Hedra v3 API Quickstart | Developer Platform

Generate images, video, and audio with over 100 models through one API. Fund your wallet, then every image, video, and audio model runs through the same three requests: submit a job, poll it, download the output. Browse the model catalog to pick one. The API also serves open-weight LLMs through POST /v3/chat/completions, in OpenAI’s chat completions format, and bills each request to the same wallet. Chat completions shows how to call them with the stock OpenAI SDK.

Step 1: Create an API key

Generate a key in the developer console, and put it in the HEDRA_KEY environment variable, which the examples below use:

export HEDRA_KEY="<key_id>:<secret>"

Send the key in this header with every request:

Authorization: Key <key_id>:<secret>

Step 2: Fund the API wallet

The API bills a prepaid wallet held in US dollars. (This USD balance is separate from your Hedra Studio credit balance.) Add funds in the developer console, and read the wallet any time with GET /balance. Until you add funds, POST /models/{id} will return 402 INSUFFICIENT_BALANCE.

Step 3: Pick a model

GET /models lists every model with its id and display name, so a model you know by name (“GPT Image 2”) gives you the id for its submit path (POST /models/gpt-image-2). Each model publishes its typed input schema at GET /models/{id}/openapi.json.

curl https://api.hedra.com/v3/models -H "Authorization: Key $HEDRA_KEY"

Optionally, to see a job’s price before you submit it, ask for an estimate:

curl -X POST https://api.hedra.com/v3/models/gpt-image-2/estimate \
  -H "Authorization: Key $HEDRA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"prompt": "a space cat", "quality": "medium", "aspect_ratio": "1:1", "resolution": "1K"}}'

Step 4: Submit, poll, download

Every generation follows the same lifecycle: submit a job, poll it, then read the output URL.

# 1. Submit: capture the job id from the 202 response
JOB_ID=$(curl -sS -X POST https://api.hedra.com/v3/models/gpt-image-2 \
  -H "Authorization: Key $HEDRA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"prompt": "a space cat", "quality": "medium", "aspect_ratio": "1:1", "resolution": "1K"}}' | jq -r .job_id)

# 2. Poll until status is COMPLETED (or FAILED)
curl https://api.hedra.com/v3/jobs/$JOB_ID/status -H "Authorization: Key $HEDRA_KEY"

# 3. Read the result: outputs[].url holds the generated file
curl https://api.hedra.com/v3/jobs/$JOB_ID -H "Authorization: Key $HEDRA_KEY"

While the job runs, the status response carries progress and estimated_completion_at, so you can tell your users how long it will take. See Job progress.

Next steps

Model catalog

Every model, with its id, name, and purpose.

Chain generations

Pass a completed job’s output as input to the next job.

Quality levels

How each quality level changes price and latency across models.

Chat completions

Call open-weight LLMs with the OpenAI or Anthropic SDK.

Enterprise

For volume pricing and custom limits, talk to us.

Legacy API

Integrations built on the legacy /web-app/public API keep working. Their guide is the legacy API quickstart.

Getting Started

Guides

Concepts

API Reference

Hedra v3 API Quickstart | Developer Platform

Hedra Developer Platform

Step 1: Create an API key

Step 2: Fund the API wallet

Step 3: Pick a model

Step 4: Submit, poll, download

Next steps

Model catalog

Chain generations

Quality levels

Chat completions

Enterprise

Legacy API

​Hedra Developer Platform

​Step 1: Create an API key

​Step 2: Fund the API wallet

​Step 3: Pick a model

​Step 4: Submit, poll, download

​Next steps

Model catalog

Chain generations

Quality levels

Chat completions

​Enterprise

​Legacy API

Hedra Developer Platform

Step 1: Create an API key

Step 2: Fund the API wallet

Step 3: Pick a model

Step 4: Submit, poll, download

Next steps

Enterprise

Legacy API