GPT-5.4 mini brings the main capabilities of GPT-5.4 to a faster and more efficient model optimized for high-volume workloads. It supports both text and image inputs, offering strong performance in reasoning, coding, and tool use while lowering latency and cost for large-scale deployment. The model is built for production environments that need the right balance between capability and efficiency, making it a strong fit for chat applications, coding assistants, and large-scale agent workflows. GPT-5.4 mini provides reliable instruction following, solid multi-step reasoning, and consistent results across a wide range of tasks with better cost efficiency.
$0.188market price $0.375
$0.0187market price $0.0375
$1.13market price $2.25
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
GPT-5.4 mini brings the main capabilities of GPT-5.4 to a faster and more efficient model optimized for high-volume workloads. It supports both text and image inputs, offering strong performance in reasoning, coding, and tool use while lowering latency and cost for large-scale deployment.
On NagaAI, GPT 5.4 Mini costs $0.188 per 1M input tokens and $1.13 per 1M output tokens. You pay only for what you use, with no subscription.
GPT 5.4 Mini reads up to 400k tokens in one request, counting the prompt and the answer together.
Yes. GPT 5.4 Mini can call your functions as tools and can answer in a JSON schema you give it.
It takes text, images and files as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.