GPT-5.3 Codex (xhigh)
GPT-5.3 Codex (xhigh) is a text-based AI model by OpenAI. It features 72 tok/s output speed, $1.75/1M input tokens pricing. It scores 54.0 on the intelligence index.
Strengths
- +Top-tier intelligence score (54.0)
- +Strong coding performance (53.1)
Benchmarks
Intelligence54.0Coding53.1MathN/A
GPQA
0.9
Intelligence
54.0
Coding
53.1
Output Speed
72 tok/s
Latency (TTFT)
83.91s
Blended Price
$4.81/M
Pricing per 1M Tokens
| Input (Prompt) | $1.75 |
| Output (Completion) | $14 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare GPT-5.3 Codex (xhigh) with:
Alternatives to GPT-5.3 Codex (xhigh)
More from OpenAI
Frequently Asked Questions
How much does GPT-5.3 Codex (xhigh) cost?
GPT-5.3 Codex (xhigh) costs $1.75/1M input tokens and $14/1M output tokens.
Is GPT-5.3 Codex (xhigh) good for coding?
Yes, GPT-5.3 Codex (xhigh) has a strong coding score of 53.1, placing it among the top coding models.
How fast is GPT-5.3 Codex (xhigh)?
GPT-5.3 Codex (xhigh) generates output at 72 tok/s. Time to first token is 83.91s.
Is there a free version of GPT-5.3 Codex (xhigh)?
No, GPT-5.3 Codex (xhigh) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to GPT-5.3 Codex (xhigh)?
Last updated: