πͺ’ Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
TypeScript analyticsautogenevaluationlangchainlarge-language-modelsllama-indexllmllm-evaluationllm-observabilityllmopsmonitoringobservabilityopen-sourceopenaiplaygroundprompt-engineeringprompt-managementself-hostedycombinator
chore(pricing): add Claude Sonnet 5.5 default pricing (#18023)
langfuse-botd59f50ea3636
diff --git a/.agents/skills/add-model-price/references/model-audit-memory.md b/.agents/skills/add-model-price/references/model-audit-memory.mdindex e14f1757a7..b6c277fb19 100644--- a/.agents/skills/add-model-price/references/model-audit-memory.md+++ b/.agents/skills/add-model-price/references/model-audit-memory.md@@ -12,11 +12,23 @@ audit date.## Latest useful snapshot-**Audit date:** 2026-09-22+**Audit date:** 2026-09-29All prices listed as `$X / MTok` (per million tokens). Per-token JSON values: divide by 1,000,000.-The 2026-09-22 run re-fetched the full Anthropic pricing page, the Anthropic+The 2026-09-29 run re-fetched the full Anthropic pricing page (model table,+cache-hits footnote, Fast mode and Batch tables), the Anthropic models-overview+comparison table, the OpenAI aggregate Standard/Fast-mode/Flex pricing summary,+the full OpenAI model catalog, a dedicated re-fetch of `gpt-5-chat-latest`'s own+model page, and both Gemini pricing pages (3.x and 2.5 families) plus the+Gemini models catalog. This run found one new model, released the day before+the audit: **Claude Sonnet 5.5** (`claude-sonnet-5-5`), Anthropic's new+Sonnet-tier flagship (Sonnet 5 demoted to legacy), priced identically to+`claude-sonnet-5` ($2/$10 input/output, standard 0.1x cache-read multiplier, no+Fast mode, flat 1M context) β see `provider-sources-and-price-keys.md`'s+"September 29 2026" entry for full detail. Every other price checked this run β+including every existing Anthropic, OpenAI, and Gemini row below β matched+verbatim. The 2026-09-22 run before it re-fetched the full Anthropic pricing page, the Anthropicmodels-overview comparison table, the OpenAI aggregate Standard/Batch/Flex/Fast-modepricing tables plus the full model catalog, and both Gemini pricing pages (3.x and2.5 families) plus the Gemini models catalog, with a follow-up verbatim-quote fetch@@ -78,7 +90,8 @@ to have siblings `gpt-5.5-cyber`/`gpt-5.4-cyber`, see provider-sources-and-price| Anthropic | claude-opus-4-5-20251101 | Same as Opus 5 | Yes | Single Standard tier in file (no separate Large Context tier); page wording on the 1M-flat-context list is ambiguous for 4.5 specifically but the main pricing table shows no separate rate, so the file's single-tier treatment is correct either way | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged. || Anthropic | claude-opus-4-1-20250805 | Input $15/MTok, Output $75/MTok, 5m $18.75/MTok, 1h $30/MTok, read $1.50/MTok | Yes | Deprecated β no tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing https://platform.claude.com/docs/en/about-claude/model-deprecations | Still "retired, except on Bedrock and Google Cloud"; deprecations page now shows a firm retirement date of August 5, 2026 (previously open-ended). || Anthropic | claude-opus-4-20250514 | Input $15/MTok, Output $75/MTok, 5m $18.75/MTok, 1h $30/MTok, read $1.50/MTok | Yes | Retired except Google Cloud β no tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing https://platform.claude.com/docs/en/about-claude/model-deprecations | Re-confirmed present; deprecations page shows firm retirement date June 15, 2026. |-| Anthropic | claude-sonnet-5 | Input $2/MTok, Output $10/MTok; 5m $2.50/MTok, 1h $4/MTok, read $0.20/MTok | Yes | Flat 1M context; permanent pricing (no Sep 1 2026 increase) | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged; the $2/$10 permanent-pricing note is still on the page verbatim. |+| Anthropic | claude-sonnet-5 | Input $2/MTok, Output $10/MTok; 5m $2.50/MTok, 1h $4/MTok, read $0.20/MTok | Yes | Flat 1M context; permanent pricing (no Sep 1 2026 increase) | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged; the $2/$10 permanent-pricing note is still on the page verbatim. Now "legacy (still available)" behind Sonnet 5.5. |+| Anthropic | claude-sonnet-5-5 | Input $2/MTok, Output $10/MTok; 5m $2.50/MTok, 1h $4/MTok, read $0.20/MTok (standard 0.1x multiplier) | Yes | Flat 1M context; no Fast mode (only Opus 5.5/5/4.8 have it) | Yes | Added | https://platform.claude.com/docs/en/about-claude/pricing https://platform.claude.com/docs/en/models/overview https://platform.claude.com/docs/en/models/sonnet-5-5/overview | New model, released 2026-09-28, now the current Sonnet-tier flagship (Sonnet 5 demoted to legacy). Pricing numerically identical to claude-sonnet-5. matchPattern mirrors claude-sonnet-5 with a `-5` suffix, verified not to collide with it via the match-pattern tester. || Anthropic | claude-sonnet-4-6 | Input $3/MTok, Output $15/MTok, 5m $3.75/MTok, 1h $6/MTok, read $0.30/MTok | Yes | Flat 1M context | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged. || Anthropic | claude-sonnet-4-5-20250929 | Input $3/MTok, Output $15/MTok, 5m $3.75/MTok, 1h $6/MTok, read $0.30/MTok | Yes | No large-context tier (200k hard cap) | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged. || Anthropic | claude-sonnet-4-20250514 | Input $3/MTok, Output $15/MTok, 5m $3.75/MTok, 1h $6/MTok, read $0.30/MTok | Yes | Retired except Bedrock/Google Cloud β no tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed present on current page's main table, unchanged. |diff --git a/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md b/.agents/skills/add-model-price/references/provider-sources-and-price-keys.mdindex 90ec55ec68..2626766cd9 100644--- a/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md+++ b/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md@@ -340,6 +340,33 @@ file and `openAIModels`in July 27 2026 audit. Official sources:`https://developeapplying it to the bare (non-`ft:`) entry β a summarizer can silently pick either tablewhen both rows share the same model name.+- **Claude Sonnet 5.5 (added September 29 2026)** β Anthropic released+ `claude-sonnet-5-5` on September 28, 2026 ("Latest"), confirmed via+ `https://platform.claude.com/docs/en/about-claude/pricing`,+ `https://platform.claude.com/docs/en/models/overview`, and its dedicated+ model page `https://platform.claude.com/docs/en/models/sonnet-5-5/overview`.+ It supersedes `claude-sonnet-5` as the current Sonnet-tier model (Sonnet 5+ moved to "Legacy models (still available)"). API ID / alias / Bedrock ID /+ Google Cloud ID / Microsoft Foundry ID / Claude Platform on AWS ID are all+ the dateless `claude-sonnet-5-5` / `anthropic.claude-sonnet-5-5` pattern.+ Pricing is numerically identical to `claude-sonnet-5`: $2/MTok input,+ $10/MTok output, 5m cache write $2.50/MTok, 1h cache write $4/MTok, cache+ read $0.20/MTok (standard 0.1x multiplier β the pricing page's cache-hits+ footnote only lists Fable 5.1/Mythos 5.1 at 0.025x and Opus 5.5 at 0.05x as+ non-standard, so Sonnet 5.5 is not an exception). On the flat 1M-context+ list (1M context window, 128K max output, no Large Context tier) since it is+ a Claude 4.6-or-later-generation model. **No Fast mode**: the Fast mode+ pricing table lists only Claude Opus 5.5, Claude Opus 5, and Claude Opus+ 4.8 β no Sonnet or Haiku model has ever had a Fast-mode tier. Batch is+ $1/$5 (50% of standard, matching `claude-sonnet-5`'s Batch row exactly) but,+ per existing precedent, no Batch tier was added (no Anthropic model in this+ file has one). Added to the pricing file mirroring `claude-sonnet-5`'s exact+ key set and to `anthropicModels` in `types.ts` immediately after+ `claude-sonnet-5`, not as the first entry. matchPattern:+ `(?i)^((anthropic\/)?claude-sonnet-5-5|(eu\.|us\.|apac\.|au\.|jp\.|global\.)?anthropic\.claude-sonnet-5-5(-v1(:0)?)?)$`+ β verified via the bundled match-pattern tester that this does not collide+ with `claude-sonnet-5`'s pattern (both fully anchored with `^...$`, mirroring+ the `claude-opus-5` / `claude-opus-5-5` precedent).- **Premium speed-tier pricing (`service_tier`/`speed`) is documented for far moremodels than the initial rollout covered (implemented 2026-08-20)** β The`model_parameters` tier-condition mechanism landed in PR #16204 (2026-08-18) and was@@ -785,6 +812,27 @@ file and `openAIModels`in July 27 2026 audit. Official sources:`https://developeBedrock Public Extended Access SKU, and the legacy Claude 3.x/Gemini 1.xcatalog tail were not re-checked this run β no new evidence, standingexclusions.+- **September 29 2026 audit: Claude Sonnet 5.5 added, released the day before+ this run; everything else confirmed unchanged** β Re-fetched the full+ Anthropic pricing page (model table, cache-hits footnote, Fast mode and+ Batch tables), the Anthropic models-overview comparison table, the dedicated+ `claude-sonnet-5-5` model page, the OpenAI aggregate Standard/Fast-mode/Flex+ pricing summary, the full OpenAI model catalog, the dedicated+ `gpt-5-chat-latest` model page ($1.25/$0.125/$10, 128K context, no+ large-context tier β unchanged), both Gemini pricing pages (3.x and 2.5+ families, explicit Free/Paid column separation), and the Gemini models+ catalog. Every price already in the file β including every+ `gpt-6-astra`/`gpt-6-sol`/`gpt-6-luna`, `claude-opus-5-5`, and+ `gemini-3.6/3.7/3.8-flash` tier β matched verbatim; the only drift was the+ new Sonnet 5.5 model (see its own dedicated entry above). No further new+ general-purpose text/chat models were found: the Gemini models catalog's new+ entries this run (`gemini-3.8-live-extended-thinking`, another+ `gemini-omni-1.1-flash`/`lyria-3.5` mention, more robotics variants) are all+ Live/voice, video, or robotics endpoints, consistent with the existing+ modality-specific skip rule. The Daybreak cyber/Rosalind restricted family,+ the AWS Bedrock Public Extended Access SKU, and the legacy Claude+ 3.x/Gemini 1.x catalog tail were not re-checked this run β no new evidence,+ standing exclusions.Capture:diff --git a/packages/shared/src/server/llm/types.ts b/packages/shared/src/server/llm/types.tsindex 76391febbf..01b22603dd 100644--- a/packages/shared/src/server/llm/types.ts+++ b/packages/shared/src/server/llm/types.ts@@ -395,6 +395,7 @@ export type OpenAIModel = (typeof openAIModels)[number];export const anthropicModels = ["claude-sonnet-4-5-20250929","claude-sonnet-5",+ "claude-sonnet-5-5","claude-fable-5","claude-fable-5-1","claude-mythos-5",diff --git a/worker/src/constants/default-model-prices.json b/worker/src/constants/default-model-prices.jsonindex 0e5fc19bc5..8b88ba4e62 100644--- a/worker/src/constants/default-model-prices.json+++ b/worker/src/constants/default-model-prices.json@@ -4680,6 +4680,37 @@}]},+ {+ "id": "daf8fbc2-52d3-4782-9dd0-b34d56046703",+ "modelName": "claude-sonnet-5-5",+ "matchPattern": "(?i)^((anthropic\\/)?claude-sonnet-5-5|(eu\\.|us\\.|apac\\.|au\\.|jp\\.|global\\.)?anthropic\\.claude-sonnet-5-5(-v1(:0)?)?)$",+ "createdAt": "2026-09-29T00:00:00.000Z",+ "updatedAt": "2026-09-29T00:00:00.000Z",+ "tokenizerConfig": null,+ "tokenizerId": "claude",+ "pricingTiers": [+ {+ "id": "daf8fbc2-52d3-4782-9dd0-b34d56046703_tier_default",+ "name": "Standard",+ "isDefault": true,+ "priority": 0,+ "conditions": [],+ "prices": {+ "input": 2e-6,+ "input_tokens": 2e-6,+ "output": 10e-6,+ "output_tokens": 10e-6,+ "cache_creation_input_tokens": 2.5e-6,+ "input_cache_creation": 2.5e-6,+ "input_cache_creation_5m": 2.5e-6,+ "input_cache_creation_1h": 4e-6,+ "cache_read_input_tokens": 2e-7,+ "input_cached_tokens": 2e-7,+ "input_cache_read": 2e-7+ }+ }+ ]+ },{"id": "a5b2c3d4-e5f6-4789-8abc-def012345678","modelName": "claude-opus-5",