Question 1

What is GPT-4o Mini?

Accepted Answer

GPT-4o Mini is a model from OpenAI, released on Jul 18, 2024. GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards. Check out the launch announcement to learn more. #multimodal.

Question 2

How much does GPT-4o Mini cost?

Accepted Answer

On the Respan gateway, input starts at $0.15 per 1M tokens on every provider, and output starts at $0.60 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve GPT-4o Mini on Respan?

Accepted Answer

6 providers serve GPT-4o Mini: Azure OpenAI, Inference.net, OpenAI, and OpenRouter. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is GPT-4o Mini's context window?

Accepted Answer

GPT-4o Mini accepts up to 128K tokens of context on its largest provider route.

Question 5

How do I use GPT-4o Mini with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "openai/gpt-4o-mini". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is GPT-4o Mini?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenAI at 539 tokens per second, and the lowest response latency was 0.5 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does GPT-4o Mini rank on the Respan Index?

Accepted Answer

GPT-4o Mini scores 8.8 out of 100 on the Respan Index v1.1, ranking #136 of 138 models. By category: Coding 0.7, Agents 2.4, Reasoning 9.7, Knowledge & language 8.2, and Human preference 32.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does GPT-4o Mini score on benchmarks?

Accepted Answer

GPT-4o Mini has 17 published benchmark scores, including WeirdML 11.8%, BALROG 17.4%, and GPQA Diamond 40.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
Azure OpenAIBYOK only`azure/gpt-4o-mini`	128K	$0.15/M	$0.60/M
Inference.net`inference_net/gpt-4o-mini`	128K	$0.15/M	$0.60/M
OpenAI`openai/gpt-4o-mini`	128K	$0.15/M	$0.60/M
OpenAI`openai/gpt-4o-mini-2024-07-18`	128K	$0.15/M	$0.60/M
OpenRouter`openrouter/openai/gpt-4o-mini`	128K	$0.15/M	$0.60/M
OpenRouter`openrouter/openai/gpt-4o-mini-2024-07-18`	128K	$0.15/M	$0.60/M

GPT-4o Mini

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding1

Agents1

Apps

GPT-4o Mini FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Reasoning5

Math5

Knowledge3

Arena2