Changelog

Tap the microphone in the message box to speak instead of type. Your speech is transcribed straight into the composer, so you can dictate questions hands-free.

Every assistant reply now has a read-aloud button. Listen to answers in a natural voice, and choose from several voices (Aria, Atlas, Sol and more) in Settings.

The system prompt is now cached across requests on supported models, and streamlined for signed-out users, so responses start sooner and cost less without changing answer quality.

The assistant now uses your browser timezone for “today”, “now”, and other time-sensitive answers instead of UTC.

When a model produces a malformed tool request, the assistant now repairs it automatically instead of failing, so web search, image generation, and other tools succeed more often.

Google has just announced Gemini 3.5 Flash and it is already available in the JustSimpleChat model picker. It is fast, supports up to one million tokens of context, and includes a thinking mode for harder prompts.

Auto Mode now picks Gemini 3.5 Flash for everyday simple and standard prompts, so replies come back quicker on routine questions. Harder prompts still route to higher-capability models when that is the better fit.

When a lighter model is the best fit, Auto Mode now uses Gemini 3.1 Flash Lite. It keeps responses snappy on short questions and quick follow-ups while reducing cost.

You can now import a public ChatGPT share link into JustSimpleChat from the Import chat link option in the sidebar. The imported conversation becomes a private chat in your JustSimpleChat history.

Changing a ChatGPT share URL to a JustSimpleChat share URL now opens the import flow with the link ready to review, so moving a public shared chat into JustSimpleChat is quicker.

A styling issue that could make the app look wrong on some phones and browsers has been corrected. The app should now keep a consistent dark appearance across chat, navigation, dialogs, and public pages.

The chat message box has been tidied up so the typing area and the model controls sit together more naturally, without extra lines or heavy focus styling getting in the way.

The assistant has expanded X support for finding posts, checking public profiles, reading timelines, and working with social context when those tools are available.

You can compare a response with another model from the chat, making it easier to see which model gives the better answer for the same prompt.

The model picker has been redesigned with search, categories, provider logos, and clearer controls for Auto Mode and reasoning preferences.

Mobile chat controls now fit more cleanly, avoid awkward overflow, and stop the keyboard from opening unexpectedly when browsing models.

The model trigger now keeps the right label after you choose a specific model, and model lists are less likely to appear empty while account access is loading.

Deep Research is now a fuller research workflow with progress updates, broader source coverage, report synthesis, and completed reports saved back into chat.

Memory support has been added with settings to view, manage, and pause memory use, giving you more control over what the assistant can remember.

Longer replies and background chat runs are more resilient, with better history updates while a response is still being generated.

Response typography, active chat highlighting, streaming indicators, and generated chat titles have been polished so conversations are easier to scan.

Agent tools now have stronger sandbox support, clearer tool activity, and better file download/export handling for generated work.

Auto Mode, provider fallbacks, model access rules, prompt caching, and simple-chat routing were tuned so everyday chats should feel quicker and fail less often.

PDF exports now handle more characters correctly, reducing failures caused by unsupported glyphs in generated documents.

Several behind-the-scenes fixes make login, payment verification, Stripe flows, and error reporting more reliable without adding friction to normal chat use.

The model catalogue has been refreshed with newer GPT, Claude, Grok, DeepSeek, OpenRouter, Cohere, Google, Mistral, Fireworks, and Together options. The aim is simple: more current models, fewer dead ends, and better choices in one place.

Auto Mode now uses fresh scorecard data to choose models more confidently for writing, coding, research, reasoning, and everyday chat. You can still pick a model yourself, but leaving it on Auto should now feel more reliable.

We removed duplicate model entries and turned off models that were failing live checks, so the picker should show fewer options that look available but fail when you try to use them.

Several providers now route through the most dependable connection available. That means fewer failed replies and a smoother experience when a model is best served through a partner route.

We updated the AI engine and app runtime behind JustSimpleChat. This is mostly invisible, but it helps keep the app faster, more compatible, and easier to improve.

The OpenAI model list has been refreshed, including newer GPT models and better handling for reasoning settings. This should make the latest OpenAI options easier to find and use.

The assistant is now better at deciding when web search is useful and when it should answer directly. Fresh information should still be searched, while normal questions should feel quicker.

A styling issue from the deployment pipeline was corrected, restoring the intended look and feel across the app.

Auto Mode now looks more carefully at what you are asking for before choosing a model. Simple tasks can use faster models, while harder reasoning and coding tasks can be sent to stronger ones.

Routing improvements help the app keep context when conversations become more detailed, especially when a task needs several replies to complete properly.

Some models are available through more than one provider. JustSimpleChat now does a better job choosing the cleaner route, which helps avoid confusing duplicates and failed attempts.

Model pages and comparison links have been refreshed so it is easier to browse popular models, compare options, and choose what fits your task.

The model selector now highlights a fresher set of strong everyday choices, so you do not need to dig through the full catalogue as often.

Recent model additions from providers including OpenRouter, Anthropic, xAI, and DeepSeek have been added or re-routed where needed, giving you more up to date options in one place.

New OpenAI models were added to the picker, including GPT-5.4, GPT-5.4 Pro, GPT-5.3, and related GPT options. This gives you newer choices for stronger reasoning, writing, coding, and general assistant work.

The model picker was updated so newer models appear more clearly and Auto Mode can favour stronger defaults where they make sense.

Added Kimi K2.5 from Moonshot AI and refreshed a wider set of OpenRouter models, giving you more choice for writing, reasoning, and longer conversations.

Tidied model copy and fixed small display issues so model details are easier to read and less likely to show awkward formatting.

Added the GPT-5.1 series and refreshed provider model settings, giving Auto Mode and manual selection newer OpenAI options to work with.

Cleaned up OpenRouter models, removed older Gemini 1.0 options, and added provider checks so unavailable models are easier to catch before they affect your chat.

Improved guest account creation and chat saving, including fixes for duplicate chat IDs and migration edge cases.

Added Gemini 3 Flash through Google, giving you another fast option for everyday questions, summaries, and general assistant work.

Added a fresh batch of models from the previous month across supported providers, keeping the model picker closer to what is currently available.

Sending messages now requires an account. This helps protect the service from abuse and keeps access more reliable for genuine users.

Updated the app framework and React packages with security fixes, along with safer handling for image generation routes.

Added Claude Opus 4.5, updated the OpenAI flagship list to GPT-5.1, added Grok 4.1 Fast from xAI, and added Olmo 3 from Ai2.

Auto Mode mappings were refreshed to make better use of Grok 4.1, GPT-5.1, and Claude Opus 4.5 when they are a good fit for the task.

Corrected Gemini 3 Pro model details and removed confusing duplicate entries so the picker is easier to trust.

Added more than 15 newer models from October and November releases, with the featured list updated so the strongest options are easier to find.

Plan access rules were refreshed so newly added higher-tier models are included correctly where your plan allows them.

Search behaviour was tuned so the assistant is less likely to over-search, loop, or fall back awkwardly when a normal answer is enough.

The system prompt limit was increased for large uploads, helping the assistant keep more useful context when working with bigger files or detailed instructions.

Added Claude Haiku 4.5 to the Anthropic model list, giving you another fast Claude option for lighter chats and everyday tasks.

Reasoning output now streams more naturally in the interface, so it is clearer when a model is thinking through a harder answer.

Gemini provider routing was refreshed through Vertex AI, with stronger chat streaming reliability and cleaner web tool behaviour.

Added early memory support and a text correction tool, making it easier for the assistant to help with ongoing context and quick writing fixes.

Uploaded files now carry clearer URLs into chat prompts, helping the assistant understand and refer back to attachments more reliably.

Added a full blog setup, expanded model pages, comparison pages, and new guides written in a more helpful consumer style.

Refreshed key public pages so it is easier to understand what JustSimpleChat offers, which providers are included, and how the platform compares.

Added GPT-5 Pro to the model list and featured options, with updated model details and cleaner handling in the picker.

Chats can now suggest useful follow-up questions after a reply, making it easier to keep exploring without thinking of the next prompt from scratch.

Added a more accurate streaming token tracker and clearer model badges with provider icons, so you can better see what model answered and how the response performed.

Fixed mobile overflow issues, improved follow-up formatting, and made guest-to-account chat migration more reliable.

The assistant now verifies answers by reading official pages directly. When asking about service status (like Royal Mail or Canada Post), flight updates, or government services, it fetches the actual page to give you accurate, real-time information instead of guessing.

Upgraded web search to use Perplexity by default for better quality results with clear source citations. Perfect for research, news, and finding authoritative information. The assistant automatically uses the right search tool based on what you need.

Just share a URL and ask the assistant to read it. Gets clean content without ads or clutter, perfect for analyzing articles, documentation, or research papers.

Updated to the latest AI technology stack with better performance and compatibility. Navigation between pages is now smoother and more responsive.

Fixed several technical issues to make everything run more smoothly and reliably.

Added Anthropic's latest Claude Sonnet 4.5 with superior coding, reasoning, and instruction following. Now featured at the top of the model picker with extended thinking mode and 200K context window.

Added DeepSeek's latest experimental model with DeepSeek Sparse Attention (DSA) for improved long-context efficiency. Features 163K context window with 65K output at 50%+ lower cost.

Complexity-aware model selection automatically picks the best model for your task based on benchmark data from over 280 AI models.

See tokens per second (TPS) for every response across all providers, helping you understand model speed and efficiency.

Added latest September 2025 models from OpenRouter including updated reasoning and coding specialists.

Improved authentication telemetry for faster troubleshooting and more reliable sign-ins.

Updated social media preview images and artwork for better sharing across platforms.

TPS timer now starts on first data chunk and estimates client-side for instant feedback without page refresh.

Added xAI's Grok 4 Fast with its 2M token context window and optional reasoning traces. It is now selectable in the model picker and Auto Mode routes to it for tougher reasoning tasks.

Promoted Grok 4 Fast across featured lists and fallbacks while keeping Grok 4 (0709) as the heavyweight fallback when you need deeper analysis.

Now featuring Qwen3 Next (instruct & thinking), Qwen Plus 0728, Qwen3 30B & 235B Thinking, StepFun Step3, Moonshot Kimi 0905, Sonoma Alpha previews, Seed OSS 36B, Cogito V2 previews, and NVIDIA Nemotron Nano 9B v2.

Each new model highlights its strengths (reasoning, coding, multimodal, long-context) so you can pick the right fit faster.

Every addition was live-tested so you can jump in without worrying about availability surprises.

Added “forgot password” and email verification so you can securely get back into your account.

More reliable guest and OAuth sign‑ins with clearer messages if something goes wrong.

Cleaner plan switching and smarter currency handling for a faster checkout.

Refreshed pages (Terms, Privacy, Changelog) and general UI copy/visual updates.

Resolved occasional issues with email handling and sign‑in on certain devices.

One‑click sign‑in options, plus classic email accounts. Stay as a guest if you prefer.

Ask questions that need fresh info. We search the web and summarize with sources.

Attach screenshots, photos, and PDFs so the assistant can see and discuss them.

Auto Mode chooses a great model for your task and enables “thinking” when helpful.

Hundreds of models supported across providers, with better defaults for speed and quality.

Access to the newest releases (like GPT‑5, Claude 4.1, and Grok 4) across providers.

Cleaner interface and easier flows across devices for a nicer feel.

Updated model comparison pages so you can pick with confidence.

General performance and reliability improvements across the app.

Let the AI take a more careful, step‑by‑step approach on harder tasks.

A guided mode that pulls from multiple sources and returns clear, cited summaries.

Lots of reliability fixes so sessions run smoothly without interruptions.

Quicker first responses thanks to routing and caching improvements.

Access Anthropic's latest Claude with stronger reasoning and coding skills.

New open‑weight GPT OSS options for creative work and problem‑solving.

The router now picks improved defaults so you get great results with less effort.

More choices for reasoning and coding tasks with excellent language coverage.

Improved formatting and highlighting makes generated code easier to read.

Better handling for images and documents so you can keep working without hiccups.

Resolved rare cases where messages didn’t send correctly during streaming.

Uploaded files stay “in mind” longer so follow‑ups feel more natural.

Smoother handling of bigger files with better caching.

Fewer interruptions while the AI is replying.

Start a chat, add images and PDFs, and get helpful answers.

Stop an answer mid‑way when you already have what you need.

See when tools run and how results show up in the conversation.

A round of fixes for uploads, scrolling, and login edge cases.