feat(pricing): add Z.AI GLM model pricing to hardcoded fallback by pullfrog[bot] · Pull Request #1225 · ryoppippi/ccusage

pullfrog · 2026-06-06T14:20:17Z

Add per-token pricing for six Z.AI GLM models to the hardcoded fallback in put_builtin_pricing() so offline and fallback cost calculations work for GLM models.

Models added

Model	Input ($/1M)	Cached Input ($/1M)	Output ($/1M)
glm-5.1	$1.4	$0.26	$4.4
glm-5	$1.0	$0.20	$3.2
glm-5-turbo	$1.2	$0.24	$4.0
glm-4.7	$0.6	$0.11	$2.2
glm-4.6	$0.6	$0.11	$2.2
glm-4.5	$0.6	$0.11	$2.2

Source: https://docs.z.ai/guides/overview/pricing

Closes #1201

@coderabbitai review

^{｜ View workflow run ｜ via Pullfrog ｜ Using DeepSeek Pro (free via Pullfrog for OSS) ｜ 𝕏}

Summary by cubic

Added embedded per-token pricing for six Z.AI GLM models so offline and fallback cost calculations work without remote pricing. Also added .npmrc to .gitignore.

New Features
- Adds fallback pricing for glm-4.5, glm-4.6, glm-4.7, glm-5, glm-5-turbo, glm-5.1 (sourced from Z.AI pricing docs) in put_builtin_pricing().
- Adds a unit test to confirm the models are included and rates (including cache read and cache_read_explicit) match the docs.
Misc
- Adds .npmrc to .gitignore.

^{Written for commit 00c471b. Summary will update on new commits.}

Add per-token pricing for glm-4.5, glm-4.6, glm-4.7, glm-5, glm-5-turbo, and glm-5.1 sourced from https://docs.z.ai/guides/overview/pricing so offline and fallback cost calculations work for Z.AI's GLM models.

cloudflare-workers-and-pages · 2026-06-06T14:20:52Z

Deploying with Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	ccusage-guide	`00c471b`	Commit Preview URL Branch Preview URL	Jun 06 2026, 02:25 PM

pkg-pr-new · 2026-06-06T15:26:45Z

Open in StackBlitz

ccusage

npx https://pkg.pr.new/ccusage@1225

@ccusage/ccusage-darwin-arm64

npx https://pkg.pr.new/@ccusage/ccusage-darwin-arm64@1225

@ccusage/ccusage-darwin-x64

npx https://pkg.pr.new/@ccusage/ccusage-darwin-x64@1225

@ccusage/ccusage-linux-arm64

npx https://pkg.pr.new/@ccusage/ccusage-linux-arm64@1225

@ccusage/ccusage-linux-x64

npx https://pkg.pr.new/@ccusage/ccusage-linux-x64@1225

@ccusage/ccusage-win32-arm64

npx https://pkg.pr.new/@ccusage/ccusage-win32-arm64@1225

@ccusage/ccusage-win32-x64

npx https://pkg.pr.new/@ccusage/ccusage-win32-x64@1225

commit: 00c471b

github-actions · 2026-06-06T15:41:34Z

ccusage performance comparison

PR SHA: 26f2eb245fc1
Base SHA: bee4a26e6cf5

This compares the Rust PR release binary against the configured base package on the same CI runner.

Package runner startup

Execution setup measures any pre-benchmark package materialization used by the execution benchmark. Bunx temp cache measures one bunx -p <url> ccusage --version run with an empty Bun install cache. Warm reuses that cache and reports the median of repeated runs.

Package	SHA	Execution setup	Bunx temp cache	Bunx warm median	Warm samples
Base pkg.pr.new	`bee4a26e6cf5`	547.2ms	800.2ms	31.5ms	3
PR pkg.pr.new	`26f2eb2`	932.9ms	646.6ms	32.4ms	3

Cached bunx execution performance

Runs the same large fixture through bunx -p <pkg.pr.new URL> ccusage after the Bun install cache has already been populated by the startup measurement. This separates cached package-runner execution from first-fetch package materialization.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base package: bee4a26e6cf5; PR package: 26f2eb2. Both run through bunx -p <pkg.pr.new URL> ccusage using the warmed Bun install cache from package runner startup, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`bunx -p <pkg> ccusage claude --offline --json`	1.01 GiB	550.8ms	540.3ms	1.02x	327.70 MiB	296.58 MiB	0.91x	1.83 GiB/s	1.86 GiB/s
`bunx -p <pkg> ccusage codex --offline --json`	1.01 GiB	376.9ms	374.6ms	1.01x	79.45 MiB	79.58 MiB	1.00x	2.67 GiB/s	2.69 GiB/s

Package runtime diagnostics

Compares the PR package wrapper, the installed native optional dependency binary, and the workspace release binary on the same large fixture. This identifies whether slow package results come from JavaScript wrapper overhead, the published native binary build, or the Rust core itself.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
All rows run --offline --json, measured by hyperfine with 0 warmups and 1 runs. This isolates wrapper overhead from the installed native optional dependency and the workspace release binary built on the runner.

Command	Runtime	Input	Median	Throughput	Samples
`claude --offline --json`	Package wrapper	1.01 GiB	554.3ms	1.82 GiB/s	1
`claude --offline --json`	Installed native binary	1.01 GiB	523.3ms	1.92 GiB/s	1
`codex --offline --json`	Package wrapper	1.01 GiB	366.2ms	2.75 GiB/s	1
`codex --offline --json`	Installed native binary	1.01 GiB	338.9ms	2.97 GiB/s	1

Committed fixture performance

Committed small fixtures for stable PR-to-PR feedback and explicit Claude/Codex command coverage.

Fixtures: Claude apps/ccusage/test/fixtures/claude (0.00 MiB, 2 files), Codex apps/ccusage/test/fixtures/codex (0.00 MiB, 1 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs rust/target/release/ccusage directly. Both run --offline --json, measured by hyperfine with 2 warmups and 7 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude daily --offline --json`	29.4ms	3.8ms	7.66x	43.73 MiB	2.70 MiB	0.06x	0.05 MiB/s	0.40 MiB/s
`claude session --offline --json`	29.5ms	4.1ms	7.28x	43.73 MiB	2.83 MiB	0.06x	0.05 MiB/s	0.38 MiB/s
`codex daily --offline --json`	29.1ms	3.8ms	7.71x	43.61 MiB	2.70 MiB	0.06x	0.03 MiB/s	0.23 MiB/s
`codex session --offline --json`	28.9ms	3.6ms	7.97x	43.48 MiB	2.70 MiB	0.06x	0.03 MiB/s	0.24 MiB/s

Large real-world-shaped fixture performance

Generated fixtures shaped from aggregate local log statistics: thousands of JSONL files, many small sessions, and a long tail of larger sessions. No real prompts, paths, or outputs are stored in the fixtures.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs rust/target/release/ccusage directly. Both run --offline --json, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude --offline --json`	1.01 GiB	542.5ms	518.4ms	1.05x	320.20 MiB	326.45 MiB	1.02x	1.86 GiB/s	1.94 GiB/s
`codex --offline --json`	1.01 GiB	359.8ms	335.5ms	1.07x	78.83 MiB	77.20 MiB	0.98x	2.80 GiB/s	3.00 GiB/s

Artifact size

Artifact	Base	PR	Delta	Ratio
packed `ccusage-*.tgz`	14.35 KiB	14.35 KiB	+0.00 KiB	1.00x
installed native package binary	3289.62 KiB	3289.62 KiB	+0.00 KiB	1.00x

Lower medians and smaller artifacts are better. CI runner noise still applies; use same-run ratios as directional PR feedback, not release guarantees.

github-actions · 2026-06-06T15:42:16Z

ccusage performance comparison

PR SHA: 26f2eb245fc1
Base SHA: bee4a26e6cf5

This compares the PR package against the configured base package on the same CI runner.

Package runner startup

Execution setup measures any pre-benchmark package materialization used by the execution benchmark. Bunx temp cache measures one bunx -p <url> ccusage --version run with an empty Bun install cache. Warm reuses that cache and reports the median of repeated runs.

Package	SHA	Execution setup	Bunx temp cache	Bunx warm median	Warm samples
Base pkg.pr.new	`bee4a26e6cf5`	686.1ms	735.4ms	31.4ms	3
PR pkg.pr.new	`26f2eb2`	697.5ms	858.2ms	32.1ms	3

Cached bunx execution performance

Runs the same large fixture through bunx -p <pkg.pr.new URL> ccusage after the Bun install cache has already been populated by the startup measurement. This separates cached package-runner execution from first-fetch package materialization.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base package: bee4a26e6cf5; PR package: 26f2eb2. Both run through bunx -p <pkg.pr.new URL> ccusage using the warmed Bun install cache from package runner startup, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`bunx -p <pkg> ccusage claude --offline --json`	1.01 GiB	550.6ms	548.8ms	1.00x	315.83 MiB	288.95 MiB	0.91x	1.83 GiB/s	1.83 GiB/s
`bunx -p <pkg> ccusage codex --offline --json`	1.01 GiB	371.1ms	376.7ms	0.99x	81.33 MiB	76.70 MiB	0.94x	2.71 GiB/s	2.67 GiB/s

Package runtime diagnostics

Compares the PR package wrapper, the installed native optional dependency binary, and the workspace release binary on the same large fixture. This identifies whether slow package results come from JavaScript wrapper overhead, the published native binary build, or the Rust core itself.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
All rows run --offline --json, measured by hyperfine with 0 warmups and 1 runs. This isolates wrapper overhead from the installed native optional dependency and the workspace release binary built on the runner.

Command	Runtime	Input	Median	Throughput	Samples
`claude --offline --json`	Package wrapper	1.01 GiB	546.2ms	1.84 GiB/s	1
`claude --offline --json`	Installed native binary	1.01 GiB	525.2ms	1.92 GiB/s	1
`codex --offline --json`	Package wrapper	1.01 GiB	383.9ms	2.62 GiB/s	1
`codex --offline --json`	Installed native binary	1.01 GiB	346.3ms	2.91 GiB/s	1

Committed fixture performance

Committed small fixtures for stable PR-to-PR feedback and explicit Claude/Codex command coverage.

Fixtures: Claude apps/ccusage/test/fixtures/claude (0.00 MiB, 2 files), Codex apps/ccusage/test/fixtures/codex (0.00 MiB, 1 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs the published ccusage package from pkg.pr.new, installed before measurement. Both run --offline --json, measured by hyperfine with 2 warmups and 7 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude daily --offline --json`	29.5ms	29.4ms	1.01x	43.48 MiB	43.73 MiB	1.01x	0.05 MiB/s	0.05 MiB/s
`claude session --offline --json`	30.5ms	30.6ms	1.00x	43.73 MiB	43.48 MiB	0.99x	0.05 MiB/s	0.05 MiB/s
`codex daily --offline --json`	30.0ms	29.2ms	1.03x	43.48 MiB	43.61 MiB	1.00x	0.03 MiB/s	0.03 MiB/s
`codex session --offline --json`	29.2ms	29.0ms	1.01x	-	43.61 MiB	-	0.03 MiB/s	0.03 MiB/s

Large real-world-shaped fixture performance

Generated fixtures shaped from aggregate local log statistics: thousands of JSONL files, many small sessions, and a long tail of larger sessions. No real prompts, paths, or outputs are stored in the fixtures.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs the published ccusage package from pkg.pr.new, installed before measurement. Both run --offline --json, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude --offline --json`	1.01 GiB	552.1ms	542.3ms	1.02x	327.95 MiB	300.58 MiB	0.92x	1.82 GiB/s	1.86 GiB/s
`codex --offline --json`	1.01 GiB	366.3ms	369.3ms	0.99x	78.70 MiB	79.33 MiB	1.01x	2.75 GiB/s	2.73 GiB/s

Artifact size

Artifact	Base	PR	Delta	Ratio
packed `ccusage-*.tgz`	14.35 KiB	14.35 KiB	+0.00 KiB	1.00x
installed native package binary	3289.62 KiB	3289.62 KiB	+0.00 KiB	1.00x

Lower medians and smaller artifacts are better. CI runner noise still applies; use same-run ratios as directional PR feedback, not release guarantees.

github-actions · 2026-06-06T15:49:08Z

ccusage performance comparison

PR SHA: 00c471bc69b8
Base SHA: bee4a26e6cf5

This compares the Rust PR release binary against the configured base package on the same CI runner.

Package runner startup

Execution setup measures any pre-benchmark package materialization used by the execution benchmark. Bunx temp cache measures one bunx -p <url> ccusage --version run with an empty Bun install cache. Warm reuses that cache and reports the median of repeated runs.

Package	SHA	Execution setup	Bunx temp cache	Bunx warm median	Warm samples
Base pkg.pr.new	`bee4a26e6cf5`	489.0ms	696.4ms	31.8ms	3
PR pkg.pr.new	`00c471b`	739.5ms	593.8ms	30.8ms	3

Cached bunx execution performance

Runs the same large fixture through bunx -p <pkg.pr.new URL> ccusage after the Bun install cache has already been populated by the startup measurement. This separates cached package-runner execution from first-fetch package materialization.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base package: bee4a26e6cf5; PR package: 00c471b. Both run through bunx -p <pkg.pr.new URL> ccusage using the warmed Bun install cache from package runner startup, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`bunx -p <pkg> ccusage claude --offline --json`	1.01 GiB	561.7ms	549.5ms	1.02x	320.58 MiB	295.08 MiB	0.92x	1.79 GiB/s	1.83 GiB/s
`bunx -p <pkg> ccusage codex --offline --json`	1.01 GiB	369.8ms	375.4ms	0.98x	70.08 MiB	82.83 MiB	1.18x	2.72 GiB/s	2.68 GiB/s

Package runtime diagnostics

Compares the PR package wrapper, the installed native optional dependency binary, and the workspace release binary on the same large fixture. This identifies whether slow package results come from JavaScript wrapper overhead, the published native binary build, or the Rust core itself.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
All rows run --offline --json, measured by hyperfine with 0 warmups and 1 runs. This isolates wrapper overhead from the installed native optional dependency and the workspace release binary built on the runner.

Command	Runtime	Input	Median	Throughput	Samples
`claude --offline --json`	Package wrapper	1.01 GiB	545.5ms	1.85 GiB/s	1
`claude --offline --json`	Installed native binary	1.01 GiB	515.1ms	1.95 GiB/s	1
`codex --offline --json`	Package wrapper	1.01 GiB	367.8ms	2.74 GiB/s	1
`codex --offline --json`	Installed native binary	1.01 GiB	343.6ms	2.93 GiB/s	1

Committed fixture performance

Committed small fixtures for stable PR-to-PR feedback and explicit Claude/Codex command coverage.

Fixtures: Claude apps/ccusage/test/fixtures/claude (0.00 MiB, 2 files), Codex apps/ccusage/test/fixtures/codex (0.00 MiB, 1 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs rust/target/release/ccusage directly. Both run --offline --json, measured by hyperfine with 2 warmups and 7 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude daily --offline --json`	29.4ms	4.0ms	7.36x	43.73 MiB	2.70 MiB	0.06x	0.05 MiB/s	0.39 MiB/s
`claude session --offline --json`	29.0ms	3.9ms	7.35x	43.61 MiB	2.70 MiB	0.06x	0.05 MiB/s	0.39 MiB/s
`codex daily --offline --json`	28.9ms	3.6ms	8.10x	43.73 MiB	2.70 MiB	0.06x	0.03 MiB/s	0.24 MiB/s
`codex session --offline --json`	28.9ms	3.5ms	8.18x	43.48 MiB	2.70 MiB	0.06x	0.03 MiB/s	0.24 MiB/s

Large real-world-shaped fixture performance

Generated fixtures shaped from aggregate local log statistics: thousands of JSONL files, many small sessions, and a long tail of larger sessions. No real prompts, paths, or outputs are stored in the fixtures.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs rust/target/release/ccusage directly. Both run --offline --json, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude --offline --json`	1.01 GiB	549.1ms	527.5ms	1.04x	302.58 MiB	320.70 MiB	1.06x	1.83 GiB/s	1.91 GiB/s
`codex --offline --json`	1.01 GiB	361.4ms	344.2ms	1.05x	80.20 MiB	72.83 MiB	0.91x	2.79 GiB/s	2.92 GiB/s

Artifact size

Artifact	Base	PR	Delta	Ratio
packed `ccusage-*.tgz`	14.35 KiB	14.35 KiB	+0.00 KiB	1.00x
installed native package binary	3289.62 KiB	3289.62 KiB	+0.00 KiB	1.00x

Lower medians and smaller artifacts are better. CI runner noise still applies; use same-run ratios as directional PR feedback, not release guarantees.

github-actions · 2026-06-06T15:49:28Z

ccusage performance comparison

PR SHA: 00c471bc69b8
Base SHA: bee4a26e6cf5

This compares the PR package against the configured base package on the same CI runner.

Package runner startup

Execution setup measures any pre-benchmark package materialization used by the execution benchmark. Bunx temp cache measures one bunx -p <url> ccusage --version run with an empty Bun install cache. Warm reuses that cache and reports the median of repeated runs.

Package	SHA	Execution setup	Bunx temp cache	Bunx warm median	Warm samples
Base pkg.pr.new	`bee4a26e6cf5`	544.7ms	666.2ms	31.7ms	3
PR pkg.pr.new	`00c471b`	763.0ms	880.2ms	31.6ms	3

Cached bunx execution performance

Runs the same large fixture through bunx -p <pkg.pr.new URL> ccusage after the Bun install cache has already been populated by the startup measurement. This separates cached package-runner execution from first-fetch package materialization.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base package: bee4a26e6cf5; PR package: 00c471b. Both run through bunx -p <pkg.pr.new URL> ccusage using the warmed Bun install cache from package runner startup, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`bunx -p <pkg> ccusage claude --offline --json`	1.01 GiB	558.2ms	553.3ms	1.01x	308.83 MiB	332.45 MiB	1.08x	1.80 GiB/s	1.82 GiB/s
`bunx -p <pkg> ccusage codex --offline --json`	1.01 GiB	369.4ms	375.3ms	0.98x	79.45 MiB	81.70 MiB	1.03x	2.73 GiB/s	2.68 GiB/s

Package runtime diagnostics

Compares the PR package wrapper, the installed native optional dependency binary, and the workspace release binary on the same large fixture. This identifies whether slow package results come from JavaScript wrapper overhead, the published native binary build, or the Rust core itself.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
All rows run --offline --json, measured by hyperfine with 0 warmups and 1 runs. This isolates wrapper overhead from the installed native optional dependency and the workspace release binary built on the runner.

Command	Runtime	Input	Median	Throughput	Samples
`claude --offline --json`	Package wrapper	1.01 GiB	539.8ms	1.87 GiB/s	1
`claude --offline --json`	Installed native binary	1.01 GiB	519.9ms	1.94 GiB/s	1
`codex --offline --json`	Package wrapper	1.01 GiB	370.0ms	2.72 GiB/s	1
`codex --offline --json`	Installed native binary	1.01 GiB	343.4ms	2.93 GiB/s	1

Committed fixture performance

Committed small fixtures for stable PR-to-PR feedback and explicit Claude/Codex command coverage.

Fixtures: Claude apps/ccusage/test/fixtures/claude (0.00 MiB, 2 files), Codex apps/ccusage/test/fixtures/codex (0.00 MiB, 1 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs the published ccusage package from pkg.pr.new, installed before measurement. Both run --offline --json, measured by hyperfine with 2 warmups and 7 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude daily --offline --json`	29.9ms	29.8ms	1.00x	43.73 MiB	43.61 MiB	1.00x	0.05 MiB/s	0.05 MiB/s
`claude session --offline --json`	29.3ms	28.8ms	1.02x	43.61 MiB	43.48 MiB	1.00x	0.05 MiB/s	0.05 MiB/s
`codex daily --offline --json`	28.6ms	29.0ms	0.99x	43.48 MiB	43.48 MiB	1.00x	0.03 MiB/s	0.03 MiB/s
`codex session --offline --json`	29.4ms	28.6ms	1.03x	43.61 MiB	43.61 MiB	1.00x	0.03 MiB/s	0.03 MiB/s

Large real-world-shaped fixture performance

Generated fixtures shaped from aggregate local log statistics: thousands of JSONL files, many small sessions, and a long tail of larger sessions. No real prompts, paths, or outputs are stored in the fixtures.

Fixtures: Claude /home/runner/work/_temp/ccusage-large-fixture (1.01 GiB, 2,597 files), Codex /home/runner/work/_temp/ccusage-large-codex-fixture (1.01 GiB, 2,597 files)
Base runs the published ccusage package from pkg.pr.new, installed before measurement; PR runs the published ccusage package from pkg.pr.new, installed before measurement. Both run --offline --json, measured by hyperfine with 0 warmups and 1 runs.
Peak RSS is measured separately with /usr/bin/time using 1 runs. Lower RSS ratios are better.

Command	Input	Base median	PR median	PR vs base	Base peak RSS	PR peak RSS	PR/base RSS	Base throughput	PR throughput
`claude --offline --json`	1.01 GiB	552.2ms	541.7ms	1.02x	325.33 MiB	306.58 MiB	0.94x	1.82 GiB/s	1.86 GiB/s
`codex --offline --json`	1.01 GiB	363.0ms	368.0ms	0.99x	71.70 MiB	78.95 MiB	1.10x	2.77 GiB/s	2.74 GiB/s

Artifact size

Artifact	Base	PR	Delta	Ratio
packed `ccusage-*.tgz`	14.35 KiB	14.35 KiB	+0.00 KiB	1.00x
installed native package binary	3289.62 KiB	3289.62 KiB	+0.00 KiB	1.00x

Lower medians and smaller artifacts are better. CI runner noise still applies; use same-run ratios as directional PR feedback, not release guarantees.

feat(pricing): add Z.AI GLM model pricing to hardcoded fallback

26f2eb2

Add per-token pricing for glm-4.5, glm-4.6, glm-4.7, glm-5, glm-5-turbo, and glm-5.1 sourced from https://docs.z.ai/guides/overview/pricing so offline and fallback cost calculations work for Z.AI's GLM models.

pullfrog Bot requested a review from ryoppippi June 6, 2026 14:20

pullfrog Bot mentioned this pull request Jun 6, 2026

feat(pricing): add Z.AI GLM model pricing for cost calculation #1201

Closed

chore: add .npmrc to .gitignore

00c471b

ryoppippi merged commit 72e2372 into main Jun 8, 2026
37 checks passed

ryoppippi deleted the pullfrog/1201-add-glm-pricing branch June 8, 2026 20:30

ryoppippi mentioned this pull request Jun 8, 2026

fix(pricing): do not charge GLM cache creation #1235

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(pricing): add Z.AI GLM model pricing to hardcoded fallback#1225

feat(pricing): add Z.AI GLM model pricing to hardcoded fallback#1225
ryoppippi merged 2 commits into
mainfrom
pullfrog/1201-add-glm-pricing

pullfrog Bot commented Jun 6, 2026 •

edited by cubic-dev-ai Bot

Loading

Uh oh!

cloudflare-workers-and-pages Bot commented Jun 6, 2026 •

edited

Loading

Uh oh!

pkg-pr-new Bot commented Jun 6, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

pullfrog Bot commented Jun 6, 2026 • edited by cubic-dev-ai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Models added

Summary by cubic

Uh oh!

cloudflare-workers-and-pages Bot commented Jun 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Deploying with Cloudflare Workers

Uh oh!

pkg-pr-new Bot commented Jun 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jun 6, 2026

ccusage performance comparison

Package runner startup

Cached bunx execution performance

Package runtime diagnostics

Committed fixture performance

Large real-world-shaped fixture performance

Artifact size

Uh oh!

github-actions Bot commented Jun 6, 2026

ccusage performance comparison

Package runner startup

Cached bunx execution performance

Package runtime diagnostics

Committed fixture performance

Large real-world-shaped fixture performance

Artifact size

Uh oh!

github-actions Bot commented Jun 6, 2026

ccusage performance comparison

Package runner startup

Cached bunx execution performance

Package runtime diagnostics

Committed fixture performance

Large real-world-shaped fixture performance

Artifact size

Uh oh!

github-actions Bot commented Jun 6, 2026

ccusage performance comparison

Package runner startup

Cached bunx execution performance

Package runtime diagnostics

Committed fixture performance

Large real-world-shaped fixture performance

Artifact size

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

pullfrog Bot commented Jun 6, 2026 •

edited by cubic-dev-ai Bot

Loading

cloudflare-workers-and-pages Bot commented Jun 6, 2026 •

edited

Loading

pkg-pr-new Bot commented Jun 6, 2026 •

edited

Loading