---
title: "Run Nano Banana 2.1 (nano-banana-2.1)"
method: POST
path: "/models/nano-banana-2.1"
tags: ["Run a model"]
---

# Run Nano Banana 2.1 (nano-banana-2.1)

`POST /models/nano-banana-2.1`

## Request

- Base URL: `https://api.hedra.com/v3`
- URL: `https://api.hedra.com/v3/models/nano-banana-2.1`
- Auth: one of:
  - API key in header `Authorization`
  - HTTP bearer

Nano Banana 2 with cleaner text and layouts, and characters that stay consistent across references, up to 4K.

Submits an asynchronous job and returns `202` with a job id. Fetch the result at `GET /v3/jobs/{job_id}` — each item in its `outputs[]` follows the `OutputItem` schema — or track progress via `GET /v3/jobs/{job_id}/status` / the SSE stream at `GET /v3/jobs/{job_id}/stream`.

## Headers

- `Idempotency-Key` string

## Request body

- SubmitBodyNanoBanana21
  - `input` InputNanoBanana21, required: Model-specific inputs for `nano-banana-2.1`.
    - `prompt` string, required: Generation prompt.
    - `num_outputs` 1: Number of outputs generated per job. Only 1 is supported.
    - `enhance_prompt` boolean: Rewrite the prompt before generation. An LLM expands it into a fuller description and the model receives that text instead of the submitted one; the result's `prompt` reports what ran.
    - `aspect_ratio` 'adaptive' | '16:9' | '9:16' | '1:1' | '21:9' | '4:3' | '3:4' | '3:2' | '2:3' | '5:4' | '4:5' | '1:4' | '4:1' | '1:8' | '8:1', required: Output aspect ratio. 'adaptive' lets the model size the output itself — matching the source image when you pass one.
    - `images` union[]: Images to edit or blend, at most 10 high-fidelity objects and 4 characters. 1 to 14 images, each at most 30 MB.
      - union
        - object: A file uploaded via POST /v3/files, referenced by the returned url.
          - `source` 'url', required
          - `url` string, uri, required: A URL returned by POST /v3/files.
        - object: An existing asset you own, referenced by its id.
          - `source` 'asset', required
          - `asset_id` string, required: The asset's id (`asset_<uuid>`), as issued by the server — a completed generation publishes one per output as `outputs[].asset_id`. Do not construct one or derive it from any other id.
    - `google_search` boolean: Ground the generation in live Google Search results, so a prompt about current events or real-world specifics draws on what the web says now. Grounded generations cost more than ungrounded ones.
    - `image_search` boolean: Let the grounding search return images as well as text, so the model sees what it found rather than only reading about it. Turning this on grounds the generation whether or not google_search is also set.
    - `thinking_level` 'minimal' | 'high': How much the model plans before it draws. Omit for the model's own default ('minimal'); 'high' reasons further at the cost of latency.
    - `resolution` '1K' | '2K' | '4K', required: Output resolution.
  - `webhook` string, uri, nullable: URL to receive a signed completion webhook.

## Response `202`

Accepted. The job runs asynchronously; poll `status_url` / `result_url` from the ack.

- SubmitResponse
  - `job_id` string, required: This job's id — server-issued, and opaque.
  - `model` string, required: The resolved model id this job runs on.
  - `status` 'IN_QUEUE' | 'IN_PROGRESS' | 'COMPLETED' | 'FAILED', required: The four states a job can be in.
  - `status_url` string, required: Path of this job's status monitor: poll GET /v3/jobs/{job_id}/status for status, progress, and the estimated completion time.
  - `result_url` string, required: Path of the job resource itself: GET /v3/jobs/{job_id} returns the result envelope, including the outputs once it completes. Also the value of this response's `Location` header.
  - `estimated_completion_at` string, date-time, nullable: ISO-8601 instant this job is estimated to finish, as of this response. Null when no estimate is available yet, and when the job has already finished. The estimate can change while the job runs: poll `GET /v3/jobs/{job_id}/status` for the current one.

## Other responses

- `400`: Invalid or failed-validation request.
- `401`: Authentication failed: missing, malformed, or invalid credentials.
- `402`: The API wallet cannot cover this request. `error.billing` carries the balance, the price, and where to add funds.
- `403`: Insufficient scope or plan.
- `404`: Resource not found.
- `422`: Moderation refused the request's content.
- `429`: Rate limit exceeded.
- `500`: Internal error.

## Changes

- **2026-10-16** `06692d16e78a`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/hedra-labs/apis/hedra-api/changes/models/nano-banana-2.1/post.md)

---

[API](https://skmtc.dev/hedra-labs/apis/hedra-api.md) - [All operations](https://skmtc.dev/hedra-labs/apis/hedra-api/llms.txt) - [OpenAPI document](https://skmtc.dev/hedra-labs/apis/hedra-api/revisions/6ef35a11cefe?raw)