Router One
Back to Models
Low cost

gpt-5.4-mini

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

Model IDopenai/gpt-5.4-mini
ChatStreamingTool callingVision
Try itQuick Start

Call summary

Input
$0.25$0.07/ 1M tokens
Cache write $0.04
Output
$1.00$0.30/ 1M tokens
Cache read $0.00
Context Window
400K
Max output
128K
API Endpoints
2
Available Configurations
5

Production reliability

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

Successful response share

96.64%

Success 2xx

96.64%

Rate limit 429

0.03%

Server 5xx

3.34%

TPS

157.29

tokens/s
Avg. time to first token

12.74 s

Avg. latency

22.43 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.

DeepSeek V4 ProvsGPT-5.4 mini