GPT-5.3-Codex

openai/gpt-5.3-codex

GPT-5.3-Codex is OpenAI's agentic coding model announced in February 2026, optimized for Codex and similar environments, with text and image input and text output. OpenAI called it its most capable agentic coding model at release and says it extends Codex from writing and reviewing code to most tasks developers and professionals do on a computer. It supports low to extra-high reasoning effort and suits long-running coding, debugging and computer-use agents.

Input price
$1.75USD / 1M tokens
Output price
$14.00USD / 1M tokens
Cache read
$0.18USD / 1M tokens
Context window
400K
Max output
128K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call OpenAI GPT-5.3-Codex through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-5.3-codex" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI GPT-5.3-Codex cost?

$1.75 per 1M input tokens and $14 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

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

400K tokens of context, with up to 128K output tokens per response.

Which features does OpenAI GPT-5.3-Codex support?

OpenAI GPT-5.3-Codex supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-5.3-Codex and the other models in the catalog; you do not need to sign up with OpenAI separately.