GPT-5.4API
OpenAI GPT-5.4 — strong general reasoning, 1M context.
Preço input
$1.00
per 1M tokens
Preço output
$6.00
per 1M tokens
Prompt caching
Passe cache_control em prefixos estáveis — hits de cache são cobrados a uma fração do preço de input. Escritas de cache sempre na taxa normal de input.
Calculado automaticamente como input × 0.2
Especificações
- Modelo ID
gpt-5-4- Endpoint
POST /v1/chat/completions- Categoria
- Text
- Provedor
- OpenAI
- Capabilities
- functionstreamingthinkinglong-context
Compatibilidade drop-in com OpenAI
Aponte seu SDK OpenAI existente para api.kunavo.com/v1 e troque o ID do modelo. Sem mudança de streaming, sem SDK novo.
Ver docGPT API pricing guideTeste você mesmo
Configure KUNAVO_API_KEY em /app/keys e rode o snippet abaixo.
curl https://api.kunavo.com/v1/chat/completions \
-H "Authorization: Bearer $KUNAVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5-4",
"messages": [
{"role": "user", "content": "Hello, GPT-5.4"}
],
"stream": false
}'FAQ
How much does GPT-5.4 cost?
On Kunavo, GPT-5.4 is $1.00 per 1M input tokens and $6.00 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-5.4 with the OpenAI SDK?
Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gpt-5-4". Requests and responses are OpenAI-compatible.
What endpoint does GPT-5.4 use?
GPT-5.4 is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.
What is GPT-5.4 good for?
GPT-5.4 is a text model from OpenAI, with support for function, streaming, thinking, long-context.