[model-inventory] Model alias inventory update - 2026-10-06
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 75/100
- Issue type
- Bug
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- json
- Domain
- tooling
Research direction
Read the pricing analysis in the issue, then inspect pkg/cli/data/models.json and actions/setup/js/models.json; the issue says they are currently identical. Update the three listed cache_read values in both files, using make refresh-models-json if helpful. Done means the files match and contain the SDK values for all three models.
Written by the indexing model from the issue text.
Description
Summary
Aliases are essentially up to date; only small pricing drift found in models.json.
- Providers queried: Anthropic (11 models), Gemini (50), OpenAI (135), Copilot SDK (23), Copilot reflect (41). The OpenAI and Anthropic proxy endpoints in reflect were not configured, so their data comes from the pre-job inventory.
- Proposed alias changes: 0 required
- Pricing gaps found: 3 (cache-read values)
- Copilot docs pricing table (Playwright, Step 2.5) was not extracted this run, so docs cross-check is skipped.
Provider Model Counts
| Provider | Models | Status |
|---|---|---|
| openai | 135 | ✅ ok |
| anthropic | 11 | ✅ ok |
| gemini | 50 | ✅ ok |
| copilot-sdk | 23 | ✅ ok |
| copilot (reflect) | 41 | ✅ ok |
models.json Pricing Analysis
Missing from models.json
| Model ID | Provider | Note |
|---|---|---|
auto |
copilot | Virtual router (discountPercent: 10), no token prices; intentionally not stored. |
dated OpenAI snapshots (e.g. gpt-5.5-2026-04-23, gpt-5.4-mini-2026-03-17) and legacy/audio/tts models |
openai | Snapshot aliases of stored models; no action. |
gemini-2.5-flash*, gemini-3.1-flash-lite*, gemini-3.5-flash-lite, image/tts variants |
gemini | Not in the Copilot-routed payload; refresh via make refresh-models-json if desired. |
Anthropic: no missing models.
Inferred vs stored pricing discrepancies (Copilot SDK cacheReadPrice, per token)
| Model ID | Stored cache_read |
SDK value |
|---|---|---|
gpt-5.4-mini |
7e-08 | 7.5e-08 |
gpt-5.3-codex |
1.7e-07 | 1.75e-07 |
gpt-5-mini |
2e-08 | 2.5e-08 |
Input and output prices for all other SDK models match. Update both pkg/cli/data/models.json and actions/setup/js/models.json identically (they are currently identical), e.g. via make refresh-models-json and then verifying these three values.
Historical entries not currently returned
Retained as history: claude-fable-5*, claude-opus-4.5/4.6/4.7, claude-sonnet-4/4.5/4.6, gemini-*, gpt-5.2*, kimi-*, mai-code-1-flash-picker, raptor-mini and the deprecated-excluded IDs.
Proposed Alias Updates
None required. Live Copilot models (claude-opus-5.5, claude-sonnet-5.5, gpt-5.6-*, gpt-6*, gpt-6.1-sol, grok-4.5/4.6/4.7, mai-code-1.1-flash) are all covered by existing globs (opus, sonnet, gpt-5.6, gpt-6, grok, mai-code). sonnet-6x lists *sonnet-5*, which also matches sonnet-5.5. Task aliases (coding, reasoning, vision, summarization) already exist.
Notes
- Stale-pattern check:
kimi,kiwi,raptor-miniandfabledon't match the current live Copilot list but remain inmodels.json; left as-is.
Generated by 📦 Daily Model Inventory Checker · copilot · auto · 22.3 AIC · ⌖ 9.92 AIC · ⊞ 13.6K · ◷
- expires on Oct 13, 2026, 4:00 PM UTC-08:00
- Dominant language
- Go
- Stars
- 5.4k
- Forks
- 576
- Avg merge
- 8h 59m
- Merged PRs (30d)
- 722
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- Ships a Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from github/gh-aw
-
[duplicate-code] Duplicate Code: pull_request event detection duplicated across safe_update filesOpenautomated-analysis code-quality cookie duplication
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Maintainers usually reply within 1 day
-
automation code-quality cookie improvement quick-win task-mining
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 1 day
-
automation code-quality cookie improvement quick-win task-mining
Difficulty 2/5 Under an hour Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
ai-generated cookie high-priority security
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
github/gh-aw#66212 · 13 comments ·
Maintainers usually reply within 1 day
-
automation cli cookie documentation
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Maintainers usually reply within 1 day
Similar issues
-
Controller pods on default limits CrashLoopBackOff and constantly reclaim memoryPossibly taken @brsmnv claimed this today. Openbug
Difficulty 2/5 Under an hour Newbie friendliness 68/100
ironcore-dev/ironcore-net#560 ·
Maintainers usually reply within 1 day
-
enhancement
Difficulty 2/5 Under an hour Newbie friendliness 78/100
JuliusBrussee/caveman#1214 ·
Maintainers usually reply within 1 day
-
model-drift
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 83/100
Maintainers usually reply within 1 day
-
Helm IPv4 host checks accept addresses Go rejectsPossibly taken @ericcaiwx-star claimed this today. Openclawsweeper:bulk-filed clawsweeper:linked-pr-open clawsweeper:no-new-fix-pr clawsweeper:source-repro impact:other issue-rating: 🦞 diamond lobster P2
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
openclaw/openclaw-enterprise#1588 · 1 comment · 1 reaction ·
Maintainers usually reply within 1 day