GPT-5.3 CodexAPI
OpenAI GPT-5.3 Codex — coding-specialized.
Tarif input
$0.70
per 1M tokens
Tarif output
$5.60
per 1M tokens
Prompt caching
Passez cache_control sur les préfixes stables — les hits de cache sont facturés à une fraction du tarif d'input. Les écritures restent au tarif d'input normal.
Calculé automatiquement comme input × 0.2
Spécifications
- ID du modèle
gpt-5-3-codex- Endpoint
POST /v1/chat/completions- Catégorie
- Text
- Fournisseur
- OpenAI
- Capacités
- functionstreamingthinkinglong-context
Compatibilité OpenAI drop-in
Pointez votre SDK OpenAI existant sur api.kunavo.com/v1 et changez l'ID du modèle. Pas de changement de streaming, pas de nouveau SDK.
Voir la docGPT API pricing guideEssayez vous-même
Récupérez KUNAVO_API_KEY depuis /app/keys puis exécutez le snippet ci-dessous.
curl https://api.kunavo.com/v1/chat/completions \
-H "Authorization: Bearer $KUNAVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5-3-codex",
"messages": [
{"role": "user", "content": "Hello, GPT-5.3 Codex"}
],
"stream": false
}'FAQ
How much does GPT-5.3 Codex cost?
On Kunavo, GPT-5.3 Codex is $0.70 per 1M input tokens and $5.60 per 1M output tokens — about 60% under OpenAI's official price. Failed requests are never billed, and it's pay-as-you-go — you only pay for successful calls.
Can I call GPT-5.3 Codex with the OpenAI SDK?
Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gpt-5-3-codex". Requests and responses are OpenAI-compatible.
What endpoint does GPT-5.3 Codex use?
GPT-5.3 Codex is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.
What is GPT-5.3 Codex good for?
GPT-5.3 Codex is a text model from OpenAI, with support for function, streaming, thinking, long-context.