Question 1

What is GPT-5.2 Codex?

Accepted Answer

GPT-5.2 Codex is a model from OpenAI, released on Dec 18, 2025. GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. $1.75 per million input tokens, $14 per million output tokens. 400,000 token context window, maximum output of 128,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does GPT-5.2 Codex cost?

Accepted Answer

On the Respan gateway, input starts at $1.75 per 1M tokens on every provider, and output starts at $14.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve GPT-5.2 Codex on Respan?

Accepted Answer

3 providers serve GPT-5.2 Codex: Azure OpenAI, OpenAI, and OpenRouter. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is GPT-5.2 Codex's context window?

Accepted Answer

GPT-5.2 Codex accepts up to 400K tokens of context on its largest provider route.

Question 5

How do I use GPT-5.2 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 "openai/gpt-5.2-codex". 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-5.2 Codex?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 8 tokens per second, and the lowest response latency was 4.2 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does GPT-5.2 Codex rank on the Respan Index?

Accepted Answer

GPT-5.2 Codex scores 26.4 out of 100 on the Respan Index v1.1, ranking #74 of 138 models. By category: Coding 18.6, Agents 17.7, Reasoning 26.6, Knowledge & language 33.6, and Human preference 48.5. 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-5.2 Codex score on benchmarks?

Accepted Answer

GPT-5.2 Codex has 13 published benchmark scores, including LiveBench Coding 83.6%, LiveBench Agentic Coding 49.4%, and LiveBench Data Analysis 78.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
Azure OpenAIBYOK only`azure/gpt-5.2-codex`	400K	$1.75/M	$14.00/M
OpenAI`openai/gpt-5.2-codex`	400K	$1.75/M	$14.00/M
OpenRouter`openrouter/openai/gpt-5.2-codex`	400K	$1.75/M	$14.00/M

GPT-5.2 Codex

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding5

Apps

GPT-5.2 Codex FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Agents2

Reasoning2

Math1

Knowledge2

Arena1