Model catalog

SuperGemma 4 26B · UncensoredUnlid

SuperGemma 4 26B · Uncensored accepts text, images and returns text. The canonical context window is 256,000 tokens.

Gemma 4 26B A4B · UncensoredUnlid

Gemma 4 26B A4B · Uncensored accepts text, images and returns text. The canonical context window is 32,768 tokens.

Nemotron Cascade 2 30B A3BNvidia

Nemotron Cascade 2 30B A3B accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,768 tokens.

Qwen3.5 9B · AbliteratedUnlid

Qwen3.5 9B · Abliterated accepts text, images and returns text. The canonical context window is 32,768 tokens.

Mistral Small 3.2 24B RP · UncensoredUnlid

Mistral Small 3.2 24B RP · Uncensored accepts text, images and returns text. The canonical context window is 128,000 tokens.

Tiny Aya EarthCohere

Tiny Aya Earth accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 8,000 tokens.

Tiny Aya FireCohere

Tiny Aya Fire accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 8,000 tokens.

Tiny Aya GlobalCohere

Tiny Aya Global accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 8,000 tokens.

Tiny Aya WaterCohere

Tiny Aya Water accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 8,000 tokens.

GLM 4.7 Flash · HereticUnlid

GLM 4.7 Flash · Heretic accepts text and returns text. The canonical context window is 131,072 tokens.

GLM-ImageZhipu AI

GLM-Image accepts text, images and returns images. The canonical context window is 10,240 tokens.

Trinity Nano PreviewArcee Ai

Trinity Nano Preview accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Kling Avatar ProfessionalKling AI

Kling Avatar Professional accepts text, images, audio and returns video.

Kling Avatar StandardKling AI

Kling Avatar Standard accepts text, images, audio and returns video.

Kimi K2 Thinking TurboMoonshot AI

Kimi K2 Thinking Turbo accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Llama Nemotron Embed 1B v2Nvidia

Llama Nemotron Embed 1B v2 accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 2,048 tokens.

Veo 3.1 Fast PreviewGoogle

Veo 3.1 Fast Preview accepts text, images, video and returns video. The canonical context window is 1,024 tokens.

Devstral MediumMistral

Devstral Medium accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 128,000 tokens.

Devstral SmallMistral

Devstral Small accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 128,000 tokens.

Dolphin Mistral 24B · UncensoredUnlid

Dolphin Mistral 24B · Uncensored accepts text, images and returns text. The canonical context window is 128,000 tokens.

Nova PremierAmazon

Nova Premier accepts text, images, video, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 10,000 tokens.

Aya Vision 32BCohere

Aya Vision 32B accepts text, images and returns text. The canonical context window is 16,000 tokens. The canonical maximum output is 4,000 tokens.