Gleamrouter is the prism for AI: one API key goes in, every frontier model comes out. OpenAI-compatible, smart routing, automatic failover, unified billing.
# 只需把 base_url 指向 Gleamrouter，一个 Key 调用全部模型
curl https://api.gleamrouter.ai/v1/chat/completions \
-H "Authorization: Bearer $GLEAMROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.5",
"messages": [{"role": "user", "content": "你好，世界"}]
}'
# 换模型只改一个字段："claude-opus-4.7"、"gemini-3-pro"、"deepseek-v3" ...Seedance and MiniMax Hailuo, routed through the same gleam — one task API for text-to-video and image-to-video, billed by the second.
Dual-channel redundancy across Volcano Ark and Tencent VOD — if one channel degrades, traffic switches automatically.
Cinematic motion and strong subject consistency from MiniMax's flagship video generation models.
Final settlement follows the actual resolution tier — over-charge refunded automatically.
Explore Video ModelsContinuously adding the latest models with a unified calling experience
An OpenRouter-style aggregation layer: one key, one bill, every model.
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.
Seedance 2.0 / 2.0 Fast text-to-video & image-to-video in the same API. 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.
Sign up and get one key that unlocks every model on the platform.
Keep your OpenAI SDK — just change base_url and the key. Zero code rewrite.
Pick a model name and go. Requests auto-route to the best available channel.