GPT-5-Codex
Pricing & Specs
OpenAI · $1.25 input / $10 output per 1M tokens · 400K context window
No longer offered on OpenMark
GPT-5-Codex is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.
GPT-5-Codex API Pricing
| Tokens | Price |
|---|---|
| Input | $1.25 / 1M tokens |
| Output | $10 / 1M tokens |
| Cached input | $0.125 / 1M tokens |
Cached input tokens are billed when caching is enabled.
What that means in practice
GPT-5-Codex Specs
| Spec | Value |
|---|---|
| Context window | 400K tokens |
| Max input per request | 272K tokens |
| Max output tokens | 128K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Latency (measured by OpenMark) | ~963ms median response |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | No |
Notes
Shut down July 23, 2026. Shutdown July 23, 2026.
FAQ
How much does GPT-5-Codex cost?
GPT-5-Codex costs $1.25 per 1M input tokens and $10 per 1M output tokens ($0.125 per 1M cached input tokens).
What is GPT-5-Codex's context window?
GPT-5-Codex has a 400K-token context window. Maximum output is 128K tokens.
Can I test GPT-5-Codex on my own task?
GPT-5-Codex is no longer offered on OpenMark, but you can benchmark its current alternatives from OpenAI and other providers on your own task — free tier available.
Still using GPT-5-Codex?
It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.