OpenAI: GPT-5-Codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Source-linked gpt-codex Closed weights Released 2025-09-15

API record Report

InputT

OutputT

Input price$1.1/M

Output price$9/M

Context400K

Max output128K

Providers13

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering GPT-5-Codex
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Poe	`openai/gpt-5-codex`	400K	128K	$1.1	$9	—	ReasoningTools	Docs ↗
Requesty	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.13	ReasoningToolsJSON	Docs ↗
ZenMux	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningTools	Docs ↗
OpenAI	`gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
OrcaRouter	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
Abacus	`gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
Azure	`gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningTools	Docs ↗
Kilo Gateway	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningTools	Docs ↗
OpenRouter	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
Azure Cognitive Services	`gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningTools	Docs ↗
NanoGPT	`openai/gpt-5-codex`	256K	32.768K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗
Impossibl	`openai/gpt-5-codex`	400K	128K	$1.25	$10	$0.125	ReasoningToolsJSON	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $1.1/M

Across 13 priced providers

Median input $1.25/M

Midpoint of listed rates

Highest input $1.25/M

1.1× the lowest listed rate

Output range $9 – $10

Per million output tokens

Poe $1.1/MLowest

Requesty $1.25/M

Vercel AI Gateway $1.25/M

ZenMux $1.25/M

OpenAI $1.25/M

OrcaRouter $1.25/M

Abacus $1.25/M

Azure $1.25/M

Kilo Gateway $1.25/M

OpenRouter $1.25/M

Azure Cognitive Services $1.25/M

NanoGPT $1.25/M

Impossibl $1.25/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 256K to 400K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: OpenAI
Model family: gpt-codex
Knowledge cutoff: 2024-09-30
License: Not documented
Release date: 2025-09-15
Model ID: openai/gpt-5-codex

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Benchmark profile

Each axis is this model's percentile among the 5 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Design Arena: webapps elo Source ↗

Design Arena: webapps #56 of 80

1138.0

Design Arena: mobileapps elo Source ↗

Design Arena: mobileapps #60 of 77

1126.0

SciCode percent correct · 2026-06-01 Source ↗

SciCode #2 of 27

40.9

Artificial Analysis Coding Index index · 2026-06-01 Source ↗

Artificial Analysis Coding Index #1 of 26

38.9

Terminal-Bench Hard success rate · 2026-06-01 Source ↗

Terminal-Bench Hard #1 of 22

37.9

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Design Arena: webapps, the benchmark with the widest published coverage that this model appears in.

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Jul 30, 2026Price Completion10.0 → 9.0

Jul 30, 2026Price Prompt1.25 → 1.1

Jul 30, 2026Price Completion9.0 → 10.0

Jul 30, 2026Price Prompt1.1 → 1.25

Jul 26, 2026Price Completion10.0 → 9.0

Jul 26, 2026Price Prompt1.25 → 1.1

Jul 26, 2026Price Completion9.0 → 10.0

Jul 26, 2026Price Prompt1.1 → 1.25

Jul 25, 2026Price Completion10.0 → 9.0

Jul 25, 2026Price Prompt1.25 → 1.1

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Oct 24, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://modelbench.lol/api/v1/models/openai/gpt-5-codex

curl

curl "https://modelbench.lol/api/v1/models/openai/gpt-5-codex"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is GPT-5-Codex?

Coding-optimized GPT model for repository edits, reviews, and agentic software work. It is published by OpenAI and catalogued here from Models.dev.

How much does GPT-5-Codex cost?

Listed input pricing starts at $1.1 per million tokens from Poe, rising to $1.25 across 13 listed providers.

What is the context length of GPT-5-Codex?

GPT-5-Codex accepts up to 400K tokens of context and returns up to 128K output tokens.

Does GPT-5-Codex support tool calling and structured output?

Provider catalogs list support for tool calling, reasoning, and image input.

Which providers serve GPT-5-Codex?

13 providers list this model: Poe, Requesty, Vercel AI Gateway, ZenMux, OpenAI, OrcaRouter and 7 more.

Are the weights for GPT-5-Codex open?

No. This model is served through hosted APIs only.

When was GPT-5-Codex released?

The catalog records a release date of 2025-09-15, last verified Oct 24, 2026.

More models from OpenAI

View all →

OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

1.05M ctx $0.2/M in GPT-5.6 Luna

Cost-efficient GPT-5.6 model for fast, high-volume workloads

1.05M ctx $0.2/M in OpenAI: GPT-5.6 Terra Pro

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

1.05M ctx $2/M in GPT-5.6 Terra

Balanced GPT-5.6 model for capable, cost-efficient everyday work

1.05M ctx $2/M in