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 gemini-3.7-flash, cut gemini-3.6-flash intro pricing (#16015)
langfuse-bot65a86cb8565c
diff --git a/.agents/skills/add-model-price/references/model-audit-memory.md b/.agents/skills/add-model-price/references/model-audit-memory.mdindex cc063d80aa..1fcbce6bd4 100644--- a/.agents/skills/add-model-price/references/model-audit-memory.md+++ b/.agents/skills/add-model-price/references/model-audit-memory.md@@ -12,7 +12,7 @@ audit date.## Latest useful snapshot-**Audit date:** 2026-08-07+**Audit date:** 2026-08-14All prices listed as `$X / MTok` (per million tokens). Per-token JSON values: divide by 1,000,000.@@ -27,7 +27,7 @@ All prices listed as `$X / MTok` (per million tokens). Per-token JSON values: di| Anthropic | claude-opus-4-5-20251101 | Same as Opus 5 | Yes | Flat 1M context | 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 | Still listed as "retired, except on Bedrock and Google Cloud" on the current page. Entry retained, unchanged. || 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 | Re-confirmed present on current page's main table, unchanged. |-| Anthropic | claude-sonnet-5 | Input $2/MTok, Output $10/MTok (through Aug 31, 2026); 5m $2.50/MTok, 1h $4/MTok, read $0.20/MTok | Yes | Flat 1M context; introductory pricing through Aug 31 2026 | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed. Standard pricing $3/$15 (cache $3.75/$6/$0.30) still scheduled for Sep 1, 2026 β update the file then. |+| 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; pricing is now PERMANENT (see comment) | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | **Resolved 2026-08-14: the $2/$10 pricing is now permanent, not introductory.** The official page now states: "The $2/$10 per million input/output token pricing for Claude Sonnet 5, announced at launch as introductory pricing through August 31, 2026, is now the standard price. The previously scheduled increase to $3/$15 per million input/output tokens on September 1, 2026 will not occur." No file change needed (file already holds $2/$10). This closes unresolved finding #1 from the Aug 7 2026 memory β do not re-flag a Sep 1, 2026 price increase in future audits. || 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 context-window cap) | Yes | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed unchanged; the Large Context tier removed on Aug 4 2026 was not reintroduced. || Anthropic | claude-sonnet-4-20250514 | Input $3/MTok, Output $15/MTok, 5m $3.75/MTok, 1h $6/MTok, read $0.30/MTok | Yes | Retired except Bedrock/Google Cloud β no tiering | Not applicable | None | https://platform.claude.com/docs/en/about-claude/pricing | Re-confirmed present on current page's main table, unchanged. |@@ -92,37 +92,43 @@ All prices listed as `$X / MTok` (per million tokens). Per-token JSON values: di| Google | gemini-3.1-pro-preview | Input $2/$4 MTok (β€200K/>200K), Output $12/$18 | Yes | Large Context (>200K) confirmed | Yes | None | https://ai.google.dev/pricing | Re-confirmed unchanged. || Google | gemini-3-flash-preview | Input $0.50/$1.00 (text/audio), Output $3.00, Cache read $0.05/$0.10 | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Re-confirmed unchanged. || Google | gemini-3-pro-preview | Input $2/$4 MTok (β€200K/>200K), Output $12/$18 | No | Large Context (>200K) set in file | Not applicable | None | https://ai.google.dev/pricing | Still not listed on official AI Studio page this run either; existing prices retained, not re-verified. |-| Google | gemini-3.6-flash | Input $1.50/MTok, Output $7.50/MTok, Cache read $0.15/MTok | Yes | No large-context tier | Yes | None | https://ai.google.dev/pricing | Re-confirmed unchanged. |+| Google | gemini-3.6-flash | Input $0.75/MTok, Output $3.75/MTok, Cache read $0.075/MTok (all through Dec 31, 2026; reverts to $1.50/$7.50/$0.15 from Jan 1, 2027) | Yes | No large-context tier | Yes | Updated | https://ai.google.dev/pricing https://ai.google.dev/gemini-api/docs/pricing | **Price cut found 2026-08-14.** Two independent targeted verbatim fetches (both `ai.google.dev/pricing` and `ai.google.dev/gemini-api/docs/pricing`, each explicitly separating Free/Paid columns) confirm Google introduced introductory-style pricing for this model: Paid tier is now $0.75/MTok input, $3.75/MTok output, $0.075/MTok cache read (10% ratio preserved) "through December 31, 2026", stepping up to $1.50/$7.50/$0.15 (the previously-confirmed and still-current file price before this run) "starting January 1, 2027". Since Langfuse's schema has no time-based tiering, the file now holds the current discounted price β **revert to $1.50/$7.50/$0.15 on or after 2027-01-01.** Grounding/web-search-queries price ($14/1,000 requests = 0.014/query) unchanged and confirmed via a dedicated grounding-pricing fetch to apply uniformly across Gemini 3.x models including this one. |+| Google | gemini-3.7-flash | Input $0.75/MTok, Output $3.75/MTok, Cache read $0.075/MTok (all through Dec 31, 2026; reverts to $1.50/$7.50/$0.15 from Jan 1, 2027) | Yes | No large-context tier | Yes | Added | https://ai.google.dev/pricing https://ai.google.dev/gemini-api/docs/pricing https://ai.google.dev/gemini-api/docs/models | **New model found 2026-08-14.** `gemini-3.7-flash` is confirmed via the official Gemini models page as a "New Stable" GA release, described as "Our latest and most capable Flash model, built for complex coding, agentic workflows, and reliable multi-step execution" β the successor to `gemini-3.6-flash` ("previous-generation Flash model"). It launched at the exact same current promotional price as `gemini-3.6-flash` (see that row) and shares the same Jan 1, 2027 step-up. Added to the pricing file mirroring the `gemini-3.6-flash` key set (input/output/cache-read aliases plus `grounding_queries`/`web_search_queries` at 0.014/query) and to `vertexAIModels`/`googleAIStudioModels` in `types.ts` (not as the first entry). matchPattern: `(?i)^(google(ai)?\/)?(gemini-3.7-flash)$`. || Google | gemini-2.0-flash | Input $0.10/MTok, Output $0.40/MTok | No | Deprecated (shut down June 1, 2026) | Not applicable | None | https://ai.google.dev/pricing | Not re-verified this run; retained for backward compatibility. || Google | gemini-2.0-flash-001 | Same as gemini-2.0-flash | No | Deprecated (shut down June 1, 2026) | Not applicable | None | https://ai.google.dev/pricing | Not re-verified this run; retained for backward compatibility. |-## Unresolved findings (updated 2026-08-07)+## Unresolved findings (updated 2026-08-14)-1. **claude-sonnet-5 introductory pricing** β Introductory pricing ($2/$10/MTok) expires- August 31, 2026. Standard pricing ($3/$15/MTok, cache $3.75/$6/$0.30) takes effect- September 1, 2026. The pricing file must be updated before or on that date.--2. **claude-opus-4-1-20250805 retirement** β Deprecated, past its originally stated Aug 5+1. **claude-opus-4-1-20250805 retirement** β Deprecated, past its originally stated Aug 52026 retirement date but still listed on the official pricing page as "retired, excepton Bedrock and Google Cloud" this run. File entry retained; no action required, butcheck whether it is fully removed from the official page in the next audit.-3. **AWS Bedrock "Claude 3.5 Sonnet (Public Extended Access)" pricing** β Confirmed real+2. **AWS Bedrock "Claude 3.5 Sonnet (Public Extended Access)" pricing** β Confirmed realin the Aug 4 2026 audit (see provider-sources-and-price-keys.md) but not representablein Langfuse's schema because it matches by model-ID string only. No file change shouldbe made for this; treat it as a permanent, documented limitation rather than something- to re-investigate each run.+ to re-investigate each run. Not re-checked this run (no `aws.amazon.com` fetch performed).-4. **Legacy Claude 3.x / 3.5 / 3.7 models not on the current pricing page** β Not+3. **Legacy Claude 3.x / 3.5 / 3.7 models not on the current pricing page** β Notre-verified this run (`claude-3.7-sonnet-20250219`, `claude-3.5-sonnet-20241022`,`claude-3-5-sonnet-20240620`, `claude-3-opus-20240229`, `claude-3-sonnet-20240229`,`claude-3-haiku-20240307`). Existing prices retained. Low priority since these areretired/legacy.-5. **gemini-3.1-flash-lite-preview and gemini-3-pro-preview** β Still not separately listed+4. **gemini-3.1-flash-lite-preview and gemini-3-pro-preview** β Still not separately listedon the official AI Studio pricing page. Existing prices retained without freshconfirmation. Re-verify if these move from preview to GA or gain their own pricing row.+5. **gemini-3.6-flash / gemini-3.7-flash promotional pricing reverts 2027-01-01** β Both+ models are confirmed on introductory pricing ($0.75/$3.75/MTok input/output, $0.075/MTok+ cache read) "through December 31, 2026", stepping up to $1.50/$7.50/$0.15 "starting+ January 1, 2027". The pricing file currently holds the discounted price (correct for+ now); update both entries to the higher rate on or after 2027-01-01. This is the same+ time-based-tiering limitation previously seen with `claude-sonnet-5` β Langfuse's schema+ cannot express a calendar-date price step, so the file always holds the *currently+ active* rate, not a future one.+6. **OpenAI "cache writes" is still gpt-5.6-family-only** β As of this audit (re-confirmedvia the full standard-pricing-table dump), the distinct 1.25x-of-input cache-writebilling dimension applies only to `gpt-5.6-sol`, `gpt-5.6-terra`, and `gpt-5.6-luna`.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 b9d8cbc88e..d03476d656 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@@ -76,15 +76,16 @@ Always fetch pricing from the provider's official docs before editing.models must NOT have a Large Context tier in the pricing file. Models not on this list(e.g. Sonnet 4.5, Haiku 4.5) may retain a Large Context tier if it was previously set.The Sonnet 4.6 Large Context tier was found and removed during the June 2026 audit.-- **Claude Sonnet 5 introductory pricing** β The API model ID is `claude-sonnet-5` (no- date suffix; pinned snapshot, not an alias). Introductory pricing of $2/$10 per- input/output MTok is in effect through August 31, 2026; standard pricing of $3/$15 will- apply from September 1, 2026. Cache write 5m = $2.50/MTok, 1h = $4/MTok, read =- $0.20/MTok during introductory period. Since the pricing schema cannot express- time-based tiers, the file holds the current introductory prices; update to $3/$15 and- cache equivalents ($3.75/$6/$0.30) after August 31, 2026. AWS Bedrock ID:- `anthropic.claude-sonnet-5`. The model is in the flat long-context list (no Large- Context tier). Added to pricing file and `anthropicModels` in July 2026 audit.+- **Claude Sonnet 5 pricing is now permanent (resolved August 14 2026)** β The API model ID+ is `claude-sonnet-5` (no date suffix; pinned snapshot, not an alias). Pricing is $2/$10+ per input/output MTok; cache write 5m = $2.50/MTok, 1h = $4/MTok, read = $0.20/MTok. This+ was originally announced as introductory pricing through August 31, 2026 with a scheduled+ increase to $3/$15 on September 1, 2026, but the official pricing page now states that+ increase "will not occur" and the $2/$10 rate "is now the standard price". No file change+ was needed (the file already held $2/$10). Do not re-flag a September 1, 2026 price+ increase for this model in future audits. AWS Bedrock ID: `anthropic.claude-sonnet-5`.+ The model is in the flat long-context list (no Large Context tier). Added to pricing file+ and `anthropicModels` in July 2026 audit.- **Claude Mythos Preview** β Listed in the Anthropic long-context pricing section and onthe models page (access is invitation-only via Project Glasswing) but has NO separatepricing row in the main model pricing table and NO selectable-model entry in types.ts.@@ -106,12 +107,40 @@ Always fetch pricing from the provider's official docs before editing.Long context prices: sol $10/$1.00/$45, terra $5/$0.50/$22.50, luna $2/$0.20/$9per MTok input/cached/output. Added Large Context (>272K) tiers to the pricing file inJuly 2026. The threshold of 272K is unique to this family; most other models use 200K.-- **Gemini 3.6 Flash (added July 2026)** β `gemini-3.6-flash` appeared on the official AI Studio- pricing page in July 2026 at $1.50/MTok input, $7.50/MTok output, cache read $0.15/MTok- (10% cache-read ratio). No large-context tier. Added to pricing file and selectable model lists- (`vertexAIModels`, `googleAIStudioModels`) in the July 22 2026 audit. Note: despite the higher- version number, output price ($7.50) is lower than gemini-3.5-flash ($9.00); this is correct- per the official page (improved efficiency at same input price).+- **Gemini 3.6 Flash (added July 2026; introductory price cut found August 14 2026)** β+ `gemini-3.6-flash` appeared on the official AI Studio pricing page in July 2026 at+ $1.50/MTok input, $7.50/MTok output, cache read $0.15/MTok (10% cache-read ratio). No+ large-context tier. Added to pricing file and selectable model lists (`vertexAIModels`,+ `googleAIStudioModels`) in the July 22 2026 audit. Note: despite the higher version+ number, output price ($7.50) is lower than gemini-3.5-flash ($9.00); this is correct per+ the official page (improved efficiency at same input price). On August 14 2026, two+ independent targeted verbatim fetches (both `ai.google.dev/pricing` and+ `ai.google.dev/gemini-api/docs/pricing`, each explicitly separating Free/Paid columns)+ found Google had introduced introductory pricing for this model: $0.75/MTok input,+ $3.75/MTok output, $0.075/MTok cache read, explicitly "through December 31, 2026",+ stepping up to $1.50/$7.50/$0.15 (the original price above) "starting January 1, 2027".+ The pricing file was updated to the discounted rate; revert to $1.50/$7.50/$0.15 on or+ after 2027-01-01. Grounding/web-search pricing ($14 per 1,000 requests = 0.014/query,+ shared free quota across all Gemini 3.x models) is unchanged and confirmed via a+ dedicated grounding-pricing fetch.+- **Gemini 3.7 Flash (added August 14 2026)** β `gemini-3.7-flash` is a new GA ("New+ Stable") release confirmed via `https://ai.google.dev/gemini-api/docs/models`, described+ as "Our latest and most capable Flash model, built for complex coding, agentic workflows,+ and reliable multi-step execution" β the direct successor to `gemini-3.6-flash` (now+ described as the "previous-generation Flash model"). It launched at the exact same+ current introductory price as `gemini-3.6-flash`: $0.75/MTok input, $3.75/MTok output,+ $0.075/MTok cache read, "through December 31, 2026", stepping up to $1.50/$7.50/$0.15+ "starting January 1, 2027" β confirmed via two independent fetches of+ `ai.google.dev/pricing` and `ai.google.dev/gemini-api/docs/pricing`. Because a single,+ generically-worded WebFetch prompt about this page range previously mis-summarized both+ 3.6 and 3.7 Flash (and even 3.1 Flash-Lite, a long-GA priced model) as "Free of charge"+ by picking the Free-tier column instead of Paid, always use a fetch prompt that+ explicitly asks to separate Free vs. Paid columns for these rows, per the existing+ Gemini free/paid column-collapse lesson above. No large-context tier. Grounding/web-search+ pricing ($14 per 1,000 requests) confirmed to apply uniformly to Gemini 3.x models+ including this one. Added to pricing file (mirroring the `gemini-3.6-flash` key set) and+ to `vertexAIModels`/`googleAIStudioModels` in `types.ts`, not as the first entry.+ matchPattern: `(?i)^(google(ai)?\/)?(gemini-3.7-flash)$`.- **Gemini 3.5 Flash-Lite (added July 2026; cache pricing corrected August 2026)** β`gemini-3.5-flash-lite` appeared on the official AI Studio pricing page in July 2026 at$0.30/MTok input, $2.50/MTok output. No large-context tier. The entry was initially addeddiff --git a/.github/workflows/model-price-audit.yml b/.github/workflows/model-price-audit.ymlindex be9f16cfad..00659f9ca6 100644--- a/.github/workflows/model-price-audit.yml+++ b/.github/workflows/model-price-audit.yml@@ -241,7 +241,7 @@ jobs:--max-turns ${{ steps.validate-inputs.outputs.max_turns }}--max-budget-usd ${{ steps.validate-inputs.outputs.max_budget_usd }}--no-session-persistence- --allowedTools "Read(/.github/workflows/model-price-audit.yml),Read(/worker/src/constants/default-model-prices.json),Read(/packages/shared/src/server/llm/types.ts),Read(/packages/shared/src/server/otel/OtelIngestionProcessor.ts),Read(/.agents/skills/add-model-price/SKILL.md),Read(/.agents/skills/add-model-price/references/*.md),Edit(/.github/workflows/model-price-audit.yml),Edit(/worker/src/constants/default-model-prices.json),Edit(/packages/shared/src/server/llm/types.ts),Edit(/.agents/skills/add-model-price/references/*.md),Write(/.agents/skills/add-model-price/references/*.md),WebFetch(domain:platform.claude.com),WebFetch(domain:docs.anthropic.com),WebFetch(domain:developers.openai.com),WebFetch(domain:ai.google.dev),WebFetch(domain:cloud.google.com),WebFetch(domain:aws.amazon.com),WebFetch(domain:azure.microsoft.com),Bash(date -u +%Y-%m-%dT00:00:00.000Z),Bash(node .agents/skills/add-model-price/scripts/validate-pricing-file.mjs:*),Bash(node .agents/skills/add-model-price/scripts/test-match-pattern.mjs:*)"+ --allowedTools "Read(/.github/workflows/model-price-audit.yml),Read(/worker/src/constants/default-model-prices.json),Read(/packages/shared/src/server/llm/types.ts),Read(/packages/shared/src/server/otel/OtelIngestionProcessor.ts),Read(/.agents/skills/add-model-price/SKILL.md),Read(/.agents/skills/add-model-price/references/*.md),Edit(/.github/workflows/model-price-audit.yml),Edit(/worker/src/constants/default-model-prices.json),Edit(/packages/shared/src/server/llm/types.ts),Edit(/.agents/skills/add-model-price/references/*.md),Write(/.agents/skills/add-model-price/references/*.md),WebFetch(domain:platform.claude.com),WebFetch(domain:docs.anthropic.com),WebFetch(domain:developers.openai.com),WebFetch(domain:ai.google.dev),WebFetch(domain:cloud.google.com),WebFetch(domain:aws.amazon.com),WebFetch(domain:azure.microsoft.com),Bash(date -u +%Y-%m-%dT00:00:00.000Z),Bash(uuidgen),Bash(node .agents/skills/add-model-price/scripts/validate-pricing-file.mjs:*),Bash(node .agents/skills/add-model-price/scripts/test-match-pattern.mjs:*)"--json-schema '{"type":"object","additionalProperties":false,"properties":{"summary":{"type":"string"},"auditDate":{"type":"string","pattern":"^[0-9]{4}-[0-9]{2}-[0-9]{2}$"},"pullRequestTitle":{"type":"string","maxLength":100},"modelsChecked":{"type":"array","minItems":1,"items":{"type":"object","additionalProperties":false,"properties":{"provider":{"type":"string","minLength":1},"model":{"type":"string","minLength":1},"pricingChecked":{"type":"string","minLength":1},"priceConfirmed":{"type":"string","enum":["yes","no"]},"usageKeysChecked":{"type":"string","minLength":1},"usageKeyCoverageConfirmed":{"type":"string","enum":["yes","no"]},"tieringChecked":{"type":"string","minLength":1},"tieringCorrect":{"type":"string","enum":["yes","no","not_applicable"]},"change":{"type":"string","enum":["none","updated","added","unresolved"]},"officialSources":{"type":"array","items":{"type":"string"}},"comments":{"type":"string"}},"required":["provider","model","pricingChecked","priceConfirmed","usageKeysChecked","usageKeyCoverageConfirmed","tieringChecked","tieringCorrect","change","officialSources","comments"]}},"changedModels":{"type":"array","items":{"type":"string"}},"skillReferenceUpdates":{"type":"array","items":{"type":"string"}},"workflowUpdates":{"type":"array","items":{"type":"string"}},"unresolvedFindings":{"type":"array","items":{"type":"string"}},"validation":{"type":"array","items":{"type":"string"}}},"required":["summary","auditDate","pullRequestTitle","modelsChecked","changedModels","skillReferenceUpdates","workflowUpdates","unresolvedFindings","validation"]}'- name: Mock Claude price auditdiff --git a/packages/shared/src/server/llm/types.ts b/packages/shared/src/server/llm/types.tsindex 66aa5decec..8d0ade6257 100644--- a/packages/shared/src/server/llm/types.ts+++ b/packages/shared/src/server/llm/types.ts@@ -410,6 +410,7 @@ export const anthropicModels = [export const vertexAIModels = ["gemini-2.5-flash","gemini-2.5-pro",+ "gemini-3.7-flash","gemini-3.6-flash","gemini-3.5-flash","gemini-3.5-flash-lite",@@ -435,6 +436,7 @@ export const vertexAIModels = [export const googleAIStudioModels = ["gemini-2.5-flash","gemini-2.5-pro",+ "gemini-3.7-flash","gemini-3.6-flash","gemini-3.5-flash","gemini-3.5-flash-lite",diff --git a/worker/src/constants/default-model-prices.json b/worker/src/constants/default-model-prices.jsonindex 3756327572..d443f9557a 100644--- a/worker/src/constants/default-model-prices.json+++ b/worker/src/constants/default-model-prices.json@@ -4667,7 +4667,7 @@"modelName": "gemini-3.6-flash","matchPattern": "(?i)^(google(ai)?\/)?(gemini-3.6-flash)$","createdAt": "2026-07-22T00:00:00.000Z",- "updatedAt": "2026-07-22T00:00:00.000Z",+ "updatedAt": "2026-08-14T00:00:00.000Z","pricingTiers": [{"id": "a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d_tier_default",@@ -4676,22 +4676,60 @@"priority": 0,"conditions": [],"prices": {- "input": 1.5e-6,- "input_text": 1.5e-6,- "input_modality_1": 1.5e-6,- "prompt_token_count": 1.5e-6,- "promptTokenCount": 1.5e-6,- "input_cached_tokens": 0.15e-6,- "cached_content_token_count": 0.15e-6,- "output": 7.5e-6,- "output_text": 7.5e-6,- "output_modality_1": 7.5e-6,- "candidates_token_count": 7.5e-6,- "candidatesTokenCount": 7.5e-6,- "thoughtsTokenCount": 7.5e-6,- "thoughts_token_count": 7.5e-6,- "output_reasoning_tokens": 7.5e-6,- "output_reasoning": 7.5e-6,+ "input": 0.75e-6,+ "input_text": 0.75e-6,+ "input_modality_1": 0.75e-6,+ "prompt_token_count": 0.75e-6,+ "promptTokenCount": 0.75e-6,+ "input_cached_tokens": 0.075e-6,+ "cached_content_token_count": 0.075e-6,+ "output": 3.75e-6,+ "output_text": 3.75e-6,+ "output_modality_1": 3.75e-6,+ "candidates_token_count": 3.75e-6,+ "candidatesTokenCount": 3.75e-6,+ "thoughtsTokenCount": 3.75e-6,+ "thoughts_token_count": 3.75e-6,+ "output_reasoning_tokens": 3.75e-6,+ "output_reasoning": 3.75e-6,+ "grounding_queries": 14e-3,+ "groundingQueries": 14e-3,+ "web_search_queries": 14e-3,+ "webSearchQueries": 14e-3+ }+ }+ ]+ },+ {+ "id": "b91d332c-a2fd-b85c-f6e6-971796f3f111",+ "modelName": "gemini-3.7-flash",+ "matchPattern": "(?i)^(google(ai)?\/)?(gemini-3.7-flash)$",+ "createdAt": "2026-08-14T00:00:00.000Z",+ "updatedAt": "2026-08-14T00:00:00.000Z",+ "pricingTiers": [+ {+ "id": "b91d332c-a2fd-b85c-f6e6-971796f3f111_tier_default",+ "name": "Standard",+ "isDefault": true,+ "priority": 0,+ "conditions": [],+ "prices": {+ "input": 0.75e-6,+ "input_text": 0.75e-6,+ "input_modality_1": 0.75e-6,+ "prompt_token_count": 0.75e-6,+ "promptTokenCount": 0.75e-6,+ "input_cached_tokens": 0.075e-6,+ "cached_content_token_count": 0.075e-6,+ "output": 3.75e-6,+ "output_text": 3.75e-6,+ "output_modality_1": 3.75e-6,+ "candidates_token_count": 3.75e-6,+ "candidatesTokenCount": 3.75e-6,+ "thoughtsTokenCount": 3.75e-6,+ "thoughts_token_count": 3.75e-6,+ "output_reasoning_tokens": 3.75e-6,+ "output_reasoning": 3.75e-6,"grounding_queries": 14e-3,"groundingQueries": 14e-3,"web_search_queries": 14e-3,