Question 1

What is GPT-4 Turbo?

Accepted Answer

GPT-4 Turbo is a model from OpenAI, released on Apr 9, 2024. The GPT-4 Turbo model (currently points to gpt-4-turbo-2024-04-09) introduces vision capabilities, enhancing its utility by accepting both text and image inputs. This version is available as a snapshot of the continuously upgraded GPT-4 model.

It leverages JSON mode and function calling for vision requests, expanding its application range. This update signifies an advancement in the model's ability to process and understand complex requests more efficiently.

Its training data cutoff is December 2023, and it offers a context window of 128,000 tokens.

Question 2

How much does GPT-4 Turbo cost?

Accepted Answer

On the Respan gateway, input starts at $10.00 per 1M tokens on every provider, and output starts at $30.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve GPT-4 Turbo on Respan?

Accepted Answer

3 providers serve GPT-4 Turbo: OpenAI and OpenRouter.

Question 4

What is GPT-4 Turbo's context window?

Accepted Answer

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

Question 5

How do I use GPT-4 Turbo 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-4-turbo-2024-04-09". 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-4 Turbo?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 6 tokens per second, and the lowest response latency was 1.4 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output
OpenAI`openai/gpt-4-turbo`	128K	$10.00/M	$30.00/M
OpenAI`openai/gpt-4-turbo-2024-04-09`	128K	$10.00/M	$30.00/M
OpenRouter`openrouter/openai/gpt-4-turbo`	128K	$10.00/M	$30.00/M

GPT-4 Turbo

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

GPT-4 Turbo FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.