Skip to main content
OpenAI

GPT-5 Codex

GPT-5 Codex is a coding-oriented variant of OpenAI's GPT-5 model line, tuned for software engineering tasks such as code generation, refactoring, and agentic development workflows.

Input from
$1.25 / 1M tokens
on Liquid Inference · 1 provider
Output from
$10.01 / 1M tokens
on Liquid Inference

API Pricing

ProviderInput / 1MOutput / 1M
$1.25$10.01

Prices updated daily. Last check: Nov 20, 2026

Compare API pricing for every OpenAI model →

GPT-5 Codex pricing by provider

Input, output, and batch rates, plus alternatives, for one provider at a time.

Performance & Benchmarks

Source: Artificial Analysis →
Output Speed
164 t/s
Latency (TTFT)
8.6s

Benchmarks measured Nov 2026. Scores are independent evaluations, not vendor-reported.

Model Details

General

Creator
OpenAI
Modalities
Text

Capabilities

Open Source
No

Strengths & Limitations

Strengths

  • Tuned specifically for software engineering tasks rather than general-purpose chat
  • Part of the GPT-5 family, so it inherits that generation's training and alignment work
  • Designed for long-running agentic coding sessions that span many turns and files
  • Exposed through the standard OpenAI chat-completions interface, easing integration with existing clients
  • Associated with OpenAI's Codex surfaces (CLI, IDE extensions, cloud agents), giving ready-made tooling paths
  • Suited to multi-file repository work such as refactors, migrations, and test authoring

Limitations

  • Specialization toward coding makes it a less natural fit for creative writing, marketing, or general conversational workloads
  • Context window is not tracked in our database — confirm limits with OpenAI documentation before designing long-repository prompts
  • Model weights are served via API only; self-hosting is not an option
  • Throughput and time-to-first-token figures in our benchmark record are unpopulated, so latency expectations should be validated against your own workload
  • Provider availability for Codex-branded variants is narrower than for general GPT-5 models

Key Features

•Coding-specialized variant within the GPT-5 model family
•Chat-completions API interface compatible with existing OpenAI clients
•Designed for agentic, multi-turn software engineering loops
•Code generation, editing, and refactoring across multiple files
•Integration path through OpenAI Codex CLI, IDE, and cloud agent surfaces
•Code review and diff analysis workloads
•Test generation and debugging assistance

About GPT-5 Codex

GPT-5 Codex is a chat-completion model from OpenAI positioned within the GPT-5 family as a variant specialized for software engineering work. Where general-purpose GPT-5 models are tuned to handle a broad mix of writing, analysis, and conversation, the Codex branding signals a model trained and configured around coding tasks: reading existing repositories, producing and editing code, and operating inside agent loops that run for extended periods on a single engineering task. The model is exposed through a standard chat interface, so it accepts conversational message histories and returns text completions, which makes it a drop-in option for tools that already speak the OpenAI chat API. It is the model OpenAI associates with Codex coding surfaces — command-line agents, IDE integrations, and cloud-hosted coding agents — where the model is expected to work across many files and multiple turns rather than answering a single isolated question. We do not currently track a published context window, modality list, or tool-calling specification for this entry in our database, so check OpenAI's model documentation for those details before building against specific limits. In practice, GPT-5 Codex is chosen for development workloads rather than general chat: implementing features from an issue description, migrating code between frameworks, writing tests, and reviewing diffs. Compared to general GPT-5 variants, the trade-off is specialization — more of the tuning budget went toward code and agentic behavior, which is useful for engineering teams and less relevant for marketing copy or open-ended conversation. Availability and pricing differ by provider; the pricing table on this page shows which providers currently serve it.

Common Use Cases

GPT-5 Codex fits development workflows where the model is expected to act on a codebase rather than just discuss it: implementing a feature from a ticket description, performing framework or language migrations across many files, generating unit and integration tests, and reviewing pull request diffs for defects. Its orientation toward agentic operation makes it a candidate for autonomous or semi-autonomous coding agents that plan, edit, run, and iterate over multiple turns, as well as for IDE assistants that need to reason about surrounding project context. Teams running high-volume, non-coding text workloads — summarization, classification, customer-facing chat — will usually get better cost and behavior alignment from a general-purpose or lightweight model instead, reserving Codex for engineering tasks where code quality dominates.

Frequently Asked Questions

How much does GPT-5 Codex cost?

Pricing varies by provider and by pricing type — input tokens, output tokens, cached input, and any batch or committed-use discounts are all billed differently. Rates also change frequently. See the pricing table on this page for the current figures from each provider that serves this model.

What is GPT-5 Codex best used for?

Software engineering work: generating and editing code across a repository, refactoring, writing tests, debugging, reviewing diffs, and powering coding agents that run for many turns on a single task. It is specialized for these workloads rather than general conversation or content writing.

How does GPT-5 Codex differ from a general GPT-5 model?

Both come from OpenAI's GPT-5 family, but the Codex variant is tuned around coding and agentic development behavior. General GPT-5 models are broader and better suited to mixed workloads, while GPT-5 Codex concentrates on repository-level engineering tasks.

What context window does GPT-5 Codex support?

We do not currently track a confirmed context window for this entry. Because agentic coding sessions can consume large amounts of context, verify the current limit in OpenAI's model documentation or with your chosen provider before relying on very long repository prompts.

Can I run GPT-5 Codex on my own hardware?

No — it is served through API providers rather than distributed as downloadable weights. If self-hosting is a requirement, you would need to compare against open-weight coding models instead.