GPT-5.3 Codex

GPT-5.3 Codex is OpenAI's latest entry in the Codex line, positioning itself as the most capable agentic coding model released to date. It brings together the frontier software-engineering performance of GPT-5.2 Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2, merged into a single model that OpenAI also reports runs about 25% faster than its predecessor. This unified design aims at long-running work that mixes research, tool use, and multi-step execution rather than short, single-turn coding prompts, making it suitable for end-to-end agentic workflows on a computer.

Beyond raw capability, GPT-5.3 Codex is built for sustained, interactive collaboration. OpenAI highlights that users can steer and interact with the model mid-task without losing context, treating the agent more like a working colleague than a one-shot code generator. The model also sets a new industry high on SWE-Bench Pro and Terminal-Bench, with strong performance on OSWorld and GDPval benchmarks that span coding, agentic execution, and real-world professional tasks. Notably, GPT-5.3 Codex is the first model that OpenAI reports was instrumental in its own creation, as earlier versions helped debug training, manage deployment, and diagnose evaluation results during development.

Kilo Gatewayopenai/gpt-5.3-codexgpt-codex

Open provider page Provider docs

Quick Info

Provider: Kilo Gateway
Model key: openai/gpt-5.3-codex
Release date: Feb 5, 2026
Last updated: Feb 5, 2026
Knowledge cutoff: 2025-08-31
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $1.75
Output token cost: $14.00

Limits

Input tokens: 272,000 tokens
Output tokens: 128,000 tokens
Context window: 400,000 tokens

Transparent token rates

Compare GPT-5.3 Codex pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT-5.3 Codex

Azure

CoverageBenchmark

According to BenchLM's benchmark aggregation page (updated September 8, 2026), GPT-5.3 Codex was released on February 5, 2026, with a 400K token context window and is tracked across 418 destinations and 427 benchmarks. The model receives a composite capability score of 64.2 out of 100, ranking it 41st out of 231 tracke Speed measurements place GPT-5.3 Codex at 139 tokens per second (field median 92 tok/s) with a first-token latency of 62.36 seconds, making it notably faster than peers on throughput. BenchLM notes that Reasoning, Knowledge, Math, Multilingual, Multimodal, and Instruction Following categories are not rank-eligible for

Azure

CoverageRelease Notes

GitHub announced on May 17, 2026 that GPT-5.3-Codex became the base model for all Copilot Business and Copilot Enterprise organizations, replacing GPT-4.1 in that role. The model is also GitHub's first long-term support (LTS) offering built in partnership with OpenAI, guaranteeing availability for a full 12 months from The change applies only to Copilot Business and Enterprise plans; individual Copilot Pro, Pro+, and Free tiers follow the standard deprecation timeline. GitHub noted that enterprise telemetry showed a significantly high code survival rate for GPT-5.3-Codex, which informed its selection as the default. Organizations tha

Kilo Gateway

CoverageBenchmark

GPT-5.3-Codex moved to No. 1 in Quality on the Microsoft Foundry AI Model Leaderboard soon after release, while a cross-metric "podium" scoring method put GPT-5-Nano on top overall for efficiency.

Pioneer

CoverageRelease Notes

The OpenAI Help Center Model Release Notes page provides official first-party context for GPT-5.3-Codex and its place in the OpenAI catalog. The page records that GPT-5.3-Codex became available in the Responses API via OpenAI's changelog, confirming its distribution as a released OpenAI coding model, and it situates th The same Model Release Notes index documents the broader OpenAI model lifecycle relevant to GPT-5.3-Codex users, including the May 28, 2026 continuation of older-model retirements covering OpenAI o3 and GPT-4.5 in ChatGPT to make room for newer capable models, and a Model Spec update on August 18, 2026 adding clarity o

Azure Cognitive Services

Coverage

OpenAI's March 5, 2026 announcement for GPT-5.4 states that the new model "incorporates the industry-leading coding capabilities of GPT-5.3-Codex" while improving tool use, software environment handling, and professional tasks such as spreadsheets, presentations, and documents. This directly positions GPT-5.3-Codex as The same announcement notes that GPT-5.4 is the first general-purpose model released with native, state-of-the-art computer-use capabilities, supports up to 1M tokens of context for long-horizon agentic tasks, and adds tool search for more efficient tool selection; it also describes GPT-5.4 as OpenAI's most token-effic