.agents/skills/add-model-price/references/model-audit-memory.md
This file is an optional snapshot of the latest automated audit whose per-model results add useful context for a future run. It is orientation only; reconfirm every price and tier against official provider sources before making a change or reporting a row as confirmed.
The audit agent may replace the snapshot below with its complete current table. Keep only one snapshot, never append an unbounded run history, never persist a partial set of checked models, and do not update this file only to refresh the date.
Audit date: 2026-07-13
All prices listed as $X / MTok (per million tokens). Per-token JSON values: divide by 1,000,000.
| Provider | Model / pricing entry | Pricing checked | Price confirmed | Tiering checked | Tiering correct | Change | Official source(s) | Comments |
|---|---|---|---|---|---|---|---|---|
| Anthropic | claude-fable-5 | Input $10/MTok (10e-6), Output $50/MTok (50e-6), 5m cache write $12.5/MTok (12.5e-6), 1h cache write $20/MTok (20e-6), cache read $1/MTok (1e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Confirmed in Long context pricing section. No Large Context tier in file — correct. |
| Anthropic | claude-mythos-5 | Input $10/MTok (10e-6), Output $50/MTok (50e-6), 5m cache write $12.5/MTok (12.5e-6), 1h cache write $20/MTok (20e-6), cache read $1/MTok (1e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Limited availability (Project Glasswing). Same prices as Fable 5. Claude Mythos Preview also listed in flat-context list but has no pricing row and no selectable model entry; no changes needed. |
| Anthropic | claude-opus-4-8 | Input $5/MTok (5e-6), Output $25/MTok (25e-6), 5m cache write $6.25/MTok (6.25e-6), 1h cache write $10/MTok (10e-6), cache read $0.5/MTok (0.5e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Fast mode available at $10/$50 per input/output MTok (additional SKU, not in pricing file). |
| Anthropic | claude-opus-4-7 | Input $5/MTok (5e-6), Output $25/MTok (25e-6), 5m cache write $6.25/MTok (6.25e-6), 1h cache write $10/MTok (10e-6), cache read $0.5/MTok (0.5e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Fast mode deprecated July 24 2026. |
| Anthropic | claude-opus-4-6 | Input $5/MTok (5e-6), Output $25/MTok (25e-6), 5m cache write $6.25/MTok (6.25e-6), 1h cache write $10/MTok (10e-6), cache read $0.5/MTok (0.5e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | inference_geo: "us" adds 1.1x multiplier for this and later models. |
| Anthropic | claude-opus-4-5-20251101 | Input $5/MTok (5e-6), Output $25/MTok (25e-6), 5m cache write $6.25/MTok (6.25e-6), 1h cache write $10/MTok (10e-6), cache read $0.5/MTok (0.5e-6) | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Listed as "Claude Opus 4.5" on pricing page. File uses dated ID claude-opus-4-5-20251101. |
| Anthropic | claude-opus-4-1-20250805 | Input $15/MTok (15e-6), Output $75/MTok (75e-6), 5m cache write $18.75/MTok, 1h cache write $30/MTok, cache read $1.5/MTok | Yes | No tiering — deprecated model | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Deprecated. Retained for backward pricing compatibility. |
| Anthropic | claude-opus-4-20250514 | Input $15/MTok (15e-6), Output $75/MTok (75e-6), 5m cache write $18.75/MTok, 1h cache write $30/MTok, cache read $1.5/MTok | Yes | No tiering — retired model | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Retired except on Google Cloud. |
| Anthropic | claude-sonnet-5 | Input $2/MTok (2e-6), Output $10/MTok (10e-6), 5m cache write $2.5/MTok, 1h cache write $4/MTok, cache read $0.2/MTok | Yes | Flat 1M context at standard pricing — no large-context tier; introductory prices through August 31 2026 | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Introductory pricing in effect through Aug 31 2026. Standard pricing from Sep 1 2026: $3/$15, cache $3.75/$6/$0.30. File must be updated after Aug 31 2026. |
| Anthropic | claude-sonnet-4-6 | Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTok | Yes | Flat 1M context at standard pricing — no large-context tier | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Confirmed flat list (no Large Context tier). |
| Anthropic | claude-sonnet-4-5-20250929 | Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTok | Yes | Large Context tier active for >200K input tokens at 2× input / 1.5× output | No | None | https://platform.claude.com/docs/en/about-claude/pricing | Sonnet 4.5 is NOT on the flat list; Large Context tier is retained. Official page does not explicitly state >200K tier pricing for Sonnet 4.5; tier was set when model was added. |
| Anthropic | claude-sonnet-4-20250514 | Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTok | Yes | No tiering — retired model | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Retired except on Bedrock and Google Cloud. |
| Anthropic | claude-haiku-4-5-20251001 | Input $1/MTok (1e-6), Output $5/MTok (5e-6), 5m cache write $1.25/MTok, 1h cache write $2/MTok, cache read $0.1/MTok | Yes | No large-context tier noted — Haiku 4.5 not on flat list | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Haiku 4.5 is NOT on the flat list. No Large Context tier in file — consistent with not being on list. |
| Anthropic | claude-3-5-haiku-20241022 | Input $0.8/MTok (8e-7), Output $4/MTok (4e-6), 5m cache write $1/MTok, 1h cache write $1.6/MTok, cache read $0.08/MTok | Yes | No tiering — retired model | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Retired except on Bedrock and Google Cloud. |
| Anthropic | claude-3.7-sonnet-20250219 | Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTok | No | No tiering visible | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Not listed on current official pricing page. File retains previously set prices. |
| Anthropic | claude-3.5-sonnet-20241022 | Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTok | No | No tiering visible | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Not listed on current official pricing page. |
| Anthropic | claude-3-5-sonnet-20240620 | Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTok | No | No tiering visible | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Not listed on current official pricing page. |
| Anthropic | claude-3-opus-20240229 | Input $15/MTok, Output $75/MTok | No | No tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Legacy. Not on current pricing page. |
| Anthropic | claude-3-sonnet-20240229 | Input $3/MTok, Output $15/MTok, cache set | No | No tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Legacy. Not on current pricing page. |
| Anthropic | claude-3-haiku-20240307 | Input $0.25/MTok, Output $1.25/MTok | No | No tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Legacy. Not on current pricing page. |
| OpenAI | gpt-5.6-sol | Input $5/MTok (5e-6), Cached input $0.5/MTok (0.5e-6), Output $30/MTok (30e-6) | Yes | Large Context (>272K tokens): input $10/MTok (10e-6), cached $1/MTok, output $45/MTok (45e-6) | Yes | None | https://developers.openai.com/api/docs/pricing | Reasoning model. 272K threshold unique to gpt-5.6 family. |
| OpenAI | gpt-5.6-terra | Input $2.5/MTok (2.5e-6), Cached input $0.25/MTok (0.25e-6), Output $15/MTok (15e-6) | Yes | Large Context (>272K tokens): input $5/MTok, cached $0.5/MTok, output $22.5/MTok | Yes | None | https://developers.openai.com/api/docs/pricing | Reasoning model. |
| OpenAI | gpt-5.6-luna | Input $1/MTok (1e-6), Cached input $0.1/MTok (0.1e-6), Output $6/MTok (6e-6) | Yes | Large Context (>272K tokens): input $2/MTok, cached $0.2/MTok, output $9/MTok | Yes | None | https://developers.openai.com/api/docs/pricing | Reasoning model. |
| OpenAI | gpt-5.5-2026-04-23 (also matches gpt-5.5) | Input $5/MTok (5e-6), Cached input $0.5/MTok (0.5e-6), Output $30/MTok (30e-6) | Yes | No large-context tier in file; page mentions long context with doubled rates but threshold not confirmed this run | No | None | https://developers.openai.com/api/docs/pricing | Reasoning model. Single pricing entry covers both gpt-5.5 and gpt-5.5-2026-04-23 via matchPattern. |
| OpenAI | gpt-5.5-pro-2026-04-23 (also matches gpt-5.5-pro) | Input $30/MTok (30e-6), Output $180/MTok (180e-6); no cache | Yes | No tiering in file | Not applicable | None | https://developers.openai.com/api/docs/pricing | Reasoning model; no cached input pricing. |
| OpenAI | gpt-5.4 | Input $2.5/MTok (2.5e-6), Cached input $0.25/MTok (0.25e-6), Output $15/MTok (15e-6) | Yes | No large-context tier in file; page mentions long context but threshold not confirmed | No | None | https://developers.openai.com/api/docs/pricing | Reasoning model. |
| OpenAI | gpt-5.4-2026-03-05 | Input $2.5/MTok, Cached $0.25/MTok, Output $15/MTok | Yes | No tiering | Not applicable | None | https://developers.openai.com/api/docs/pricing | Dated snapshot for gpt-5.4. |
| OpenAI | gpt-5.4-pro | Input $30/MTok (30e-6), Output $180/MTok (180e-6); no cache | Yes | No tiering in file | Not applicable | None | https://developers.openai.com/api/docs/pricing | Reasoning model; no cached input pricing. |
| OpenAI | gpt-5.4-mini | Input $0.75/MTok (0.75e-6), Cached $0.075/MTok (0.075e-6), Output $4.5/MTok (4.5e-6) | Yes | No tiering | Not applicable | None | https://developers.openai.com/api/docs/pricing | Non-reasoning model. |
| OpenAI | gpt-5.4-nano | Input $0.2/MTok (0.2e-6), Cached $0.02/MTok (0.02e-6), Output $1.25/MTok (1.25e-6) | Yes | No tiering | Not applicable | None | https://developers.openai.com/api/docs/pricing | Non-reasoning model. |
| OpenAI | gpt-5-chat-latest | Input $1.25/MTok in file; pricing page mentions "chat-latest: $5/$30" | No | No tiering | Not applicable | Unresolved | https://developers.openai.com/api/docs/pricing | WebFetch summary mentioned "chat-latest: $5/$30" — possible price change or confusion with gpt-5.6-sol pricing. Leaving unchanged pending direct verification. Verify this alias before next update. |
| OpenAI | gpt-5.3-codex | Not in pricing file; pricing page shows ~$1.75/$14/MTok | No | Unknown | Not applicable | Unresolved | https://developers.openai.com/api/docs/models/all | Confirmed in OpenAI models list but absent from selectable models and pricing file. Matches gpt-5.2 prices. Appears to be a coding-specific variant; not adding without selectable-model registration and official pricing page confirmation. |
| gemini-2.5-flash | Input $0.30/MTok (3e-7), Audio input $1/MTok (1e-6), Output $2.5/MTok (2.5e-6), Cache read $0.03/MTok (3e-8) | Yes | No large-context tier; single tier confirmed | Yes | None | https://ai.google.dev/pricing | Cache read = 10% of standard input ($0.03/$0.30). Confirmed. | |
| gemini-2.5-flash-lite | Input $0.10/MTok (1e-7), Audio input $0.30/MTok (3e-7), Output $0.40/MTok (4e-7), Cache read $0.01/MTok (1e-8) | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Cache read = 10% of input. Confirmed. | |
| gemini-2.5-pro | Input $1.25/MTok (1.25e-6) ≤200K, Output $10/MTok (10e-6) ≤200K; Cache read $0.125/MTok (0.125e-6) | Yes | Large Context (>200K): input $2.5/MTok (2.5e-6), output $15/MTok (15e-6), cache read $0.25/MTok | Yes | None | https://ai.google.dev/pricing | Two tiers confirmed. Cache = 10% of input at each tier. | |
| gemini-3.5-flash | Input $1.5/MTok (1.5e-6), Output $9/MTok (9e-6), Cache read $0.15/MTok (0.15e-6) | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Cache = 10% of input. Confirmed on AI Studio page. | |
| gemini-3.1-flash-lite | Input $0.25/MTok (0.25e-6), Audio $0.50/MTok (0.5e-6), Output $1.5/MTok (1.5e-6), Cache read $0.025/MTok (0.025e-6) | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Cache = 10% of text input. Confirmed on AI Studio page. | |
| gemini-3.1-flash-lite-preview | Input $0.25/MTok, Output $1.5/MTok (same as GA) | No | No large-context tier | Not applicable | None | https://ai.google.dev/pricing | Preview variant; same prices as GA version in file; not separately listed on official page. | |
| gemini-3.1-pro-preview | Input $2/MTok (2e-6) ≤200K, Output $12/MTok (12e-6) ≤200K; Large Context >200K: input $4/MTok (4e-6), output $18/MTok (18e-6) | Yes | Large Context (>200K) at 2× input / 1.5× output confirmed | Yes | None | https://ai.google.dev/pricing | Two tiers confirmed on AI Studio page. | |
| gemini-3-flash-preview | Input $0.5/MTok (0.5e-6), Audio $1/MTok, Output $3/MTok (3e-6), Cache read $0.05/MTok (0.05e-6) | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Confirmed on AI Studio page. | |
| gemini-3-pro-preview | Input $2/MTok (2e-6) ≤200K, $4/MTok >200K; Output $12/MTok ≤200K, $18/MTok >200K | No | Large Context (>200K) set in file | Not applicable | None | https://ai.google.dev/pricing | Not listed on current AI Studio pricing page; existing prices retained per reference notes. Do not update without explicit official evidence. | |
| gemini-2.0-flash | Input $0.10/MTok (1e-7), Output $0.40/MTok (4e-7) in file | No | No tiering | Not applicable | None | https://ai.google.dev/pricing | Not listed on current AI Studio pricing page per June 2026 reference note. Existing prices retained. | |
| gemini-2.0-flash-001 | Same as gemini-2.0-flash | No | No tiering | Not applicable | None | https://ai.google.dev/pricing | Not listed on current AI Studio pricing page. Existing prices retained. |
gpt-5-chat-latest pricing — WebFetch summary of the OpenAI pricing page mentioned "chat-latest: $5.00 / $30.00" while the existing file entry has $1.25/$10 MTok. Could indicate a price change for this alias or could be a WebFetch artifact confusing it with gpt-5.6-sol ($5/$30). Needs a dedicated fetch to https://developers.openai.com/api/docs/models/gpt-5-chat-latest or the pricing page to confirm.
gpt-5.3-codex — OpenAI model list confirms this model exists. The pricing page summary attributes $1.75/$14 MTok to it, matching gpt-5.2 prices. Not in the selectable models list (openAIModels in types.ts) and appears to be a coding-specific variant, not a general chat model. Do not add to pricing file until it appears in the selectable models list or explicit official pricing page evidence is available.
gpt-5.5 / gpt-5.4 large-context tiers — The OpenAI pricing page mentions these models "offer extended context with doubled input/output rates" but this audit could not confirm the exact tier threshold (possibly 200K like other models). No Large Context tiers exist in the file for these models. Future audits should verify whether a 200K-threshold Large Context tier should be added.
claude-sonnet-4-5-20250929 Large Context tier — The file has a Large Context (>200K) tier for this model. The official Anthropic page does not explicitly publish per-tier pricing for this model separately. The tier was set when the model was first added. Future audits should verify whether Anthropic publishes explicit tier pricing.