GPT-4o-mini (batch)
openai/gpt-4o-mini:batch
Multimodal
2 gateways
Batch only
Where you can run it
Batch only. This is the batch price of openai/gpt-4o-mini, and it can only be called through an
asynchronous Batch API — requests are submitted together and answered within 24 hours,
typically at about half the synchronous price. A chat-completions call with this id fails.
FreeRouter runs it through
POST /v1/batches on openrouter
(Batch API docs).
| Gateway | Its id | Context | Max output | Input / Mtok | Output / Mtok |
|---|---|---|---|---|---|
| Cloudflare AI Gateway Catalog listing only | openai/gpt-4o-mini:batch |
— | — | — | — |
| OpenRouter | openai/gpt-4o-mini:batch |
128K | 16.4K | $0.075 | $0.300 |
Prices are US dollars per million tokens, as published in each gateway's own catalog at the last crawl. A dash means that gateway publishes no value — not that it is free. Rows differ because gateways set their own markup, and some let you bring your own provider key.
- Canonical id
openai/gpt-4o-mini:batch- Vendor
- OpenAI
- Type
- Multimodal
- Gateways serving it
- CloudflareOpenRouter
- Batch variant of
- openai/gpt-4o-mini
- Largest context window
- 128K tokens
- Input price range
- $0.075 / Mtok
- Accepts
- Text, Image, File
- Returns
- Text
- Cataloged since