Edge Impulse

Edge Impulse Optimization API

The Optimization API from Edge Impulse — 15 operation(s) for optimization.

GitHub OpenAPI
Business capability
Artificial Intelligence Management BC-610.60

Operations 18

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /api/{projectId}/optimize/runs List EON Tuner runs for a project · List all tuner runs #
Ask an LLM
“What EON Tuner runs have been executed on my Edge Impulse project?”
“Can I see the history of every hyperparameter tuning run in a project?”
Tell an agent
List all EON Tuner runs for project {projectId}.
Show the tuner run history of project {projectId}.
GET /api/{projectId}/optimize/config Get the EON Tuner configuration · Get config #
Ask an LLM
“What target device and latency is the EON Tuner currently configured for?”
“Which tuning algorithm and trial limits are set for my project's optimizer?”
Tell an agent
Get the EON Tuner configuration for project {projectId}.
Show the current optimization settings of project {projectId}.
POST /api/{projectId}/optimize/config Configure the EON Tuner · Update config #
Ask an LLM
“How do I set a target device and latency budget for the EON Tuner?”
“Can I cap the maximum number of trials and parallel workers the tuner uses?”
Tell an agent
Configure the EON Tuner for project {projectId} to target {targetDevice} with {targetLatency} ms latency.
Set project {projectId} tuner to target {targetDevice} at {targetLatency} ms, max {tuningMaxTrials} trials.
GET /api/{projectId}/optimize/all-learn-blocks List learn blocks available to the tuner · Get all available learn blocks #
Ask an LLM
“Which learning blocks can the EON Tuner choose from in my project?”
“What learn blocks are available for hyperparameter search?”
Tell an agent
List all available learn blocks for project {projectId}.
Show the learn blocks the optimizer can use in project {projectId}.
GET /api/{projectId}/optimize/window-settings Get the tuner's window settings · Get window settings #
Ask an LLM
“What window size and stride settings will the EON Tuner explore?”
“Can I check the time-series window settings used by the optimizer?”
Tell an agent
Get the EON Tuner window settings for project {projectId}.
Show the windowing options the optimizer uses in project {projectId}.
POST /api/{projectId}/optimize/score-trial Score a candidate tuner trial · Score trial #
Ask an LLM
“Can I estimate how a combination of input, DSP and learn blocks would score before running it?”
“How do I get a score for a proposed EON Tuner trial configuration?”
Tell an agent
Score a trial in project {projectId} using learn blocks {learnBlocks}.
Evaluate proposed trial {id} for project {projectId} with DSP blocks {dspBlocks}.
POST /api/{projectId}/optimize/{jobId}/create-trial Create a trial within a tuner job · Create trial #
Ask an LLM
“How do I add a new trial to an EON Tuner job that's already running?”
“Can I launch a trial with my own choice of DSP and learn blocks inside a tuner job?”
Tell an agent
Create a trial in tuner job {jobId} of project {projectId}.
Add trial {id} to job {jobId} in project {projectId} using learn blocks {learnBlocks}.
POST /api/{projectId}/optimize/{jobId}/complete-search Mark an EON Tuner run as complete · Complete EON tuner run #
Ask an LLM
“How do I finish an EON Tuner run and record whether it succeeded?”
“Can I mark a tuner search job as completed from my own coordinator?”
Tell an agent
Complete tuner job {jobId} in project {projectId} with success set to {success}.
Mark the EON Tuner search {jobId} for project {projectId} as finished, success {success}.
GET /api/{projectId}/optimize/space Get the EON Tuner search space · Search space #
Ask an LLM
“What range of impulse designs is the EON Tuner going to search over?”
“Can I inspect the search space the optimizer explores for my project?”
Tell an agent
Get the EON Tuner search space for project {projectId}.
Show which impulse variations the tuner will search in project {projectId}.
GET /api/{projectId}/optimize/state Get the project's current EON Tuner state · Retrieves the EON tuner state #
Ask an LLM
“What is the EON Tuner doing right now in my project, and which trials has it produced?”
“Can I check the overall tuner state for a project without picking a run?”
Tell an agent
Get the current EON Tuner state for project {projectId}.
Show the latest optimizer status and trials of project {projectId}.
DELETE /api/{projectId}/optimize/state Clear the project's EON Tuner state · Delete EON tuner state #
Ask an LLM
“How do I wipe all EON Tuner results and start optimization over?”
“Can I reset the tuner state for a project completely?”
Tell an agent destructive · confirm first
Clear the EON Tuner state for project {projectId}.
Reset all tuner results in project {projectId} from scratch.
GET /api/{projectId}/optimize/dsp-parameters Get parameters of an organization DSP block · Retrieves DSP block parameters #
Ask an LLM
“What parameters does a custom organization DSP block expose to the tuner?”
“Can I fetch the configurable settings of my organization's DSP block for optimization?”
Tell an agent
Get the parameters of DSP block {organizationDspId} from organization {organizationId} in project {projectId}.
Show tuner parameters for organization {organizationId} DSP block {organizationDspId} in project {projectId}.
GET /api/{projectId}/optimize/transfer-learning-models List transfer learning models for the tuner · Retrieves available transfer learning models #
Ask an LLM
“Which pretrained transfer learning models can the optimizer try?”
“What base models are available for transfer learning in my project's tuner?”
Tell an agent
List the transfer learning models available in project {projectId}.
Show pretrained models the tuner can use for project {projectId}.
GET /api/{projectId}/optimize/trial/{trialId}/stdout Get logs for a tuner trial · Get trial logs #
Ask an LLM
“Where can I read the training output of one EON Tuner trial?”
“How do I debug a trial that failed during optimization?”
Tell an agent
Get the logs for trial {trialId} in project {projectId}.
Show stdout from tuner trial {trialId} of project {projectId}.
GET /api/{projectId}/optimize//{jobId}/trial/{trialId}/end-trial End an EON Tuner trial early · End EON tuner trial #
Ask an LLM
“Can I stop a single tuner trial early, for example to implement my own early stopping?”
“How do I cut short a trial that is clearly underperforming?”
Tell an agent destructive · confirm first
End trial {trialId} of job {jobId} in project {projectId} early.
Stop tuner trial {trialId} in job {jobId} for project {projectId} now.
GET /api/{projectId}/optimize/{tunerCoordinatorJobId}/state Get the state of a specific tuner run · Retrieves EON tuner state for a run #
Ask an LLM
“What were the results of one particular EON Tuner run, not just the latest?”
“Can I check progress for a tuner run by its coordinator job ID?”
Tell an agent
Get the EON Tuner state for run {tunerCoordinatorJobId} in project {projectId}.
Show results of tuner run {tunerCoordinatorJobId} from project {projectId}.
POST /api/{projectId}/optimize/{tunerCoordinatorJobId} Rename a specific tuner run · Update EON tuner state #
Ask an LLM
“How do I give an EON Tuner run a more descriptive name?”
“Can I edit the label of a past tuner run?”
Tell an agent
Rename tuner run {tunerCoordinatorJobId} in project {projectId} to {name}.
Set the name of EON Tuner run {tunerCoordinatorJobId} for project {projectId} to {name}.
GET /api/{projectId}/optimize/all-blocks List all impulse blocks with tuner details · Get impulse blocks #
Ask an LLM
“Which input, DSP and learn blocks can go into an impulse, with the extra info the tuner needs?”
“Can I get the full catalog of impulse blocks for my project in one call?”
Tell an agent
List every possible impulse block for project {projectId}.
Show all impulse blocks, including tuner metadata, available in project {projectId}.

Documentation

📖
Documentation
https://docs.edgeimpulse.com/reference/edge-impulse-api

Specifications

⚙
OpenAPI
https://artifacts.apis.io/edge-impulse/openapi/edge-impulse-optimization-api-openapi.yml

Other Resources

🔗
Overlay
https://artifacts.apis.io/edge-impulse/overlays/edge-impulse-optimization-overlay.yaml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/edge-impulse:edge-impulse-optimization-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

edge-impulse-optimization-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Edge Impulse Optimization API
  version: 1.0.0
  description: 'Operations tagged Optimization across 2 of this provider''s published API definitions: edge-impulse-openapi.yml, edge-impulse-studio-openapi-2026-09-06.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://studio.edgeimpulse.com/v1
tags:


# --- truncated at 32 KB (82 KB total) ---
# Full source: https://artifacts.apis.io/edge-impulse/openapi/edge-impulse-optimization-api-openapi.yml