Router One
Back to Models
Text model

gpt-5.4

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

Model IDopenai/gpt-5.4
ChatStreamingTool callingVision
Try itQuick Start

Call summary

Input
$2.50$0.25/ 1M tokens
Cache write $1.25
Output
$11.00$1.10/ 1M tokens
Cache read $0.13
Context Window
400K
Max output
128K
API Endpoints
2
Available Configurations
8

Production reliability

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

Successful response share

99.88%

Success 2xx

99.88%

Rate limit 429

0.00%

Server 5xx

0.12%

TPS

57.71

tokens/s
Avg. time to first token

5.03 s

Avg. latency

9.95 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 16, 2026, 9:44 AM UTC

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

Model comparisons

Spec and price matchups against peer models.

GPT-5.4vsGemini 3 Pro