OpenAI: GPT-5 Codex

Public pricingIntelligence 82/100Large memoryVisionRéflexion approfondieOutils

OpenAI: GPT-5 Codex est un modèle multimodal conçu pour codage, génie logiciel et workflows agentiques. Il associe la gestion multimodale des entrées et de bonnes performances en codage, un contexte de 400K tokens et un profil à coût équilibré pour un travail fiable sur codage, génie logiciel et workflows agentiques.

Input

$1.25/1M

Output

$10.00/1M

Cached

$0.13/1M

Batch

$0.63/1M

Calculate your GPT-5 Codex bill.

Set your workload — see cost at your exact volume.

What would GPT-5 Codex cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

GPT-5 Codex at a glance.

Memory

400,000

tokens

Max reply

128,000

tokens

Memory tier

Large

an entire book or large codebase

Tokenizer

tiktoken-o200k

Released

Sep 2025

Training cutoff

Sep 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • gpqa_diamond

    83.7

  • mmlu

    86.5

  • swe_bench_verified

    74

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick GPT-5 Codex

  • Multi-step reasoning, research agents, or hard math.
  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • Long documents, full codebases, or extensive chat histories.

When to look elsewhere

  • Very latency-sensitive, real-time apps where every millisecond counts.

Alternatives

Similar models to compare.

FAQ

GPT-5 Codex — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, GPT-5 Codex costs roughly $494 per month. Input is $1.25 /1M tokens and output is $10.00 /1M tokens.
GPT-5 Codex has a 400,000-token context window (large memory — an entire book or large codebase). That means you can fit about 75,000 words of input and history in a single call.
Beyond text generation, GPT-5 Codex supports understanding images, deep step-by-step reasoning, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
GPT-5 Codex was released in September 2025, with training data cut off around September 2024.
Models in a similar class include GPT-5, GPT-5.1, GPT-5.1-Codex. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare GPT-5 Codex against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard