> ## Documentation Index
> Fetch the complete documentation index at: https://www.hedra.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Developer Platform Quickstart

> Create an API key, fund the API wallet, and run your first generation on the Hedra v3 API in minutes.

Every leading image, video, and audio model behind one endpoint, one key, and
one bill. Browse the [model catalog](https://www.hedra.com/develop/models),
pick a model, and ship — the same key and the same job lifecycle work for all
of them.

### Step 1: Create an API key

Generate a key in the [developer console](https://www.hedra.com/develop/api-keys).
Every request authenticates with it:

```
Authorization: Key <key_id>:<secret>
```

### Step 2: Fund the API wallet

The API bills a **prepaid wallet** held in US dollars. It is separate from your
Hedra Studio balance, and a workspace starts with **\$0.00** in it — nothing you
buy or hold in Studio moves money into it. Until it is funded, every generation
is refused with `402 INSUFFICIENT_BALANCE`.

Add funds in the [developer console](https://www.hedra.com/develop/billing),
and read the wallet any time with `GET /balance`.

<Note>
  Uploading inputs with `POST /files` is free and works on an empty wallet, so
  you can stage a request end-to-end and only meet the billing gate at submit.
</Note>

### Step 3: Pick a model

`GET /models` lists every model with its `id` and human `name`, so a model you
know by name ("GPT Image 2") maps straight to the id you submit to
(`gpt-image-2`). Each model publishes its typed input schema at
`GET /models/{id}/openapi.json`.

```bash theme={null}
curl https://api.hedra.com/v3/models -H "Authorization: Key $HEDRA_KEY"
```

To know the price before you run, ask for an estimate:

```bash theme={null}
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.

```bash theme={null}
# 1. Submit — capture the job id from the 202 ack
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"
```

Generated media is retained for **48 hours** after a job completes — download
outputs to your own storage, or chain them into the next job by `asset_id`.

### Next steps

<CardGroup cols={2}>
  <Card title="Model catalog" href="/docs/pages/developer/v3/model-catalog">
    Every model behind the endpoint, with ids, names, and what each one is for.
  </Card>

  <Card title="Chain generations" href="/docs/pages/developer/v3/chain-generations">
    Reuse a completed job's output as an asset in the next submit.
  </Card>

  <Card title="Quality levels" href="/docs/pages/developer/v3/quality-levels">
    How the quality tiers map to cost and latency across models.
  </Card>
</CardGroup>

### Enterprise

For volume pricing and custom limits, [talk to us](https://www.hedra.com/enterprise).