[model-inventory] Model alias inventory update - 2026-07-13

[github-actions]

Summary

models.json refreshed from models.dev catalog — 5 new OpenAI model entries added, 12 historical Anthropic claude-3.x entries pruned, 1 Copilot-only model removed (raptor-mini). No alias changes required: all 35 live Copilot models are covered by existing alias patterns. All stored pricing entries validated against the GitHub Docs pricing table.

• Providers queried: Copilot (reflect endpoint ✅), OpenAI ✅, Anthropic ✅, Gemini ✅, Vertex ❌ (not configured)
• Total models found: Copilot 35, OpenAI 219, Anthropic 9, Gemini 50
• Proposed alias changes: 0
• Pricing gaps found: 0 (all current entries validated)

Provider Model Counts

Provider	Models Available	Status
openai	219	✅ ok
anthropic	9	✅ ok
gemini	50	✅ ok
copilot	35	✅ ok
vertex	—	⚠️ not configured

Raw API Fields Discovered

Anthropic (/v1/models):

• id, display_name, created_at
• max_input_tokens, max_tokens
• capabilities: batch, citations, code_execution, effort (low/med/high/xhigh/max), image_input, streaming, tool_use, vision
• No direct billing/pricing fields

OpenAI (/v1/models):

• id, object, created, owned_by
• No context-limit or pricing fields in list API (requires separate model detail fetch)

Gemini (/v1beta/models):

• name, version, displayName, description
• inputTokenLimit, outputTokenLimit — useful proxy for pricing tier
• supportedGenerationMethods — useful for capability flags (thinking, etc.)
• temperature, topP, topK, maxTemperature

Copilot (/reflect endpoint):

• provider, base_url, models_url, configured, models (list of IDs only)
• No billing/multiplier fields exposed via reflect (unlike previous versions)

models.json Pricing Analysis

Refresh changes (from make refresh-models-json)

pkg/cli/data/models.json and actions/setup/js/models.json were refreshed from the models.dev catalog. The two files remain identical.

OpenAI additions:

Model	Cost input/M	Cost output/M
gpt-5.6	$5.00	$30.00
gpt-5.6-luna	$1.00	$6.00
gpt-5.6-sol	$5.00	$30.00
gpt-5.6-terra	$2.50	$15.00
gpt-realtime-2.1	—	—

Removed from models.json (historical Anthropic claude-3.x entries no longer in models.dev):
claude-3-5-haiku-20241022, claude-3-5-haiku-latest, claude-3-5-sonnet-20240620, claude-3-5-sonnet-20241022, claude-3-7-sonnet-20250219, claude-3-haiku-20240307, claude-3-opus-20240229, claude-3-sonnet-20240229, claude-opus-4-0, claude-opus-4-20250514, claude-sonnet-4-0, claude-sonnet-4-20250514

Also removed: gpt-5-search-api, o1-mini, o1-preview (from openai provider), raptor-mini (from github-copilot)

Historical entries not currently returned by live APIs

The following github-copilot entries are in models.json but absent from the live Copilot reflect endpoint — kept as historical records:
claude-fable-5, claude-sonnet-4, gemini-3.1-pro-preview, gemini-3.5-flash, gpt-4.1, gpt-5.2, gpt-5.2-codex, gpt-5.4-nano, kimi-k2.7-code

Pricing validation (docs table vs models.json)

All Copilot model entries cross-checked against GitHub Docs pricing table — no discrepancies found:

Model	Docs input/M	Stored input	Match
claude-haiku-4.5	$1.00	$1.00	✅
claude-sonnet-4.5/4.6	$3.00	$3.00	✅
claude-opus-4.5–4.8	$5.00	$5.00	✅
claude-sonnet-5	$2.00	$2.00	✅
claude-fable-5	$10.00	$10.00	✅
gpt-5-mini	$0.25	$0.25	✅
gpt-5.4	$2.50	$2.50	✅
gpt-5.5	$5.00	$5.00	✅
gpt-5.6-luna	$1.00	$1.00	✅
gpt-5.6-sol	$5.00	$5.00	✅
gpt-5.6-terra	$2.50	$2.50	✅

Proposed Alias Updates

No changes required. All 35 live Copilot models are matched by existing alias glob patterns:

Live Model	Matching Alias
claude-haiku-4.5	haiku → copilot/*haiku*
claude-sonnet-4.5/4.6	sonnet → copilot/*sonnet*
claude-opus-4.5–4.8	opus → copilot/*opus*
claude-sonnet-5	sonnet → copilot/*sonnet*
gemini-2.5-pro	gemini-pro → copilot/gemini-*pro*
gemini-3-flash-preview	gemini-3-flash → copilot/gemini-3*flash*
gpt-5-mini	gpt-5-mini → copilot/gpt-5*mini*
gpt-5.3-codex	gpt-5-codex → copilot/gpt-5*codex*
gpt-5.4	gpt-5.4 → copilot/gpt-5.4*
gpt-5.4-mini	gpt-5-mini → copilot/gpt-5*mini*
gpt-5.5	gpt-5.5 → copilot/gpt-5.5*
gpt-5.6-luna/sol/terra	gpt-5.6 → copilot/gpt-5.6*
mai-code-1-flash-picker	mai-code → copilot/mai-code*

Full Model Lists by Provider

Copilot (live, 35 models)

claude-haiku-4.5, claude-opus-4.5, claude-opus-4.6, claude-opus-4.7, claude-opus-4.8,
claude-sonnet-4.5, claude-sonnet-4.6, claude-sonnet-5,
gemini-2.5-pro, gemini-3-flash-preview,
gpt-3.5-turbo, gpt-3.5-turbo-0613, gpt-4, gpt-4-0613, gpt-4-o-preview,
gpt-4.1, gpt-4.1-2025-04-14, gpt-4o, gpt-4o-2024-05-13, gpt-4o-2024-08-06,
gpt-4o-2024-11-20, gpt-4o-mini, gpt-4o-mini-2024-07-18,
gpt-5-mini, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.5,
gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra,
mai-code-1-flash-picker,
text-embedding-3-small, text-embedding-3-small-inference, text-embedding-ada-002

Anthropic (direct API, 9 models)

claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-5-20251101,
claude-opus-4-6, claude-opus-4-7, claude-opus-4-8,
claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-sonnet-5

Gemini (direct API, 50 models) — notable ones

antigravity-preview-05-2026, deep-research-*,
gemini-2.0-flash, gemini-2.0-flash-lite, gemini-2.5-flash, gemini-2.5-flash-lite,
gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview,
gemini-3.1-flash-*, gemini-3.1-pro-preview, gemini-3.5-flash,
gemma-4-26b-a4b-it, gemma-4-31b-it,
imagen-4.0-*, lyria-3-*, nano-banana-pro-preview, veo-3.1-*

OpenAI (direct API, 219 models) — stable/notable ones

gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro,
gpt-5.1 through gpt-5.6 (including luna/sol/terra variants),
o1, o1-pro, o3, o3-mini, o3-pro, o4-mini,
gpt-image-1, gpt-image-2, gpt-audio-*, gpt-realtime-*,
gemini-2.5-pro (openai serving Gemini)

Notes

• make refresh-models-json was run and resulted in real changes to pkg/cli/data/models.json and actions/setup/js/models.json. The build step (make agent-report-progress) could not complete due to Go toolchain download restrictions in this sandbox, so the changes could not be committed automatically.
• Treat removed historical Anthropic claude-3.x entries as a models.dev catalog pruning — these models may still be usable via direct Anthropic API but are no longer listed in models.dev.
• gpt-4o-mini, gpt-4.1, gpt-4o, gpt-5.4-nano remain excluded per policy even though they appear in the Copilot live endpoint.
• The gemini-3.5-flash alias was already added previously and correctly covers the live Gemini gemini-3.5-flash model.

Warning

Firewall blocked 8 domains

The following domains were blocked by the firewall during workflow execution:

• accounts.google.com
• android.clients.google.com
• clients2.google.com
• collector.githubapp.com
• contentautofill.googleapis.com
• proxy.golang.org
• safebrowsingohttpgateway.googleapis.com
• www.google.com

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "accounts.google.com"
    - "android.clients.google.com"
    - "clients2.google.com"
    - "collector.githubapp.com"
    - "contentautofill.googleapis.com"
    - "proxy.golang.org"
    - "safebrowsingohttpgateway.googleapis.com"
    - "www.google.com"

See Network Configuration for more information.

Generated by 📦 Daily Model Inventory Checker · 121.8 AIC · ⌖ 11.1 AIC · ⊞ 8.5K · ◷

• expires on Jul 19, 2026, 4:22 PM UTC-08:00

[github-actions]

This issue is being closed as outdated. A newer issue has been created: #45349

View newer issue

---

This action was performed automatically by the Daily Model Inventory Checker workflow.