Back to Langfuse

Model Price Audit Memory

.agents/skills/add-model-price/references/model-audit-memory.md

3.213.016.0 KB
Original Source

Model Price Audit Memory

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.

Latest useful snapshot

Audit date: 2026-07-13

All prices listed as $X / MTok (per million tokens). Per-token JSON values: divide by 1,000,000.

ProviderModel / pricing entryPricing checkedPrice confirmedTiering checkedTiering correctChangeOfficial source(s)Comments
Anthropicclaude-fable-5Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingConfirmed in Long context pricing section. No Large Context tier in file — correct.
Anthropicclaude-mythos-5Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingLimited 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.
Anthropicclaude-opus-4-8Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingFast mode available at $10/$50 per input/output MTok (additional SKU, not in pricing file).
Anthropicclaude-opus-4-7Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingFast mode deprecated July 24 2026.
Anthropicclaude-opus-4-6Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricinginference_geo: "us" adds 1.1x multiplier for this and later models.
Anthropicclaude-opus-4-5-20251101Input $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)YesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingListed as "Claude Opus 4.5" on pricing page. File uses dated ID claude-opus-4-5-20251101.
Anthropicclaude-opus-4-1-20250805Input $15/MTok (15e-6), Output $75/MTok (75e-6), 5m cache write $18.75/MTok, 1h cache write $30/MTok, cache read $1.5/MTokYesNo tiering — deprecated modelNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingDeprecated. Retained for backward pricing compatibility.
Anthropicclaude-opus-4-20250514Input $15/MTok (15e-6), Output $75/MTok (75e-6), 5m cache write $18.75/MTok, 1h cache write $30/MTok, cache read $1.5/MTokYesNo tiering — retired modelNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingRetired except on Google Cloud.
Anthropicclaude-sonnet-5Input $2/MTok (2e-6), Output $10/MTok (10e-6), 5m cache write $2.5/MTok, 1h cache write $4/MTok, cache read $0.2/MTokYesFlat 1M context at standard pricing — no large-context tier; introductory prices through August 31 2026YesNonehttps://platform.claude.com/docs/en/about-claude/pricingIntroductory 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.
Anthropicclaude-sonnet-4-6Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTokYesFlat 1M context at standard pricing — no large-context tierYesNonehttps://platform.claude.com/docs/en/about-claude/pricingConfirmed flat list (no Large Context tier).
Anthropicclaude-sonnet-4-5-20250929Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTokYesLarge Context tier active for >200K input tokens at 2× input / 1.5× outputNoNonehttps://platform.claude.com/docs/en/about-claude/pricingSonnet 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.
Anthropicclaude-sonnet-4-20250514Input $3/MTok (3e-6), Output $15/MTok (15e-6), 5m cache write $3.75/MTok, 1h cache write $6/MTok, cache read $0.3/MTokYesNo tiering — retired modelNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingRetired except on Bedrock and Google Cloud.
Anthropicclaude-haiku-4-5-20251001Input $1/MTok (1e-6), Output $5/MTok (5e-6), 5m cache write $1.25/MTok, 1h cache write $2/MTok, cache read $0.1/MTokYesNo large-context tier noted — Haiku 4.5 not on flat listNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingHaiku 4.5 is NOT on the flat list. No Large Context tier in file — consistent with not being on list.
Anthropicclaude-3-5-haiku-20241022Input $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/MTokYesNo tiering — retired modelNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingRetired except on Bedrock and Google Cloud.
Anthropicclaude-3.7-sonnet-20250219Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTokNoNo tiering visibleNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingNot listed on current official pricing page. File retains previously set prices.
Anthropicclaude-3.5-sonnet-20241022Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTokNoNo tiering visibleNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingNot listed on current official pricing page.
Anthropicclaude-3-5-sonnet-20240620Input $3/MTok, Output $15/MTok, cache $3.75/$6/$0.3 per MTokNoNo tiering visibleNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingNot listed on current official pricing page.
Anthropicclaude-3-opus-20240229Input $15/MTok, Output $75/MTokNoNo tieringNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingLegacy. Not on current pricing page.
Anthropicclaude-3-sonnet-20240229Input $3/MTok, Output $15/MTok, cache setNoNo tieringNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingLegacy. Not on current pricing page.
Anthropicclaude-3-haiku-20240307Input $0.25/MTok, Output $1.25/MTokNoNo tieringNot applicableNonehttps://platform.claude.com/docs/en/about-claude/pricingLegacy. Not on current pricing page.
OpenAIgpt-5.6-solInput $5/MTok (5e-6), Cached input $0.5/MTok (0.5e-6), Output $30/MTok (30e-6)YesLarge Context (>272K tokens): input $10/MTok (10e-6), cached $1/MTok, output $45/MTok (45e-6)YesNonehttps://developers.openai.com/api/docs/pricingReasoning model. 272K threshold unique to gpt-5.6 family.
OpenAIgpt-5.6-terraInput $2.5/MTok (2.5e-6), Cached input $0.25/MTok (0.25e-6), Output $15/MTok (15e-6)YesLarge Context (>272K tokens): input $5/MTok, cached $0.5/MTok, output $22.5/MTokYesNonehttps://developers.openai.com/api/docs/pricingReasoning model.
OpenAIgpt-5.6-lunaInput $1/MTok (1e-6), Cached input $0.1/MTok (0.1e-6), Output $6/MTok (6e-6)YesLarge Context (>272K tokens): input $2/MTok, cached $0.2/MTok, output $9/MTokYesNonehttps://developers.openai.com/api/docs/pricingReasoning model.
OpenAIgpt-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)YesNo large-context tier in file; page mentions long context with doubled rates but threshold not confirmed this runNoNonehttps://developers.openai.com/api/docs/pricingReasoning model. Single pricing entry covers both gpt-5.5 and gpt-5.5-2026-04-23 via matchPattern.
OpenAIgpt-5.5-pro-2026-04-23 (also matches gpt-5.5-pro)Input $30/MTok (30e-6), Output $180/MTok (180e-6); no cacheYesNo tiering in fileNot applicableNonehttps://developers.openai.com/api/docs/pricingReasoning model; no cached input pricing.
OpenAIgpt-5.4Input $2.5/MTok (2.5e-6), Cached input $0.25/MTok (0.25e-6), Output $15/MTok (15e-6)YesNo large-context tier in file; page mentions long context but threshold not confirmedNoNonehttps://developers.openai.com/api/docs/pricingReasoning model.
OpenAIgpt-5.4-2026-03-05Input $2.5/MTok, Cached $0.25/MTok, Output $15/MTokYesNo tieringNot applicableNonehttps://developers.openai.com/api/docs/pricingDated snapshot for gpt-5.4.
OpenAIgpt-5.4-proInput $30/MTok (30e-6), Output $180/MTok (180e-6); no cacheYesNo tiering in fileNot applicableNonehttps://developers.openai.com/api/docs/pricingReasoning model; no cached input pricing.
OpenAIgpt-5.4-miniInput $0.75/MTok (0.75e-6), Cached $0.075/MTok (0.075e-6), Output $4.5/MTok (4.5e-6)YesNo tieringNot applicableNonehttps://developers.openai.com/api/docs/pricingNon-reasoning model.
OpenAIgpt-5.4-nanoInput $0.2/MTok (0.2e-6), Cached $0.02/MTok (0.02e-6), Output $1.25/MTok (1.25e-6)YesNo tieringNot applicableNonehttps://developers.openai.com/api/docs/pricingNon-reasoning model.
OpenAIgpt-5-chat-latestInput $1.25/MTok in file; pricing page mentions "chat-latest: $5/$30"NoNo tieringNot applicableUnresolvedhttps://developers.openai.com/api/docs/pricingWebFetch 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.
OpenAIgpt-5.3-codexNot in pricing file; pricing page shows ~$1.75/$14/MTokNoUnknownNot applicableUnresolvedhttps://developers.openai.com/api/docs/models/allConfirmed 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.
Googlegemini-2.5-flashInput $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)YesNo large-context tier; single tier confirmedYesNonehttps://ai.google.dev/pricingCache read = 10% of standard input ($0.03/$0.30). Confirmed.
Googlegemini-2.5-flash-liteInput $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)YesNo large-context tierYesNonehttps://ai.google.dev/pricingCache read = 10% of input. Confirmed.
Googlegemini-2.5-proInput $1.25/MTok (1.25e-6) ≤200K, Output $10/MTok (10e-6) ≤200K; Cache read $0.125/MTok (0.125e-6)YesLarge Context (>200K): input $2.5/MTok (2.5e-6), output $15/MTok (15e-6), cache read $0.25/MTokYesNonehttps://ai.google.dev/pricingTwo tiers confirmed. Cache = 10% of input at each tier.
Googlegemini-3.5-flashInput $1.5/MTok (1.5e-6), Output $9/MTok (9e-6), Cache read $0.15/MTok (0.15e-6)YesNo large-context tierYesNonehttps://ai.google.dev/pricingCache = 10% of input. Confirmed on AI Studio page.
Googlegemini-3.1-flash-liteInput $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)YesNo large-context tierYesNonehttps://ai.google.dev/pricingCache = 10% of text input. Confirmed on AI Studio page.
Googlegemini-3.1-flash-lite-previewInput $0.25/MTok, Output $1.5/MTok (same as GA)NoNo large-context tierNot applicableNonehttps://ai.google.dev/pricingPreview variant; same prices as GA version in file; not separately listed on official page.
Googlegemini-3.1-pro-previewInput $2/MTok (2e-6) ≤200K, Output $12/MTok (12e-6) ≤200K; Large Context >200K: input $4/MTok (4e-6), output $18/MTok (18e-6)YesLarge Context (>200K) at 2× input / 1.5× output confirmedYesNonehttps://ai.google.dev/pricingTwo tiers confirmed on AI Studio page.
Googlegemini-3-flash-previewInput $0.5/MTok (0.5e-6), Audio $1/MTok, Output $3/MTok (3e-6), Cache read $0.05/MTok (0.05e-6)YesNo large-context tierYesNonehttps://ai.google.dev/pricingConfirmed on AI Studio page.
Googlegemini-3-pro-previewInput $2/MTok (2e-6) ≤200K, $4/MTok >200K; Output $12/MTok ≤200K, $18/MTok >200KNoLarge Context (>200K) set in fileNot applicableNonehttps://ai.google.dev/pricingNot listed on current AI Studio pricing page; existing prices retained per reference notes. Do not update without explicit official evidence.
Googlegemini-2.0-flashInput $0.10/MTok (1e-7), Output $0.40/MTok (4e-7) in fileNoNo tieringNot applicableNonehttps://ai.google.dev/pricingNot listed on current AI Studio pricing page per June 2026 reference note. Existing prices retained.
Googlegemini-2.0-flash-001Same as gemini-2.0-flashNoNo tieringNot applicableNonehttps://ai.google.dev/pricingNot listed on current AI Studio pricing page. Existing prices retained.

Unresolved findings from 2026-07-13 audit

  1. 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.

  2. 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.

  3. 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.

  4. 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.