The video-first AI gateway. Seedance 2.0 & Fast text/image-to-video, plus 60+ frontier LLMs — one OpenAI-compatible API, per-second billing, smart failover.
# 文生视频：一句话生成 6 秒电影感画面
curl https://api.yestoken.ai/v1/video/generate \
-H "Authorization: Bearer $YESTOKEN_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedance-2-0-260128",
"prompt": "一只猫在赛博朋克城市的雨夜漫步，霓虹倒影",
"duration": 6,
"resolution": "1080p"
}'
# 轮询任务，获取成片
curl "https://api.yestoken.ai/v1/video/task?task_id=<task_id>" \
-H "Authorization: Bearer $YESTOKEN_KEY"POST /v1/video/generate with text — or an image for image-to-video.
Task accepted instantly. Per-second pre-charge only, never overpay.
Poll the task endpoint. Settled to actual duration — failed tasks auto-refund in full.
Seedance-first, but every frontier model is one endpoint away.
Text-to-video & image-to-video on Seedance 2.0 / 2.0 Fast. Per-second billing: pre-charge on submit, settle on completion, auto-refund on failure.
Token-accurate metering, balance pre-checks, idempotent settlement. Every cent traceable.
OpenAI, Claude, Gemini, Kimi, GLM, DeepSeek and more — OpenAI-compatible, switch models without changing code.
Weighted load balancing, automatic failover and circuit breaking across upstream channels.
Continuously adding the latest models with a unified calling experience