LLM Reference

GPT-5.3-Codex

Released
2026-02-05
Last refreshed
2026-06-15
Status
Researched 16d ago
ProprietaryCommercial use: conditionalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

GPT-5.3-Codex is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 400k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Codex
Released
2026-02-05
Context
400k
Max output
128,000
Architecture
Decoder Only
Knowledge cutoff
2025-08
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Created by

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

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).

GPT-5.3-Codex is a proprietary model in the Codex family. The structured metadata tracks a 400k-token context window, vision, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenRouter, OpenAI API, and Vercel AI Gateway, with the cheapest tracked route listed at $1.75 input and $14 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 85.0, SWE-bench Pro 56.8, and τ-bench 77.8.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 3

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

ProviderInput / 1MOutput / 1MCacheRoute
OpenAI API$1.75$14.00read $0.175
Serverless
OpenRouter$1.75$14.00-
Serverless
Vercel AI Gateway$1.75$14.00read $0.175
Serverless

Available via routers & gateways(15)

Capabilities

VisionReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch API

Benchmark peer barsfor Coding

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.
BenchmarkScoreVersionSource
SWE-bench Verified85.0SWE-bench Verifiedhttps://www.swebench.com/verified.html
SWE-bench Pro56.8SWE-bench Pro Public (pass@1)https://www.digitalapplied.com/blog/gpt-5-3-codex-release-features-benchmarks-guide
τ-bench77.8τ-benchhttps://taubench.com/
SWE-rebench58.2pass@1 (best of 5 runs)https://swe-rebench.com/leaderboard
Terminal-Bench 2.077.3Terminal-Bench 2.0 (accuracy%)https://llm-stats.com/benchmarks/terminal-bench-2
OSWorld64.7OSWorld-Verifiedhttps://mlq.ai/news/openai-releases-gpt-53-codex-as-advanced-agentic-coding-upgrade/

Migration checks

No linked migration route is available for this model yet.

Show all 5 popular comparisonssorted by 7-day search impressions