GPT-5.3-Codex

Name: GPT-5.3-Codex
Author: OpenAI

Released

2026-02-05

Last refreshed

2026-10-17

Status

Researched 23d ago

ProprietaryCommercial use: restrictedCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

OpenAI releases · 48 in the last 12 months · this family litChangelog →

Specifications

Family: Codex
Released: 2026-02-05
Lifecycle: Scheduled retirement: April 1, 2027
Context: 400K
Max output: 128K
Architecture: Decoder Only
Knowledge cutoff: 2025-08
Specialization: code
Openness: Proprietary
License: ProprietaryRestricted
Weights: Not released
Code: Unknown

Created by

OpenAI

Cutting-edge research and development.

San Francisco, California, United States

Founded 2015

Website

Pricing

Output / 1M

$14.00

Input / 1M

$1.75

Cheapest of 3 routes · OpenAI API · cache read $0.175

Providers(3)

OpenRouter OpenAI API Vercel AI Gateway

View 3 provider routes

Links

Website

About

Most capable agentic coding model from OpenAI. Optimized for long-horizon, agentic coding tasks in the Codex CLI and API. Note: GPT-5.3-Codex-Spark is a distinct ChatGPT Pro research preview (not API-accessible).

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Cache	Route
OpenAI API	$1.75	$14.00	read $0.175	Serverless
OpenRouter	$1.75	$14.00	read $0.175	Serverless
Vercel AI Gateway	$1.75	$14.00	read $0.175	Serverless

Available via routers & gateways(15)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSOpenAI API

OpenRouter

Hybrid

Unified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.

Passthrough + feeOpenAI API

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.

SubscriptionOpenAI API

AIRouter

Router

Commercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.

SubscriptionOpenAI API

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache-2.0 open-source platform with a managed hosted tier for logging and analytics.

SubscriptionOpenAI API

Kong AI Gateway

Gateway

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

SubscriptionOpenAI API

Capabilities

VisionReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API

Benchmark peer barsfor Coding

SWE-bench ProRank 32 of 60

89.9

81.3

81.2

80.3

56.8

SWE-bench VerifiedRank 7 of 102

Claude Fable 5

96.0

Claude Opus 5

96.0

Claude Mythos Preview

93.9

Claude Opus 4.8

88.6

GPT-5.3-Codexcurrent

85.0

Benchmark scores(6)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.

Benchmark	Score	Version	Evaluation	Source
SWE-bench Verified	85.0	SWE-bench VerifiedObserved 2026-04-24	—	Source
SWE-bench Pro	56.8	SWE-bench Pro Public (pass@1)Observed 2026-06-07	—	Source
τ-bench	77.8	τ-benchObserved 2026-04-24	—	Source
SWE-rebench	58.2	pass@1 (best of 5 runs)Observed 2026-05-28	—	Source
Terminal-Bench 2.0	77.3	Terminal-Bench 2.0 (accuracy%)Observed 2026-06-07	—	Source
OSWorld	64.7	OSWorld-VerifiedObserved 2026-02-05	—	Source