Collections

Use LLMs

These large language models understand and generate natural language. They power chatbots, search engines, writing aids, and more.

Use these for:

  • Conversational AI: Chat and engage in natural dialogue. Get an AI assistant.
  • Question answering: Provide informative answers to questions. Build a knowledge base.
  • Text generation: Generate fluent continuations of text. Autocomplete your writing.
  • Summarization: Summarize long passages of text. Get key points quickly.
  • Translation: Translate between languages. Communicate across language barriers.

Language models keep getting bigger and better at these tasks. The largest models today exhibit impressive reasoning skills. But you can get great results from smaller, faster, cheaper models too.

Recommended models

openai / gpt-4o

OpenAI's high-intelligence chat model

Updated 2 days, 21 hours ago

193.8K runs

ibm-granite / granite-3.3-8b-instruct

Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.

Updated 1 week ago

1.3M runs

openai / gpt-5-nano

Fastest, most cost-effective GPT-5 model from OpenAI

Updated 1 month ago

34.9K runs

openai / gpt-5-mini

Faster version of OpenAI's flagship GPT-5 model

Updated 1 month ago

42.6K runs

openai / o4-mini

OpenAI's fast, lightweight reasoning model

Updated 1 month ago

246.2K runs

openai / o1-mini

A small model alternative to o1

Updated 1 month ago

658 runs

openai / o1

OpenAI's first o-series reasoning model

Updated 1 month ago

15.8K runs

openai / gpt-4o-mini

Low latency, low cost version of OpenAI's GPT-4o model

Updated 1 month ago

3M runs

openai / gpt-4.1

OpenAI's Flagship GPT model for complex tasks.

Updated 1 month ago

107.4K runs

openai / gpt-4.1-nano

Fastest, most cost-effective GPT-4.1 model from OpenAI

Updated 1 month ago

364.7K runs

openai / gpt-4.1-mini

Fast, affordable version of GPT-4.1

Updated 1 month ago

1.1M runs

qwen / qwen3-235b-a22b-instruct-2507

Updated Qwen3 model for instruction following

Updated 1 month, 1 week ago

47.4K runs

moonshotai / kimi-k2-instruct

Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities

Updated 1 month, 1 week ago

27.7K runs

deepseek-ai / deepseek-v3

DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source

Updated 5 months, 2 weeks ago

3.2M runs

anthropic / claude-3.7-sonnet

The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)

Updated 6 months, 2 weeks ago

2.7M runs

anthropic / claude-3.5-haiku

Anthropic's fastest, most cost-effective model, with a 200K token context window (claude-3-5-haiku-20241022)

Updated 7 months ago

2.5M runs

anthropic / claude-3.5-sonnet

Anthropic's most intelligent language model to date, with a 200K token context window and image understanding (claude-3-5-sonnet-20241022)

Updated 7 months ago

523.2K runs

meta / meta-llama-3.1-405b-instruct

Meta's flagship 405 billion parameter language model, fine-tuned for chat completions

Updated 1 year, 1 month ago

6.4M runs

yorickvp / llava-13b

Visual instruction tuning towards large language and vision models with GPT-4 level capabilities

Updated 1 year, 1 month ago

30.6M runs

meta / meta-llama-3-70b

Base version of Llama 3, a 70 billion parameter language model from Meta.

Updated 1 year, 4 months ago

837.7K runs

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

A 70 billion parameter language model from Meta, fine tuned for chat completions

Updated 1 year, 4 months ago

160.4M runs

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

An 8 billion parameter language model from Meta, fine tuned for chat completions

Updated 1 year, 4 months ago

379.4M runs

meta / meta-llama-3-8b

Base version of Llama 3, an 8 billion parameter language model from Meta.

Updated 1 year, 4 months ago

51M runs

google-deepmind / gemma-2b-it

2B instruct version of Google’s Gemma model

Updated 1 year, 6 months ago

133.8K runs

yorickvp / llava-v1.6-vicuna-13b

LLaVA v1.6: Large Language and Vision Assistant (Vicuna-13B)

Updated 1 year, 7 months ago

3.7M runs

yorickvp / llava-v1.6-mistral-7b

LLaVA v1.6: Large Language and Vision Assistant (Mistral-7B)

Updated 1 year, 7 months ago

4.9M runs

stability-ai / stablelm-tuned-alpha-7b

7 billion parameter version of Stability AI's language model

Updated 2 years, 4 months ago

140.6K runs

replicate / flan-t5-xl

A language model by Google for tasks like classification, summarization, and more

Updated 2 years, 4 months ago

150.9K runs

replicate / llama-7b

Transformers implementation of the LLaMA language model

Updated 2 years, 5 months ago

99.3K runs