Robostral Navigate
Mistral's first robotics model; built in-house without an existing open VLM. Outputs navigation actions. Access appears to be via Mistral's team ('talk with our team'); status set to preview.
- Input
- text, image, video
- Output
- action
- License
- proprietary
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Mistral AI (contact sales / partners; no public API id or weights found) | — | mistral.ai/news/robostral-navigate/ | docs |
Notable capabilities (2)
- Single-RGB-camera vision-language navigation: 8B model navigates buildings from one RGB camera plus language instructions (no LiDAR/depth); R2R-CE success 79.4% val-seen, 76.6% val-unseen (+9.7 pts over best single-camera method, +4.5 over depth/multi-camera systems). source
- Sim-only training, embodiment-agnostic: Trained in simulation (~2.4M trajectories across 350k scenes per Mistral's page), with prefix caching (22x fewer training tokens) and online RL (CISPO, +3.2 pts); works on wheeled, legged and flying robots. source
Sources: Mistral: Robostral Navigate, tech report.
Timeline entry
- Mistral enters robotics with Robostral Navigate, an 8B single-camera navigation model ★★
Mistral AI released its first robotics model, Robostral Navigate, in early July 2026: an 8B-parameter, hardware-agnostic model that navigates buildings from a single RGB camera and language instructions, trained purely in simulation and scoring 76.6% on R2R-CE val-unseen.
Other Mistral AI models
Mistral OCR 4.1 · Mistral Medium 3.5 · Voxtral TTS · Mistral Small 4 · Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime) · Mistral Large 3 · Codestral 25.08 · Voxtral Small