Settings
Color theme
Storage
The estimated amount of storage used to store your conversations and images. You can free up space by deleting conversations.
Conversation
Gemini with the ability to understand and use what3words locations.
ChatGPT with the ability to understand and use what3words locations.
ChatGPT with the ability to understand and use what3words locations.
Automatically uses the best model for your task. Categorizes the prompt, then uses the model that performs best in that particular category according to global user preferences. Scores updated daily.
OpenAI's current recommended model, the well-known ChatGPT.
OpenAI's flagship reasoning model for solving hard problems. Useful when tackling complex problems in science, coding, math, and similar fields.
OpenAI's flagship reasoning model for solving hard problems. Useful when tackling complex problems in science, coding, math, and similar fields.
Google's newest experimental model as of 12 December 2024. Tops the leaderboards in all categories.
Model Recommender - input your query to have it recommend the best model for your task
Google's newest model, outperforming even Gemini 1.5 Pro, now with a thinking mode enabled similar to the o1 series of OpenAI.
Google's newest model, outperforming even Gemini 1.5 Pro.
Google's newest experimental model as of 21 November 2024. Tops the leaderboards on many independent benchmarks.
Google's newest experimental model as of 14 November 2024. Tops the leaderboards on many independent benchmarks.
OpenAI's new flagship series of reasoning models for solving hard problems. Useful when tackling complex problems in science, coding, math, and similar fields
A fast, cost-efficient version of OpenAI's o1 reasoning model tailored to coding, math, and science use cases.
Google's next-generation model with a breakthrough 4 million context window. Comparable to GPT-4o.
Experimental version of Google's next-generation model with a breakthrough 4 million context window. Comparable to GPT-4o.
Grok 2 1212 introduces significant enhancements to accuracy, instruction adherence, and multilingual support, making it a powerful and flexible choice for developers seeking a highly steerable, intelligent model..
Grok-2 is xAI's frontier language model, the one used on X. Claims state-of-the-art reasoning capabilities, best for complex and multi-step use cases.
Anthropic's updated most intelligent model, offering even better results on many subjects than GPT-4o.
Experimental release of Qwen's reasoning model. Great at coding and math, but still in development so may exhibit odd bugs. Not production-ready.
Chinese-based trillion-parameter model by StepFun that scores extremely well on Livebench for a broad range of tasks. Supports a variety of languages, but has a relatively small context window (~8000 words).
Llama 3.3 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Llama 3.3 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Dolphin is the most uncensored model yet, built on top of Qwen's 72b model.
Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.
Anthropic's most intelligent model, offering even better results on many subjects than GPT-4o.
Anthropic's updated faster and cheaper model, offering good results on chatbots and coding.
Anthropic's flagship model, outperforming GPT-4 on most benchmarks.
Chinese-developed multilingual (English, Chinese and others) model by 01.ai that's very fast and cheap, yet scores high on independent leaderboards.
Amazon's new flagship model. Can handle up to 300k input tokens, with comparable performance to ChatGPT and Claude 3.5 Sonnet.
OpenAI's most cost-efficient small model. Cheaper and smarter than GPT-3.5 (the original ChatGPT), but less performant than gpt-4o
GLM high-intelligence flagship model with 128K context window
LearnLM is a task-specific model trained to align with learning science principles when following system instructions for teaching and learning use cases. For instance, the model can take on tasks to act as an expert or guide to educate users on specific topics.
Note: comes with a 90% discount currently, enjoy! Meta's largest Llama 3.1 405B model. Open-source, run through an open permissionless crypto network (no central provider).
Llama 3.1 405b with the brakes taken off. Less censored than the regular version, but not abliterated
Alibaba's fastest and cheapest model. Suitable for simple tasks, fast and low cost, with a 1 million token context window.
Alibaba's flagship model. Suitable for complex tasks, with the strongest reasoning ability
Alibaba's balanced model. Fast, cheap, yet still very powerful.
Alibaba's huge context window model. Takes in up to 10 million tokens, which is equivalent to dozens of books.
The latest series of Code-Specific Qwen large language models.
Amazon's new lower cost model. Can handle up to 300k input tokens, with faster output but less thorough understanding than Amazon's Nova Pro.
Amazon's lowest cost model. Comparable to GPT-4o-mini and Gemini 1.5 Flash, with the fastest output.
Large version of Yi Lightning with a 32k context window, but more expensive.
Medium version of Yi Lightning with a huge 200k context window
Medium version of Yi.
Small and powerful, lightweight and fast model. Provides enhanced mathematical operation and code writing capabilities.
A Mistral Nemo 12b finetuned for roleplay and storytelling.
A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
Llama 3.1 70b finetune that offers improvements on coding.
Upgrade to Mistral's flagship model. It is fluent in English, French, Spanish, German, and Italian, with high grammatical accuracy, with a long context window.
Upgrade to Llama-3 Lumimaid 70B. A Llama 3.1 70B finetune trained on curated roleplay data. Extremely uncensored and suitable for NSFW.
A chatbot with emotional intelligence. Has access to recent news, excels in scenarios like customer support and roleplay. Mirrors your conversation style.
Optimized for instruction following. Good at tasks that require precise adherence to provided guidelines. Has access to recent news.
Microsoft's advanced Wizard model. The most popular role-playing model.
Advanced roleplaying model with reasoning and emotional intelligence for engaging interactions, contextual awareness and enhanced narrative depth
Meta's largest and most capable Llama model. Competitive with GPT-4o and Claude 3.5 Sonnet.
OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.
Medium-size (and capability) version of Meta's newest model (3.2 series).
Meta's updated version of their medium Llama model. Slightly lesser performance than Llama Large, but cheaper.
An abliterated (removed restrictions and censorship) version of Llama 3.3 70b.
Meta's GPT-4 level model. Cheaper than GPT-4 and Claude 3, with similar performance according to most.
The bigger version of the Perplexity model that is able to browse the web and access up-to-date information.
Meta's largest and most capable Llama model. Competitive with GPT-4o and Claude 3.5 Sonnet.
Experimental version of Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 2 million words context window.
Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 2 million words context window.
A Perplexity model that is able to browse the web and access up-to-date information.
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
Combination of DeepSeek V2 Chat and Coder, integrating capabilities from both.
High-intelligence model with 128K context window
Extended context model supporting up to 1M tokens
Super cost-effective, excellent performance. Balanced high-precision tuning based on performance, inference speed, and cost.
Great multilingual support, strong at mathematics and coding, supports roleplay and chatbots.
Full-parameter finetune of Qwen2.5-72B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
Designed for instruction following, conversational, and coding.
Can take in the largest messages (up to 300 pages of context), and all round seen as one of the best in class models.
OpenAI's most advanced model. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50% cheaper.
Older model. Brought ChatGPT to the mainstream, seen as dated nowadays. 90% cheaper than GPT-4-Turbo, recommended for very simple tasks.
Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 1 million context window.
Google's next-generation model with a breakthrough 1 million context window. Comparable to GPT-4o.
Free model to try out our service with.
Upgraded model of Magnum V2 72B. From the creators of Goliath. Aimed at achieving prose quality similar to Claude Opus 3, trained on 55 million tokens of curated Roleplay data.
Successor to Dolphin 2.6 Mixtral 8x7b. Great for instruction following, conversational, and coding.
Optimized for high quality dialogue usecases.
Fast and efficient for simple purposes.
A recreation trial of the original MythoMax-L2-B13 but merged with updated models.
Powered by Mistral-7B-v0.2, best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.
Optimized for speed with decent context length
Optimized for high quality dialogue usecases.
Finetune of Mistral 7B Instruct, very fast.
35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents
104B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents
The best performing 8B abliterated model according to most benchmarks.
An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.
An abliterated (removed restrictions and censorship) version of Llama 3.1 70b Nemotron.
12B parameter model with multilingual support.
RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive by making sure no two entries in the dataset have repeated characters or situations, which makes sure the model does not latch on to a certain personality and be capable of understanding and acting appropriately to any characters or situations.
Much more inclined to output adult content than its predecessor. Great choice for novelty roleplay scenarios.
Overall it provides a solid option for RP and creative writing while still functioning as an assistant model, if desired. If used to continue a roleplay it will generally follow the ongoing cadence of the conversation.
Mag Mell demonstrates worldbuilding capabilities unlike any model in its class, comparable to old adventuring models like Tiefighter, and prose that exhibits minimal slop.
Combination of EVA and Euryale.
Combination of EVA, Euryale and Anubis.
L3.3 finetune for roleplaying.
Small model optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization
Small model optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization
Meta's Llama 3.1 8B model via an open permissionless network
Fastest GLM-4 variant with 8K context window
High-performance model with 128K context window
Extremely cheap model with 128K context window
Euryale v2.2-based finetune.
Designed for engaging storytelling and rich prose. Expanded vocabulary with unique and expressive word choices, enhanced creativity and captivating stories.
A 70B parameter model from SAO10K based on Llama 3.3 70B, offering high-quality text generation.
A 70B parameter model from SAO10K based on Llama 3.1 70B, offering high-quality text generation.
UnslopNemo v4 is the previous version from the creator of Rocinante, designed for adventure writing and role-play scenarios.
Generalist language model including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.
Great for RP and storytelling.
Mistral Nemo finetine that offers improvements on roleplay.
Creative model based on Llama 3.1 70B
Inferor is a merge of top roleplay models, expert on immersive narratives and storytelling.
Anthropic's updated most intelligent model, offering even better results on many subjects than GPT-4o.