GPT-5.3 Codex
GPT-5.3 Codex is an OpenAI model available in SteelEngine. It supports a 400k token context window. Pricing starts at $1.75/1M input tokens and $14/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, medium, high, xhigh.
Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 400k tokens of context and writes up to 128k tokens.
INPUT / 1M
$1.75
CACHED INPUT / 1M
$0.175
OUTPUT / 1M
$14
CONTEXT WINDOW
400k
MAX OUTPUT
128k
PRICING
What GPT-5.3 Codex costs to run.
List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.
01 / INPUT
$1.75
per 1M input tokens
02 / CACHED INPUT
$0.175
per 1M cached input tokens
03 / OUTPUT
$14
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What GPT-5.3 Codex supports.
Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.
CAPABILITIES
Tool choice, Structured outputs, Reasoning low, medium, high, xhigh, Max output 128k, Image input
CONTEXT WINDOW
400k
MAX OUTPUT TOKENS
128k
MODEL ID
gpt-5.3-codex
PROVIDER
OpenAI
MORE MODELS
More from OpenAI
Compare nearby options from the same provider before you pick a default for your workflow.
OpenAI
RECOMMENDED
GPT-6.1 Sol
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. A recommended default among SteelEngine’s OpenAI models. Released Sep 29, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
OpenAI
RECOMMENDED
GPT-6 Sol
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. A recommended default among SteelEngine’s OpenAI models. Released Sep 22, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
OpenAI
RECOMMENDED
GPT-5.6 Sol
Higher-priced reasoning model for complex planning and multi-step agent work. A recommended default among SteelEngine’s OpenAI models.
IN / 1M
$4
OUT / 1M
$20
CONTEXT
1.05M
BUILD WITH STEELENGINE
Put GPT-5.3 Codex to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.