gpt-5.3-codex

Code-focused reasoning model for agentic software-development workflows.

API IDgpt-5.3-codex
View setup
View usage

Overview

Context
272,000 tokens
Max output
32,768 tokens
Input
Text, Image
Output
Text
Providers
Azure OpenAI
Released
Feb 2026
Latest operational check
Healthy
API compatibility
  • OpenAI Chat Completions
  • OpenAI Responses
Recommended for
  • Code generation and explanation
  • Agentic software-development workflows

Keep in mind: A specialized AI Service matches the workload more directly

Supported features
  • Function calling: Supported
  • Structured outputs: Supported
  • Vision: Supported
  • Streaming: Supported
  • Reasoning: Supported
  • Prompt caching: Supported
Supported parameters
function_callfunctionsmax_completion_tokensmax_tokensnparallel_tool_callsprompt_cache_keyreasoning_effortresponse_formatseedservice_tierstorestreamstream_optionstemperaturetool_choicetoolsverbosity
View API reference

Make your first request

View full setup
curl --fail-with-body https://gateway.primexos.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.3-codex","messages":[{"role":"user","content":"Hello from Primex"}],"stream":false}'

Executing this request uses your account’s API credits.