deepseek
GPT-5.2-Codex vs DeepSeek V4 Flash 0731
74.2 overall · $0.190 / 1M
// openai
GPT-5.2-Codex
openai/gpt-5.2-codex
reasoningtool callingimage inputprompt caching
GPT-5.2-Codex costs $1.75 per 1M input tokens and $14.00 per 1M output tokens with a 400K-token context window.
A reasoning, tool-calling model from openai, released Jan 14, 2026. On LiveBench it scores 74.0 overall — #33 of 55 benchmarked models — and ranks highest in coding (#5).
- Input / 1M
- $1.75
- Output / 1M
- $14.00
- Context
- 400K
- LiveBench overall
- 74.0 · #33
Specs and pricing
| Input price USD per 1M prompt tokens | $1.75 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $14.00 |
| Blended price 3:1 input:output — #37 most expensive of 343 listed models | $4.81 |
| Cached input read Blank means not priced separately — not free | $0.175 |
| Cache write | — |
| Context window | 400,000 tokens |
| Max output | 128,000 tokens |
| Input modalities | text, image |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jan 14, 2026 |
Benchmarks by category
LiveBench scores out of 100, with GPT-5.2-Codex's rank among the 55 benchmarked models listed here. Run: gpt-5.2-codex.
Language#45 of 55
73.7
$0.0484 measured per point
What GPT-5.2-Codex costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,427/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,610/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,638/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,721/mo |
| Bulk classification 500 in / 20 out × 5M requests | $4,988/mo |
Compare GPT-5.2-Codex with
The benchmarked models closest to it on overall score.
GPT-5.2-Codex vs Gemini 3.6 Flash
73.6 overall · $1.50 / 1M
openai
GPT-5.2-Codex vs GPT-5.6 Luna
73.6 overall · $0.450 / 1M
anthropic
GPT-5.2-Codex vs Claude Opus 4.6
74.5 overall · $10.00 / 1M
openai
GPT-5.2-Codex vs GPT-5.2
74.6 overall · $4.81 / 1M
GPT-5.2-Codex vs Gemini 3.5 Flash
74.6 overall · $3.38 / 1M
GPT-5.2-Codex FAQ
How much does GPT-5.2-Codex cost?
GPT-5.2-Codex lists at $1.75 per 1M input tokens and $14.00 per 1M output tokens, with cached input reads at $0.175 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $1,610 at list price.
What is the context window of GPT-5.2-Codex?
GPT-5.2-Codex accepts up to 400,000 tokens of context and can return up to 128,000 output tokens per response.
Does GPT-5.2-Codex support tool calling?
Yes — GPT-5.2-Codex supports tool (function) calling and exposes extended reasoning. It accepts text, image input.
How does GPT-5.2-Codex score on benchmarks?
On LiveBench release 2026-06-25 (run: gpt-5.2-codex), GPT-5.2-Codex scores 74.0 overall, ranking #33 of 55 benchmarked models.
What is the API model ID for GPT-5.2-Codex?
On OpenRouter the model ID is "openai/gpt-5.2-codex". It was listed on Jan 14, 2026.
More from openai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.