Summary
Daily model inventory check for 2026-06-01. All major providers returned data. The multiplier table has a few missing entries for new non-preview Gemini model variants and one OpenAI internal preview model. The alias map is largely up to date, but the sonnet-6x alias has a coverage gap: Copilot serves Claude Sonnet with dot-notation IDs (claude-sonnet-4.5, claude-sonnet-4.6) that the current *sonnet-4-5-* / *sonnet-4-6* dash-hyphenated glob patterns do not match.
- Providers queried: OpenAI, Anthropic, Gemini, Copilot
- Total models found: 194 (OpenAI) + 10 (Anthropic) + 50 (Gemini) + 32 (Copilot) = 286 total (with overlap across providers)
- Proposed alias changes: 1
- Multiplier gaps found: 5
Provider Model Counts
| Provider |
Models Available |
Status |
| openai |
194 |
✅ ok |
| anthropic |
10 |
✅ ok |
| gemini |
50 |
✅ ok |
| copilot |
32 |
✅ ok |
Raw API Fields Discovered
Anthropic — richest capability metadata: display_name, created_at, max_input_tokens, max_tokens, and a detailed capabilities map covering batch, citations, code_execution, context_management, effort (low/medium/high/xhigh/max), image_input, pdf_input, structured_outputs, and thinking (with sub-types enabled / adaptive). No billing/pricing fields exposed.
OpenAI — minimal fields in the list endpoint: id, object, created, owned_by. Capability and pricing data requires the models detail endpoint or documentation. Useful for family grouping via owned_by and model-ID naming conventions.
Gemini — good metadata: name, version, displayName, description, inputTokenLimit, outputTokenLimit, supportedGenerationMethods, temperature, topP, topK, maxTemperature, thinking flag. Token limits are useful for tier inference.
Copilot (via api-proxy /models) — richest billing-adjacent data: capabilities.limits (context window, output, prompt limits), capabilities.supports (adaptive_thinking, reasoning_effort, vision, streaming, structured_outputs, tool_calls), model_picker_category (lightweight / versatile / powerful), vendor, version, policy.state. The billing field is present in the schema but returned as null for all current models — no ET multiplier data available directly from the endpoint.
Token Multiplier Analysis
Billing multipliers are sourced from the official GitHub Copilot docs table (primary, since billing.multiplier is null for all Copilot endpoint models). All doc-table entries are already correctly reflected in model_multipliers.json.
Missing from model_multipliers.json
| Model ID |
Provider |
Inferred Multiplier |
Basis |
gemini-3-pro-image |
gemini |
6.0 |
Same family as gemini-3-pro-image-preview (currently 6.0); production/GA release of the preview |
gemini-3.1-flash-image |
gemini |
0.33 |
Same family as gemini-3.1-flash-image-preview (currently 0.33); production release |
antigravity-preview-05-2026 |
gemini |
unknown |
New Gemini model, not yet in billing docs; needs pricing confirmation before adding |
nano-banana-pro-preview |
gemini |
unknown |
Likely an internal/test model name; not in billing docs; defer |
gpt-5.3-codex-api-preview-preambles |
openai |
6.0 |
Same gpt-5.3-codex family (currently 6.0); preambles variant |
Historical entries not currently returned
The following model IDs appear in model_multipliers.json but are absent from all live API inventories. These should remain as historical records:
claude-3-5-haiku, claude-3-haiku, claude-3-5-sonnet, claude-3-7-sonnet, claude-3-sonnet, claude-opus-4, claude-opus-4-20250514, claude-opus-4-1, claude-opus-4-1-20250805, claude-3-5-opus, claude-3-opus, claude-sonnet-4, claude-sonnet-4-20250514, gpt-4-turbo, gpt-41-copilot, gpt-4.1-mini, gpt-4.1-nano, gpt-5, gpt-5-2025-08-07, gpt-5-search-api, gpt-5-search-api-2025-10-14, gpt-5-chat-latest, gpt-5-nano, gpt-5-nano-2025-08-07, gpt-5-pro, gpt-5-pro-2025-10-06, gpt-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max, gpt-5.1-codex-max-customsummarizer, gpt-5.2-2025-12-11, gpt-5.2-chat-latest, gpt-5.2-pro, gpt-5.2-pro-2025-12-11, gpt-5.3-chat-latest, gpt-5.3-codex-api-preview, gpt-5.4-2026-03-05, gpt-5.4-mini-2026-03-17, gpt-5.4-pro, gpt-5.4-pro-2026-03-05, gpt-5.5-2026-04-23, gpt-5.5-pro, gpt-5.5-pro-2026-04-23, o1-mini, o3-deep-research-2025-06-26, gemini-2.5-flash-native-audio-*, gemini-1.5-pro, gemini-1.5-flash, grok-code-fast-1.
Inferred vs stored discrepancies
No discrepancies found. All models present in both live inventories and model_multipliers.json have matching multipliers.
Proposed Alias Updates
1. Fix sonnet-6x alias to match Copilot dot-notation model IDs
What: Add dot-notation patterns to sonnet-6x so it matches claude-sonnet-4.5 and claude-sonnet-4.6 as served by the Copilot endpoint.
Why: The Copilot /models endpoint currently returns claude-sonnet-4.5 and claude-sonnet-4.6 (dots, no date suffix). The existing patterns copilot/*sonnet-4-5-* and copilot/*sonnet-4-6* use hyphens and would only match claude-sonnet-4-5-<date> variants. Workflows using sonnet-6x on the Copilot engine would fall back to the sonnet alias (which does match) rather than resolving to the intended generation-specific model. Adding dot-notation patterns closes the gap without breaking existing date-suffixed matches from the Anthropic direct provider.
Syntax:
{
"sonnet-6x": [
"copilot/*sonnet-4.5*",
"copilot/*sonnet-4.6*",
"copilot/*sonnet-4-5-*",
"anthropic/*sonnet-4-5-*",
"copilot/*sonnet-4-6*",
"anthropic/*sonnet-4-6*"
]
}
Full Model Lists by Provider
Anthropic (10 models):
claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-20250514, claude-sonnet-4-5-20250929, claude-sonnet-4-6
Copilot (32 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, gemini-2.5-pro, 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-5.2, gpt-5.2-codex, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5, text-embedding-3-small, text-embedding-3-small-inference, text-embedding-ada-002
OpenAI (key text/chat models, 194 total):
gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2, gpt-5.2-codex, gpt-5.2-pro, gpt-5.3-codex, gpt-5.3-codex-api-preview, gpt-5.3-codex-api-preview-preambles, gpt-5.4, gpt-5.4-mini, gpt-5.4-pro, gpt-5.5, gpt-5.5-pro, o1, o1-pro, o3, o3-mini, o3-pro, o3-deep-research, o4-mini, o4-mini-deep-research (plus dated variants)
Gemini (50 models, text/multimodal highlights):
antigravity-preview-05-2026, deep-research-max-preview-04-2026, deep-research-preview-04-2026, deep-research-pro-preview-12-2025, gemini-2.0-flash, gemini-2.0-flash-lite, gemini-2.5-computer-use-preview-10-2025, gemini-2.5-flash, gemini-2.5-flash-image, gemini-2.5-flash-lite, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-image, gemini-3-pro-image-preview, gemini-3-pro-preview, gemini-3.1-flash-image, gemini-3.1-flash-image-preview, gemini-3.1-flash-lite, gemini-3.1-flash-tts-preview, gemini-3.1-pro-preview, gemini-3.5-flash, gemma-4-26b-a4b-it, gemma-4-31b-it, nano-banana-pro-preview (plus image/video/audio generation models)
Notes
billing.multiplier is null for all Copilot endpoint models; the billing docs table was used as the primary multiplier source.
gpt-4.1, gpt-4o, gpt-4o-mini, and gpt-5.4-nano are intentionally excluded per inventory policy (deprecated Copilot-facing IDs).
antigravity-preview-05-2026 and nano-banana-pro-preview are new Gemini models without confirmed billing tiers; they should be added to model_multipliers.json once Google publishes pricing.
- All existing Gemini/OpenAI/Anthropic alias patterns already cover the newly-graduated non-preview model variants (
gemini-3-pro-image, gemini-3.1-flash-image) at the alias level — only the multiplier table needs updates for those.
Generated by 📦 Daily Model Inventory Checker · sonnet46 1.8M · ◷
Summary
Daily model inventory check for 2026-06-01. All major providers returned data. The multiplier table has a few missing entries for new non-preview Gemini model variants and one OpenAI internal preview model. The alias map is largely up to date, but the
sonnet-6xalias has a coverage gap: Copilot serves Claude Sonnet with dot-notation IDs (claude-sonnet-4.5,claude-sonnet-4.6) that the current*sonnet-4-5-*/*sonnet-4-6*dash-hyphenated glob patterns do not match.Provider Model Counts
Raw API Fields Discovered
Anthropic — richest capability metadata:
display_name,created_at,max_input_tokens,max_tokens, and a detailedcapabilitiesmap coveringbatch,citations,code_execution,context_management,effort(low/medium/high/xhigh/max),image_input,pdf_input,structured_outputs, andthinking(with sub-typesenabled/adaptive). No billing/pricing fields exposed.OpenAI — minimal fields in the list endpoint:
id,object,created,owned_by. Capability and pricing data requires the models detail endpoint or documentation. Useful for family grouping viaowned_byand model-ID naming conventions.Gemini — good metadata:
name,version,displayName,description,inputTokenLimit,outputTokenLimit,supportedGenerationMethods,temperature,topP,topK,maxTemperature,thinkingflag. Token limits are useful for tier inference.Copilot (via api-proxy
/models) — richest billing-adjacent data:capabilities.limits(context window, output, prompt limits),capabilities.supports(adaptive_thinking, reasoning_effort, vision, streaming, structured_outputs, tool_calls),model_picker_category(lightweight/versatile/powerful),vendor,version,policy.state. Thebillingfield is present in the schema but returned asnullfor all current models — no ET multiplier data available directly from the endpoint.Token Multiplier Analysis
Billing multipliers are sourced from the official GitHub Copilot docs table (primary, since
billing.multiplieris null for all Copilot endpoint models). All doc-table entries are already correctly reflected inmodel_multipliers.json.Missing from model_multipliers.json
gemini-3-pro-imagegemini-3-pro-image-preview(currently 6.0); production/GA release of the previewgemini-3.1-flash-imagegemini-3.1-flash-image-preview(currently 0.33); production releaseantigravity-preview-05-2026nano-banana-pro-previewgpt-5.3-codex-api-preview-preamblesgpt-5.3-codexfamily (currently 6.0); preambles variantHistorical entries not currently returned
The following model IDs appear in
model_multipliers.jsonbut are absent from all live API inventories. These should remain as historical records:claude-3-5-haiku,claude-3-haiku,claude-3-5-sonnet,claude-3-7-sonnet,claude-3-sonnet,claude-opus-4,claude-opus-4-20250514,claude-opus-4-1,claude-opus-4-1-20250805,claude-3-5-opus,claude-3-opus,claude-sonnet-4,claude-sonnet-4-20250514,gpt-4-turbo,gpt-41-copilot,gpt-4.1-mini,gpt-4.1-nano,gpt-5,gpt-5-2025-08-07,gpt-5-search-api,gpt-5-search-api-2025-10-14,gpt-5-chat-latest,gpt-5-nano,gpt-5-nano-2025-08-07,gpt-5-pro,gpt-5-pro-2025-10-06,gpt-5.1,gpt-5.1-2025-11-13,gpt-5.1-chat-latest,gpt-5-codex,gpt-5.1-codex,gpt-5.1-codex-mini,gpt-5.1-codex-max,gpt-5.1-codex-max-customsummarizer,gpt-5.2-2025-12-11,gpt-5.2-chat-latest,gpt-5.2-pro,gpt-5.2-pro-2025-12-11,gpt-5.3-chat-latest,gpt-5.3-codex-api-preview,gpt-5.4-2026-03-05,gpt-5.4-mini-2026-03-17,gpt-5.4-pro,gpt-5.4-pro-2026-03-05,gpt-5.5-2026-04-23,gpt-5.5-pro,gpt-5.5-pro-2026-04-23,o1-mini,o3-deep-research-2025-06-26,gemini-2.5-flash-native-audio-*,gemini-1.5-pro,gemini-1.5-flash,grok-code-fast-1.Inferred vs stored discrepancies
No discrepancies found. All models present in both live inventories and
model_multipliers.jsonhave matching multipliers.Proposed Alias Updates
1. Fix
sonnet-6xalias to match Copilot dot-notation model IDsWhat: Add dot-notation patterns to
sonnet-6xso it matchesclaude-sonnet-4.5andclaude-sonnet-4.6as served by the Copilot endpoint.Why: The Copilot
/modelsendpoint currently returnsclaude-sonnet-4.5andclaude-sonnet-4.6(dots, no date suffix). The existing patternscopilot/*sonnet-4-5-*andcopilot/*sonnet-4-6*use hyphens and would only matchclaude-sonnet-4-5-<date>variants. Workflows usingsonnet-6xon the Copilot engine would fall back to thesonnetalias (which does match) rather than resolving to the intended generation-specific model. Adding dot-notation patterns closes the gap without breaking existing date-suffixed matches from the Anthropic direct provider.Syntax:
{ "sonnet-6x": [ "copilot/*sonnet-4.5*", "copilot/*sonnet-4.6*", "copilot/*sonnet-4-5-*", "anthropic/*sonnet-4-5-*", "copilot/*sonnet-4-6*", "anthropic/*sonnet-4-6*" ] }Full Model Lists by Provider
Anthropic (10 models):
claude-haiku-4-5-20251001,claude-opus-4-1-20250805,claude-opus-4-20250514,claude-opus-4-5-20251101,claude-opus-4-6,claude-opus-4-7,claude-opus-4-8,claude-sonnet-4-20250514,claude-sonnet-4-5-20250929,claude-sonnet-4-6Copilot (32 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,gemini-2.5-pro,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-5.2,gpt-5.2-codex,gpt-5.3-codex,gpt-5.4,gpt-5.4-mini,gpt-5.4-nano,gpt-5.5,text-embedding-3-small,text-embedding-3-small-inference,text-embedding-ada-002OpenAI (key text/chat models, 194 total):
gpt-4,gpt-4-turbo,gpt-4.1,gpt-4.1-mini,gpt-4.1-nano,gpt-4o,gpt-4o-mini,gpt-5,gpt-5-mini,gpt-5-nano,gpt-5-pro,gpt-5.1,gpt-5.1-codex,gpt-5.1-codex-max,gpt-5.1-codex-mini,gpt-5.2,gpt-5.2-codex,gpt-5.2-pro,gpt-5.3-codex,gpt-5.3-codex-api-preview,gpt-5.3-codex-api-preview-preambles,gpt-5.4,gpt-5.4-mini,gpt-5.4-pro,gpt-5.5,gpt-5.5-pro,o1,o1-pro,o3,o3-mini,o3-pro,o3-deep-research,o4-mini,o4-mini-deep-research(plus dated variants)Gemini (50 models, text/multimodal highlights):
antigravity-preview-05-2026,deep-research-max-preview-04-2026,deep-research-preview-04-2026,deep-research-pro-preview-12-2025,gemini-2.0-flash,gemini-2.0-flash-lite,gemini-2.5-computer-use-preview-10-2025,gemini-2.5-flash,gemini-2.5-flash-image,gemini-2.5-flash-lite,gemini-2.5-pro,gemini-3-flash-preview,gemini-3-pro-image,gemini-3-pro-image-preview,gemini-3-pro-preview,gemini-3.1-flash-image,gemini-3.1-flash-image-preview,gemini-3.1-flash-lite,gemini-3.1-flash-tts-preview,gemini-3.1-pro-preview,gemini-3.5-flash,gemma-4-26b-a4b-it,gemma-4-31b-it,nano-banana-pro-preview(plus image/video/audio generation models)Notes
billing.multiplieris null for all Copilot endpoint models; the billing docs table was used as the primary multiplier source.gpt-4.1,gpt-4o,gpt-4o-mini, andgpt-5.4-nanoare intentionally excluded per inventory policy (deprecated Copilot-facing IDs).antigravity-preview-05-2026andnano-banana-pro-previeware new Gemini models without confirmed billing tiers; they should be added tomodel_multipliers.jsononce Google publishes pricing.gemini-3-pro-image,gemini-3.1-flash-image) at the alias level — only the multiplier table needs updates for those.