Seed GR-RL

Name: Seed GR-RL
Author: ByteDance Seed

other

A reinforcement learning framework for long-horizon dexterous manipulation, enabling robots to execute multi-step, high-precision tasks in real-world.

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Details

Model IDseed-gr-rl

ProviderByteDance Seed

Creatorbytedance

Family—

License—

Statusactive

Typeother

Input modalities—

Output modalities—

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date—

Sourceofficial

API

GET/v1/models/bytedance/seed-gr-rl

Seed GR-RL

seed-gr-rl

A reinforcement learning framework for long-horizon dexterous manipulation, enabling robots to execute multi-step, high-precision tasks in real-world.

Changes · 3 entries

seed-gr-rlcreateca7a400Nov 2, 2026, 03:02 AM

seed-gr-rlupdate118451aSep 24, 2026, 07:08 AM

descriptionA reinforcement learning framework for long-horizon dexte...→A reinforcement learning framework for long-horizon dexte...

seed-gr-rlcreate08f0ffeMay 11, 2026, 08:27 AM