Theta EdgeCloud AI Inference API
Theta EdgeCloud AI Inference API provides access to a diverse set of AI/ML models running on a decentralized edge computing network. **Use Cases:** - Audio transcription with Whisper - Image generation with Stable Diffusion - Text generation with LLMs - Video processing and analysis - Speech synthesis and audio enhancement **Features:** - Fast inference with edge distribution - Synchronous (wait…
7 subscribers
9.2/10 popularity
3773 ms avg latency
83% success rate
14 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Theta EdgeCloud AI Inference API endpoints
| Method | Endpoint | Description |
|---|---|---|
| Services | ||
| GET |
/service/list /service/list |
Retrieve a list of all available AI/ML services. Each service has different input/output specifications and capabilities. |
| Inference | ||
| GET |
/infer_request/{infer_request_id} /infer_request/{infer_request_id} |
Retrieve the status and results of an inference request. Use this to poll for completion of async requests. |
| POST |
/infer_request/{alias} /infer_request/{alias} |
Create an AI inference request using the service alias. The `wait` parameter controls synchronous behavior: - `wait: 0` - Returns immediately with request ID (async) - `wait:… |
| POST |
/infer_request/{alias}/input_presigned_urls /infer_request/{alias}/input_presigned_urls |
Generate presigned URLs to upload large input files (audio, images, video). **Workflow:** 1. Call this endpoint to get presigned URL(s) 2. Upload your file(s) to the presigned… |
| GET |
/infer_request/{project_id}/list /infer_request/{project_id}/list |
List all inference requests for your project. Useful for tracking usage and debugging. |
| POST |
/infer_request/{alias}/{prediction}/input_presigned_urls /infer_request/{alias}/{prediction}/input_presigned_urls |
Generate presigned URLs for a specific prediction method |
| POST |
/infer_request/{alias}/{prediction} /infer_request/{alias}/{prediction} |
Create an inference request for a specific prediction method. Some services have multiple prediction methods (e.g., different model sizes). |
| Other endpoints | ||
| GET |
/service/list /service/list |
Retrieve a list of all available AI/ML services. Each service has different input/output specifications and capabilities. |
| GET |
/infer_request/{project_id}/list /infer_request/{project_id}/list |
List all inference requests for your project. Useful for tracking usage and debugging. |
| POST |
/infer_request/{alias}/{prediction}/input_presigned_urls /infer_request/{alias}/{prediction}/input_presigned_urls |
Generate presigned URLs for a specific prediction method |
| POST |
/infer_request/{alias} /infer_request/{alias} |
Create an AI inference request using the service alias. The `wait` parameter controls synchronous behavior: - `wait: 0` - Returns immediately with request ID (async) - `wait:… |
| POST |
/infer_request/{alias}/input_presigned_urls /infer_request/{alias}/input_presigned_urls |
Generate presigned URLs to upload large input files (audio, images, video). **Workflow:** 1. Call this endpoint to get presigned URL(s) 2. Upload your file(s) to the presigned… |
| POST |
/infer_request/{alias}/{prediction} /infer_request/{alias}/{prediction} |
Create an inference request for a specific prediction method. Some services have multiple prediction methods (e.g., different model sizes). |
| GET |
/infer_request/{infer_request_id} /infer_request/{infer_request_id} |
Retrieve the status and results of an inference request. Use this to poll for completion of async requests. |
Theta EdgeCloud AI Inference API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
