Save 15%
MiniMax-H3-Max
MiniMax-H3-Max text-to-video via RouterBase. Long-form audio-inclusive clips: 5-15 seconds at 480P or 768P, six fixed aspect ratios.
Catalog
Mercado de modelos
Explore todos os modelos de IA disponíveis — compare preços, funcionalidades e comece a integrar.
Vídeo
Imagem
Chat
MiniMax-H3-Max (Image-to-Video)
MiniMax-H3-Max image-to-video via RouterBase. Animate a first frame into a 5-15 second audio-inclusive clip at 480P or 768P.
Save 15% GPT-5.6-Luna
OpenAI GPT-5.6 Luna via RouterBase. The lightweight GPT-5.6 tier: 1M-token context, reasoning, tool calling and prompt caching at a fraction of the flagship rate.
Save 15% GPT-5.6-Sol
OpenAI GPT-5.6 Sol via RouterBase. The highest-capability GPT-5.6 tier for the hardest reasoning work; 1M-token context with prompt caching.
Save 15% GPT-5.6-Terra
OpenAI GPT-5.6 Terra via RouterBase. The balanced GPT-5.6 tier: 1M-token context, reasoning, structured outputs and tool calling.
Save 15% GLM-5.3-Flash
ZAI GLM-5.3-Flash via RouterBase. The fast, low-cost GLM-5.3 tier: 1M-token context, reasoning, tool calling and structured outputs.
DeepSeek V4 Pro (0813)
DeepSeek V4 Pro (0813 snapshot) via RouterBase. Pinned build of V4 Pro; 1M-token context, reasoning, function calling, OpenAI-compatible chat completions.
Save 5%
MiniMax H3(Image-to-Video)
MiniMax-H3 image-to-video via RouterBase. Animate a still first-frame image into a 2K clip with synchronized audio; flagship multimodal quality.
Save 5%
MiniMax H3(Reference-to-Video)
MiniMax-H3 reference-to-video via RouterBase. Provide a subject/character reference image and MiniMax-H3 keeps that identity consistent across a 2K clip.
Save 5%
MiniMax H3(Text-to-Video)
MiniMax-H3 text-to-video via RouterBase. Flagship multimodal video model with synchronized audio, 2K output, and 4-15s clips.
Claude Opus 5
Anthropic Claude Opus 5 via RouterBase. Fifth-generation Opus flagship for agentic coding and long-horizon work; 1M-token context, 128K max output, prompt caching, OpenAI-compatible chat completions.
Save 5% Kimi K3
Moonshot AI Kimi K3 via RouterBase. Flagship reasoning model with native vision understanding and a 1M-token context window. OpenAI-compatible chat completions with tool calling.
Claude Sonnet 5
Anthropic Claude Sonnet 5 via RouterBase. Sonnet-tier flagship; 1M-token context, prompt caching, OpenAI-compatible chat completions.
Save 5% GLM-5.2
ZAI GLM-5.2 via RouterBase. Latest GLM-5 generation, OpenAI-compatible chat completions with tool calling.
Claude Fable 5
Anthropic Claude Fable 5 via RouterBase. Top-tier Claude model; 1M-token context, adaptive thinking, mid-conversation system messages, prompt caching.
Save 15% GPT-5.5
OpenAI GPT-5.5 via RouterBase. Highest-capability GPT-5 chat model; prompt caching and tool calling.
...