Question 1

What is gpt-5-codex?

Accepted Answer

gpt-5-codex is a model from OpenAI, released on Sep 15, 2025. GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. $1.25 per million input tokens, $10 per million output tokens. 400,000 token context window, maximum output of 128,000 tokens. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does gpt-5-codex cost?

Accepted Answer

On the Respan gateway, input starts at $1.25 per 1M tokens on Azure OpenAI, and output starts at $10.00 per 1M tokens on Azure OpenAI, after gateway discounts.

Question 3

Which providers serve gpt-5-codex on Respan?

Accepted Answer

gpt-5-codex is served by Azure OpenAI. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is gpt-5-codex's context window?

Accepted Answer

gpt-5-codex accepts up to 400K tokens of context.

Question 5

How do I use gpt-5-codex 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 "gpt-5-codex". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How does gpt-5-codex score on benchmarks?

Accepted Answer

gpt-5-codex has 2 published benchmark scores, including SWE-bench Verified 74.5%. Each score links to where it was published; the data is collected by llmmetric.com.

gpt-5-codex

Providers

Pricing

Cost by volume

Benchmarks

Certified where it counts.

Coding2

Apps

gpt-5-codex FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.