RSS

OpenAI

GPT-5.3-Codex

Benchmarks, price, context and versions

Also searched as

GPT 5.3 Codex

Direct answer: GPT-5.3-Codex is a model from OpenAI. 74.8% on SWE-bench Verified, per Epoch AI. On OpenRouter, US$ 1.75 per 1 million input tokens and US$ 14.00 per 1 million output tokens.

✓ Good for

  • Not enough data in the open sources this section uses to build this block.

✕ Not the best for

  • when the input budget sits at the top of the table (input price in the highest 25% on OpenRouter)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

SWE-bench Verified

?what it is
74.8%

highest score on this metric 83.5%

15º / 32 · Epoch AI, latest version we checked

τ-bench Verified (airline)

?
75.3%

highest score on this metric 82%

51º / 131 · OpenRouter Benchmarks, latest version we checked

Key specs

Origin
the US
Family
GPT Codex provisional data
Weights?
closed
License
no data
Input US$/1M?
US$ 1.75
Output US$/1M
US$ 14.00
Context?
400,000 tokens
Parameters
no data
Input
file, image, text
OpenRouter usage?
no data
Downloads (30 days)?
no data
Use cases provisional data
Text Agents Code
Dates in sources
  • 2026, published, per Epoch AI
  • 2026, listed on OpenRouter

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

What is GPT-5.3-Codex?

GPT-5.3-Codex is a model from OpenAI, with closed weights, used for text, agents, code.

How much does GPT-5.3-Codex cost?

On OpenRouter, US$ 1.75 per 1 million input tokens and US$ 14.00 per 1 million output tokens.

What is the context window of GPT-5.3-Codex?

400,000 tokens, per OpenRouter.

Is GPT-5.3-Codex open source?

No. It is available through API only.

What is GPT-5.3-Codex's SWE-bench Verified score?

74.8% on SWE-bench Verified, per Epoch AI.

Is GPT-5.3-Codex good for coding?

It scores 74.8% on SWE-bench Verified, per Epoch AI.

Who made GPT-5.3-Codex?

It was made by OpenAI, a lab from the US.

provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.

Models from OpenAI

See lab

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.