by OpenAI· 3 weeks ago
OpenAI's most capable coding model combining Codex and GPT-5 training stacks. Agentic coding, research, and tool use with 77.3% on Terminal-Bench 2.0.
Context Window
400K
Max Output
128K
TTFT
600ms
Speed
55 tok/s
Input Price
$2.00/M tokens
Output Price
$16.00/M tokens
Performance Profile
Frontier-tier performance at $2.00/M input tokens
400K token context window — handles lengthy documents with ease
Supports text + code — true multimodal capability
Consistently scores 80%+ across major benchmarks
Build complete applications with agentic coding, research, and tool use capabilities.
First model rated 'High' for cybersecurity — ideal for code security audits.
77.3% on Terminal-Bench 2.0 — executes multi-step terminal workflows autonomously.
vs similar-tier models
| Model | Input | Output | Context | Avg Score |
|---|---|---|---|---|
GPT-5.3-CodexCurrent OpenAI | $2.00 | $16.00 | 400K | 88.9 |
Kimi K2.5 Moonshot AI | $0.45 | $2.20 | 256K | 92.3 |
Gemini 2.5 Pro | $1.25 | $10.00 | 1.0M | 88.4 |
Generate a function
$0.0058Spec → implementation with tests
500 in · 300 out
Review a 2,000-line PR
$0.052Full pull request code review
10,000 in · 2,000 out
Refactor a 5,000-line module
$0.130Major refactoring with explanations
25,000 in · 5,000 out
Analyze a full codebase
$0.360Architecture analysis + recommendations
100,000 in · 10,000 out
Code generation
$174/mo
$6/day
PR reviews
$1560/mo
$52/day
Codebase analysis
$6840/mo
$228/day
No ratings yet. Be the first to rate this model!
Sign in to rate this model and share your experience.
Sign in to leave a comment and join the discussion.
OpenAI
OpenAI's most advanced multimodal model. Excels at text, vision, and audio tasks with fast response times.
Input
$2.50/M
Output
$10.00/M
Context
128K
OpenAI
OpenAI's reasoning model with chain-of-thought capabilities for complex problem solving.
Input
$15.00/M
Output
$60.00/M
Context
200K
OpenAI
OpenAI's efficient reasoning model, optimized for speed while maintaining strong analytical capabilities.
Input
$1.10/M
Output
$4.40/M
Context
200K
Moonshot AI
Moonshot AI's frontier multimodal MoE model with 1T total parameters (32B active). Tops SWE-bench and AIME 2025 benchmarks.
Input
$0.45/M
Output
$2.20/M
Context
256K
Google's most capable thinking model with breakthrough performance on reasoning and coding.
Input
$1.25/M
Output
$10.00/M
Context
1.0M
Anthropic
Anthropic's most powerful model. Top-tier performance on coding, analysis, and complex reasoning tasks.
Input
$15.00/M
Output
$75.00/M
Context
200K