Primary use stated or inferred cautiously from official documentation.
Praxis-1 Base
Base checkpoint of Praxis-1, Runway’s video-action model family made public on November 11. It includes the MoE diffusion trunk and action expert but lacks heads for any particular robot.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | runwayml/praxis-1-base |
|---|---|
| Model type | Robotics · Video · Multimodal |
| Access model | Downloadable weights |
| License | Apache-2.0 · dependencies under their own licenses |
| Deployment | Self-hosted |
| Release | 11 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Robot state |
| Exit | Video · Robot actions |
| Context window | Instruction, cameras and robot state |
| maximum output | Actions only after adding heads and fine-tuning |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Hugging Face · LeRobot |
Prepare adaptation to another robot configuration. Initialize action and proprioception heads and fine-tune accordingly. This checkpoint cannot run directly as a control policy.
Reference BF16 inference requires an 80 GB GPU. Weights occupy 54.4 GB, which is not total memory usage. Wan2.2 VAE and Qwen3.5-2B are distributed separately under their own licenses. Long tasks and similar-looking objects remain limitations.
What it can do
Orientation
Prepare adaptation to another robot configuration. Initialize action and proprioception heads and fine-tune accordingly. This checkpoint cannot run directly as a control policy.
Context
Instruction, cameras and robot state · Actions only after adding heads and fine-tuning
Tools and integration
Not published
Access
Hugging Face · Runway code
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
No hosted API rate has been verified for this checkpoint. Self-hosting consumes infrastructure. BF16, NVFP4 and the LeRobot layout must be assessed separately; their requirements and results are not interchangeable.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
RoboLab-120 results published for the DROID policy do not apply to this checkpoint. Evaluate adaptation on the actual robot, cameras and tasks; Inferama has not run its own test.
i We have not found published benchmarks for this model.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
runwayml/praxis-1-base
Public weight release; the initial September announcement was not general availability.