GPT-5.3-Codex Pricing
FlagshipOpenAI · 400K tokens context
GPT-5.3-Codex from OpenAI costs $1.75 per 1 million input tokens and $14.00 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 400,000-token context window (approximately 300,000 words) with a 128K-token maximum output. A typical 1,000-token request costs $0.0018 in input charges; a 10,000-token request costs $0.0175.
| Input price | $1.75 / 1M tokens |
|---|---|
| Output price | $14.00 / 1M tokens |
| Output / input ratio | 8.0× |
| Context window | 400,000 tokens (~300,000 words) |
| Maximum output | 128,000 tokens |
| Cost per 1K tokens (input) | $0.0018 |
| Tier | Flagship |
| Last verified |
GPT-5. 3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.
Input Price
$1.75
per 1 million tokens
Output Price
$14.00
per 1 million tokens
Context Window
400K tokens
max 128K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.00233 | $0.0056 |
| 10-page document (2,500 words) | 3,333 | $0.00583 | $0.014 |
| 1,000 lines of code | 5,000 | $0.00875 | $0.021 |
| 100K token document | 100,000 | $0.175 | $0.42 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Large 400K-token context window
- ✓Frontier-class quality on complex tasks
- ✓Multimodal: understands images as well as text
Limitations
- –Quality and availability can vary by hosting provider
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate GPT-5.3-Codex Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact GPT-5.3-Codex costs — and compare across all models.
Open Calculator →GPT-5.3-Codex — FAQ
Related Models
Related Guides