Skip to content

v0.18.4 — GPT-6 Sol and Luna pricing

Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 22 Sep 20:48
· 1 commit to main since this release
v0.18.4
ec50833

GPT-6 Sol and Luna pricing

Codexometer now recognises published GPT-6 Sol and Luna prices for API-equivalent estimates, using OpenAI's September 22 pricing—including the lower rates relative to GPT-5.6, not an additional discount applied on top.

  • GPT-6 Sol: $2 input, $0.20 cached input, $2.50 cache writes and $10 output per million tokens.
  • GPT-6 Luna: $0.10 input, $0.01 cached input, $0.125 cache writes and $0.50 output per million tokens.
  • Includes published long-context pricing above 272,000 input tokens per response and requested Fast/priority premiums in live estimates. Benchmark API EQ remains a standard-price comparison.
  • Shared pricing covers terminal and web consumers; pricing dates and README are updated. Existing model prices are retained, and unknown variants remain unpriced.
  • Regression coverage includes threshold boundaries, both cache classes, dated model IDs, Fast rates and the pricing footer.

API EQ remains an estimate, not a subscription bill or a guarantee of the tier delivered by the backend.

Sources: OpenAI pricing, GPT-6 Sol, GPT-6 Luna.

Upgrade

macOS, Linux and WSL:

curl -fsSL https://raw.githubusercontent.com/merefield/codexometer/main/install-release.sh | sh

Windows PowerShell:

$installer = Join-Path $env:TEMP 'codexometer-install.ps1'
Invoke-WebRequest https://raw.githubusercontent.com/merefield/codexometer/main/install-release.ps1 -OutFile $installer
& $installer

Or download your platform archive below. Restart Codexometer and check codexometer --version reports 0.18.4.

Includes PR #65.

Full changelog: v0.18.3...v0.18.4

Assets 9
Loading