GPT-5.3 Codex Official Specifications, Pricing & Benchmarks
GPT-5.3 Codex (gpt-5.3-codex) by OpenAI, released 2026-02-05, featuring 400,000 context window, 128,000 max output tokens, and Text+Image+PDF input.
📋 GPT-5.3 Codex Official API & System Card Specifications
Verified against official OpenAI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- gpt-5.3-codex
- Release Date
- 2026-02-05
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 400,000 tokens (400K)
- Max Output Tokens
- 128,000 tokens
- Input Modalities
- Text + Image + PDF
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 1.75
- Cached Input / 1M
- $ 0.175 -90%
- Output / 1M Tokens
- $ 14
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 GPT-5.3 Codex Full Benchmark Scorecard
6 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 3 items
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000 feature implementations.
Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal.
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to GPT-5.3 Codex
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is GPT-5.3 Codex open-source or proprietary?
GPT-5.3 Codex (gpt-5.3-codex) is a proprietary commercial model by OpenAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of GPT-5.3 Codex?
GPT-5.3 Codex supports 400K input context and 128,000 max output tokens, priced at $1.75/1M input ($0.175/1M cached) and $14/1M output.