GPT-5.4

2026-03 GA, 1M context

Model ID: gpt-5.4 · Type: chat · Provider: OpenAI

Endpoints: /v1/chat/completions · /v1/responses · /v1/messages

Pricing

Input (per 1M tokens)$1.625 USD
Output (per 1M tokens)$9.75 USD
Cache read (per 1M tokens)$0.1625 USD

Context tiers

≤ 272000 tokens$1.625 / 1M in$9.75 / 1M out
> 272000$3.25 / 1M in$14.625 / 1M out
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",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does GPT-5.4 cost on 370.AI?

GPT-5.4 (`gpt-5.4`) is billed per usage at $1.625/1M in · $9.75/1M out, in USD. Current pricing is always listed at https://www.370.ai/models/gpt-5.4.

How do I call GPT-5.4 through 370.AI?

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"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does GPT-5.4 support?

GPT-5.4 can be called on: /v1/chat/completions; /v1/responses; /v1/messages.

What is GPT-5.4's context window?

GPT-5.4 accepts up to 1,047,576 input tokens and can return up to 128,000 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can GPT-5.4 do?

GPT-5.4 supports: vision, function_calling, prompt_caching.

Who makes GPT-5.4?

GPT-5.4 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.

API reference · All models