Model catalog

GPT-5 Image MiniOpenAI

GPT-5 Image Mini accepts PDFs, images, text and returns images, text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

PaddleOCR VLPaddlepaddle

PaddleOCR VL accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 16,384 tokens.

Claude Haiku 4.5Anthropic

Claude Haiku 4.5 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Claude Haiku 4.5 (latest)Anthropic

Claude Haiku 4.5 (latest) accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Qwen3 VL Flash (Alibaba Cloud)Alibaba

Qwen3 VL Flash (Alibaba Cloud) accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Seed 1.6Bytedance Seed

Seed 1.6 accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 64,000 tokens.

Veo 3.1 PreviewGoogle

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

GPT-5 ImageOpenAI

GPT-5 Image accepts images, text, PDFs and returns images, text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

Gemini 2.5 Computer Use PreviewGoogle

Gemini 2.5 Computer Use Preview accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 64,000 tokens.

GPT-5 ProOpenAI

GPT-5 Pro accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 272,000 tokens.

Qwen3 VL 30B A3B InstructAlibaba

Qwen3 VL 30B A3B Instruct accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Granite-4.0-H-MicroIbm

Granite-4.0-H-Micro accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Granite-4.0-H-SmallIbm

Granite-4.0-H-Small accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Gemini 2.5 Flash TTSGoogle

Gemini 2.5 Flash TTS accepts text and returns audio. The canonical context window is 32,768 tokens. The canonical maximum output is 16,384 tokens.

Gemini 2.5 Pro TTSGoogle

Gemini 2.5 Pro TTS accepts text and returns audio. The canonical context window is 32,768 tokens. The canonical maximum output is 16,384 tokens.

GLM-4.6Zhipu AI

GLM-4.6 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

Claude Sonnet 4.5Anthropic

Claude Sonnet 4.5 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Claude Sonnet 4.5 (latest)Anthropic

Claude Sonnet 4.5 (latest) accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Cydonia 24B V4.1Thedrummer

Cydonia 24B V4.1 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 117,964 tokens.

Relace Apply 3Relace

Relace Apply 3 accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 128,000 tokens.

Gemma-SEA-LION-v4-27B-ITAisingapore

Gemma-SEA-LION-v4-27B-IT accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 128,000 tokens.

Qwen3 MaxAlibaba

Qwen3 Max accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Qwen3 VL 235B A22B InstructAlibaba

Qwen3 VL 235B A22B Instruct accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Qwen3 VL 235B A22B ThinkingAlibaba

Qwen3 VL 235B A22B Thinking accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.