Question 1

What is o1?

Accepted Answer

o1 is a model from OpenAI, released on Dec 5, 2024. The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the launch announcement.

Question 2

How much does o1 cost?

Accepted Answer

On the Respan gateway, input starts at $15.00 per 1M tokens on every provider, and output starts at $60.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve o1 on Respan?

Accepted Answer

3 providers serve o1: Azure OpenAI, OpenAI, and OpenRouter. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is o1's context window?

Accepted Answer

o1 accepts up to 200K tokens of context on its largest provider route.

Question 5

How do I use o1 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/o1". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is o1?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenAI at 28 tokens per second, and the lowest response latency was 0.8 seconds on OpenAI. Speed varies with request size and provider.

Provider	Context	Input	Output
Azure OpenAIBYOK only`azure/o1`	200K	$15.00/M	$60.00/M
OpenAI`openai/o1`	200K	$15.00/M	$60.00/M
OpenRouter`openrouter/openai/o1`	200K	$15.00/M	$60.00/M

o1

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

o1 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

o1