# SayFlow: AI Chat, Translate — BYOK AI chat and translator

> BYOK AI chat and translator (iPhone/iPad app by DONGHWAN CHOI.)

- Source: https://appshunter.io/ios/app/sayflow-ai-chat-translate/id6766947682 (this page in markdown: same URL + `.md`)
- Developer: [DONGHWAN CHOI](https://appshunter.io/developer/1888758596)
- Category: Productivity, Reference
- Price: Free
- Age rating: 12+
- Requires: iOS 26.0 · 41 MB
- Languages: English, Japanese, Korean
- Released: 2026-05-07
- Data updated: 2026-08-14
- User reviews in markdown: https://appshunter.io/ios/app/sayflow-ai-chat-translate/id6766947682/reviews.md

## What is SayFlow?

SayFlow is a flexible AI chat app that lets you bring your own API keys and talk with multiple leading AI providers in one place.

Chat with models from OpenAI, Anthropic, Google, xAI, DeepSeek, and on-device Apple Intelligence when available. Switch models by conversation, adjust reasoning and response settings, generate images, use voice input, and keep reusable prompts ready in your custom instruction library.

SayFlow is built for people who want control over their AI workspace. Your API keys are stored securely on your device, and conversations are saved locally on your device.

Key Features:
• Chat with multiple AI providers in one app
• Bring your own API keys
• External web search model support
• Switch models for different conversations
• Use reasoning controls where supported
• Generate images from prompts
• Save and reuse custom instructions and skills
• Use voice input for quick prompts
• View estimated tokens and response metrics
• Pin, search conversation, archive, export, and organize chats
• Use on-device Apple Intelligence when available
• Translate using the API of your selected model
...and more feature!

SayFlow does not sell API credits or subscriptions. Usage of third-party AI services may require your own provider account, API key, billing setup, and agreement to each provider’s terms.

SayFlow is an independent app and is not affiliated with OpenAI, Anthropic, Google, xAI, DeepSeek, or Apple.

Terms of Use: https://saypop.kr/sayflow/terms/?lang=en
Privacy Policy: https://saypop.kr/sayflow/privacy/?lang=en


## Version history (last 5 releases)

### 1.0.8 — 2026-08-12

[v1.0.8]
* Support Google ‘Gemini 3.6 Flash’, ‘Gemini 3.5 Flash Lite’ API.
* Support Anthropic ‘Opus5’ API.
* Support SpaceXAI ‘Grok 4.6’ API.
* Refresh New DeepSeek V4 Pro, Flash API.
* Remove API pricing info. (redirect to provider docs instead)
* Other bug fixes.

### 1.0.7 — 2026-07-17

[v1.0.7]
* Moved Gemini image models to the latest stable APIs and improved continuous image editing and model-specific aspect ratios. 
* Gemini Google Search responses now include sources and Search Suggestions. 
* The Translation Extension now follows reasoning effort, Thinking, and temperature settings more accurately. 
* Improved reasoning controls and automatic title generation for Grok 4.20 Multi-Agent. 
* Improved voice input reliability and privacy disclosures. 
* Fixed issues affecting provider requests, token metrics, caching, and conversation stability.

### 1.0.6 — 2026-07-10

-Some UI Improvements.
-Added a reminder that AI can make mistakes, so important information should be cross-checked.
-AI Provider Name and Logo Change - Existing 'xAI' Changed to 'SpaceXAI’.
-Support OpenAI 'GPT-5.6' series API.
-Support Grok Imagine - Image Editing.
-Support SpaceXAI ‘Grok 4.5’ API.
-Support Google ‘Nano Banana Lite’ API.
-Support Anthropic ‘Sonnet 5’ API.
-Moved default provider selection to its own page, with options to choose which providers are shown and reorder their display order.
-You can now save translation results as SayFlow conversations. From the translation screen, archive a result or open it directly as a new chat session.
-Improved the reliability of conversation saving and recovery.
-Made stopping responses and switching or deleting chats more accurate.
-Improved the safety and reliability of attachments, shared photos, and imported translations.
-Improved streaming responses and provider-specific error handling.
-Improved performance for long conversations and image exports.
-Enhanced accessibility and overall app stability.

### 1.0.4 — 2026-06-02

[v1.0.4]
* Added support for Anthropic’s Claude Opus 4.8 API
* App optimizations

### 1.0.3 — 2026-05-25

[v1.0.3]
* Improved some UI elements
* Optimizations related to reasoning process output
* Fixed an issue where built-in wallpapers, except for “None,” were affected by Dark Mode
* Fixed an issue where the temperature adjustment button was shown for the Gemini 3.5 Flash model
* Fixed an issue where copy, share, regenerate, and response time options were displayed in the reasoning process
* Fixed an issue where additional images could not be generated in the same session after generating an image with Nano Banana-series models
* Fixed an issue where image generation models could occasionally output two copies of the same image
* Updated the cost information for the DeepSeek V4 Pro model
* Added a share button to the photo preview screen
* Added pinch-to-zoom in/out support on the photo preview screen

## More apps by DONGHWAN CHOI

- [SayDay: All-in-One Planner](https://appshunter.io/ios/app/sayday-all-in-one-planner/id6761300584)

All apps by DONGHWAN CHOI: https://appshunter.io/developer/1888758596

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-14.*