AI Agent Hub

LLM Models

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

Compare
🤖
Claude Opus 5 (Fast)
anthropic

Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Multimodal
🤖
Qwen: Qwen3.7 Flash
qwen

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

Closed Source
🤖
Thinking Machines: Inkling Small (free)
thinkingmachines

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Closed Source
🤖
Thinking Machines: Inkling Small (batch)
thinkingmachines

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Closed Source
🤖
Thinking Machines: Inkling Small
thinkingmachines

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Closed Source
🤖
DeepSeek: DeepSeek V4 Flash 0731 (batch)
deepseek

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Closed Source
🤖
DeepSeek: DeepSeek V4 Flash 0731
deepseek

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Closed Source
🤖
DeepSeek V4 Flash Latest
~deepseek

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Closed Source
🤖
Qwen: Qwen3.8 Max
qwen

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...

Closed Source
🤖
Meta: Muse Spark 1.2
meta

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

Closed Source
🤖
Meta: Muse Glimmer 30B (batch)
meta

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

Closed Source
🤖
Meta: Muse Glimmer 30B
meta

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

Closed Source