|---|
| Gemini 3.1 Pro⭐💙 | 2.4 | 14.4 | high | 1M tokens | 66k tokens |
| Gemini 3 Flash | 0.6 | 3.6 | medium | 1M tokens | 66k tokens |
| Gemini 3.1 Flash Lite | 0.3 | 1.8 | low | 1M tokens | 66k tokens |
| Gemini 2.5 Pro⭐ | 1.5 | 12 | high | 1M tokens | 66k tokens |
| Gemini 2.0 Flash💙 | 0.18 | 0.72 | very low | 1M tokens | 8k tokens |
| Claude 4.6 Sonnet | 3.6 | 18 | very high | 200k tokens | 64k tokens |
| Claude 4.5 Haiku | 1.2 | 6 | medium | 200k tokens | 64k tokens |
| Grok 4.3 | 1.5 | 3 | medium | 1M tokens | 1M tokens |
| Grok 4.1 Fast | 0.24 | 0.6 | low | 2M tokens | 30k tokens |
| GPT-5.4⭐ | 3 | 18 | high | 1.1M tokens | 128k tokens |
| GPT-5.4 mini | 0.9 | 5.4 | medium | 400k tokens | 128k tokens |
| GPT-5.4 nano | 0.24 | 1.5 | low | 400k tokens | 128k tokens |
| GPT-5.2⭐ | 2.1 | 16.8 | high | 400k tokens | 128k tokens |
| GPT-5.1 | 1.5 | 12 | high | 400k tokens | 128k tokens |
| GPT-5⭐💙 | 1.5 | 12 | high | 400k tokens | 128k tokens |
| GPT-5 mini | 0.3 | 2.4 | low | 400k tokens | 128k tokens |
| GPT-5 nano | 0.06 | 0.48 | very low | 400k tokens | 128k tokens |
| OpenAI o3 | 2.4 | 9.6 | high | 200k tokens | 100k tokens |
| DeepSeek V4 Pro | 2.1 | 4.2 | medium | 1M tokens | 384k tokens |
| DeepSeek V4 Flash | 0.18 | 0.36 | low | 1M tokens | 384k tokens |
| DeepSeek V3.2 | 0.56 | 1.68 | low | 131k tokens | 66k tokens |
| DeepSeek R1💙 | 1.2 | 3.3 | medium | 128k tokens | 64k tokens |
| GLM 5.1 | 1.68 | 5.28 | medium | 203k tokens | 66k tokens |
| Free Models | 0 | 0 | N/A | Varies | Varies |
* These are estimated costs and limits, and are subject to change. Input/Output token costs may vary. Refer to the dashboard for precise figures.
Token: A unit of text processed by the LLM. Roughly 4 characters or 0.75 words.
Context Length: The maximum number of tokens (input + output history) the model can consider at once.
Max Completion: The maximum number of tokens the model can generate in a single response.
Transcription (Experimental)
Audio transcription tasks consume credits based on the duration of the audio and the number of output tokens generated. More models will be added in the future.
| Model Type | Credit per 1 minute audio |
Credit per Output Token |
Max Duration |
|---|---|---|---|
| mitsuko-premium | 3240 | 13.5 | 30 minutes |
| whisper-large-v3 | 4500 | 0 | 180 minutes |
| whisper-large-v3-turbo | 2000 | 0 | 180 minutes |
* The costs shown are not including system prompts and custom instructions input costs.
Background Processing
Background processing allows audio transcriptions to run on our server even if you close the browser tab. This means you don't have to wait for the process to finish.
Let Mitsuko translate your subtitles
All you need is editing and QA. Mitsuko handles the heavy lifting of the translation step with context-aware AI.