Model catalog

Llama Nemotron Rerank VL 1B v2Nvidia

Llama Nemotron Rerank VL 1B v2 accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Veo 3.1 Lite PreviewGoogle

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

Gemini 3.1 Flash Live PreviewGoogle

Gemini 3.1 Flash Live Preview accepts text, images, video, audio and returns text, audio. The canonical context window is 131,072 tokens. The canonical maximum output is 65,536 tokens.

Lyria 3 Clip PreviewGoogle

Lyria 3 Clip Preview accepts text, images and returns text, audio. The canonical context window is 131,072 tokens. The canonical maximum output is 65,536 tokens.

Lyria 3 Pro PreviewGoogle

Lyria 3 Pro Preview accepts text, images and returns text, audio. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Reka EdgeRekaai

Reka Edge accepts images, text, video and returns text. The canonical context window is 16,384 tokens. The canonical maximum output is 14,745 tokens.

MiMo-V2-OmniXiaomi

MiMo-V2-Omni accepts text, images, audio, video, PDFs and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 131,072 tokens.

MiMo-V2-ProXiaomi

MiMo-V2-Pro accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

MiniMax-M2.7MiniMax (minimax.io)

MiniMax-M2.7 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

MiniMax-M2.7-highspeedMiniMax (minimax.io)

MiniMax-M2.7-highspeed accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

GPT-5.4 miniOpenAI

GPT-5.4 mini accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5.4 nanoOpenAI

GPT-5.4 nano accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GLM-5-TurboZhipu AI

GLM-5-Turbo accepts text and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 131,072 tokens.

Mistral Small (latest)Mistral

Mistral Small (latest) accepts text, images and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

Mistral Small 4Mistral

Mistral Small 4 accepts text, images and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

Nemotron 3 Super 120B A12BNvidia

Nemotron 3 Super 120B A12B accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Grok 4.20 (Non-Reasoning)xAI

Grok 4.20 (Non-Reasoning) accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 30,000 tokens.

Grok 4.20 (Reasoning)xAI

Grok 4.20 (Reasoning) accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 30,000 tokens.

GPT-5.4OpenAI

GPT-5.4 accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5.4 ProOpenAI

GPT-5.4 Pro accepts text, images and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

Mercury 2Inception

Mercury 2 accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 50,000 tokens.

Gemini 3.1 Flash Lite PreviewGoogle

Gemini 3.1 Flash Lite Preview accepts text, images, video, audio, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

GPT-5.3 Chat (latest)OpenAI

GPT-5.3 Chat (latest) accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 16,384 tokens.

Nano Banana 2 PreviewGoogle

Nano Banana 2 Preview accepts text, images, PDFs and returns text, images. The canonical context window is 65,536 tokens. The canonical maximum output is 65,536 tokens.