Model Terminal

Robostral Navigate

Robostral Navigate is an 8B vision-language-action model from Mistral AI that enables robots to follow plain-language navigation instructions using only a single monocular RGB camera, with no depth sensors or pre-built maps required. Trained entirely in simulation, it generalizes across wheeled, legged, and flying robot platforms. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Identity

Developer
Unknown
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed