Connect your coding tools and applications through RoboVAI. Check model permissions, protocol support and billing before you call.
Connected model catalog
19 models across text, vision, video, image, speech, and embedding
Official model documentation: https://developers.openai.com/api/docs/models
Claude Opus 5.5, released September 2026; 1M context, 128K output, adaptive thinking and vision.
Zhipu's latest flagship GLM-5.3, with major advances in complex software engineering and agent tasks. Same base model as GLM-5.2, all gains from post-training: 50% coding improvement and emergent cybersecurity / vulnerability-discovery capability. 1M context, 128K output, always-on thinking (reasoning_effort: low/high/max).
ByteDance Doubao Seedream 5.0 Pro, high-quality text-to-image and image editing model, strong Chinese scene understanding.
Input: text, image; Output: text; Context window: 500000 tokens.
DeepSeek-V4.1-Flash; official API model deepseek-flash.
DeepSeek-V4-Pro flagship model, with a 1M context window and 384K output. Significantly enhanced agent capabilities and rich world knowledge. Thinking is on by default and can be turned off.
Input: text, image, video, audio, file; Output: text; Context window: 1048576 tokens.
Input: text, image, video; Output: text; Context window: 1000000 tokens.
Input: text, image; Output: video.
Input: text, image, video, audio, file; Output: video.
Kimi K3, Moonshot AI's latest flagship model with a 1M token context window and 128K output. Cutting-edge reasoning, long-context processing, and coding capabilities. Thinking is on by default and can be turned off.
Official MiniMax model; specifications and prices verified against official documentation on 2026-10-07. Language reasoning and tool calling.
Official GPT Image 2.5 generation and editing model; cost varies with token usage, size and quality.
Official GPT Image 2.5 generation and editing model; cost varies with token usage, size and quality.
ByteDance Doubao Seed 2.1 Pro, enhanced capability flagship, 256K context, strong reasoning and agent capabilities.
CosyVoice 3.5 Plus speech synthesis, high-quality multilingual voices.
Alibaba Cloud HappyHorse 1.1 T2V video generation model. Text-to-video with upgraded dynamics, texture and audio. More fluid and natural character motion and scene atmosphere.
新一代视频创作模型，单次 30 秒长叙事、全模态参考、视频编辑与延长。
Check available models and their limits before connecting a client.
One API key for models available to your account. Check each model’s protocol and limits.
Routing and retries depend on the endpoint and account configuration. See the documented limits.
Check eligible models, quota windows and rate multipliers before selecting a Token Plan.
Check routing rules and model rate multipliers before running a task.