Release Notes

Follow along with CodingFleet updates.

Mar 24, 2025

  • Gemini 2.0 Flash, Gemini 2.0 Pro (Exp), and Claude 3.7 Sonnet Thinking models now support tool use, including URL Fetching, Web Browsing and Code Execution.
  • Fixed a bug where Claude 3.7 Sonnet Thinking results not being saved.

Mar 18, 2025

  • Code Execution now supports file upload, where you can upload files to the sandbox environment, and execute code that interacts with those files.
  • We also added the ability to download files from the sandbox environment when code execution is enabled, make sure to prompt the AI for any resulting files residing in the environment.
  • Once again, we've increased the input character limit for Elite users, from 250k to 300k.

Mar 10, 2025

  • We've added the Code Execution feature, allowing the AI to iterate on code by executing and analyzing code output. It's currently available in all of our tools except for the Code Enhancer. Learn more here.

Feb 26, 2025

  • Claude 3.7 Sonnet & Claude 3.7 Sonnet Thinking are added to the models list. Claude 3.7 Sonnet Thinking uses extended thinking before generating a response.
  • You can now perform Web Browsing and URL Fetching in the chat tool, simply click on the tools button, and enable what you want. Web Browsing allows the AI to fetch up to date information, or for fact check. URL Fetching is more about fetching the exact HTML of a URL provided by you in the prompt, particularly useful for web scraping tasks.
  • Fixed some bugs and some UI enhancements in the chat tool:
    • There was an issue with "Continue Generation" button, that appears when a response is not complete. Previously the continuation wasn't being shown in the UI, now it is.
    • LaTeX text is now correctly formatted, when LLMs generate LaTeX, it'll be automatically formatted into nice equations!
    • We did some improvements to the chat toolbar, although we'll do more.
    • The top navigation bar is removed for a better user experience, it is replaced with a button in the bottom of the toolbar.
  • We've added LiveBench Coding, LiveBench Average, and WebDev Arena Score to the models list, to give you an idea on how good these LLMs are.

Feb 7, 2025

  • We've added two buttons to all model responses across all tools:
    • Stats for nerds:
    • Downloading all code snippets in the response:
  • Gemini 2.0 Flash is updated with the new endpoint, and the newly released Gemini 2.0 Pro replaced Gemini 1.5 Pro.

Jan 31, 2025

  • OpenAI's newly released o3-mini reasoning model is now available in all tools! We replaced it with o1-mini, and added the streaming feature!
  • o3-mini with high reasoning effort (o3-mini-high) is also replacing OpenAI o1, as it proved to outperform OpenAI o1 on all benchmarks. It is available only for Elite users.
  • Daily and monthly premium credits limit is removed, and replaced with a simpler weekly limit. Elite users have 1,000 premium credits, where Unlimited users have 300.
  • We've added a new code comparison feature to compare code versions across all tools. To see code comparison, click on this button on any generation you want:

Code Comparison Feature Button

Jan 24, 2025

  • We've added this models page, where we display usage statistics from CodingFleet users, showing total characters, votes, and speed for each model.

Jan 21, 2025

Jan 20, 2025

  • We've restructured our plans:
    • All users can choose any Large Language Model (LLM) they want, except for premium models such as GPT-4o, Claude 3.5 Sonnet, o1-mini, and some others (models that costs 2 credits or more)
    • At the time of writing this, any paid user can select any AI model for their generation except for OpenAI o1, which is exclusively for Elite users.
    • Elite and Unlimited users can use our tools with no limits, but there are daily premium requests quotas, which are 300, and 100 respectively. Premium requests are requests using premium models that costs 2 or more credits.
    • When daily requests exceed the premium request limit, the system will automatically switch the user to lower-cost models, such as GPT-4o mini, Llama 3.3 70B, and others. The system will revert to premium models once usage falls below the set quotas.
    • Elite users input character limit is increased from 200,000 to 250,000.
    • Free users can use the chat tool.
    • File Upload is exclusively available for Elite users.
  • A new optional field is added to the Code Converter tool, allowing you to insert instructions for the AI to take into account during code conversion.
  • The chat tool no longer truncates old messages when exceeding the character limit. Instead, it summarizes them, and so you'll notice a delay of 3-15 seconds when sending messages.
  • Fixed some minor bugs in Gemini and Llama models output.

Jan 6, 2025

  • Introducing Instruction Templates: In the Chat tool, you can now change default system messages for the AI models, instructing the LLMs to do your desired task in the format/way you want. We've also added the option to save these instructions as templates for later use.
  • We've added xAI's Grok-2 and DeepSeek V3 models to the AI models list.
  • We've made some enhancements to the chat tool:
    • Adding copy & delete buttons on each assistant message.
    • Streaming is now smoother than before.
  • We've added an optional Instructions field to the Code Converter, so you can guide the AI with specific requirements or preferences during the conversion process.

Dec 23, 2024

  • Elite users can now upload files to GPT-4o, GPT-4o mini, Claude 3.5 Sonnet, Claude 3.5 Haiku, Gemini 2.0 Flash, and Gemini 1.5 Pro models across all tools, including chat. The uploaded files must not exceed 50MB. All text-based formats are supported such as .py, .js, .cpp, .sql, .csv, etc. With .pdf, .pptx, .doc, .docx, and .xlsx.
  • OpenAI o1 has replaced o1 Preview, with better coding abilities. All paid users have access to this state-of-the-art model.

Dec 11, 2024

  • Elite users can now upload files to GPT-4o and GPT-4o mini models across all CodingFleet tools, including the chat tool. The uploaded file must not exceed 512MB and is one of the following formats: .c, .cpp, .cs, .css, .doc, .docx, .go, .html, .java, .js, .json, .md, .pdf, .php, .pptx, .py, .rb, .sh, .tex, .ts, .txt.
  • The newly released Gemini 2.0 Flash model from Google is added to the list of AI models.

Dec 4, 2024

  • Users can now edit their last message in the chat tool by clicking on the edit icon at the left side of the user message:
    Editing Messages

         Once you're done editing, click Submit to re-generate the response.

Nov 29, 2024

  • A new toolbar is added to the chat tool, so users can now navigate through recent chats.

Nov 19, 2024

  • Team owners can now delete requests of users in the team.
  • Teams now have an activity log, logging team creation, invitations, members, and finally request deletions done by owners.
  • Qwen2.5-Coder 30B from Qwen is added to model options across all tools.
  • Fixed some minor issues in the chat tool.
  • Our biggest discount of the year is here! Check the pricing page.

Nov 9, 2024

  • Paid users can now start a new chat without the need to use other tools.
  • We fixed markdown parsing for clearer formatting in AI responses.

Nov 4, 2024

  • Elite users can now re-generate responses in the chat tool with a different AI model. If you don't like a response, hover over the model dropdown menu of that result, and choose a different model for generation. You can still view all the responses by using the navigation buttons:Re-generating responses with different LLMs
  • We've added Microsoft Authentication alongside Google, GitHub and regular form filling on the signup/login pages.
  • Claude 3 Haiku is replaced with the newly released Claude 3.5 Haiku from Anthropic.

Oct 27, 2024

  • We've added Teams feature. Everyone can create a team. Team owners or admins can invite members, manage them, and access each member’s usage history and billing details.

Oct 23, 2024

  • Claude 3.5 Sonnet is updated. Now it is even better in coding and many other fields.
  • We fixed an authentication error in the Ephemeral VM Instances feature.

Oct 7, 2024

  • We've added two more LLMs: Llama 3.2 90b and Mistral Large 2. Elite users can select across all tools, while others can still use them in the code generator tool.
  • Google updated Gemini 1.5 Pro and Gemini 1.5 Flash models with new endpoints, enhancing their capabilities.

Sep 28, 2024

  • We're introducing the Ephemeral VM instances feature to Elite users, which allows you to spin up a temporary VM and interact with it using either GPT-4o Mini, GPT-4o and Claude 3.5 Sonnet. Particularly useful for code testing, and execution, although there are surely more other use cases. Learn more.
  • Elite users can now choose from any available LLM in the chat tool.

Sep 13, 2024

  • We've added OpenAI's o1 models, including o1 Preview and o1 Mini. These models "think" before generating a response, making them especially useful for scientific applications. They're available to paid users only: Pro, Unlimited and Elite.
  • Input character limit is increased for all user tiers: Pro from 32k to 50k, Unlimited from 64k to 100k, and Elite from 128k to 200k.

Sep 8, 2024

  • You can now upload your code files and directories to the code editor in all tools, except the code generator, reducing the burden of manually copying and pasting into our code editor. Drag and drop is also supported.
  • We've improved the UI for the chat and other pages.

Aug 31, 2024

  • Claude 3.5 Sonnet now outputs 2x more text than before, up to ~20,000 characters (20kB of code) in one generation.
  • We've added Meta AI's Llama 3.1 models, namely Llama 3.1 70b and Llama 3.1 405b to the model selection dropdown menu.

Aug 12, 2024

  • We've added the URL Fetching feature to GPT-4o, GPT-4o Mini and Claude 3.5 Sonnet. Learn more.
  • GPT-4o and GPT-4o Mini now can output 4x more text than before, up to ~40,000 characters (40kB of code) in one generation.

Aug 5, 2024

  • We've added the Python Code Interpreter to GPT-4o and GPT-4o Mini for Elite Users. Learn more.
  • GPT-4o Mini now completely replaces the old GPT-3.5 Turbo.

Jul 18, 2024

  • We've added GPT-4o Mini from OpenAI to the list of AI models.
  • Users can now share their generations to any one with the link. Choose your desired generation from the usage history, then click on the Share button at the top right of the page, then hit Publish Link and copy it.

Jul 7, 2024

June 24, 2024

  • We've added the Elite Plan, check this page for more information.

June 21, 2024

  • We've replaced Claude 3 Sonnet with Claude 3.5 Sonnet and removed Claude 3 Opus, as Claude 3.5 Sonnet now outperforms both in all areas.

June 17, 2024

  • Codestral model from MistralAI is added to the list of Large Language Models (LLMs) to be used in most tools.

June 2, 2024

  • All users can now choose Google Gemini (Gemini 1.5 Pro and Gemini 1.5 Flash) models among others, in the code generator tool, while Elite users have the option to select from the list of Large Language Models (LLMs) across all tools.
  • Added the Dark Theme, which you can toggle in the navbar.

   Last Updated: mar 2025