GPT-5.3-Codex

openai/gpt-5.3-codex
VisionToolsJSONReasoning
by OpenAI · 2026-02-24

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

ctx400K tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT596 ms
INPUT$1.75/ 1M tokens
OUTPUT$14.00/ 1M tokens
p50 TTFT596 ms7d
p95 TTFT1.71 s7d
TRAFFIC110.1Mtokens / 7d

GPT-5.3-Codex is a large language model from OpenAI, accessible through OrcaRouter's OpenAI-compatible API. It is specifically named "Codex," indicating a focus on code generation and understanding,…

What is GPT-5.3-Codex?

Who should use GPT-5.3-Codex?

What modalities does GPT-5.3-Codex support?

How does GPT-5.3-Codex compare in size?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-5.3-codex",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stream
  • structured_outputs
  • tool_choice
  • tools

Pricing

Input / 1M tokens$1.75
Output / 1M tokens$14.00
Cache read / 1M$0.175
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $54.25 · With prompt caching $48.74

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.007035

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
596 ms
Output speed
81.1 tok/s
p95 TTFT
1.71 s
Error rate
0%

Public benchmarks

53.1
AA Coding
Better than 66% of models compared
#42 of 123
44.3
AA Intelligence
Better than 75% of models compared
#30 of 125
GPQA Diamond
91.5
Humanity's Last Exam
39.9
IFBench
75.4
Long-Context Recall
74.0
SciCode
53.2
TerminalBench Hard
53.0
τ²-Bench
86.0
Source: artificialanalysis.ai

How it compares

GPT-5.3-CodexGPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$1.75$21.00$60.00$5.00
Output $/M$14.00$168.00$270.00$30.00
Context400K400K1.1M
Quality9/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use GPT-5.3-Codex?
Pricing is $1.75 per 1 million input tokens and $14.00 per 1 million output tokens, billed at provider rate with zero markup by OrcaRouter.
What is the context window of GPT-5.3-Codex?
The context window is 400,000 tokens, meaning you can input up to 400K tokens of text, images, and files combined.
What are the strengths of GPT-5.3-Codex?
It has a large context (400K), high output limit (128K), supports multimodal inputs (text, image, file), and achieved a strong GPQA Diamond score of 91.5, indicating excellent reasoning on graduate-level questions.
How does GPT-5.3-Codex compare to GPT-4o?
GPT-5.3-Codex has a larger context window (400K vs 128K) and higher output limit (128K vs 16K). Its GPQA Diamond score (91.5) suggests better reasoning, but it also costs more per token. Specific comparative benchmark data is not provided.
Is my data handled when using GPT-5.3-Codex via OrcaRouter?
OrcaRouter passes requests directly to OpenAI without modification. Data handling follows OpenAI's privacy policy. OrcaRouter does not store or log your prompts unless explicitly agreed. Check OrcaRouter's data policy for details.
How do I call GPT-5.3-Codex via an OpenAI-compatible API?
Use OrcaRouter's base URL https://api.orcarouter.ai/v1 with model id "openai/gpt-5.3-codex". Provide your API key in the Authorization header. The API is fully compatible with the OpenAI Python SDK and curl.
Can I use GPT-5.3-Codex for file processing?
Yes, the model accepts file inputs in addition to text and images. Files are tokenized and count toward the 400K context limit. Use appropriate content parts in the API message.
What is the maximum output length?
The maximum output is 128,000 tokens. Set the max_tokens parameter accordingly.
Are there any discounts or caching?
No discounts or caching are mentioned. OrcaRouter bills at the provider rate per token. For high-volume, contact OrcaRouter directly.

Embed this badge

OpenAI: GPT-5.3-Codex$1.75/M in596ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5.3-codex" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5.3-codex.svg" alt="OpenAI: GPT-5.3-Codex on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-5.3-Codex](https://www.orcarouter.ai/embed/openai/gpt-5.3-codex.svg)](https://www.orcarouter.ai/models/openai/gpt-5.3-codex)

Model card as data

GET /api/public/models/openai/gpt-5.3-codexOpen
Machine-readable:/llms.txt/llms-full.txt