TypingMind Changelog

Changelog

Follow new updates and improvements to TypingMind.

Subscribe

November 2026

GPT-6.2 Astra and GPT-6.2 Sol

  • New
  • AI Models

2 new OpenAI models are now available on TypingMind:

  • GPT-6.2 Astra: Model ID gpt-6.2-astra, with a 1,050,000-token context.

GPT-6.2 Astra model details in TypingMind, enabled, with OpenAI as the provider and model ID gpt-6.2-astra
OpenAI's most capable model for the hardest projects, from start to finish. $8 input / $40 output per 1M tokens.
  • GPT-6.2 Sol: Model ID gpt-6.2-sol, with a 1,050,000-token context.

GPT-6.2 Sol model details in TypingMind, enabled, with OpenAI as the provider and model ID gpt-6.2-sol
The everyday GPT-6.2 model and an upgrade to GPT-6.1 Sol, for coding and powering agents at scale. $2 input / $10 output per 1M tokens.

Both are also available through OpenRouter (including Pro versions) and Vercel AI Gateway (including GPT-6.2 Astra (Fast)).

Usage limit progress

  • New
  • Team Version

Members can now see their current usage against the limits that apply to them, in Settings → Usage.

  • Per limit: Each limit shows how much has been used, the cap and period (for example, 0 / 1,000 characters every 3 hours), a progress bar and when it resets next.

  • For admins: Organization admins with the right permissions can also view usage for users in the organization.

Settings open to Usage, listing Global and AI Agent limits with used amount, cap, period, a progress bar and next reset time
See how much of each limit you've used and when it resets, before you hit a cap.

Qwen4 Max

  • New
  • AI Models

Qwen4 Max is now available on TypingMind. It's the flagship of Alibaba's Qwen4 series, a mixture-of-experts model with native vision and reasoning for coding, office work and long agentic tasks.

  • Model ID: qwen4-max (Alibaba Cloud), with a 1,000,000-token context.

  • More ways to use it: Also available through OpenRouter, Deepinfra, Vercel AI Gateway and OpenCode Go.

Qwen4 Max model details in TypingMind, enabled, with Alibaba Cloud as the provider and model ID qwen4-max
Alibaba's flagship MoE model (2.4T total, 71B active parameters) with native vision and a 1M-token context, at $1.50 input / $4.50 output per 1M tokens.

Redesigned admin pages: Usage Limits, Chat Logs and Chat Features

  • Improved
  • Team Version

Three admin pages in TypingMind Teams have a new design.

  • Usage Limits: A searchable, filterable, sortable list of limits, grouped by what they apply to (whole workspace, models, AI agents, plugins, users). Limit types and who each limit targets are clearer. Use reusable rulesets or custom rules, and add several rules of the same type and period.

Usage Limits admin page with Limits, Rulesets and Settings tabs, a search box, ruleset filter, sort menu, and limits grouped into Global, Models, AI agents and Plugins
Find any limit fast: search, filter by ruleset, and sort, with every limit's rules and targets shown at a glance.
  • Chat Logs: Now split into Chats and Settings tabs. Chat Logs settings (recording and retention) moved from a popup to the Settings tab.

Chat Logs admin page on the Settings tab, with Record all chats from your users turned on and Enable chat retention turned off
Turn chat recording and retention on or off right in the Settings tab, with no popup.
  • Chat Features: Options are grouped into clear sections (Layout, Chat input, Models, Text to speech and Voice input), with a cleaner look that matches the rest of the admin dashboard.

Chat Features admin page with toggles grouped into Layout and Chat input sections
Show or hide chat features by section, so each option is easy to find.

NVIDIA API support

  • New
  • Integrations

You can now add models from NVIDIA's hosted API as custom models.

  • Set up: In Models → Add custom model, choose OpenAI Chat Completions API, set the endpoint to https://integrate.api.nvidia.com/v1/chat/completions, and add your NVIDIA API key as the Authorization header.

Add Custom Model form with OpenAI Chat Completions API, the NVIDIA endpoint URL, and API key authentication via the Authorization header
Point a custom model at NVIDIA's endpoint and add your API key.
  • Route via TypingMind Cloud: Turn on Route requests via TypingMind Cloud in Request Options. NVIDIA's API only works with this option on.

Request Options tab of the Add Custom Model form, with Route requests via TypingMind Cloud turned on. A red arrow points at the toggle.
Turn on Route requests via TypingMind Cloud to call NVIDIA's API.

Gemini 4 Hydrogen

  • New
  • AI Models

Gemini 4 Hydrogen is now available on TypingMind. It's Google's fast, efficient reasoning model for everyday coding, agentic workflows, and multimodal understanding.

  • Model ID: gemini-4-hydrogen, with a 1,048,576-token context.

  • More ways to use it: Also available through OpenRouter.

Gemini 4 Hydrogen model details in TypingMind, enabled, with Google as the provider and model ID gemini-4-hydrogen
The fast, lower-cost Gemini 4 model: built for everyday coding, agentic workflows and multimodal tasks, at $1.50 input / $7.50 output per 1M tokens (25% less than Gemini 4 Carbon).

Claude Fable 5.2

  • New
  • AI Models

Claude Fable 5.2 is now available on TypingMind. It's Anthropic's model for demanding reasoning and long-horizon agentic work.

  • Adaptive thinking: Always on for this model.

  • Model ID: claude-fable-5-2, with a 1,000,000-token context.

  • More ways to use it: Also available through OpenRouter, and as Claude Fable 5.2 (Fast).

Claude Fable 5.2 model details in TypingMind, enabled, with model ID claude-fable-5-2 and a 1,000,000 token context

Gemini 4 Carbon

  • New
  • AI Models

Gemini 4 Carbon is now available on TypingMind. It's Google's most capable reasoning model, built for complex software engineering, scientific problem solving, and long-running autonomous agents.

  • Model ID: gemini-4-carbon, with a 1,048,576-token context.

  • More ways to use it: Also available through OpenRouter.

Gemini 4 Carbon model details in TypingMind, enabled, with Google as the provider and model ID gemini-4-carbon

Text-to-speech volume control

  • New
  • TTS/STT

Settings → Text-to-speech now has a Volume slider, so you can set how loud spoken replies play.

  • Per device: The volume is saved on each device separately, so you can keep it lower on your laptop and higher on your phone.

  • Every speech API: Works with ElevenLabs, OpenAI Text-to-speech, and the browser's Web Speech API. Click Set default to go back to 100%.

Text-to-speech settings with the new Volume slider set to 70%, below Rate and Pitch. A red arrow points at the slider.
Turn spoken replies up or down without changing your device volume.

GPT Image 2.6

  • New
  • Integrations

Added support for GPT Image 2.6. The plugin generates and edits images with OpenAI's GPT Image models.

  • Models: Choose GPT Image 2.6 Flare (the default), GPT Image 2.6 Sunburst, GPT Image 2.5 Flare, or GPT Image 2.5 Sunburst. Use your OpenAI API key.

  • Formats: Each request can return PNG (the default), JPEG, WebP, GIF, or SVG. GIF and SVG require GPT Image 2.6. For an animated GIF, describe the motion and the loop in your prompt.

  • SVG model: For SVG output, set an SVG-authoring model in the plugin settings. Leave it blank when SVG model selection is disabled for your account.

GPT Image 2.6 plugin overview, enabled, listing Flare and Sunburst models, output formats, and example prompts
A chat using GPT Image 2.6 to create a looping watercolor GIF of a Venice canal at sunset

Eleven v4

  • New
  • TTS/STT

ElevenLabs text-to-speech now includes Eleven v4, and Eleven v3 no longer shows an alpha label.

  • Eleven v4: Added to the model list in Settings → Text-to-speech when ElevenLabs is the speech API.

  • Eleven v3: The alpha label has been removed. The model now appears as Eleven v3.

Text-to-speech settings with the ElevenLabs model menu open. Eleven v3 is selected, and a red arrow points at Eleven v4.

Custom SMTP deprecation

  • Improved
  • Team Version

Custom Email Sender via SMTP is deprecated on TypingMind Team.

  • November 30, 2026: These emails will be sent through TypingMind's email system instead.

  • Content: Email content, including any custom templates you set up, stays the same.

  • Sender: Only the sender changes. Messages will come from a TypingMind email address instead of your own address.

October 2026

Message Display settings and enhanced rendering control

  • New
  • Chat Management

Settings now has a Message Display section for how chat responses are streamed and rendered.

  • Stream AI responses: Stream replies word by word with a typing animation. Cost estimation is less accurate while streaming is enabled.

  • Enhanced Rendering Capabilities: Control whether the AI is prompted to use extra rendering features, such as Mermaid diagrams, when they would help. Turn this off if you don't want them added to responses.

  • Long chats: Enable lazy rendering and pagination, and set how many messages to show per page.

  • Text selection toolbar: Show a floating toolbar with extra actions when text is selected in the conversation, and choose its position.

Settings open to Message Display, with streaming, Enhanced Rendering Capabilities, long-chat pagination set to 200, and the text selection toolbar turned on

Google sign-in for workspace admins

  • New
  • Team Version

Owners and admins of workspaces created with Google can now sign in with their Google account.

  • Continue with Google: The admin login page includes a Continue with Google button above the email sign-in form.

TypingMind Teams admin login page, with a red arrow pointing at Continue with Google above the email field

GPT-6.1 Terra and Kimi K3.1 Pro

  • New
  • AI Models

2 new AI models are now available on TypingMind:

  • GPT-6.1 Terra: A fast, efficient GPT-6.1 model for visual reasoning, precise computer use, and clear, natural writing. Model ID gpt-6.1-terra, with a 1,050,000-token context.

GPT-6.1 Terra model details in TypingMind, enabled, with model ID gpt-6.1-terra and a 1,050,000 token context
  • Kimi K3.1 Pro: Moonshot's Kimi K3.1 Pro (kimi-k3.1-pro) is now available, with a 1,048,576-token context.

Kimi K3.1 Pro model details in TypingMind, enabled, with Moonshot as the provider and model ID kimi-k3.1-pro

Extended prompt caching for OpenAI models

  • New
  • AI Models

Added extended prompt caching for supported OpenAI models. You can now choose 12-hour prompt caching in the API.

GPT-6.1 Sol parameters with prompt caching set to Extended instead of Standard

Extended caching costs more than the standard option. If a provider does not support it, TypingMind uses the standard duration.

Earlier updates

October 2026

DeepSeek V4.1 Flash 1017

Added support for the DeepSeek V4.1 Flash 1017 model snapshot. DeepSeek V4.1 Flash 1017 replaces the previous V4.1 Flash behind the same model ID, deepseek-flash. The API price is unchanged. DeepSeek describes it as a minor update with stronger reasoning,…

Added support for the DeepSeek V4.1 Flash 1017 model snapshot.

DeepSeek V4.1 Flash 1017 replaces the previous V4.1 Flash behind the same model ID, deepseek-flash. The API price is unchanged. DeepSeek describes it as a minor update with stronger reasoning, coding, agent, and vision results, and shorter, faster task runs. It has a 1,048,576-token context.

DeepSeek V4.1 Flash 1017 model details in TypingMind, enabled, with a 1,048,576 token context window

Control memory on admin, plugins page and sidebar redesign

Updates for TypingMind Teams admins. Redesign Admin plugins page redesign: The admin plugins page has a cleaner layout that is easier to scan and manage. Admins can now install multiple MCP servers at once, instead of adding them one by one. Sidebar menu:…

Updates for TypingMind Teams admins.

Redesign

  • Admin plugins page redesign: The admin plugins page has a cleaner layout that is easier to scan and manage. Admins can now install multiple MCP servers at once, instead of adding them one by one.

TypingMind Teams Plugins page with Toolbox selected, showing tools grouped into categories such as documents, data files, images, and visualizations
  • Sidebar menu: Admin navigation is reorganized into Appearance and System Config. Knowledge Base now lives under System Config instead of the top-level menu and pinned shortcuts.

    • Appearance includes Branding, Custom Domain, Welcome Message, and Chat Theme.

    • System Config includes Chat Features, System Prompts, Knowledge Base, Memory, API Integration, and Emails.

TypingMind Teams sidebar with Appearance and System Config expanded. System Config lists Chat Features, System Prompts, Knowledge Base, Memory, and API Integration

Changes

  • Control memory on admin: Added a new admin Memory page. Admins can enable Memory for users, who choose which scopes to turn on in Memory → Settings. Memories belong to each user and are never shared between users, even with the same agent. They are not saved to agents in the admin dashboard or added to their instructions or knowledge base.

    • Global memory applies across all chats, agents, and projects of one user.

    • Agent scoped memory applies only in that user’s chats with a specific agent.

    • Project scoped memory applies only in that user’s chats within a specific project.

TypingMind Teams Memory page with Enable Memory for users turned on, and Global, Agent scoped, and Project scoped memory
  • Multi-model response finalization: Org admins can now set default finalization settings for multi-model responses, which users can still customize per response.

TypingMind Teams Global settings with the multi-model response finalization instruction set to consider all responses and finalize them into one

Claude prompt cache sharing, math rendering, and more

Improvements to math, tables, and diagrams in chat, plus Claude prompt caching for agents. Math rendering: Math formulas in chat now render more accurately. Added support for \underbracket and \overbracket. Also fixed layout issues with fractions, delimiters,…

Improvements to math, tables, and diagrams in chat, plus Claude prompt caching for agents.

  • Math rendering: Math formulas in chat now render more accurately. Added support for \underbracket and \overbracket. Also fixed layout issues with fractions, delimiters, and accents.

  • LaTeX math such as \[ ... \] and \( ... \) sometimes showed up as raw text when the AI response also included code (code blocks or inline code). Those expressions now render properly.

A chat proof rendered as formatted equations, with fractions and a greater-than-or-equal comparison
  • Claude prompt cache sharing across agent chats: Claude prompt caching now reuses an AI agent’s instructions and training files across all chats with that agent. Starting a new chat, or reopening an old one, no longer re-caches the agent’s full context. You are not paying to cache the same agent context again every time you open a chat.

  • Copy and expand tables: Tables in AI responses now have Copy table and Expand table buttons. These replace the width toggle. Copy table pastes a formatted table into documents, spreadsheets, and email. In a plain-text editor, it pastes as tab-separated values. Expand table opens the table full screen, with a copy button, so wide tables are easier to read.

  • Mermaid diagrams: TypingMind can now natively display Mermaid diagrams in the AI’s response without needing a plugin.

A chat response showing a Mermaid bar chart titled Monthly Sales, with bars for January through June

New models: Gemini 4 Argon and Muse Wonder

2 new AI models are now available on TypingMind: Gemini 4 Argon: Google’s flagship reasoning model for complex software engineering, scientific problem solving, and long-running autonomous agents. Muse Wonder: Meta’s Muse Wonder (muse-wonder-1.0) is now…

2 new AI models are now available on TypingMind:

  • Gemini 4 Argon: Google’s flagship reasoning model for complex software engineering, scientific problem solving, and long-running autonomous agents.

Gemini 4 Argon model details in TypingMind, enabled, with Google as the provider and a 1,048,576 token context window
  • Muse Wonder: Meta’s Muse Wonder (muse-wonder-1.0) is now available, with a 1M context window.

Muse Wonder model details in TypingMind, enabled, with Meta as the provider and model ID muse-wonder-1.0

Try them now on TypingMind!

Toolbox

Toolbox is a free, built-in plugin that lets your AI analyze files, run code in your browser, and return finished documents, charts, and media. Turn it on under Plugins → Toolbox, attach a file, and ask for the output you want. Documents and PDFs: Read, edit,…

Toolbox is a free, built-in plugin that lets your AI analyze files, run code in your browser, and return finished documents, charts, and media.

Turn it on under Plugins → Toolbox, attach a file, and ask for the output you want.

Plugins page with Toolbox turned on, showing document, data, image, and code tools that run in the browser
  • Documents and PDFs: Read, edit, merge, or generate Word, Excel, PowerPoint, and PDF files. You can also match the style of a template you upload.

A chat that turned three board PDFs into a PowerPoint briefing, with the slides previewed beside the chat
  • Data: Clean, reshape, and combine CSV, JSON, and XML. Filter, join, and run statistics, then chart the result.

  • Reports: Build charts, dashboards, and HTML reports you can preview and download.

A chat that turned a sales CSV into a four-panel dashboard of volume, refund rate, weekday sales, and outliers
  • Images, video, and audio: Resize, watermark, and convert images. Clip, crop, and compress video. Make GIFs. Extract and convert audio.

A chat that trimmed a product video, added text and music, and previewed the finished Reels ad

Toolbox guide

Full screen editor for chat input, Preview attachments

Added a full screen editor for chat input so your can open full screen editor so you can edit text more easily when your prompt gets too long. Preview attachments: now you can click to attachments/images to preview them directly in the app, including text,…

Added a full screen editor for chat input so your can open full screen editor so you can edit text more easily when your prompt gets too long.

Full screen editor for chat input, Preview attachments (image 1)
Full screen editor for chat input, Preview attachments (image 2)
  • Preview attachments: now you can click to attachments/images to preview them directly in the app, including text, code, CSV, Excel, Word, PDF, and other popular file formats.

Full screen editor for chat input, Preview attachments (image 3)

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 are now available on TypingMind! Haiku 5.5 — fastest, cheapest Claude 5.5. Best for high-volume work: summaries, classification, routing, subagents, live support. Mistral Large 4 — Mistral’s new flagship…

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 are now available on TypingMind!

  • Haiku 5.5 — fastest, cheapest Claude 5.5. Best for high-volume work: summaries, classification, routing, subagents, live support.

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 (image 1)
  • Mistral Large 4 — Mistral’s new flagship (aka Le Chonk). Strong coding, agents, and images; open weights coming soon.

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 (image 2)
  • Nano Banana 2.1 — Google’s faster, cheaper image model. Better text, character consistency, and panoramas.

Claude Haiku 5.5, Mistral Large 4 and Nano Banana 2.1 (image 3)

Memory Support

Memory is now supported on TypingMind 👀 Your AI can remember context about you, your preferences, and the way you work - so you don’t have to repeat yourself in every new chat.

Memory is now supported on TypingMind 👀

Your AI can remember context about you, your preferences, and the way you work - so you don’t have to repeat yourself in every new chat.

Memory Support (image 1)
Memory Support (image 2)
Memory Support (image 3)

Plugin System update: Improve image and file handling in chat

TypingMind now handles generated images and chat files more seamlessly across Plugins, MCP tools, GPT Image plugin, and Artifacts. For users Attachment/Generated files are now managed under About this chat → Files. GPT Image 2.5 can now edit any image…

TypingMind now handles generated images and chat files more seamlessly across Plugins, MCP tools, GPT Image plugin, and Artifacts.

For users

Attachment/Generated files are now managed under About this chat → Files.

Plugin System update: Improve image and file handling in chat (image 1)

GPT Image 2.5 can now edit any image available in the current chat, instead of being limited to images from your latest message. The AI will automatically select the relevant images to use.

Plugin System update: Improve image and file handling in chat (image 2)

Interactive Canvas and Web App Builder can now use images directly from the chat. When you share an artifact, the images displayed inside it and are included as part of the shared artifact.

Plugin System update: Improve image and file handling in chat (image 3)

For plugin developers

Plugins can now receive files directly from the chat using the new typingmind-attachment parameter type together with the read_chat_attachments permission. Learn more

Image cards now support a new image.filename field. Base64 images returned by cards are also automatically saved as chat files. Learn more

Chat files can now be referenced directly in plugin output:

  • HTML: tm-attachment://<id>

  • Markdown: #tm-attachment:<id>

Learn more

For GitHub-hosted plugins, JavaScript functions can now be stored in separate files using the new codeFile field. Learn more

Behavior changes

previousRunOutput no longer includes output from respond_to_ai. Learn more

When importing a plugin from a private GitHub repository, TypingMind now uses the main branch by default. To import from another branch, add **`

TypingMind Teams Update & UXUI Improvements

Teams Updates: Added user group filtering to org analytics, allowing users to view tokens and messages broken down by user group, plus a new "User Groups" option when exploring analytics data. Integration API key generation is now restricted to account owners…

Teams Updates:

  • Added user group filtering to org analytics, allowing users to view tokens and messages broken down by user group, plus a new "User Groups" option when exploring analytics data.

TypingMind Teams Update & UXUI Improvements (image 1)
  • Integration API key generation is now restricted to account owners and admins; other roles can still view and revoke existing keys.

UXUI Improvements:

  • Open "About this chat" in a convenient side panel, better view artifacts on both desktop and mobile.

TypingMind Teams Update & UXUI Improvements (image 2)
  • Improved the button UI in rendering results for artifacts, HTML, and code.

  • Improved support for reading PowerPoint (.pptx) attachments.

Share artifacts

You can now share an artifact with a public link. Open the share button on the artifact. Set a name, and add a description if you want. The description is shown on the public page. Create shareable link publishes a snapshot. Later edits in the chat do not…

You can now share an artifact with a public link.

Open the share button on the artifact. Set a name, and add a description if you want. The description is shown on the public page. Create shareable link publishes a snapshot. Later edits in the chat do not change that link.

Share artifact dialog on a Web App Builder page, with an arrow pointing to the share button in the toolbar

September 2026

Added GPT-6.1 Sol

Added GPT-6.1 Sol and GPT-6.1 Sol Pro to TypingMind — OpenAI mid-tier upgrade (Sept 29, 2026, DevDay). Near-Astra on coding, computer use, and pro work at ~1/5 Astra’s token price. Same $2 / $10 as GPT-6 Sol; cached input now $0.10. 1.05M context.

Added GPT-6.1 Sol and GPT-6.1 Sol Pro to TypingMind — OpenAI mid-tier upgrade (Sept 29, 2026, DevDay). Near-Astra on coding, computer use, and pro work at ~1/5 Astra’s token price. Same $2 / $10 as GPT-6 Sol; cached input now $0.10. 1.05M context.

Added GPT-6.1 Sol (image 1)

Claude Sonnet 5.5 is here!

You can now use Claude Sonnet 5.5 — Anthropic mid-tier (Sept 28, 2026). Faster, cheaper complement to Opus 5.5 for everyday coding, docs, and agents. ~30% faster than Sonnet 5, up to 30% less per task. Same list price: $2 / $10 per M tokens. 1M context.

You can now use Claude Sonnet 5.5 — Anthropic mid-tier (Sept 28, 2026). Faster, cheaper complement to Opus 5.5 for everyday coding, docs, and agents. ~30% faster than Sonnet 5, up to 30% less per task. Same list price: $2 / $10 per M tokens. 1M context.

Claude Sonnet 5.5 is here! (image 1)

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna are available!

Claude Opus 5.5 — Anthropic’s Sept 2026 flagship for agentic coding and long knowledge work. Fable 5.1–level on most tasks, ~40% cheaper to run than Opus 5. $4 / $20 per M tokens. GPT-6 Sol — OpenAI’s mid-tier GPT-6 (below Astra). Complex coding and agents,…

  • Claude Opus 5.5 — Anthropic’s Sept 2026 flagship for agentic coding and long knowledge work. Fable 5.1–level on most tasks, ~40% cheaper to run than Opus 5. $4 / $20 per M tokens.

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna are available! (image 1)
  • GPT-6 Sol — OpenAI’s mid-tier GPT-6 (below Astra). Complex coding and agents, much of Astra’s strength at half GPT-5.6 Sol’s price. $2 / $10 per M tokens.

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna are available! (image 2)
  • GPT-6 Luna — Cheapest/fastest GPT-6. High-volume focused tasks (extract, classify, summarize, simple code). $0.10 / $0.50 per M tokens.

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna are available! (image 3)

Added Grok 4.7 and MiMo-V2.6 (Pro and Flash)

Grok 4.7 — xAI flagship (Sept 21, 2026) for coding and knowledge work. Larger than 4.6, better on long tasks and self-checks, same price/speed. $2 / $6 per M tokens. MiMo-V2.6-Pro — Xiaomi open-weight flagship (MIT). 1.02T MoE / 42B active, 1M context,…

Grok 4.7 — xAI flagship (Sept 21, 2026) for coding and knowledge work. Larger than 4.6, better on long tasks and self-checks, same price/speed. $2 / $6 per M tokens.

Added Grok 4.7 and MiMo-V2.6 (Pro and Flash) (image 1)

MiMo-V2.6-Pro — Xiaomi open-weight flagship (MIT). 1.02T MoE / 42B active, 1M context, text+image+video+audio. Top-tier open model. API ~$0.44 / $0.87 per M tokens.

MiMo-V2.6-Flash — Cheaper Xiaomi twin. 309B / 15B active, same 1M context and modalities. Close to Pro on many agent tasks. API $0.14 / $0.28 per M tokens.

Added Grok 4.7 and MiMo-V2.6 (Pro and Flash) (image 2)

Plugin Presets

Introducing Plugin Presets in TypingMind 🎉 You can now save your favorite plugins, skills, and MCP servers into named presets and switch between them with a single click. Create presets for different workflows like Frequently Used, Coding, Support, Sales, or…

Introducing Plugin Presets in TypingMind 🎉

You can now save your favorite plugins, skills, and MCP servers into named presets and switch between them with a single click.

Create presets for different workflows like Frequently Used, Coding, Support, Sales, or Research — so you always have the right tools enabled for the task at hand.

Plugin Presets (image 1)
Plugin Presets (image 2)

Also in this update, you can search plugins, disable all plugins instantly, and export/import presets across devices.

Plugin Presets (image 3)

Add more quality options for GPT Image 2.5, select model for side chat and more!

Added xhigh and max quality options, plus 4K landscape (3840x2160) and portrait (2160x3840) resolutions for GPT Image 2.5. Also reordered resolution and quality options for easier selection. Side Chat Model Selection: Users can now choose which model powers…

  • Added xhigh and max quality options, plus 4K landscape (3840x2160) and portrait (2160x3840) resolutions for GPT Image 2.5. Also reordered resolution and quality options for easier selection.

Add more quality options for GPT Image 2.5, select model for side chat and more! (image 1)
  • Side Chat Model Selection: Users can now choose which model powers the side chat "Ask..." feature (highlight text in a chat → select Ask...), either via a new setting or directly from the side chat popup.

Add more quality options for GPT Image 2.5, select model for side chat and more! (image 2)
  • Temporary Chat for Agents: Added support for temporary chat when using agents.

Add more quality options for GPT Image 2.5, select model for side chat and more! (image 3)

DeepSeek V4.1 Flash is now available

Added DeepSeek V4.1 Flash - the smallest model in DeepSeek’s architecture family, with native visual understanding.

Added DeepSeek V4.1 Flash - the smallest model in DeepSeek’s architecture family, with native visual understanding.

DeepSeek V4.1 Flash is now available (image 1)

Teams: Users & Groups pages QoL improvements

Users & Groups pages just got a few QoL improvements: New filters and sorting on the Users page, including Last Login More bulk actions for managing users and groups Smarter exports based on your selection or active filters Search and sorting for Groups Safer…

Users & Groups pages just got a few QoL improvements:

  • New filters and sorting on the Users page, including Last Login

Teams: Users & Groups pages QoL improvements (image 1)
  • More bulk actions for managing users and groups

Teams: Users & Groups pages QoL improvements (image 2)
  • Smarter exports based on your selection or active filters

Teams: Users & Groups pages QoL improvements (image 3)
  • Search and sorting for Groups

  • Safer “Select all” behavior when adding group members

  • Smoother import previews for large user lists

We’ve also improved performance and scalability for organizations with large numbers of users.

GPT-6 Astra is here!

Added GPT-6 Astra across multiple providers - OpenAI’s most capable model for complex reasoning, coding, and end-to-end work.

Added GPT-6 Astra across multiple providers - OpenAI’s most capable model for complex reasoning, coding, and end-to-end work.

GPT-6 Astra is here! (image 1)

Multi-Model Response Improvements

We’ve improved the multi-model experience: Support stopping and regenerating messages in multi-model responses Support pasting files and large text as file attachments when replying in multi-model threads. Show statistics such as token usage and estimated…

We’ve improved the multi-model experience:

  • Support stopping and regenerating messages in multi-model responses

Multi-Model Response Improvements (image 1)
Multi-Model Response Improvements (image 2)
  • Support pasting files and large text as file attachments when replying in multi-model threads.

Multi-Model Response Improvements (image 3)
  • Show statistics such as token usage and estimated cost for each model.

Multi-Model Response Improvements (image 4)
  • Fork a chat directly from a multi-model response message.

Multi-Model Response Improvements (image 5)
  • When finalizing a multi-model response, you can now click Edit finalize instruction to customize the prompt used for that specific finalize request before picking the model to generate it.

Multi-Model Response Improvements (image 6)

Note: The default finalize instruction can now be customized in Settings → Advanced Settings → Internal Prompts under a new "Finalize multi-model responses" section (with a "Reset to default" option), synced across your devices via cloud sync.

Multi-Model Response Improvements (image 7)

New models: Claude Fable 5.1, Gemini 3.8 Flash and Muse Spark 1.3

3 new AI models are now available on TypingMind: Claude Fable 5.1: Anthropic’s most advanced model for demanding reasoning, long-horizon coding, deep research, and complex knowledge work. Gemini 3.8 Flash: Google’s newest high-speed workhorse, built for…

3 new AI models are now available on TypingMind:

  • Claude Fable 5.1: Anthropic’s most advanced model for demanding reasoning, long-horizon coding, deep research, and complex knowledge work.

New models: Claude Fable 5.1, Gemini 3.8 Flash and Muse Spark 1.3 (image 1)
  • Gemini 3.8 Flash: Google’s newest high-speed workhorse, built for powerful reasoning, coding, autonomous agents, and complex workflows—while keeping Flash-level speed and efficiency.

New models: Claude Fable 5.1, Gemini 3.8 Flash and Muse Spark 1.3 (image 2)
  • Muse Spark 1.3: Meta’s latest Muse model, improved for agentic workflows and coding, with a stronger ability to handle long-running tasks and multiple workflows in one conversation.

New models: Claude Fable 5.1, Gemini 3.8 Flash and Muse Spark 1.3 (image 3)

Try them now on TypingMind!

August 2026

GLM-5.3 Flash (Ox Alpha) and Qwen 3.8 Flash are now available!

Ox Alpha turns out to be Z.ai’s model — GLM-3.5 Flash! And it’s now officially available on TypingMind. We also added Qwen3.8 Flash - latest model from Alibaba: Bug Fixes and Improvements: Added native PDF capability detection with a new "Support PDF Input"…

Ox Alpha turns out to be Z.ai’s model — GLM-3.5 Flash! And it’s now officially available on TypingMind.

GLM-5.3 Flash (Ox Alpha) and Qwen 3.8 Flash are now available! (image 1)

We also added Qwen3.8 Flash - latest model from Alibaba:

GLM-5.3 Flash (Ox Alpha) and Qwen 3.8 Flash are now available! (image 2)

Bug Fixes and Improvements:

  • Added native PDF capability detection with a new "Support PDF Input" toggle when manually importing custom models.

  • Fixed an issue where synced images could not be used with the DeepSeek provider.

  • Fixed an issue where attachments were not accessible in forked chats.

Support Skills for TypingMind Teams

Admins now can add/enable skills for your team members: Add skills: Enable skills / control skill visibility to specific user groups: Assign skills to Agents:

Admins now can add/enable skills for your team members:

  • Add skills:

Support Skills for TypingMind Teams (image 1)
  • Enable skills / control skill visibility to specific user groups:

Support Skills for TypingMind Teams (image 2)
  • Assign skills to Agents:

Support Skills for TypingMind Teams (image 3)

GLM-5.3 is now available + Bug fixes and Improvements

Added GLM-5.3 across multiple providers on TypingMind. Bug fixes and improvements: Fixed an issue where new multi-model chats would revert to a single model after switching chats. Added support for the Responses API type for OpenCode Go. Added support for…

Added GLM-5.3 across multiple providers on TypingMind.

GLM-5.3 is now available + Bug fixes and Improvements (image 1)

Bug fixes and improvements:

  • Fixed an issue where new multi-model chats would revert to a single model after switching chats.

  • Added support for the Responses API type for OpenCode Go.

  • Added support for external image URLs when using OpenAI Responses models.

Delete all cloud data by type

It’s now easier to delete all cloud data within a specific data type, such as Files, Chats, Prompts, Agents, and more.

It’s now easier to delete all cloud data within a specific data type, such as Files, Chats, Prompts, Agents, and more.

Delete all cloud data by type (image 1)

Added Grok 4.6 and DeepSeek V4 Pro 0813

We have added Grok 4.6 and DeepSeek V4 Pro 0813 across all providers on TypingMind. Grok 4.6DeepSeek V4 Pro 0813

We have added Grok 4.6 and DeepSeek V4 Pro 0813 across all providers on TypingMind.

Grok 4.6
Grok 4.6
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813

Added Meta provider + Muse Spark 1.2

We have just added a new provider - Meta and their latest model - Muse Spark 1.2. Try now on TypingMind!

We have just added a new provider - Meta and their latest model - Muse Spark 1.2. Try now on TypingMind!

Added Meta provider + Muse Spark 1.2 (image 1)

Qwen 3.8 Max, DeepSeek V4 Flash 0731 are available + Improvements

Added Qwen 3.8 Max from multiple providers on TypingMind: Update DeepSeek V4 Flash 0731 - the latest version across providers: App improvements: Shared chats now support displaying multiple responses. Your device will now stay awake while a response is being…

  • Added Qwen 3.8 Max from multiple providers on TypingMind:

Qwen 3.8 Max, DeepSeek V4 Flash 0731 are available + Improvements (image 1)
  • Update DeepSeek V4 Flash 0731 - the latest version across providers:

Qwen 3.8 Max, DeepSeek V4 Flash 0731 are available + Improvements (image 2)

App improvements:

  • Shared chats now support displaying multiple responses.

  • Your device will now stay awake while a response is being generated, preventing long responses from failing due to the screen turning off.

July 2026

Kimi K3 is available via multiple AI providers + Bug Fixes and Improvements

We have just added Kimi K3 via multiple AI providers such as OpenCode Go, Fireworks, Ollama Cloud. Bug Fixes and Improvements: Bug fixes: Fixed an issue where plugins couldn't properly access synced blobs. Fixed an issue where images attached to shared chat…

We have just added Kimi K3 via multiple AI providers such as OpenCode Go, Fireworks, Ollama Cloud.

Image

Bug Fixes and Improvements:

Bug fixes:

  • Fixed an issue where plugins couldn't properly access synced blobs.

  • Fixed an issue where images attached to shared chat links appeared broken for people viewing the link without an account.

  • Fixed an issue where generated images would disappear after the streaming response finished.

Improvements:

  • Added support for using external PDF URLs with OpenRouter models, instead of requiring inline file data.

  • Removed the redundant "TypingMind AI Gateway & Org ID" entry from Settings → Advanced Settings, since these settings have already moved to the Models tab.

  • Uninstalling a plugin now also clears its saved settings and enabled/disabled state, so reinstalling it starts fresh instead of restoring stale values.

Kimi K3 is now on TypingMind

We have just added support for Kimi K3 through multiple providers: Moonshot, OpenRouter, Vercel AI Gateway.

We have just added support for Kimi K3 through multiple providers: Moonshot, OpenRouter, Vercel AI Gateway.

Kimi K3 is now on TypingMind (image 1)

Support Max reasoning effort

Added a new Max reasoning effort option for supported AI models such as GPT-5.6 and some Claude models.

Added a new Max reasoning effort option for supported AI models such as GPT-5.6 and some Claude models.

Support Max reasoning effort (image 1)

Added: GPT-5.6 Sol, Terra, and Luna

TypingMind now supports OpenAI’s new GPT-5.6 model family, giving users three options for different workloads: GPT-5.6 Sol — the flagship model, designed for complex reasoning, advanced coding, long-running agent workflows, scientific research, and…

TypingMind now supports OpenAI’s new GPT-5.6 model family, giving users three options for different workloads:

  • GPT-5.6 Sol — the flagship model, designed for complex reasoning, advanced coding, long-running agent workflows, scientific research, and cybersecurity tasks.

  • GPT-5.6 Terra — a balanced, lower-cost model for everyday professional work, offering strong capability at approximately half Sol’s price.

  • GPT-5.6 Luna — the fastest and most cost-efficient option, ideal for high-volume requests, quick answers, lightweight coding, summarization, and routine automation.

Added: GPT-5.6 Sol, Terra, and Luna (image 1)

New Models: Grok 4.5 & Tencent Hy3 + New Provider: Alibaba Cloud

New Models: Grok 4.5 (xAI) — A blazing-fast, highly efficient model optimized for coding and complex agentic tasks. Tencent Hy3 (Hunyuan 3) — A powerful, cost-effective model with a massive 260K context window, perfect for everyday productivity. (free API via…

  • New Models:

    • Grok 4.5 (xAI) — A blazing-fast, highly efficient model optimized for coding and complex agentic tasks.

      New Models: Grok 4.5 & Tencent Hy3 + New Provider: Alibaba Cloud (image 1)
    • Tencent Hy3 (Hunyuan 3) — A powerful, cost-effective model with a massive 260K context window, perfect for everyday productivity. (free API via OpenRouter for 2 weeks)

      New Models: Grok 4.5 & Tencent Hy3 + New Provider: Alibaba Cloud (image 2)
  • New Provider: Alibaba Cloud — You can now connect directly to Alibaba Cloud to access their Qwen models.

New Models: Grok 4.5 & Tencent Hy3 + New Provider: Alibaba Cloud (image 3)

Fable 5 is back on TypingMind + Fixes and Improvements

Claude Fable 5 is back! Enable and use it on TypingMind now! Bug Fixes and Improvements: Issue with Temporary Chat still being saved within folders: now Temporary Chat can no longer be turned on when the current chat belongs to a project/chat folder. Replaced…

Claude Fable 5 is back!

Enable and use it on TypingMind now!

Fable 5 is back on TypingMind + Fixes and Improvements (image 1)

Bug Fixes and Improvements:

  • Issue with Temporary Chat still being saved within folders: now Temporary Chat can no longer be turned on when the current chat belongs to a project/chat folder.

  • Replaced DALL-E plugin access with GPT Image Editor for all plans.

Claude Sonnet 5 and Nano Banana 2 Lite are now live on TypingMind!

Claude Sonnet 5 and Nano Banana 2 Lite are now live on TypingMind! Claude Sonnet 5: Anthropic’s most agentic Sonnet model yet. Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image): Google’s fastest and most cost-efficient image model. New models have also been…

Claude Sonnet 5 and Nano Banana 2 Lite are now live on TypingMind!

  • Claude Sonnet 5: Anthropic’s most agentic Sonnet model yet.

  • Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image): Google’s fastest and most cost-efficient image model.

Claude Sonnet 5 and Nano Banana 2 Lite are now live on TypingMind! (image 1)

New models have also been updated across providers such as OpenRouter and Vercel AI Gateway.

June 2026

Added Provider Tool Support for xAI Models, Perplexity Fixes

We’ve just added provider tool support for xAI models. You can now use Web Browser and Code Sandbox with Grok models. In this update, we also added a temporary fix for the CORS issue affecting the Perplexity Search plugin and Perplexity models.

We’ve just added provider tool support for xAI models. You can now use Web Browser and Code Sandbox with Grok models.

Added Provider Tool Support for xAI Models, Perplexity Fixes (image 1)

In this update, we also added a temporary fix for the CORS issue affecting the Perplexity Search plugin and Perplexity models.

Sakana Fugu is now on TypingMind!

You can now use Sakana Fugu on TypingMind! The Fugu Ultra model is said to match the performance of Fable and Mythos. Try now!

You can now use Sakana Fugu on TypingMind!

The Fugu Ultra model is said to match the performance of Fable and Mythos.

Try now!

Sakana Fugu is now on TypingMind! (image 1)

Update New Models, Bug Fixes and Improvements

Fixed Disable drag-and-drop uploads on Admin Panel when Upload Documents option is disabled. Now, uploaded documents are also counted toward usage limits. Fixed image uploads for AWS Bedrock Claude models by properly resolving URL-based images and showing…

Fixed

  • Disable drag-and-drop uploads on Admin Panel when Upload Documents option is disabled. Now, uploaded documents are also counted toward usage limits.

  • Fixed image uploads for AWS Bedrock Claude models by properly resolving URL-based images and showing clearer re-upload errors.

  • Fixed PDF/image issues for Fireworks and Novita by disabling unsupported PDF support.

Improved

  • Refreshed model catalogs and metadata across Chutes, DeepInfra, Fireworks, Mistral, Moonshot, Novita, OpenRouter, and Vercel.

  • Improved OpenRouter API key verification and model search/import messaging.

  • Improved MCP server display and connection reliability, including device-specific server filtering, better initialization, SSE timeout handling, and OAuth URL generation.

Added / Deprecated

  • Added/promoted new models including GLM 5.2, Kimi K2.7 Code, MiniMax-M3, Qwen 3.7 Plus, and Fireworks fast-router variants and more.

  • Deprecated older/free models.

Update New Models, Bug Fixes and Improvements (image 1)

Improved Custom Model Setup

We’ve refreshed the Add/Edit Custom Model form with a cleaner layout! Added automatic model capability checks before saving a custom model. TypingMind can now test model connectivity and detect support for features such as system role, streaming, tools,…

We’ve refreshed the Add/Edit Custom Model form with a cleaner layout!

  • Added automatic model capability checks before saving a custom model. TypingMind can now test model connectivity and detect support for features such as system role, streaming, tools, vision, thinking, prompt caching, supported parameters, and provider tools.

  • Added support for storing cache read/write pricing fields for custom models.

Improved Custom Model Setup (image 1)

Added support for more AI providers: Fireworks, Chutes, Novita, Minimax, Vercel and Xiaomi

We have just added support for more AI providers, including Fireworks AI, Chutes AI, Novita AI, Minimax, Vercel Gateway and Xiaomi. You can now connect your API keys and use models from these providers directly in TypingMind. Go to Models → API Keys to set up…

We have just added support for more AI providers, including Fireworks AI, Chutes AI, Novita AI, Minimax, Vercel Gateway and Xiaomi.

You can now connect your API keys and use models from these providers directly in TypingMind.

Go to Models → API Keys to set up your preferred provider and start using the available models.

Added support for more AI providers: Fireworks, Chutes, Novita, Minimax, Vercel and Xiaomi (image 1)

Agent Skills Support on TypingMind

Agent Skills are now supported on TypingMind! TypingMind now supports Agent Skills — bundled procedural knowledge that helps AI perform specific tasks more effectively, such as SEO audits, copywriting, code reviews, brainstorming, and more. Each Skill is…

Agent Skills are now supported on TypingMind!

TypingMind now supports Agent Skills — bundled procedural knowledge that helps AI perform specific tasks more effectively, such as SEO audits, copywriting, code reviews, brainstorming, and more.

Each Skill is packaged around a SKILL.md file, which contains task-specific instructions and optional reference files, following the open Agent Skills standard.

How to install Skills on TypingMind:

  1. Go to Plugins.

  2. Under the Store section, select Skills.

  3. Install available Skills from the Store, or import your own Skill using a GitHub URL or ZIP file.

Install skills from store
Install skills from store
Import from GitHub URL or .zip file
Import from GitHub URL or .zip file

How to use Skills on TypingMind:

Enable the Skills you want to use, then start chatting. TypingMind will use the selected Skills to provide more specialized and task-focused responses.

Agent Skills Support on TypingMind (image 3)
Agent Skills Support on TypingMind (image 4)

Learn more about Skills: https://docs.typingmind.com/skills

Note: Skills are now available on TypingMind.com (Personal version). Support for TypingMind Teams coming soon.

May 2026

Use Claude Opus 4.8 on TypingMind!

We have just added Claude Opus 4.8 on TypingMind! ✨ Also in this update: Added Claude Opus 4.8 and Opus 4.8 (Fast) via OpenRouter. Updated model provider pricing/metadata for several catalogs, including DeepSeek, Deepinfra, Groq, Mistral, and OpenRouter…

We have just added Claude Opus 4.8 on TypingMind!

Use Claude Opus 4.8 on TypingMind! (image 1)

✨ Also in this update:

  • Added Claude Opus 4.8 and Opus 4.8 (Fast) via OpenRouter.

  • Updated model provider pricing/metadata for several catalogs, including DeepSeek, Deepinfra, Groq, Mistral, and OpenRouter models.

Model Updates, Fixes, and Improvements

✨ New Added new Deepinfra models and OpenRouter models. Deprecated/deleted models are now kept as deprecated so old chats can show model status more clearly. Improvements Updated OpenRouter and Deepinfra model metadata to reflect latest limits, pricing, and…

✨ New

  • Added new Deepinfra models and OpenRouter models.

  • Deprecated/deleted models are now kept as deprecated so old chats can show model status more clearly.

Model Updates, Fixes, and Improvements (image 1)

Improvements

  • Updated OpenRouter and Deepinfra model metadata to reflect latest limits, pricing, and supported capabilities, including context/output limits, pricing, PDF support, and prompt caching support.

  • Updated OpenRouter Anthropic latest aliases to use Claude-specific settings for better reasoning effort and prompt caching support.

  • Expanded OpenRouter reasoning effort values: none, low, medium, high, xhigh.

  • Removed deprecated DALL-E 3 builtin plugin as this image model is deprecated by OpenAI. Please switch to GPT Image Editor for image generation.

Fixed

  • Fixed Fireworks provider issue where previous user input or stale/duplicated assistant content could be echoed when using the OpenAI Responses API format.

Gemini 3.5 Flash is now available!

Gemini 3.5 Flash, Google’s latest Flash-tier model, is now available on TypingMind! This models is optimized for coding proficiency and parallel agentic execution loops.

Gemini 3.5 Flash, Google’s latest Flash-tier model, is now available on TypingMind!

This models is optimized for coding proficiency and parallel agentic execution loops.

Gemini 3.5 Flash is now available! (image 1)

Support all new AI providers for Profiles

✨ What’s New Support all provider settings for profiles You can now set up API keys for different profiles from all available providers Older profile API key assignments are automatically migrated to the new provider settings format. ⚙️ Bug fixes and…

✨ What’s New

Support all provider settings for profiles
  • You can now set up API keys for different profiles from all available providers

  • Older profile API key assignments are automatically migrated to the new provider settings format.

Support all new AI providers for Profiles (image 1)
Support all new AI providers for Profiles (image 2)

⚙️ Bug fixes and improvements

  • In multi-model chats, clicking a model header/tab now scrolls directly to that model’s latest assistant message. This makes it easier to continue reading the newest response without scrolling through earlier replies.

  • Fixed an issue where switching model tabs on mobile could fail to scroll to the latest message if the response card had not mounted yet.

  • Removed unsupported metadata fields from tool calls before sending requests to OpenAI-compatible providers.

  • Fixed provider API errors caused by extra tool call fields such as output_item_id, call_id, and annotations.

Redesigned Admin Analytics, Web App Builder & Interactive Canvas Updates, Bug Fixes and Improvements

Here's what's new in this update: ✨ New Redesigned Admin Analytics The analytics dashboard now has two tabs: Overview for high-level insights and Exploration for deeper analysis. New metrics have been added, including Characters, plus breakdowns by users,…

Here's what's new in this update:

✨ New

Redesigned Admin Analytics

  • The analytics dashboard now has two tabs: Overview for high-level insights and Exploration for deeper analysis.

  • New metrics have been added, including Characters, plus breakdowns by users, models, and agents, with improved charts, styling, and tooltips.

  • CSV export for analytics data has been centralized for a more consistent experience.

  • Date ranges are now inclusive, normalized to UTC day boundaries, and consistently limited to 1 year.

Analytics 2

Exploration mode now supports filtering by metric, including user-level filtering where permitted.

Exploration

🛠 Improvements

Web App Builder & Interactive Canvas:

  • AI can now update existing HTML using small patch-style edits instead of regenerating the full document, making follow-up edits faster and more token-efficient.

Artifacts side panel — version labels:

  • When a plugin has multiple tool functions, artifact versions are now correctly grouped into one continuous stack and no longer display "undefined - Version N".

⚙️ Bug Fixes

  • Fixed DeepSeek API handling so reasoning_content is preserved for supported models.

  • Fixed an issue where MCPs/tools did not work with some providers, including Mistral.

  • Improved cross-provider tool/function calling compatibility by removing unsupported annotations from function specs before sending tool definitions.

  • Improved the Organization dashboard Recent Activity feed with clearer audit log formatting, names, and layout.

New Referral Program: Refer Friends, Earn Free Storage 🎉

We're excited to introduce the TypingMind Referral Program. Starting today, every time you refer a friend who buys a TypingMind license, you both unlock 0.5 GB of free cloud storage — forever. Here's how it works Go to Settings → Cloud Sync & Backup → Refer…

We're excited to introduce the TypingMind Referral Program. Starting today, every time you refer a friend who buys a TypingMind license, you both unlock 0.5 GB of free cloud storage — forever.

Here's how it works

  • Go to Settings → Cloud Sync & Backup → Refer friends

  • Copy your personal referral link (typingmind.com/r/<code>). For example:

    https://www.typingmind.com/r/S4G6TB5G

  • Share it with friends via Email, X, or LinkedIn — or anywhere else

New Referral Program: Refer Friends, Earn Free Storage 🎉 (image 1)

When they purchase a license through your link, you both get 0.5 GB added to your accounts instantly.

Notes:

  • Available for individual TypingMind accounts (typingmind.com)

  • No expiry on earned storage — keep it for life

  • Your friend must use your link before purchasing for both of you to receive the reward

Official Support for More AI Providers

We’ve expanded official model support beyond OpenAI, Anthropic, and Google. You can now easily add models from: OpenRouter DeepInfra DeepSeek Groq Mistral Moonshot Perplexity xAI Z.ai More providers and models will be added soon. We also moved API keys…

We’ve expanded official model support beyond OpenAI, Anthropic, and Google.

You can now easily add models from:

  • OpenRouter

  • DeepInfra

  • DeepSeek

  • Groq

  • Mistral

  • Moonshot

  • Perplexity

  • xAI

  • Z.ai

More providers and models will be added soon.

Official Support for More AI Providers (image 1)

We also moved API keys setting from Settings → API Key to Models → API Keys.

To set up API keys, go to Models from the left-side panel, then switch to the API Keys tab and enter your API key.

Official Support for More AI Providers (image 2)

You can also go to Models and click the gear icon next to each AI provider to update its API key.

Official Support for More AI Providers (image 3)

Also in this update:

  • Added support for custom endpoints for OpenAI Responses API requests.

Official Support for More AI Providers (image 4)

Added Token Limit in Admin Panel, UXUI Fixes and Improvements

What’s new: Added token limit: Admins can now set up token limit per time period for specific models, AI Agents, users/user groups. Go to Admin panel → Under the Access & Limits section, select Usage Limit. Added admin toggle for ElevenLabs: Admins can now…

What’s new:

  • Added token limit: Admins can now set up token limit per time period for specific models, AI Agents, users/user groups.

Go to Admin panel → Under the Access & Limits section, select Usage Limit.

Added Token Limit in Admin Panel, UXUI Fixes and Improvements (image 1)
Added Token Limit in Admin Panel, UXUI Fixes and Improvements (image 2)
Added Token Limit in Admin Panel, UXUI Fixes and Improvements (image 3)
  • Added admin toggle for ElevenLabs: Admins can now show or hide the ElevenLabs integration directly from the admin panel settings.

Added Token Limit in Admin Panel, UXUI Fixes and Improvements (image 4)

🛠 Improvements & Bug Fixes

  • Fixed a flashing issue during the close transition by freezing content to prevent flicker.

  • Fixed an overflow issue in attachment and file layouts. Flex layout constraints (min-width + flex-shrink) have been added to keep attachments properly contained.

  • Fixed an issue where inline agents could incorrectly search the wrong Knowledge Base tags.

  • Fixed artifact dimensions so artifacts now display with the correct height in the UI.

April 2026

GPT-5.5 is now available!

GPT-5.5 and GPT-5.5 Pro are now accessible via TypingMind! Better at coding, tool use, research and analysis!

GPT-5.5 and GPT-5.5 Pro are now accessible via TypingMind!

Better at coding, tool use, research and analysis!

Image

ChatGPT Image 2.0, Resizable Sidebar, Custom Body Parameters in Model Settings

Here's what's new in this update: GPT Image 2 model support: The GPT Image Editor plugin now supports the gpt-image-2 model, giving you access to OpenAI's latest image generation capabilities directly within the plugin. Resizable sidebar: You can now drag to…

Here's what's new in this update:

  • GPT Image 2 model support: The GPT Image Editor plugin now supports the gpt-image-2 model, giving you access to OpenAI's latest image generation capabilities directly within the plugin.

ChatGPT Image 2.0, Resizable Sidebar, Custom Body Parameters in Model Settings (image 1)
  • Resizable sidebar: You can now drag to resize the sidebar to your preferred width. The size is saved and persists across app reloads.

ChatGPT Image 2.0, Resizable Sidebar, Custom Body Parameters in Model Settings (image 2)
  • Custom body parameters in model settings: You can now add custom request body parameters directly in a model's settings. This enables use cases such as setting service_tier: "priority" to help reduce 429 rate-limit errors on models like Gemini 3.1 Pro.

ChatGPT Image 2.0, Resizable Sidebar, Custom Body Parameters in Model Settings (image 3)

Claude Opus 4.7 is now available on TypingMind!

Claude Opus 4.7 is now available on TypingMind! Better at complex coding work More reliable on long tasks Check its own work before answering Produce more polished professional outputs like UIs, slides, and documents. Try now! Other updates: - Added support…

Claude Opus 4.7 is now available on TypingMind!

  • Better at complex coding work

  • More reliable on long tasks

  • Check its own work before answering

  • Produce more polished professional outputs like UIs, slides, and documents.

Try now!

Claude Opus 4.7 is now available on TypingMind! (image 1)

Other updates:

- Added support for xhigh thinking effort for Claude Opus 4.7
- Treated xhigh as max thinking effort for other Claude models

Provider Tools for Org Agents, Permanent Cloud File Deletion, Bug Fixes and Improvements

New Users can now permanently delete files stored in cloud storage. Fixes and Improvements Fix “Request exceeds the maximum size” errors when sending large PDF files to Claude models by lowering the PDF size limit to preserve request headroom. Added support…

New

  • Users can now permanently delete files stored in cloud storage.

Provider Tools for Org Agents, Permanent Cloud File Deletion, Bug Fixes and Improvements (image 1)

Fixes and Improvements

  • Fix “Request exceeds the maximum size” errors when sending large PDF files to Claude models by lowering the PDF size limit to preserve request headroom.

  • Added support for welcome/prefill messages for Gemini image models.

  • You can now assign provider tools for AI Agents (TypingMind Team)

  • Provider code execution now reuses the active Claude container for improved execution efficiency.

Unified Reasoning Controls, Restore Deleted Data Improvements, and Bug Fixes

Here’s what’s new in this update: External URL Support for Gemini: Gemini now supports external URLs for file handling, with optimized uploads that use less bandwidth and improve response speed. Unify Reasoning Controls: The thinking level button is now…

Here’s what’s new in this update:

  • External URL Support for Gemini: Gemini now supports external URLs for file handling, with optimized uploads that use less bandwidth and improve response speed.

  • Unify Reasoning Controls: The thinking level button is now synced with the Reasoning effort setting in Chat Settings for a more consistent reasoning control experience.

  • Restore Deleted Items: You can now restore more recently deleted items, including agents, plugins, prompts, and folders.

Unified Reasoning Controls, Restore Deleted Data Improvements, and Bug Fixes (image 1)

Improvements & Bug Fixes

  • Gemini large file handling: Fixed an issue where Gemini could fail when processing large files via external URLs because documents were incorrectly detected as having no pages.

  • User’s last login for OAuth & SSO tracking: Fixed an issue where the user’s last login wasn’t being tracked for OAuth and SSO authentication.

March 2026

New Prompt Library UI for Teams, Chat Widget Deprecation Notice, and Bug Fixes

Here's what's new in this update: Prompt Library (Teams) — New UI: The Team Prompt Library has been redesigned with a refreshed interface and new capabilities: Duplicate & Share as JSON: Quickly duplicate any prompt or export it as JSON for easy sharing. Bulk…

Here's what's new in this update:

Prompt Library (Teams) — New UI: The Team Prompt Library has been redesigned with a refreshed interface and new capabilities:

  • Duplicate & Share as JSON: Quickly duplicate any prompt or export it as JSON for easy sharing.

  • Bulk Delete: Select and remove multiple prompts at once.

  • Sorting Options: Sort prompts by title, date created, or date modified.


Deprecating Chat Widget (Teams): The Chat Widget feature is being deprecated. Existing embeds will remain available until June 01, 2026, with a new widget system coming soon. The per-agent "Embed the chat widget" snippet has been removed (direct URL and public API guidance remain available).

Improvements & Bug Fixes

  • Shared Links (Teams self-hosted): Fixed an issue where Shared Links didn't appear in the Cloud Sync screen on the self-hosted version.

  • OpenRouter streaming: Prevents the format field from being incorrectly repeated when using OpenRouter in streaming mode.

  • Model/Plugin limits (Teams): Fixed an issue where model and plugin limits were being incorrectly overridden.

  • OpenAI reasoning: Messages are now kept as stateless as possible to prevent caching errors.

  • Chat Share button (Teams): Fixed the Share button displaying incorrectly in the UI.

New GPT-5.4 Mini & Nano Models, Performance Improvements & Bug Fixes

Here's what's new in this update: ✨ New GPT-5.4 Mini & GPT-5.4 Nano are now available in TypingMind. 🛠 Improvements & Bug Fixes Large chat performance: Optimized performance for large chats by removing unused OpenRouter annotations data that could be very…

Here's what's new in this update:

✨ New

GPT-5.4 Mini & GPT-5.4 Nano are now available in TypingMind.

New GPT-5.4 Mini & Nano Models, Performance Improvements & Bug Fixes (image 1)

🛠 Improvements & Bug Fixes

  • Large chat performance: Optimized performance for large chats by removing unused OpenRouter annotations data that could be very large.

  • Claude Opus 4.6 pricing: Fixed estimated cost so pricing now shows correctly for Claude Opus 4.6 and Claude Opus 4.6 1M models.

New Provider UI, Read Specific KB Files & Bug Fixes

Here's what's new in this update: ✨ New A new Provider UI A new UI has been added for configuring providers and their API keys, with unified Enter API Key widgets across all providers. Read specific files in Knowledge Base (KB) You can now read specific files…

Here's what's new in this update:

✨ New

  • A new Provider UI

    A new UI has been added for configuring providers and their API keys, with unified Enter API Key widgets across all providers.

  • Read specific files in Knowledge Base (KB)
    You can now read specific files in your Knowledge Base directly.

New Provider UI, Read Specific KB Files & Bug Fixes (image 1)

🛠 Improvements & Bug Fixes

  • OpenRouter API streaming: Improved handling of OpenRouter response API streaming.

  • Fixed an issue where redundant newline characters caused invalid Claude prompt cache entries.

Claude Automatic Prompt Caching, Plugin Timeout Config & Bug Fixes

Here's what's new in this update: ✨ New Claude automatic prompt caching: TypingMind now applies Claude's new automatic prompt caching, improving response efficiency for repeated or similar prompts. Plugin Execution Timeout (Self-Hosted Teams): Admins can now…

Here's what's new in this update:

✨ New

Claude automatic prompt caching: TypingMind now applies Claude's new automatic prompt caching, improving response efficiency for repeated or similar prompts.

Plugin Execution Timeout (Self-Hosted Teams): Admins can now set a custom timeout limit for plugin execution via an environment variable. The value should be specified in milliseconds.

🛠 Improvements & Bug Fixes

Agents/MCPs avatars: Fixed an issue where agents/MCPs avatars could not load.

Custom params in multi-model responses: Fixed an issue where custom params were not applied in some multi-model response generation cases.

New GPT-5.4 Models, Role Permissions & More Fixes

Here's what's new in this update: GPT-5.4 and GPT-5.4 Pro models: OpenAI's latest models — GPT-5.4 and GPT-5.4 Pro — are now available to use in TypingMind. 🛠 Improvements & Bug Fixes Granular permission for role assignment in the team version: Admins now…

Here's what's new in this update:

GPT-5.4 and GPT-5.4 Pro models: OpenAI's latest models — GPT-5.4 and GPT-5.4 Pro — are now available to use in TypingMind.

New GPT-5.4 Models, Role Permissions & More Fixes (image 1)

🛠 Improvements & Bug Fixes

  • Granular permission for role assignment in the team version: Admins now have finer control over who can assign roles to members in the organization.

  • GPT O-series models formatting: Formatting instructions in the system prompt are now only applied to o-series models, keeping other models clean and unaffected.

  • Audio recording for org users: Fixed an error that occurred when recording or transcribing large audio files — audio is now uploaded before transcription to prevent the issue.

  • Inline agent in chat: Your pinned inline agent is now remembered when you switch between chats and come back — it will no longer disappear unexpectedly.

  • Gemini cost calculation: Fixed an incorrect cost calculation for Gemini — image prompt pricing has been removed to reflect the correct usage cost.

  • Grok endpoints: Enabled CORS proxy support for Grok endpoints, improving connectivity and compatibility.

New Models: Gemini 3.1 Flash Lite and GPT-5.3 Chat

We've added two new models to TypingMind: Gemini 3.1 Flash Lite: Google's latest lightweight model, offering fast and efficient responses. GPT-5.3 Chat: OpenAI's newest Chat model, bringing improved capabilities to your conversations.

We've added two new models to TypingMind:

  • Gemini 3.1 Flash Lite: Google's latest lightweight model, offering fast and efficient responses.

  • GPT-5.3 Chat: OpenAI's newest Chat model, bringing improved capabilities to your conversations.

Use Gemini 3 Pro Image with other AI models, Fixes & Improvements

Generate images with Gemini 3 Pro Image + Other models You can now use Gemini 3 Pro Image alongside other AI models in the same chat, get text responses from your preferred model and generate images, all in one place. Fixes & Improvements Fixed: Shared chat…

Generate images with Gemini 3 Pro Image + Other models

You can now use Gemini 3 Pro Image alongside other AI models in the same chat, get text responses from your preferred model and generate images, all in one place.

image.png

Fixes & Improvements

  • Fixed: Shared chat links were not accessible in TypingMind Teams. Shared chats can now be opened correctly.

  • Improved: The old Google Search plugin has been removed for new users. Existing users will see a deprecation warning. Please switch to the Web Search or Web Search (Serp) plugin instead.

February 2026

Nano Banana 2 is out + Bug Fixes & Improvements

Here's what's new in this update: ✨ New Nano Banana 2 model: Google's latest image generation model that combines the advanced capabilities of Nano Banana Pro with the speed of Gemini Flash. The new Nano Banana 2 (Gemini 3.1 Flash Image) model is now…

Here's what's new in this update:

✨ New

  • Nano Banana 2 model: Google's latest image generation model that combines the advanced capabilities of Nano Banana Pro with the speed of Gemini Flash. The new Nano Banana 2 (Gemini 3.1 Flash Image) model is now available in TypingMind.


🛠 Improvements & Bug Fixes

  • Perplexity plugin: You'll now see a clear error message when something goes wrong.

  • Custom OpenAI models: Reasoning now works correctly for custom OpenAI models.

  • Gemini search tool: Knowledge Base is automatically turned off when using the Gemini search tool to avoid conflicts.

  • Self-hosted Docker: Support better compatibility for more container environments.

  • Remove member button: The button no longer gets stuck on loading after removing a member.

Google Search Plugin Deprecated, Legacy Plugins Removed & OAuth Fix

Deprecation: Google Search Plugin The Google Search plugin on TypingMind is being deprecated. Google has announced that all Programmable Search Engines will stop working on January 1, 2027, so this plugin will no longer function after that date. We recommend…

Deprecation: Google Search Plugin

The Google Search plugin on TypingMind is being deprecated. Google has announced that all Programmable Search Engines will stop working on January 1, 2027, so this plugin will no longer function after that date.

We recommend switching to one of these alternatives:

  • Use the default Web Browser tool provided by your model provider

  • Use the Perplexity Search plugin instead

Google Search Plugin Deprecated, Legacy Plugins Removed & OAuth Fix (image 1)

Learn more about Google's announcement


Deprecation: Legacy Plugins Removed

The following plugins have been removed from the default/built-in plugin set as they relied on the legacy Plugins Server:

  • PowerPoint Generator

  • Word Generator

  • Web Page Reader


Fixed: MCP OAuth Callback URL (Self-Host)

Fixed an issue in self-host deployments where the MCP OAuth callback URL wasn't working correctly.

Add Gemini 3.1 Pro Model

Gemini 3.1 Pro is now available in TypingMind! Google's latest model brings stronger reasoning, better coding, and improved multimodal understanding, all with a 1M token context window. Why use it? Smarter reasoning, scores 77.1% on ARC-AGI-2 (2x better than…

Gemini 3.1 Pro is now available in TypingMind!

Google's latest model brings stronger reasoning, better coding, and improved multimodal understanding, all with a 1M token context window.

Why use it?

  • Smarter reasoning, scores 77.1% on ARC-AGI-2 (2x better than Gemini 3 Pro)

  • Better at coding and agentic tasks

  • Handles text, images, audio, video, and code with a 1M token context window

Select Gemini 3.1 Pro from the model picker to get started.

Claude Sonnet 4.6 is out, Bug Fixes & Improvements

What's new: Added support for Claude Sonnet 4.6 and Claude Sonnet 4.6 (1M) (1 million token context window variant). They’re smarter than Sonnet 4.5, at the same price. Support deleting unused Knowledge Base tags Bug fixes & improvements: Fixed the "Use now"…

What's new:

  • Added support for Claude Sonnet 4.6 and Claude Sonnet 4.6 (1M) (1 million token context window variant). They’re smarter than Sonnet 4.5, at the same price.

  • Support deleting unused Knowledge Base tags

    Claude Sonnet 4.6 is out, Bug Fixes & Improvements (image 1)

Bug fixes & improvements:

  • Fixed the "Use now" button in the Prompts Library page not working on the first click.

  • Fixed attachment rendering for clipboard-pasted/legacy attachments, preventing "No valid blob source" errors.

  • Fixed the copy button under messages not working correctly in some cases; text extraction now includes all text blocks instead of only the first match, preventing incomplete/empty copied content.

  • Fixed errors caused by empty content: [] arrays in assistant messages during OpenAI response transformation/streaming.

Support for Claude Adaptive Thinking API, Improvements & Bug Fixes

Support for Claude Adaptive Thinking API Added support for Claude’s new adaptive thinking API Fixes & Improvements Fixed GPT-5.2-Pro so it is now affected by the reasoning effort configuration. Fixed OpenAI reasoning issue for provider tools. Support for Code…

Support for Claude Adaptive Thinking API

  • Added support for Claude’s new adaptive thinking API

    Support for Claude Adaptive Thinking API, Improvements & Bug Fixes (image 1)

Fixes & Improvements

  • Fixed GPT-5.2-Pro so it is now affected by the reasoning effort configuration.

  • Fixed OpenAI reasoning issue for provider tools.

  • Support for Code Sandbox and Web browser together with thinking.

  • Provider tools are now filtered out for unsupported models (no more showing tools for models that can't use them).

  • Fixed issue where adding Grok 4 would fail.

Let us know if you have any feedback!

New Internal Prompts Settings, Context Summarization Controls, and Bug Fixes

🎉 New Features & Improvements Internal Prompts & Context Summarization Added a new Internal Prompts settings page for better prompt management Introduced context summary settings that allow you to disable context summarization or customize the summarization…

🎉 New Features & Improvements

Internal Prompts & Context Summarization

  • Added a new Internal Prompts settings page for better prompt management

  • Introduced context summary settings that allow you to disable context summarization or customize the summarization prompt

  • For Team version users, context summary settings are now available in Admin Panel → Chat Features

Enhanced Message Controls

  • Added a new "Enter to send" toggle in General Settings, giving you control over whether pressing Enter sends messages or creates new lines

    New Internal Prompts Settings, Context Summarization Controls, and Bug Fixes (image 1)

Proxy Support for Claude Models

  • Added proxy support for Claude models to improve connectivity and reliability

🐛 Bug Fixes

  • Fixed audio recording and transcription issues with OpenAI Whisper for organization users

  • Fixed web search source annotations not rendering correctly in markdown tables

New models: Opus 4.6 + Codex 5.3

We've added support for the latest AI models from Anthropic and OpenAI! What's new: Added new selectable models: Anthropic claude-opus-4-6 and claude-opus-4-6-1m (1M context) Added OpenAI gpt-5.3-codex Go try the models on TypingMind now!

We've added support for the latest AI models from Anthropic and OpenAI!

New models: Opus 4.6 + Codex 5.3 (image 1)

What's new:

  • Added new selectable models: Anthropic claude-opus-4-6 and claude-opus-4-6-1m (1M context)

  • Added OpenAI gpt-5.3-codex

Go try the models on TypingMind now!

Bug Fixes & Improvements

We've just released several fixes and improvements to enhance your experience: Fixed: Cloud sync files size calculation now displays the correct storage usage in the cloud sync panel Citation annotations no longer cause incorrect output rendering formats…

We've just released several fixes and improvements to enhance your experience:

Fixed:

  • Cloud sync files size calculation now displays the correct storage usage in the cloud sync panel

  • Citation annotations no longer cause incorrect output rendering formats

Improved:

  • Thinking mode now supports new reasoning detail formats for more custom model providers, such as OpenRouter, Moonshot AI, etc.

These updates should make your workflow smoother. Let us know if you encounter any issues!

January 2026

Introducing Model Presets: Save and switch between AI model configurations

We've added a powerful new way to manage your AI models with Model Presets! What's new: Multi-model presets in the model menu - Save your favorite model configurations with all their settings and switch between them instantly Save, rename, and remove presets…

We've added a powerful new way to manage your AI models with Model Presets!

What's new:

  • Multi-model presets in the model menu - Save your favorite model configurations with all their settings and switch between them instantly

  • Save, rename, and remove presets with inline editing

  • Quick apply to switch between presets seamlessly

  • Sync model presets across devices - Your presets follow you everywhere


Bug fix:

  • Fixed an issue where custom model parameters in Agent settings were applied incorrectly when no default model was set. Agent parameters are now only applied when default model enforcement is enabled (matches UI behavior)

TypingMind Teams updates: Access & Limits for Plugins, Thinking UI Improvements, SSO Login Fix

We've rolled out several updates and improvements to enhance your TypingMind Teams experience! New Features Access & Limits Tab for Org Plugins We've added a new Access & Limits tab for organization plugins, giving admins better control over plugin usage. New…

We've rolled out several updates and improvements to enhance your TypingMind Teams experience!

New Features

Access & Limits Tab for Org Plugins

We've added a new Access & Limits tab for organization plugins, giving admins better control over plugin usage.

  • New Access & Limits tab in organization plugin settings

  • Admins can now configure access controls and usage limits for plugins at the organization level

Improvements

Thinking Options UI Improvement

When admins disable the thinking process, the related thinking options are now automatically hidden from the UI of the end users.

TypingMind Teams updates: Access & Limits for Plugins, Thinking UI Improvements, SSO Login Fix (image 1)

Bug Fixes

Fixed SSO Login Limit Issue

We've resolved an issue where existing users were encountering reaching limit errors when logging in via SSO.

  • Existing users can now log in via SSO without hitting false limit restrictions

  • Improved user authentication flow for SSO

GPT-5.2-codex Added & Plugin Improvements

We've rolled out several improvements to enhance your experience: New AI Model Available Added GPT-5.2-codex model as a new model option Better Plugin Interface Interactive plugin groups now expand by default for easier access Improved Tool Compatibility…

We've rolled out several improvements to enhance your experience:

New AI Model Available

GPT-5.2-codex Added & Plugin Improvements (image 1)
  • Added GPT-5.2-codex model as a new model option

Better Plugin Interface

GPT-5.2-codex Added & Plugin Improvements (image 2)
  • Interactive plugin groups now expand by default for easier access

Improved Tool Compatibility

GPT-5.2-codex Added & Plugin Improvements (image 3)
  • Fixed tool compatibility handling between Thinking Mode, Web Browser, and Code Sandbox (OpenAI) to prevent conflicts when Thinking Mode is enabled

Usage Limit for Plugins (Team versions) & Smart Model Selection

Plugin Usage Limits You can now set usage limits for plugins to better control how they're used in your workspace. What's new: Set limits for individual plugins or Model Context Protocols (MCPs) Limits are currently shared across all functions within a plugin…

Plugin Usage Limits

You can now set usage limits for plugins to better control how they're used in your workspace.

What's new:

  • Set limits for individual plugins or Model Context Protocols (MCPs)

  • Limits are currently shared across all functions within a plugin

Watch the demo:


Smart Default Model Selection

TypingMind now remembers your model preferences when you start new chats.

How it works:

When you select a model (or models) before starting a new chat, TypingMind will save that as your default for future chats — no need to keep selecting the same model every time.

What this means for you:

  • Works with both single model selection and multiple models

  • Your preference is remembered automatically

  • Only applies when you haven't set a folder-level default model

This makes starting new chats faster and more convenient!

Floating Menu Hide Option, Clipboard Paste File Rename, Table Line Bug Fix

Floating Menu Hide Option Added a ... button to the floating toolbar. Use the dropdown to Hide menu easily. Clipboard Paste File Rename You can now rename a text file attachment after pasting it from your clipboard into the chat input. Added an inline rename…

Floating Menu Hide Option

  • Added a ... button to the floating toolbar. Use the dropdown to Hide menu easily.

Floating Menu Hide Option, Clipboard Paste File Rename, Table Line Bug Fix (image 1)

Clipboard Paste File Rename

  • You can now rename a text file attachment after pasting it from your clipboard into the chat input.

  • Added an inline rename UI (edit the name, Enter to save, Escape to cancel) with a pen icon.

  • Renaming updates the attachment name directly in chat.

Floating Menu Hide Option, Clipboard Paste File Rename, Table Line Bug Fix (image 2)

Fix: New Lines Not Rendered in Tables

  • Fixed an issue where new lines (<br>) were not shown properly inside tables.

Built-in Code Interpreter tool by model providers and Bug fixes

Code Interpreter You can now run code securely in a sandbox using the new Code Interpreter plugin (supported providers: OpenAI, Anthropic, Google Gemini). We’ve updated the tool interface: you can now see code status, expand code, copy results, and check…

Code Interpreter

  • You can now run code securely in a sandbox using the new Code Interpreter plugin (supported providers: OpenAI, Anthropic, Google Gemini).

  • We’ve updated the tool interface: you can now see code status, expand code, copy results, and check program output more easily.

  • Attachment previews are better; file chips and downloads work for more file types.

Response Block Layout Fix

  • Fixed an issue where buttons sometimes covered the message text.

Summarizer ProviderInfo Fix

  • Fixed a bug causing the “No target API endpoint found” error for the context

    summarizer.

Plugins Tab UI Improvements & Bug Fixes

We've improved the Plugins tab experience and fixed several issues to make TypingMind more stable and reliable. What's improved: Plugins Tab Enhancements: Installed items + store sections are now scrollable in a split layout Enable/disable toggle moved to the…

We've improved the Plugins tab experience and fixed several issues to make TypingMind more stable and reliable.

Plugins Tab UI Improvements & Bug Fixes (image 1)

What's improved:

Plugins Tab Enhancements:

  • Installed items + store sections are now scrollable in a split layout

  • Enable/disable toggle moved to the header for quicker access

  • MCP-related panels polished: improved connection status UI, tool control layout, and new/updated connection form UX

Bug Fixes:

  • Fixed background mode issues including inability to abort requests, and improper closing.

  • Fixed an issue where OpenAI response streams could be aborted unexpectedly

  • Improved "plugin not found" error message when the selected model doesn't support plugins

Form not loading? Open it in a new tab