Router DeskHomeImage router
Image router
One key can call an image model. The slug has to be an image model. A text model will only describe a picture.
Updated 2026-09-27
OpenRouter groups image-capable models in a collection. On 27 Sep 2026 the models API included several slugs whose output modalities were image and text, among them google/gemini-3.1-flash-image, google/gemini-3-pro-image, openai/gpt-5-image, openai/gpt-5-image-mini, and openai/gpt-5.4-image-2.
| Slug | Prompt price / M | Notes |
|---|---|---|
| google/gemini-2.5-flash-image | $0.30 | Also an image field at $0.0000003 |
| google/gemini-3.1-flash-image | $0.50 | Image and text out |
| google/gemini-3-pro-image | $2 | Image field listed |
| openai/gpt-5-image-mini | $2.50 | Image and text out |
| openai/gpt-5-image | $10 | Image and text out |
| openai/gpt-5.4-image-2 | $8 | Image and text out |
Those prompt figures are the models API multiplied out to dollars per million. Image models often add a per-image charge that does not show up as a normal completion price. Read the model page before you estimate a batch of pictures. Seedance 2.0 is video and is priced per second.
openrouter/auto can return text or image. If you need a picture, name an image slug. Auto is allowed to answer with text.
Questions
What is the image router on OpenRouter?
The same API, with an image model slug. The collection is at openrouter.ai/collections/image-models.
Which slug returns a picture?
One whose card lists image output, such as google/gemini-3.1-flash-image or openai/gpt-5-image. A normal chat slug returns text.
How is video priced?
Seedance 2.0 is per second of video. See the Seedance page. It is not in the chat token table.
Related
- Seedance 2.0 price
Seedance 2.0 is ByteDance video generation. OpenRouter’s page lists from $0.06726 per second at 480p with audio to $0.7776 per second at 4K.
- GPT-4o pricing
GPT-4o on OpenRouter was $2.50 input and $10 output per million tokens on 27 Sep 2026. The May 2024 snapshot was $5 / $15.
- Qwen 3.5 9B
Qwen3.5-9B is a 9B multimodal model. OpenRouter listed qwen/qwen3.5-9b at $0.10 input and $0.15 output per million tokens, with a 262K context.
- OpenRouter API URL
The OpenRouter base URL is https://openrouter.ai/api/v1. Chat calls go to /chat/completions with a Bearer key.