Long context

gpt-5.4 API pricing

OpenAI's GPT series — broad general capability, wide ecosystem, and the native models behind Codex CLI.

Model IDopenai/gpt-5.4

ChatStreamingTool callingVision

Get API Key Try it Quick Start

Call summary

Input

$2.50$0.25/ 1M tokens

Cache write $0.63

Output

$11.00$1.10/ 1M tokens

Cache read $0.06

Context Window

1.05M

Max output

128K

API Endpoints

Available Configurations

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

99.80%

Success 2xx

99.80%

Rate limit 429

0.00%

Server 5xx

0.20%

TPS

62.77

tokens/s

Avg. time to first token

7.52 s

Avg. latency

19.72 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Jul 26, 2026, 4:25 PM UTC

gpt-5.4 API endpoints

One API key — call this model through any of the endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Docs

POST/v1/responsesResponses API · Native for Codex CLI

Docs

gpt-5.4 compared with other models

Spec and price matchups against peer models.

GPT-5.4vsGemini 3 Pro

Call gpt-5.4 from your code

The same API key works across every endpoint below.

Endpoint

/v1/chat/completions

Model ID

openai/gpt-5.4

Routing mode

auto

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key