价廉版主力
Model ID: gpt-5.4-mini · Type: chat · Provider: OpenAI
Endpoints: /v1/chat/completions · /v1/responses · /v1/messages
| Input (per 1M tokens) | $0.4875 USD |
| Output (per 1M tokens) | $2.925 USD |
| Cache read (per 1M tokens) | $0.04875 USD |
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
model="gpt-5.4-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)GPT-5.4 Mini (`gpt-5.4-mini`) is billed per usage at $0.4875/1M in · $2.925/1M out, in USD. Current pricing is always listed at https://www.370.ai/models/gpt-5.4-mini.
Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "gpt-5.4-mini"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.
GPT-5.4 Mini can be called on: /v1/chat/completions; /v1/responses; /v1/messages.
GPT-5.4 Mini accepts up to 272,000 input tokens and can return up to 128,000 output tokens. Requests exceeding the input limit are rejected before reaching the model.
GPT-5.4 Mini supports: vision, function_calling, prompt_caching.
GPT-5.4 Mini is a chat model from OpenAI, available through the 370.AI gateway with the same API key as every other model.
Call it through the 370.AI OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.