All modelsOpenAI
GPT-5.3 Codex
Covered by SkytellstextVendor: OpenAI
OpenAI / GPT-5.3 Codex
openai/gpt-5.3-codexVendor
OpenAI
openai
Description
GPT‑5.3‑Codex achieves state-of-the-art performance on SWE-Bench Pro, a rigorous evaluation of real-world software engineering. Where SWE‑bench Verified only tests Python, SWE‑Bench Pro spans four languages and is more contamination‑resistant, challenging, diverse and industry-relevant. It also far exceeds the previous state-of-the-art performance on Terminal-Bench 2.0, which measures the terminal skills a coding agent like Codex needs. Notably, GPT‑5.3‑Codex does so with fewer tokens than any prior model, letting users build more.
text-to-textcodingwritingreasoningchatanalysisproblem-solvingqualitycoding
Skytells SDK
Run predictions with the official JavaScript SDK. Use your API key from Settings.
Pricing
Multiple criteriaThis model may apply different rates depending on input fields (for example tokens, seconds, megapixels, or prediction type). The effective price uses the first matching rule when you run a prediction.
Pricing formula
Pricing is calculated separately for input, cached input, and output tokens for GPT-5.3-Codex.
- input_rate1.75
- cached_input_rate0.175
- output_rate14
Terms
- input → input_rate → billable_price
- cached_input → cached_input_rate → billable_price
- output → output_rate → billable_price
| Rule | Condition | Rate |
|---|---|---|
Base pricing Default pricing when no criteria match | — | $1.75 / million token |
Input token pricing | token_type == input | $1.75 / million token |
Cached input token pricing | token_type == cached_input | $0.175 / million token |
Output token pricing | token_type == output | $14.00 / million token |