Skip to content

OpenAI · Chat

GPT-5 Codex

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (23 Jul 2026).

Newer version: GPT-5.3 Codex. We compared release dates and version names in our catalogue.

GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments.

llminfo IQ
127.7
Max context
400K
Listings
19

Evidence and sources

llminfo IQ 127.7, ranked among chat models. From 21 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 106.4, 95% interval 98–115. From 4 benchmark families across 5 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.How Coding IQ is computedFair value (49.4). Costs per task about what its benchmark results predict. From 5 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksReleased 23 Sep 2025Maker HQ: US (according to OpenAI's own website)
Sources: OpenCode Zen data, Models.dev data, LiteLLM data, ZenMux data, Kilo AI Gateway data, llminfo researchPrimary data from OpenCode Zen from Models.dev: name, weights availability from LiteLLM: deprecation date from ZenMux: primary mode from Kilo AI Gateway: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (23 Jul 2026).

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb search

Listings

 OpenAIgpt-5-codexSource: LiteLLM data272K$1.25cache read $0.125$10.00—
 Poeopenai/gpt-5-codexSource: Models.dev data400K$1.10$9.00—
 Jiekougpt-5-codexSource: Models.dev data400K$1.1875cache read $0.1187$9.50—
 Microsoft AzureRegions: 🇦🇺🇧🇷+17 australia-east, brazil-south, canada-east, us-east, us-east-2, france-central, germany-west-central, japan-east, korea-central, us-north-central, europe-north, norway-east, poland-central, south-africa-north, us-south-central, south-india, spain-central, sweden-central, switzerland-north, uae-north, united-kingdom-south, europe-west, us-west, us-west-3gpt-5-codexSources: Azure OpenAI, LiteLLM data, Models.dev data272K$1.25cache read $0.125$10.00—
 302aigpt-5-codexSource: 302.ai data400K$1.25$10.00—
 Aihubmixgpt-5-codexSource: AIHubMix data docs400K$1.25cache read $0.125$10.00—
 Flowdotopenai/gpt-5-codexSource: FlowDot data400K$1.25$10.00—
 Kiloopenai/gpt-5-codexSources: Kilo AI Gateway data, Models.dev data400K$1.25cache read $0.13$10.00$0.00
 OpenRouteropenai/gpt-5-codexSource: Helicone Costs dataNot published by the provider$1.25$10.00—
 Vercelopenai/gpt-5-codexSources: Models.dev data, Vercel AI Gateway data400K$1.25cache read $0.13$10.00—
Show all 16 listings

Showing 10 of 16: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Abacus, Impossibl, Zenmux.

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Coding

Agentic

Reasoning

General

Other

Data credits: BullshitBench by Peter Gostev, MIT (licence) · MLE-bench (OpenAI), MIT (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

Around the web

Also known as: azure/eu/gpt-5-codex, azure/gpt-5-codex, azure/us/gpt-5-codex, gpt-5-codex-high, gpt-5-codex-low, gpt-5-codex-medium, openai/gpt-5-codex

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works