Model detail
gpt-4o
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209) #multimodal
Model specs
- Context length
- 128K
- Max output
- 16.384K
- I/O modalities
- Text / Image
- Released
- 2024-05
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Pricing
Flat rate, unit: /1M Tokens
Input
$2.5000 /1M Tokens
Completion
$10.0000 /1M Tokens
Cache read
$1.2500 /1M Tokens
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Fast multimodal text and image processing
Use GPT-4o for tasks requiring both text and image inputs. It is twice as fast and 50% more cost-effective than GPT-4 Turbo, with improved non-English language processing and visual capabilities.
What should you check before using it?
Test multimodal inputs and non-English performance
If your workload includes image inputs or non-English content, test these capabilities specifically. GPT-4o offers significant improvements in these areas compared to previous models.
Why use it through MixRoute?
Use the OpenAI-compatible endpoint with stable model ID
Use the confirmed compatible endpoint with model ID gpt-4o through MixRoute, then run the same integration tests used for the current client.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
GPT-4o (“omni”) is OpenAI’s multimodal model supporting both text and image inputs with text outputs. It is twice as fast and 50% more cost-effective than GPT-4 Turbo, with improved non-English language processing and enhanced visual capabilities.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.