Be part of our each day and weekly newsletters for the newest updates and unique content material on industry-leading AI protection. Study Extra
Token Monster, a brand new AI chatbot platform, has launched its alpha preview, aiming to vary how customers work together with massive language fashions (LLMs).
Developed by Matt Shumer, co-founder and CEO of OthersideAI and its hit AI writing assistant Hyperwrite AI, Token Monster’s key promoting level is its skill to route person prompts to one of the best accessible LLMs for the duty at hand, delivering enhanced outputs by leveraging the strengths of a number of fashions.
There are seven main LLMs presently accessible by means of Token Monster. As soon as a person varieties one thing into the immediate entry field, Token Monster makes use of pre-prompts developed by means of iteration by Shumer himself to routinely analyze the person’s enter, determine which mixture of a number of accessible fashions and linked instruments are greatest suited to reply it, after which present a mixed response leveraging the strengths of stated fashions. The accessible LLMs embrace:
- Anthropic Claude 3.5 Sonnet
- Anthropic Claude 3.5 Opus
- OpenAI GPT-4.1
- OpenAI GPT-4o
- Perplexity AI PPLX (for analysis)
- OpenAI o3 (for reasoning)
- Google Gemini 2.5 Professional
In contrast to different chatbot platforms, Token Monster routinely identifies which LLM is greatest for particular duties — in addition to which LLM-connected instruments can be useful resembling internet search or coding environments — and orchestrates a multi-model workflow.
“We’re simply constructing the connectors to every thing after which a system that decides what to make use of when,” stated Shumer.
As an example, it’d use Claude for creativity, o3 for reasoning, and PPLX for analysis, amongst others. This strategy eliminates the necessity for customers to manually select the appropriate mannequin for every immediate, simplifying the method for anybody who needs high-quality, tailor-made outcomes.
Function highlights
The alpha preview, which is at present free to enroll in at tokenmonster.ai, permits customers to add a variety of file varieties, together with Excel, PowerPoint, and Docs.
It additionally contains options resembling webpage extraction, persistent dialog classes, and a “FAST mode” that auto-routes to one of the best mannequin with out person enter.
On the coronary heart of Token Monster is OpenRouter, a third-party service that acts as a gateway to a number of LLMs, and into which Shumer has invested a small sum, by his admission.
This structure lets Token Monster faucet into a variety of fashions from completely different suppliers with out having to construct separate integrations for every one.
Pricing and availability
As of proper now, Token Monster doesn’t cost a flat month-to-month payment.
As a substitute, customers solely pay for the tokens they devour by means of OpenRouter, making it versatile for various ranges of utilization.
In keeping with Shumer, this mannequin was impressed by Cline, a instrument that permits high-spending customers to entry limitless AI energy, permitting them to realize higher outputs by merely utilizing extra compute assets.
Multi-step workflows produce richer LLM responses
Token Monster’s AI workflows lengthen past easy immediate routing.
In a single instance, the chatbot may begin with a analysis part utilizing internet search APIs, go that knowledge to o3 for figuring out info gaps, then create an overview with Gemini 2.5 Professional, draft textual content with Claude Opus, and refine it with Claude 3.5 Sonnet.
This multi-step orchestration is designed to supply richer, extra full solutions than a single LLM may have the ability to generate alone.
The platform additionally contains the flexibility to avoid wasting classes, with knowledge securely saved utilizing the open supply on-line database service Supabase. This ensures that customers can return to ongoing tasks with out shedding their work, whereas nonetheless giving them management over what knowledge is saved and what’s ephemeral.
A non-traditional CEO
In a notable experiment, Token Monster’s management has been handed over to Anthropic’s Claude mannequin.
Shumer introduced that he’s dedicated to following each resolution made by “CEO Claude,” calling it a check to see whether or not an AI can handle a enterprise successfully.
“Both we’ve revolutionized administration perpetually or made an enormous mistake,” he wrote on X.
Rising from the Reflection 70-B controversy
Token Monster’s launch comes lower than a 12 months after Shumer confronted controversy over his launch and supreme retraction of Reflection 70B, a fine-tuned versio of Meta’s Llama 3.1 that was initially touted as probably the most extremely performant open supply mannequin on this planet, however which shortly turned topic to criticism and accusations of fraud after third-party researchers have been unable to breed its said efficiency on third-party benchmark checks.
Shumer apologized and stated the problems have been born out of errors made as a result of velocity. The episode underscored the challenges and dangers of fast AI growth and the significance of transparency in mannequin releases.
MCP integrations coming subsequent
Shumer stated his staff on Token Monster can be exploring new capabilities, resembling integrating with Mannequin Context Protocol (MCP) servers that permit web sites and firms to have LLMs make use of their data, instruments, and merchandise to realize higher-order duties than simply textual content or picture era.
This is able to allow Token Monster to attach with a person’s inside knowledge and companies, opening potentialities for it to deal with duties like managing buyer help tickets or interfacing with different enterprise techniques.
Shumer emphasised that Token Monster continues to be very a lot in its early levels. Whereas it already helps a collection of highly effective options, the platform stays an alpha product and is predicted to see fast iterations and updates as extra customers present suggestions. “We’re going to maintain iterating and including issues,” he stated.
A promising experiment
For customers who wish to reap the benefits of the mixed energy of a number of LLMs with out the trouble of mannequin switching, Token Monster might be an interesting selection. It’s designed to work for individuals who don’t wish to spend hours tweaking prompts or testing completely different fashions themselves, as a substitute letting the system’s automated routing and multi-step workflows deal with the complexity.
As Token Monster’s capabilities develop, will probably be attention-grabbing to see how customers and companies undertake it — and the way its experiment with AI-led administration pans out. For now, it’s a promising addition to the quickly increasing panorama of AI chatbots and digital assistants.
