Search the modelsyour product can ship.

mistralai/mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.

openai/gpt-4o-mini

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal

openai/gpt-4o-mini-2024-07-18

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal

qwen/qwen-2-7b-instruct

Qwen2 7B is a transformer-based model that excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning. It features SwiGLU activation, attention QKV bias, and group query attention. It is pretrained on extensive data with supervised finetuning and direct preference optimization. For more details, see this [blog post](https://qwenlm.github.io/blog/qwen2/) and [GitHub repo](https://github.com/QwenLM/Qwen2). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

google/gemma-2-27b-it

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).

nousresearch/hermes-2-theta-llama-3-8b

An experimental merge model based on Llama 3, exhibiting a very distinctive style of writing. It combines the the best of [Meta's Llama 3 8B](https://openrouter.ai/models/meta-llama/llama-3-8b-instruct) and Nous Research's [Hermes 2 Pro](https://openrouter.ai/models/nousresearch/hermes-2-pro-llama-3-8b). Hermes-2 Θ (theta) was specifically designed with a few capabilities in mind: executing function calls, generating JSON output, and most remarkably, demonstrating metacognitive abilities (contemplating the nature of thought and recognizing the diversity of cognitive processes among individuals).

alpindale/magnum-72b

From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the first in a new family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet. The model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.

google/gemma-2-9b-it

Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).

sao10k/l3-stheno-8b

Stheno 8B 32K is a creative writing/roleplay model from [Sao10k](https://ko-fi.com/sao10k). It was trained at 8K context, then expanded to 32K context. Compared to older Stheno version, this model is trained on: - 2x the amount of creative writing samples - Cleaned up roleplaying samples - Fewer low quality samples

ai21/jamba-instruct

The Jamba-Instruct model, introduced by AI21 Labs, is an instruction-tuned variant of their hybrid SSM-Transformer Jamba model, specifically optimized for enterprise applications. - 256K Context Window: It can process extensive information, equivalent to a 400-page novel, which is beneficial for tasks involving large documents such as financial reports or legal documents - Safety and Accuracy: Jamba-Instruct is designed with enhanced safety features to ensure secure deployment in enterprise environments, reducing the risk and cost of implementation Read their [announcement](https://www.ai21.com/blog/announcing-jamba) to learn more. Jamba has a knowledge cutoff of February 2024.

01-ai/yi-large

The Yi Large model was designed by 01.AI with the following usecases in mind: knowledge search, data classification, human-like chat bots, and customer service. It stands out for its multilingual proficiency, particularly in Spanish, Chinese, Japanese, German, and French. Check out the [launch announcement](https://01-ai.github.io/blog/01.ai-yi-large-llm-launch) to learn more.

nvidia/nemotron-4-340b-instruct

Nemotron-4-340B-Instruct is an English-language chat model optimized for synthetic data generation. This large language model (LLM) is a fine-tuned version of Nemotron-4-340B-Base, designed for single and multi-turn chat use-cases with a 4,096 token context length. The base model was pre-trained on 9 trillion tokens from diverse English texts, 50+ natural languages, and 40+ coding languages. The instruct model underwent additional alignment steps: 1. Supervised Fine-tuning (SFT) 2. Direct Preference Optimization (DPO) 3. Reward-aware Preference Optimization (RPO) The alignment process used approximately 20K human-annotated samples, while 98% of the data for fine-tuning was synthetically generated. Detailed information about the synthetic data generation pipeline is available in the [technical report](https://arxiv.org/html/2406.11704v1).

anthropic/claude-3.5-sonnet-20240620

Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at: - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems) For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet). #multimodal

sao10k/l3-euryale-70b

Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and custom formatting / reply formats. - Very creative, lots of unique swipes. - Is not restrictive during roleplays.

microsoft/phi-3-medium-4k-instruct

Phi-3 4K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. In the MMLU-Pro eval, the model even comes close to a Llama3 70B level of performance. For 128k context length, try [Phi-3 Medium 128K](/models/microsoft/phi-3-medium-128k-instruct).

bigcode/starcoder2-15b-instruct

StarCoder2 15B Instruct excels in coding-related tasks, primarily in Python. It is the first self-aligned open-source LLM developed by BigCode. This model was fine-tuned without any human annotations or distilled data from proprietary LLMs. The base model uses [Grouped Query Attention](https://arxiv.org/abs/2305.13245) and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) objective on 4+ trillion tokens.

cognitivecomputations/dolphin-mixtral-8x22b

Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a finetune of [Mixtral 8x22B Instruct](/models/mistralai/mixtral-8x22b-instruct). It features a 64k context length and was fine-tuned with a 16k sequence length using ChatML templates. This model is a successor to [Dolphin Mixtral 8x7B](/models/cognitivecomputations/dolphin-mixtral-8x7b). The model is uncensored and is stripped of alignment and bias. It requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at [erichartford.com/uncensored-models](https://erichartford.com/uncensored-models). #moe #uncensored

qwen/qwen-2-72b-instruct

Qwen2 72B is a transformer-based model that excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning. It features SwiGLU activation, attention QKV bias, and group query attention. It is pretrained on extensive data with supervised finetuning and direct preference optimization. For more details, see this [blog post](https://qwenlm.github.io/blog/qwen2/) and [GitHub repo](https://github.com/QwenLM/Qwen2). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

openchat/openchat-8b

OpenChat 8B is a library of open-source language models, fine-tuned with "C-RLFT (Conditioned Reinforcement Learning Fine-Tuning)" - a strategy inspired by offline reinforcement learning. It has been trained on mixed-quality data without preference labels. It outperforms many similarly sized models including [Llama 3 8B Instruct](/models/meta-llama/llama-3-8b-instruct) and various fine-tuned models. It excels in general conversation, coding assistance, and mathematical reasoning. - For OpenChat fine-tuned on Mistral 7B, check out [OpenChat 7B](/models/openchat/openchat-7b). - For OpenChat fine-tuned on Llama 8B, check out [OpenChat 8B](/models/openchat/openchat-8b). #open-source

nousresearch/hermes-2-pro-llama-3-8b

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.

mistralai/mistral-7b-instruct-v0.3

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-v0.2), with the following changes: - Extended vocabulary to 32768 - Supports v3 Tokenizer - Supports function calling NOTE: Support for function calling depends on the provider.

mistralai/mistral-7b-instruct

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*

microsoft/phi-3-mini-128k-instruct

Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date.

microsoft/phi-3-medium-128k-instruct

Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. In the MMLU-Pro eval, the model even comes close to a Llama3 70B level of performance. For 4k context length, try [Phi-3 Medium 4K](/models/microsoft/phi-3-medium-4k-instruct).

neversleep/llama-3-lumimaid-70b

The NeverSleep team is back, with a Llama 3 70B finetune trained on their curated roleplay data. Striking a balance between eRP and RP, Lumimaid was designed to be serious, yet uncensored when necessary. To enhance it's overall intelligence and chat capability, roughly 40% of the training data was not roleplay. This provides a breadth of knowledge to access, while still keeping roleplay as the primary strength. Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

deepseek/deepseek-chat-v2.5

DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct. The new model integrates the general and coding abilities of the two previous versions. For model details, please visit [DeepSeek-V2 page](https://github.com/deepseek-ai/DeepSeek-V2) for more information.

google/gemini-flash-1.5

Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots. Gemini 1.5 Flash is designed for high-volume, high-frequency tasks where cost and latency matter. On most common tasks, Flash achieves comparable quality to other Gemini Pro models at a significantly reduced cost. Flash is well-suited for applications like chat assistants and on-demand content generation where speed and scale matter. Usage of Gemini is subject to Google's [Gemini Terms of Use](https://ai.google.dev/terms). #multimodal

meta-llama/llama-3-8b

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This is the base 8B pre-trained version. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

openai/gpt-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209) #multimodal

meta-llama/llama-3-70b

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This is the base 70B pre-trained version. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

openai/gpt-4o-2024-05-13

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209) #multimodal

meta-llama/llama-guard-2-8b

This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, [LlamaGuard 1](https://huggingface.co/meta-llama/LlamaGuard-7b), it can do both prompt and response classification. LlamaGuard 2 acts as a normal LLM would, generating text that indicates whether the given input/output is safe/unsafe. If deemed unsafe, it will also share the content categories violated. For best results, please use raw prompt input or the `/completions` endpoint, instead of the chat API. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

liuhaotian/llava-yi-34b

LLaVA Yi 34B is an open-source model trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: [NousResearch/Nous-Hermes-2-Yi-34B](/models/nousresearch/nous-hermes-yi-34b) It was trained in December 2023.

allenai/olmo-7b-instruct

OLMo 7B Instruct by the Allen Institute for AI is a model finetuned for question answering. It demonstrates **notable performance** across multiple benchmarks including TruthfulQA and ToxiGen. **Open Source**: The model, its code, checkpoints, logs are released under the [Apache 2.0 license](https://choosealicense.com/licenses/apache-2.0). - [Core repo (training, inference, fine-tuning etc.)](https://github.com/allenai/OLMo) - [Evaluation code](https://github.com/allenai/OLMo-Eval) - [Further fine-tuning code](https://github.com/allenai/open-instruct) - [Paper](https://arxiv.org/abs/2402.00838) - [Technical blog post](https://blog.allenai.org/olmo-open-language-model-87ccfc95f580) - [W&B Logs](https://wandb.ai/ai2-llm/OLMo-7B/reports/OLMo-7B--Vmlldzo2NzQyMzk5)

qwen/qwen-7b-chat

Qwen1.5 7B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

qwen/qwen-14b-chat

Qwen1.5 14B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

qwen/qwen-110b-chat

Qwen1.5 110B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

qwen/qwen-32b-chat

Qwen1.5 32B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

qwen/qwen-4b-chat

Qwen1.5 4B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

qwen/qwen-72b-chat

Qwen1.5 72B is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: - Significant performance improvement in human preference for chat models - Multilingual support of both base and chat models - Stable support of 32K context length for models of all sizes For more details, see this [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

neversleep/llama-3-lumimaid-8b

The NeverSleep team is back, with a Llama 3 8B finetune trained on their curated roleplay data. Striking a balance between eRP and RP, Lumimaid was designed to be serious, yet uncensored when necessary. To enhance it's overall intelligence and chat capability, roughly 40% of the training data was not roleplay. This provides a breadth of knowledge to access, while still keeping roleplay as the primary strength. Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

snowflake/snowflake-arctic-instruct

Arctic is a dense-MoE Hybrid transformer architecture pre-trained from scratch by the Snowflake AI Research Team. Arctic combines a 10B dense transformer model with a residual 128x3.66B MoE MLP resulting in 480B total and 17B active parameters chosen using a top-2 gating. To read more about this model's release, [click here](https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/).

fireworks/firellava-13b

A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4. The first commercially permissive open source LLaVA model, trained entirely on open source LLM generated instruction following data.

lynn/soliloquy-l3

Soliloquy-L3 v2 is a fast, highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities. Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

sao10k/fimbulvetr-11b-v2

Creative writing model, routed with permission. It's fast, it keeps the conversation going, and it stays in character. If you submit a raw prompt, you can use Alpaca or Vicuna formats.

meta-llama/llama-3-8b-instruct

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

meta-llama/llama-3-70b-instruct

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

mistralai/mixtral-8x22b-instruct

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe