Model · OpenAI
GPT-6 Luna (Codex CLI)
OpenAI’s GPT-6 Luna model run through the Codex CLI.
34 values from 3 studies (4 are list-price calculations) · Updated
At a glance
The best-supported value per category: a 95% interval first, then a run range, then the larger n. Three separate values from separate studies, never one score.
Qualitypass rates, accuracy and scores
63% (10/16)
95% CI 39%–82% · n = 16
Strict pass rate: single call vs agent loop on eight hard tasks
Codex CLI · single call · Single call vs agent loop: does letting the model run code help? Haiku 4.5, Sonnet 5.5 and GPT-6 Luna on 8 hard tasks
Speedtime per call or decision
5.16s
range 3.6 s–11.3 s · n = 16
Total time per attempt: single call vs agent loop
Codex CLI · single call · Single call vs agent loop: does letting the model run code help? Haiku 4.5, Sonnet 5.5 and GPT-6 Luna on 8 hard tasks
CostUS dollars per call, pass or decision
$0.0012
n = 16 · list-price calculation
List-price cost per strict pass: single call vs agent loop (calculation)
Codex CLI · single call · Single call vs agent loop: does letting the model run code help? Haiku 4.5, Sonnet 5.5 and GPT-6 Luna on 8 hard tasks
GPT-6 Luna price per 1M tokens
The 2026-10-06 OpenRouter snapshot reported 2 standard-tier providers at $0.10 per 1M input tokens and $0.50 per 1M output tokens. These are third-party-reported prices.
Third-party-reported
$0.10
Input, per 1M tokens
Third-party-reported
$0.50
Output, per 1M tokens
Third-party-reported
$0.01
Cache read, per 1M tokens
No current vendor context limit is proved for this exact model here.
No vendor list price for this model name in the price table, so the tiles show the provider snapshot.
Providers in the dated snapshot
2 standard-tier providers · snapshot 2026-10-06 · USD per 1M tokens
- OpenAIfirst-party
- Azure
| Provider | Input $/1M | Output $/1M | Cache read $/1M | Reported endpoint context (tokens) | Uptime, last day |
|---|---|---|---|---|---|
| OpenAI (first-party) | $0.10 | $0.50 | $0.01 | 1,050,000 | 99.99% |
| Azure | $0.10 | $0.50 | $0.01 | 1,050,000 | 99.92% |
Third-party-reported, not measured by Agent · Standard tier only: regional, flex, fast and priority tiers are left out · One row per provider: its cheapest standard endpoint
GPT-6 Luna: 2 standard-tier providers, all at the same price ($0.10 input, $0.50 output per 1M tokens). Third-party-reported, snapshot 2026-10-06.
Source: OpenRouter public API: models and provider endpoints (snapshot) (). The diamond marks the first-party provider in this snapshot. Current availability is not checked.
Estimate your monthly costPrices of every model at every provider
Where it sits
Every measured value, grouped by study. Each row puts the value on its own track, with the other configurations of the same chart as muted dots. A range is the fastest to slowest recorded run and p50–p95 is the median to the 95th percentile; neither is a confidence interval. Use Table for the plain values.
| Metric | Value | n | Interval or range | Configuration |
|---|---|---|---|---|
| CLI vs API: time for a one-line answer (Total time) | 3.19 s | 5 | 2.9 s–3.8 s (range) | Codex CLI · effort none · fixed exact reply, 5 runs |
| CLI vs API: time for a one-line answer (First useful output) | 2.79 s | 5 | 2.5 s–3.4 s (range) | Codex CLI · effort none · fixed exact reply, 5 runs |
| CLI vs API: time for a small coding task (Total time) | 9.23 s | 3 | 9 s–11.7 s (range) | Codex CLI · effort none · small coding task, 3 runs |
| CLI vs API: time for a small coding task (First useful output) | 8.68 s | 3 | 8.3 s–11 s (range) | Codex CLI · effort none · small coding task, 3 runs |
| Hidden prompt: input tokens for the same one-line request | 18,859 | 5 | — | Codex CLI · effort none · short fixed tasks |
Lines: fastest–slowest run (not an interval)n beside each valueMuted dots: the other configurations on the same chart
GPT-6 Luna (Codex CLI) in Claude Code CLI vs Codex CLI vs the API: latency and tokens: 5 values, first CLI vs API: time for a one-line answer (Total time) 3.19 s.
Single call vs agent loop: does letting the model run code help? Haiku 4.5, Sonnet 5.5 and GPT-6 Luna on 8 hard tasks
26 values · open the study
Whiskers: 95% Wilson intervalLines: fastest–slowest run (not an interval)n beside each valueMuted dots: the other configurations on the same chartHollow: list-price calculation
GPT-6 Luna (Codex CLI) in Single call vs agent loop: does letting the model run code help? Haiku 4.5, Sonnet 5.5 and GPT-6 Luna on 8 hard tasks: 26 values, first Strict pass rate: single call vs agent loop on eight hard tasks 63% (10/16).
| Metric | Value | n | Interval or range | Configuration |
|---|---|---|---|---|
| Time to first text: a 250-line answer, six models | 3.30 s | 4 | 3.2 s–3.5 s (range) | Codex CLI · effort low |
| Output speed after the first text: visible tokens per second (calculation) Calculation | 129 | 4 | 56–259 (range) | Codex CLI · effort low |
| Output speed in characters per second after the first text (calculation) Calculation | 524 | 4 | 225–1,052 (range) | Codex CLI · effort low |
Lines: fastest–slowest run (not an interval)n beside each valueMuted dots: the other configurations on the same chartHollow: list-price calculation
GPT-6 Luna (Codex CLI) in Where the seconds go: first text, output speed and prompt size for 6 LLMs: 3 values, first Time to first text: a 250-line answer, six models 3.30 s.
Compare GPT-6 Luna (Codex CLI)
Each bar counts the rows of one comparison: a side ahead only where its interval or range is apart, otherwise a tie or unclear.
vs model
Claude Haiku 4.5 vs GPT-6 Luna (Codex CLI)
GPT-6 Luna (Codex CLI) ahead on 1 · 9 ties · 7 unclear
vs model
Claude Sonnet 5.5 vs GPT-6 Luna (Codex CLI)
Claude Sonnet 5.5 ahead on 1 · 9 ties · 7 unclear
vs model
GPT-6.1 Sol (Codex CLI) vs GPT-6 Luna (Codex CLI)
8 unclear
vs model
GPT-6.1 Sol (OpenAI API) vs GPT-6 Luna (Codex CLI)
GPT-6.1 Sol (OpenAI API) ahead on 2 · 3 unclear
vs model
GPT-6 Luna (Codex CLI) vs GPT-6 Luna (OpenAI API)
GPT-6 Luna (OpenAI API) ahead on 2 · 3 unclear
Watch
Claude Code CLI vs Codex CLI vs the API: a latency race
For a one-line answer the Codex CLI was 3.5x slower than the API and sent 19,551 input tokens instead of 17.
Transcript
- Latency race · CLI vs API. What a coding CLI adds on top of the model. Same model, same effort, same prompt. Timed from launch to exit.
- A one-line answer: the OpenAI API replies in 1.0–1.5 s. The Codex CLI takes 3.2–4.2 s. Chart: One-line answer · median total time · real time (n = 5 each). Caveat: All runs are from one host and one network on 2026-10-03. Vendor latency changes over the day.
- It also sends more: 18,859–19,555 input tokens for the same one-line request. The API sends 17. Chart: Hidden prompt: input tokens for the same one-line request (n = 5 each). Caveat: Small samples: 3 to 5 runs per configuration. Medians with ranges, not intervals.
- A real repair, all runs passed: Claude Code 15.0 s, OpenAI API 17.3 s, Codex CLI 61.2 s. Chart: Scheduler repair · median total time · playback 8× (n = 3 each). Caveat: The scheduler comparison pairs Claude Code with Sonnet 5.5 against GPT-6.1 Sol on Codex and the API; the routes and the models differ together.
- Open benchmarks: intervals, sources and every failure kept.
Write-ups that use this data
All postsA latency budget for voice agents: which LLM steps fit in one turn?
136.5 ms for Jev, 0.82 s for a small-model API, 2.79 s to 3.79 s for Codex CLI: which steps fit a voice agent latency budget? A thought experiment.
A voice agent latency budget, with measured times: what fits in one turn?
Rules and Jev 1.13 fit every budget we assumed; a Claude router through a CLI fits none. 14 measured steps vs 300, 800 and 1,500 ms. A thought experiment.
AI coding agent best practices: 12 rules, each backed by a measurement
12 rules for running AI coding agents, each with one measured number: validation, model choice, effort, caching, memory, routing, CLIs and sample size.