Summary
4 items found — New model claude-opus-5 missing from models.json, two new Gemini versioned families lack specific aliases (gemini-3.5-flash-lite, gemini-3.6-flash), and several Copilot reflect models are absent from pkg/cli/data/models.json.
- Providers queried: OpenAI, Anthropic, Gemini, Copilot
- Total models found: Anthropic 10, Gemini 50, OpenAI 219, Copilot 37
- Proposed alias changes: 2 (new versioned Gemini aliases)
- Pricing gaps found: 1 (claude-opus-5 missing from models.json)
Provider Model Counts
| Provider |
Models Available |
Status |
| anthropic |
10 |
✅ ok |
| gemini |
50 |
✅ ok |
| openai |
219 |
✅ ok |
| copilot |
37 |
✅ ok |
Raw API Fields Discovered
Anthropic — id, display_name, created_at, type, max_input_tokens, max_tokens, capabilities (includes batch, citations, code_execution, effort levels, image_input, pdf_input, thinking, structured_outputs). Useful: capability flags and token limits for tier classification.
Gemini — name, displayName, description, inputTokenLimit, outputTokenLimit, supportedGenerationMethods, temperature, topK, topP, maxTemperature, version, thinking. Useful: inputTokenLimit/outputTokenLimit as pricing-tier proxy.
OpenAI — id, created, object, owned_by. Minimal metadata; owned_by and model-ID naming conventions are the only signals for tier classification.
Copilot (reflect) — Full model list with provider, port, base_url, configured, models, models_url. Billing multiplier data not exposed directly in reflect response for individual models.
Note: Playwright pricing table extraction (Step 2.5) failed — Chrome sandbox not available in this container. Billing multiplier validation was skipped for this run.
models.json Pricing Analysis
Missing from models.json
| Model ID |
Provider |
Inferred Pricing |
Basis |
| claude-opus-5 |
anthropic + copilot |
Opus-tier (high) |
Anthropic API: 1M token context, 128K output; family name = Opus |
Historical entries not currently returned by Copilot reflect
These models appear in pkg/cli/data/models.json under github-copilot but are absent from the live Copilot reflect inventory. Treat as historical records — do not remove automatically:
claude-fable-5claude-sonnet-4gemini-3.1-pro-previewgemini-3.5-flashgpt-5.2gpt-5.2-codexgpt-5.4-nano (also intentionally deprecated)kimi-k2.7-coderaptor-mini
Copilot reflect models not in models.json (non-deprecated)
The following appear in the live Copilot reflect but lack an entry in pkg/cli/data/models.json github-copilot section (excluding deprecated IDs):
claude-opus-5 — notable gap; Anthropic API confirms this model is livegpt-3.5-turbo, gpt-4, legacy gpt-4o* variants — low priority, legacy/deprecatedtext-embedding-*, trajectory-compaction — utility models, not relevant for workflow execution
Inferred vs stored pricing discrepancies
No direct multiplier discrepancies detected (Playwright unavailable for docs cross-check; reflect does not expose per-model billing multipliers in this run).
Proposed Alias Updates
1. Add gemini-3.5-flash-lite versioned alias
What: New specific alias for the Gemini 3.5 Flash Lite variant, which is available in the Gemini API.
Why: gemini-3.5-flash and gemini-3.5-flash-lite are live in the Gemini API. The gemini-3.5-flash alias already exists. The lite variant should have its own named alias for authors who explicitly need the smaller model.
Syntax:
"gemini-3.5-flash-lite": ["copilot/gemini-3.5*flash*lite*", "google/gemini-3.5*flash*lite*", "gemini/gemini-3.5*flash*lite*"]
2. Add gemini-3.6-flash versioned alias
What: New specific alias for the Gemini 3.6 Flash family (currently gemini-3.6-flash in Gemini API).
Why: gemini-3.6-flash is live in the Gemini API. The pattern is consistent with existing versioned aliases (gemini-3.1-flash, gemini-3.5-flash). Currently covered only by the generic gemini-flash alias; authors cannot pin to 3.6 specifically.
Syntax:
"gemini-3.6-flash": ["copilot/gemini-3.6*flash*", "google/gemini-3.6*flash*", "gemini/gemini-3.6*flash*"]
Full Model Lists by Provider
Anthropic (10 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-opus-5
claude-sonnet-4-5-20250929
claude-sonnet-4-6
claude-sonnet-5
Copilot via reflect (37 models)
claude-haiku-4.5, claude-opus-4.5, claude-opus-4.6, claude-opus-4.7, claude-opus-4.8, claude-opus-5, 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, trajectory-compaction
Gemini (50 models — LLM/generative subset)
antigravity-preview-05-2026, gemini-2.0-flash, gemini-2.0-flash-001, 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-image, gemini-3.1-flash-lite, gemini-3.1-pro-preview, gemini-3.5-flash, gemini-3.5-flash-lite, gemini-3.6-flash, ...
OpenAI (219 models — key GPT-5 subset)
gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, gpt-5-codex, gpt-5.1, gpt-5.1-codex, gpt-5.2, gpt-5.2-codex, gpt-5.2-pro, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-pro, gpt-5.5, gpt-5.5-pro, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, o1, o3, o3-mini, o3-pro, o4-mini, o4-mini-deep-research
Notes
- The
gemini-flash and gemini-flash-lite generic aliases already cover gemini-3.5-flash-lite and gemini-3.6-flash respectively, so these are versioned pin aliases for explicit targeting only.
- Playwright pricing extraction failed (Chrome sandbox not available); billing multiplier cross-validation was skipped. The historical
gpt-5.4-nano entry in models.json is correctly excluded per the deprecated list.
claude-opus-5 is the highest-priority gap: it is live in both Anthropic API and Copilot reflect but missing from pkg/cli/data/models.json.- The
opus and sonnet glob aliases (copilot/*opus*, anthropic/*opus*) already cover claude-opus-5 for workflow routing without needing explicit alias changes.
Generated by 📦 Daily Model Inventory Checker · sonnet46 · 67.6 AIC · ⌖ 9.4 AIC · ⊞ 8.8K · ◷
Summary
4 items found — New model
claude-opus-5missing frommodels.json, two new Gemini versioned families lack specific aliases (gemini-3.5-flash-lite,gemini-3.6-flash), and several Copilot reflect models are absent frompkg/cli/data/models.json.Provider Model Counts
Raw API Fields Discovered
Anthropic —
id,display_name,created_at,type,max_input_tokens,max_tokens,capabilities(includes batch, citations, code_execution, effort levels, image_input, pdf_input, thinking, structured_outputs). Useful: capability flags and token limits for tier classification.Gemini —
name,displayName,description,inputTokenLimit,outputTokenLimit,supportedGenerationMethods,temperature,topK,topP,maxTemperature,version,thinking. Useful:inputTokenLimit/outputTokenLimitas pricing-tier proxy.OpenAI —
id,created,object,owned_by. Minimal metadata;owned_byand model-ID naming conventions are the only signals for tier classification.Copilot (reflect) — Full model list with
provider,port,base_url,configured,models,models_url. Billing multiplier data not exposed directly in reflect response for individual models.models.json Pricing Analysis
Missing from models.json
Historical entries not currently returned by Copilot reflect
These models appear in
pkg/cli/data/models.jsonundergithub-copilotbut are absent from the live Copilot reflect inventory. Treat as historical records — do not remove automatically:claude-fable-5claude-sonnet-4gemini-3.1-pro-previewgemini-3.5-flashgpt-5.2gpt-5.2-codexgpt-5.4-nano(also intentionally deprecated)kimi-k2.7-coderaptor-miniCopilot reflect models not in models.json (non-deprecated)
The following appear in the live Copilot reflect but lack an entry in
pkg/cli/data/models.jsongithub-copilot section (excluding deprecated IDs):claude-opus-5— notable gap; Anthropic API confirms this model is livegpt-3.5-turbo,gpt-4, legacygpt-4o*variants — low priority, legacy/deprecatedtext-embedding-*,trajectory-compaction— utility models, not relevant for workflow executionInferred vs stored pricing discrepancies
No direct multiplier discrepancies detected (Playwright unavailable for docs cross-check; reflect does not expose per-model billing multipliers in this run).
Proposed Alias Updates
1. Add
gemini-3.5-flash-liteversioned aliasWhat: New specific alias for the Gemini 3.5 Flash Lite variant, which is available in the Gemini API.
Why:
gemini-3.5-flashandgemini-3.5-flash-liteare live in the Gemini API. Thegemini-3.5-flashalias already exists. The lite variant should have its own named alias for authors who explicitly need the smaller model.Syntax:
2. Add
gemini-3.6-flashversioned aliasWhat: New specific alias for the Gemini 3.6 Flash family (currently
gemini-3.6-flashin Gemini API).Why:
gemini-3.6-flashis live in the Gemini API. The pattern is consistent with existing versioned aliases (gemini-3.1-flash,gemini-3.5-flash). Currently covered only by the genericgemini-flashalias; authors cannot pin to 3.6 specifically.Syntax:
Full Model Lists by Provider
Anthropic (10 models)
Copilot via reflect (37 models)
Gemini (50 models — LLM/generative subset)
OpenAI (219 models — key GPT-5 subset)
Notes
gemini-flashandgemini-flash-litegeneric aliases already covergemini-3.5-flash-liteandgemini-3.6-flashrespectively, so these are versioned pin aliases for explicit targeting only.gpt-5.4-nanoentry inmodels.jsonis correctly excluded per the deprecated list.claude-opus-5is the highest-priority gap: it is live in both Anthropic API and Copilot reflect but missing frompkg/cli/data/models.json.opusandsonnetglob aliases (copilot/*opus*,anthropic/*opus*) already coverclaude-opus-5for workflow routing without needing explicit alias changes.