Router One
Back to Models
Long context

gpt-5.6-luna

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

Model IDopenai/gpt-5.6-luna
ChatStreamingTool callingVision
Try itQuick Start

Call summary

Input
$1.00$0.10/ 1M tokens
Cache write $0.63
Output
$6.00$0.60/ 1M tokens
Cache read $0.05
Context Window
1.05M
Max output
128K
API Endpoints
2
Available Configurations
3

Production reliability

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

Successful response share

99.92%

Success 2xx

99.92%

Rate limit 429

0.00%

Server 5xx

0.08%

TPS

90.45

tokens/s
Avg. time to first token

7.82 s

Avg. latency

14.36 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