Ideogram · Image
OpenClaw x Ideogram V3
Ideogram V3 is purpose-built for typography in generated images, achieving strong text accuracy. Through RunAPI, all Ideogram V3 endpoints — generation, edit, and remix — share one key.
Public versions and endpoints
| Model ID | Version | Endpoints | Starting price | Catalog |
|---|---|---|---|---|
ideogram-v3-character | Character-reference generation with one anchored identity image | /api/v1/ideogram_v3/text_to_image | $0.180 | Model detail |
ideogram-v3-character-edit | Inpaint while preserving the referenced character identity | /api/v1/ideogram_v3/edit_image | $0.180 | Model detail |
ideogram-v3-character-remix | Remix a source image with character and style references | /api/v1/ideogram_v3/remix_image | $0.180 | Model detail |
ideogram-v3-edit | Targeted editing while preserving text accuracy | /api/v1/ideogram_v3/edit_image | $0.070 | Model detail |
ideogram-v3-reframe | Change image framing and aspect ratio without a prompt | /api/v1/ideogram_v3/reframe_image | $0.070 | Model detail |
ideogram-v3-remix | Style remix from reference image + text prompt | /api/v1/ideogram_v3/remix_image | $0.070 | Model detail |
ideogram-v3-text-to-image | Strong in-image text accuracy; best for typography-heavy images | /api/v1/ideogram_v3/text_to_image | $0.070 | Model detail |
Configuration
Guide endpoint: <endpoint>
Select <model-id> to generate a request with the endpoint's public input contract.Verify
Select <model-id> to generate verification commands.How it works
- 1. Choose a model ID
Select a public catalog model ID and review its endpoint and current starting price.
- 2. Configure RunAPI
Set RUNAPI_API_KEY before making the endpoint request.
- 3. Verify the result
For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.
FAQ
Which model ID should I use?
Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.
Does this guide configure a chat model?
No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.