AI models

prism-ml

Bonsai 27B mlx 1bit is an open-weight large language model developed by prism-ml and available on Hugging Face. It is de...

200K ctx · $15/$75 per 1M · Anthropic

Claude 3 Opus is Anthropic's most capable frontier LLM, designed for complex, open-ended reasoning tasks. It supports bo...

200K ctx · $0.80/$4 per 1M · Anthropic

Claude 3.5 Haiku is Anthropic's fastest, low-cost model designed for latency-sensitive and high-volume workloads. It is ...

200K ctx · $3/$15 per 1M · Anthropic

Claude 3.5 Sonnet is Anthropic's balanced frontier large language model with vision capabilities. It excels at coding, a...

32K ctx · $0.20/$0.60 per 1M · Mistral AI

Codestral is Mistral AI's code-specialized model designed for code generation and fill-in-the-middle tasks across multip...

128K ctx · $2.50/$10 per 1M · Cohere

Command R+ is Cohere's enterprise-grade frontier language model optimized for retrieval-augmented generation (RAG) and t...

deepseek-ai

DeepSeek V3 0324 is an open-weight large language model developed by deepseek-ai and available on Hugging Face Hub. It i...

deepseek-ai

DeepSeek V3.2 is an open-weight large language model developed by deepseek-ai and available on Hugging Face Hub. It is d...

deepseek-ai

DeepSeek V4 Flash is an open-weight large language model designed for text-based tasks, published by deepseek-ai on the ...

deepseek-ai

DeepSeek V4 Flash 0731 is an open-weight language model developed by deepseek-ai and available on the Hugging Face Hub. ...

deepseek-ai

DeepSeek V4 Flash DSpark is an open-weight large language model developed by deepseek-ai and available on Hugging Face. ...

antirez

deepseek v4 gguf is an open-weight text-based large language model published by antirez on the Hugging Face Hub. It is p...

128K ctx · $0.55/$2.19 per 1M · DeepSeek

DeepSeek-R1 is an open-weights reasoning model developed by DeepSeek, optimized for generating long chains of thought. I...

128K ctx · $0.27/$1.10 per 1M · DeepSeek

DeepSeek-V3 is a large open-weight mixture-of-experts model developed by DeepSeek, offering high-quality performance at ...

distilbert

distilgpt2 is a lighter, open-weight variant of GPT-2, designed for text generation tasks. It is published by distilbert...

dphn

dolphin 2.9.1 yi 1.5 34b is an open-weight, text-based large language model developed by dphn and hosted on Hugging Face...

512 ctx · $0.10 in per 1M · Cohere

Cohere's Embed v3 is a text embedding model designed for semantic search and retrieval tasks, with support for multiple ...

1M ctx · $0.07/$0.30 per 1M · Google

Gemini 1.5 Flash is a small, fast, and low-cost multimodal LLM from Google, designed for high-throughput tasks. It excel...

2M ctx · $1.25/$5 per 1M · Google

Google's long-context multimodal model with a context window up to two million tokens.

1M ctx · $0.10/$0.40 per 1M · Google

Gemini 2.0 Flash is Google's next-generation fast multimodal model with native tool use and a long context window. It is...

google

gemma 3 1b it is an open-weight text-based language model developed by Google and hosted on Hugging Face. It is suitable...

nvidia

Gemma 4 26B A4B NVFP4 is an open-weight, text-based large language model developed by NVIDIA and hosted on Hugging Face....

nvidia

Gemma 4 31B IT NVFP4 is an open-weight, text-based large language model developed by NVIDIA. It is designed for general-...

legraphista

glm 4 9b chat IMat GGUF is an open-weight language model published on the Hugging Face Hub by legraphista. It is based o...

zai-org

GLM 4.7 Flash is an open-weight large language model published by zai-org on Hugging Face. It is designed for general te...

zai-org

GLM 5.2 is an open-weight large language model (LLM) published by zai-org on Hugging Face. It is designed for text-based...

zai-org

GLM 5.2 FP8 is an open-weight, text-based large language model developed by zai-org. It is designed for general-purpose ...

openai

gpt oss 120b is an open-weight model published on the Hugging Face Hub by openai.

openai

gpt oss 20b is an open-weight large language model published by OpenAI on the Hugging Face Hub. It is designed for gener...

128K ctx · $2.50/$10 per 1M · OpenAI

GPT-4o is OpenAI's flagship multimodal model, capable of processing text, image, and audio inputs. It excels in general ...

128K ctx · $0.15/$0.60 per 1M · OpenAI

GPT-4o mini is a smaller, low-cost OpenAI model designed for high-volume tasks. It supports both text and vision inputs,...

openai-community

gpt2 is an open-weight text generation model published by the openai-community. It is suitable for tasks like text compl...

openai-community

gpt2 large is an open-weight model published on the Hugging Face Hub by openai-community.

131K ctx · $2/$10 per 1M · xAI

Grok 2 is xAI's flagship conversational model, offering real-time context and strong reasoning capabilities. It is a Fro...

256K ctx · $2/$8 per 1M · AI21 Labs

Jamba 1.5 Large is AI21 Labs' hybrid Mamba-Transformer open LLM with a 256k token context window, designed for text-base...

RadixArk

Kimi K3 DSpark is an open-weight large language model developed by RadixArk and available on Hugging Face. It is designe...

LiquidAI

LFM2.5 2.6B GGUF is an open-weight 2.6B parameter text model by LiquidAI, available in GGUF format. It is suitable for l...

128K ctx · Meta

Llama 3.1 405B is Meta's largest open-weight language model, designed to compete with leading closed frontier models acr...

128K ctx · Meta

Llama 3.1 70B is an open-weight large language model designed for self-hosting, offering a balance between capability an...

128K ctx · Meta

Llama 3.1 8B is a small, open-weights language model from Meta designed for efficiency on modest hardware, such as on-de...

meta-llama

Llama 3.1 8B Instruct is an open-weight, text-based large language model developed by Meta. It is designed for instructi...

mlx-community

Llama 3.1 8B Instruct 4bit is an open-weight, text-based language model fine-tuned for instruction following. It is a qu...

meta-llama

Llama 3.2 1B is an open-weight, text-based large language model developed by Meta. It is suited for tasks requiring basi...

meta-llama

Llama 3.2 1B Instruct is an open-weight, text-based language model developed by Meta. It is designed for instruction-fol...

meta-llama

Llama 3.2 3B Instruct is an open-weight language model developed by Meta for instruction-following tasks. It is designed...

128K ctx · Meta

Llama 3.2 90B Vision is an open-weight multimodal model from Meta that combines text and vision capabilities. It excels ...

meta-llama

Llama 3.3 70B Instruct is an open-weight, text-based LLM developed by Meta. It is designed for instruction-following tas...

meta-llama

Meta Llama 3 8B Instruct is an open-weight model published on the Hugging Face Hub by meta-llama.