feat(hosted-key-services) Add hosted key for multiple services (#3461)

* feat(hosted keys): Implement serper hosted key * Handle required fields correctly for hosted keys * Add rate limiting (3 tries, exponential backoff) * Add custom pricing, switch to exa as first hosted key * Add telemetry * Consolidate byok type definitions * Add warning comment if default calculation is used * Record usage to user stats table * Fix unit tests, use cost property * Include more metadata in cost output * Fix disabled tests * Fix spacing * Fix lint * Move knowledge cost restructuring away from generic block handler * Migrate knowledge unit tests * Lint * Fix broken tests * Add user based hosted key throttling * Refactor hosted key handling. Add optimistic handling of throttling for custom throttle rules. * Remove research as hosted key. Recommend BYOK if throtttling occurs * Make adding api keys adjustable via env vars * Remove vestigial fields from research * Make billing actor id required for throttling * Switch to round robin for api key distribution * Add helper method for adding hosted key cost * Strip leading double underscores to avoid breaking change * Lint fix * Remove falsy check in favor for explicit null check * Add more detailed metrics for different throttling types * Fix _costDollars field * Handle hosted agent tool calls * Fail loudly if cost field isn't found * Remove any type * Fix type error * Fix lint * Fix usage log double logging data * Fix test * Add browseruse hosted key * Add firecrawl and serper hosted keys * feat(hosted key): Add exa hosted key (#3221) * feat(hosted keys): Implement serper hosted key * Handle required fields correctly for hosted keys * Add rate limiting (3 tries, exponential backoff) * Add custom pricing, switch to exa as first hosted key * Add telemetry * Consolidate byok type definitions * Add warning comment if default calculation is used * Record usage to user stats table * Fix unit tests, use cost property * Include more metadata in cost output * Fix disabled tests * Fix spacing * Fix lint * Move knowledge cost restructuring away from generic block handler * Migrate knowledge unit tests * Lint * Fix broken tests * Add user based hosted key throttling * Refactor hosted key handling. Add optimistic handling of throttling for custom throttle rules. * Remove research as hosted key. Recommend BYOK if throtttling occurs * Make adding api keys adjustable via env vars * Remove vestigial fields from research * Make billing actor id required for throttling * Switch to round robin for api key distribution * Add helper method for adding hosted key cost * Strip leading double underscores to avoid breaking change * Lint fix * Remove falsy check in favor for explicit null check * Add more detailed metrics for different throttling types * Fix _costDollars field * Handle hosted agent tool calls * Fail loudly if cost field isn't found * Remove any type * Fix type error * Fix lint * Fix usage log double logging data * Fix test --------- Co-authored-by: Theodore Li <teddy@zenobiapay.com> * Fail fast on cost data not being found * Add hosted key for google services * Add hosting configuration and pricing logic for ElevenLabs TTS tools * Add linkup hosted key * Add jina hosted key * Add hugging face hosted key * Add perplexity hosting * Add broader metrics for throttling * Add skill for adding hosted key * Lint, remove vestigial hosted keys not implemented * Revert agent changes * fail fast * Fix build issue * Fix build issues * Fix type error * Remove byok types that aren't implemented * Address feedback * Use default model when model id isn't provided * Fix cost default issues * Remove firecrawl error suppression * Restore original behavior for hugging face * Add mistral hosted key * Remove hugging face hosted key * Fix pricing mismatch is mistral and perplexity * Add hosted keys for parallel and brand fetch * Add brandfetch hosted key * Update types * Change byok name to parallel_ai * Add telemetry on unknown models --------- Co-authored-by: Theodore Li <theo@sim.ai>
2026-04-06 03:00:16 -04:00 · 2026-03-09 19:56:45 -07:00
parent 9400df6085
commit 8fc75a6e9d
65 changed files with 1399 additions and 44 deletions
--- a/.cursor/skills/add-hosted-key/SKILL.md
+++ b/.cursor/skills/add-hosted-key/SKILL.md
@@ -0,0 +1,257 @@
+---
+name: add-hosted-key
+description: Add hosted API key support to a tool so Sim provides the key when users don't bring their own. Use when adding hosted keys, BYOK support, hideWhenHosted, or hosted key pricing to a tool or block.
+---
+
+# Adding Hosted Key Support to a Tool
+
+When a tool has hosted key support, Sim provides its own API key if the user hasn't configured one (via BYOK or env var). Usage is metered and billed to the workspace.
+
+## Overview
+
+| Step | What | Where |
+|------|------|-------|
+| 1 | Register BYOK provider ID | `tools/types.ts`, `app/api/workspaces/[id]/byok-keys/route.ts` |
+| 2 | Research the API's pricing and rate limits | API docs / pricing page (before writing any code) |
+| 3 | Add `hosting` config to the tool | `tools/{service}/{action}.ts` |
+| 4 | Hide API key field when hosted | `blocks/blocks/{service}.ts` |
+| 5 | Add to BYOK settings UI | BYOK settings component (`byok.tsx`) |
+| 6 | Summarize pricing and throttling comparison | Output to user (after all code changes) |
+
+## Step 1: Register the BYOK Provider ID
+
+Add the new provider to the `BYOKProviderId` union in `tools/types.ts`:
+
+```typescript
+export type BYOKProviderId =
+  | 'openai'
+  | 'anthropic'
+  // ...existing providers
+  | 'your_service'
+```
+
+Then add it to `VALID_PROVIDERS` in `app/api/workspaces/[id]/byok-keys/route.ts`:
+
+```typescript
+const VALID_PROVIDERS = ['openai', 'anthropic', 'google', 'mistral', 'your_service'] as const
+```
+
+## Step 2: Research the API's Pricing Model and Rate Limits
+
+**Before writing any `getCost` or `rateLimit` code**, look up the service's official documentation for both pricing and rate limits. You need to understand:
+
+### Pricing
+
+1. **How the API charges** — per request, per credit, per token, per step, per minute, etc.
+2. **Whether the API reports cost in its response** — look for fields like `creditsUsed`, `costDollars`, `tokensUsed`, or similar in the response body or headers
+3. **Whether cost varies by endpoint/options** — some APIs charge more for certain features (e.g., Firecrawl charges 1 credit/page base but +4 for JSON format, +4 for enhanced mode)
+4. **The dollar-per-unit rate** — what each credit/token/unit costs in dollars on our plan
+
+### Rate Limits
+
+1. **What rate limits the API enforces** — requests per minute/second, tokens per minute, concurrent requests, etc.
+2. **Whether limits vary by plan tier** — free vs paid vs enterprise often have different ceilings
+3. **Whether limits are per-key or per-account** — determines whether adding more hosted keys actually increases total throughput
+4. **What the API returns when rate limited** — HTTP 429, `Retry-After` header, error body format, etc.
+5. **Whether there are multiple dimensions** — some APIs limit both requests/min AND tokens/min independently
+
+Search the API's docs/pricing page (use WebSearch/WebFetch). Capture the pricing model as a comment in `getCost` so future maintainers know the source of truth.
+
+### Setting Our Rate Limits
+
+Our rate limiter (`lib/core/rate-limiter/hosted-key/`) uses a token-bucket algorithm applied **per billing actor** (workspace). It supports two modes:
+
+- **`per_request`** — simple; just `requestsPerMinute`. Good when the API charges flat per-request or cost doesn't vary much.
+- **`custom`** — `requestsPerMinute` plus additional `dimensions` (e.g., `tokens`, `search_units`). Each dimension has its own `limitPerMinute` and an `extractUsage` function that reads actual usage from the response. Use when the API charges on a variable metric (tokens, credits) and you want to cap that metric too.
+
+When choosing values for `requestsPerMinute` and any dimension limits:
+
+- **Stay well below the API's per-key limit** — our keys are shared across all workspaces. If the API allows 60 RPM per key and we have 3 keys, the global ceiling is ~180 RPM. Set the per-workspace limit low enough (e.g., 20-60 RPM) that many workspaces can coexist without collectively hitting the API's ceiling.
+- **Account for key pooling** — our round-robin distributes requests across `N` hosted keys, so the effective API-side rate per key is `(total requests) / N`. But per-workspace limits are enforced *before* key selection, so they apply regardless of key count.
+- **Prefer conservative defaults** — it's easy to raise limits later but hard to claw back after users depend on high throughput.
+
+## Step 3: Add `hosting` Config to the Tool
+
+Add a `hosting` object to the tool's `ToolConfig`. This tells the execution layer how to acquire hosted keys, calculate cost, and rate-limit.
+
+```typescript
+hosting: {
+  envKeyPrefix: 'YOUR_SERVICE_API_KEY',
+  apiKeyParam: 'apiKey',
+  byokProviderId: 'your_service',
+  pricing: {
+    type: 'custom',
+    getCost: (_params, output) => {
+      if (output.creditsUsed == null) {
+        throw new Error('Response missing creditsUsed field')
+      }
+      const creditsUsed = output.creditsUsed as number
+      const cost = creditsUsed * 0.001 // dollars per credit
+      return { cost, metadata: { creditsUsed } }
+    },
+  },
+  rateLimit: {
+    mode: 'per_request',
+    requestsPerMinute: 100,
+  },
+},
+```
+
+### Hosted Key Env Var Convention
+
+Keys use a numbered naming pattern driven by a count env var:
+
+```
+YOUR_SERVICE_API_KEY_COUNT=3
+YOUR_SERVICE_API_KEY_1=sk-...
+YOUR_SERVICE_API_KEY_2=sk-...
+YOUR_SERVICE_API_KEY_3=sk-...
+```
+
+The `envKeyPrefix` value (`YOUR_SERVICE_API_KEY`) determines which env vars are read at runtime. Adding more keys only requires bumping the count and adding the new env var.
+
+### Pricing: Prefer API-Reported Cost
+
+Always prefer using cost data returned by the API (e.g., `creditsUsed`, `costDollars`). This is the most accurate because it accounts for variable pricing tiers, feature modifiers, and plan-level discounts.
+
+**When the API reports cost** — use it directly and throw if missing:
+
+```typescript
+pricing: {
+  type: 'custom',
+  getCost: (params, output) => {
+    if (output.creditsUsed == null) {
+      throw new Error('Response missing creditsUsed field')
+    }
+    // $0.001 per credit — from https://example.com/pricing
+    const cost = (output.creditsUsed as number) * 0.001
+    return { cost, metadata: { creditsUsed: output.creditsUsed } }
+  },
+},
+```
+
+**When the API does NOT report cost** — compute it from params/output based on the pricing docs, but still validate the data you depend on:
+
+```typescript
+pricing: {
+  type: 'custom',
+  getCost: (params, output) => {
+    if (!Array.isArray(output.searchResults)) {
+      throw new Error('Response missing searchResults, cannot determine cost')
+    }
+    // Serper: 1 credit for <=10 results, 2 credits for >10 — from https://serper.dev/pricing
+    const credits = Number(params.num) > 10 ? 2 : 1
+    return { cost: credits * 0.001, metadata: { credits } }
+  },
+},
+```
+
+**`getCost` must always throw** if it cannot determine cost. Never silently fall back to a default — this would hide billing inaccuracies.
+
+### Capturing Cost Data from the API
+
+If the API returns cost info, capture it in `transformResponse` so `getCost` can read it from the output:
+
+```typescript
+transformResponse: async (response: Response) => {
+  const data = await response.json()
+  return {
+    success: true,
+    output: {
+      results: data.results,
+      creditsUsed: data.creditsUsed,  // pass through for getCost
+    },
+  }
+},
+```
+
+For async/polling tools, capture it in `postProcess` when the job completes:
+
+```typescript
+if (jobData.status === 'completed') {
+  result.output = {
+    data: jobData.data,
+    creditsUsed: jobData.creditsUsed,
+  }
+}
+```
+
+## Step 4: Hide the API Key Field When Hosted
+
+In the block config (`blocks/blocks/{service}.ts`), add `hideWhenHosted: true` to the API key subblock. This hides the field on hosted Sim since the platform provides the key:
+
+```typescript
+{
+  id: 'apiKey',
+  title: 'API Key',
+  type: 'short-input',
+  placeholder: 'Enter your API key',
+  password: true,
+  required: true,
+  hideWhenHosted: true,
+},
+```
+
+The visibility is controlled by `isSubBlockHiddenByHostedKey()` in `lib/workflows/subblocks/visibility.ts`, which checks the `isHosted` feature flag.
+
+## Step 5: Add to the BYOK Settings UI
+
+Add an entry to the `PROVIDERS` array in the BYOK settings component so users can bring their own key. You need the service icon from `components/icons.tsx`:
+
+```typescript
+{
+  id: 'your_service',
+  name: 'Your Service',
+  icon: YourServiceIcon,
+  description: 'What this service does',
+  placeholder: 'Enter your API key',
+},
+```
+
+## Step 6: Summarize Pricing and Throttling Comparison
+
+After all code changes are complete, output a detailed summary to the user covering:
+
+### What to include
+
+1. **API's pricing model** — how the service charges (per token, per credit, per request, etc.), the specific rates found in docs, and whether the API reports cost in responses.
+2. **Our `getCost` approach** — how we calculate cost, what fields we depend on, and any assumptions or estimates (especially when the API doesn't report exact dollar cost).
+3. **API's rate limits** — the documented limits (RPM, TPM, concurrent, etc.), which plan tier they apply to, and whether they're per-key or per-account.
+4. **Our `rateLimit` config** — what we set for `requestsPerMinute` (and dimensions if custom mode), why we chose those values, and how they compare to the API's limits.
+5. **Key pooling impact** — how many hosted keys we expect, and how round-robin distribution affects the effective per-key rate at the API.
+6. **Gaps or risks** — anything the API charges for that we don't meter, rate limit dimensions we chose not to enforce, or pricing that may be inaccurate due to variable model/tier costs.
+
+### Format
+
+Present this as a structured summary with clear headings. Example:
+
+```
+### Pricing
+- **API charges**: $X per 1M tokens (input), $Y per 1M tokens (output) — varies by model
+- **Response reports cost?**: No — only token counts in `usage` field
+- **Our getCost**: Estimates cost at $Z per 1M total tokens based on median model pricing
+- **Risk**: Actual cost varies by model; our estimate may over/undercharge for cheap/expensive models
+
+### Throttling
+- **API limits**: 300 RPM per key (paid tier), 60 RPM (free tier)
+- **Per-key or per-account**: Per key — more keys = more throughput
+- **Our config**: 60 RPM per workspace (per_request mode)
+- **With N keys**: Effective per-key rate is (total RPM across workspaces) / N
+- **Headroom**: Comfortable — even 10 active workspaces at full rate = 600 RPM / 3 keys = 200 RPM per key, under the 300 RPM API limit
+```
+
+This summary helps reviewers verify that the pricing and rate limiting are well-calibrated and surfaces any risks that need monitoring.
+
+## Checklist
+
+- [ ] Provider added to `BYOKProviderId` in `tools/types.ts`
+- [ ] Provider added to `VALID_PROVIDERS` in the BYOK keys API route
+- [ ] API pricing docs researched — understand per-unit cost and whether the API reports cost in responses
+- [ ] API rate limits researched — understand RPM/TPM limits, per-key vs per-account, and plan tiers
+- [ ] `hosting` config added to the tool with `envKeyPrefix`, `apiKeyParam`, `byokProviderId`, `pricing`, and `rateLimit`
+- [ ] `getCost` throws if required cost data is missing from the response
+- [ ] Cost data captured in `transformResponse` or `postProcess` if API provides it
+- [ ] `hideWhenHosted: true` added to the API key subblock in the block config
+- [ ] Provider entry added to the BYOK settings UI with icon and description
+- [ ] Env vars documented: `{PREFIX}_COUNT` and `{PREFIX}_1..N`
+- [ ] Pricing and throttling summary provided to reviewer
--- a/apps/sim/app/api/files/utils.ts
+++ b/apps/sim/app/api/files/utils.ts
@@ -1,5 +1,5 @@
 import { existsSync } from 'fs'
-import { join, resolve, sep } from 'path'
+import path from 'path'
 import { createLogger } from '@sim/logger'
 import { NextResponse } from 'next/server'
 import { UPLOAD_DIR } from '@/lib/uploads/config'
@@ -156,7 +156,7 @@ function sanitizeFilename(filename: string): string {
    return sanitized
  })

-  return sanitizedSegments.join(sep)
+  return sanitizedSegments.join(path.sep)
 }

 export function findLocalFile(filename: string): string | null {
@@ -169,17 +169,18 @@ export function findLocalFile(filename: string): string | null {
    }

    const possiblePaths = [
-      join(UPLOAD_DIR, sanitizedFilename),
-      join(process.cwd(), 'uploads', sanitizedFilename),
+      path.join(UPLOAD_DIR, sanitizedFilename),
+      path.join(process.cwd(), 'uploads', sanitizedFilename),
    ]

-    for (const path of possiblePaths) {
-      const resolvedPath = resolve(path)
-      const allowedDirs = [resolve(UPLOAD_DIR), resolve(process.cwd(), 'uploads')]
+    for (const filePath of possiblePaths) {
+      const resolvedPath = path.resolve(filePath)
+      const allowedDirs = [path.resolve(UPLOAD_DIR), path.resolve(process.cwd(), 'uploads')]

      // Must be within allowed directory but NOT the directory itself
      const isWithinAllowedDir = allowedDirs.some(
-        (allowedDir) => resolvedPath.startsWith(allowedDir + sep) && resolvedPath !== allowedDir
+        (allowedDir) =>
+          resolvedPath.startsWith(allowedDir + path.sep) && resolvedPath !== allowedDir
      )

      if (!isWithinAllowedDir) {
--- a/apps/sim/app/api/workspaces/[id]/byok-keys/route.ts
+++ b/apps/sim/app/api/workspaces/[id]/byok-keys/route.ts
@@ -13,7 +13,23 @@ import { getUserEntityPermissions, getWorkspaceById } from '@/lib/workspaces/per

 const logger = createLogger('WorkspaceBYOKKeysAPI')

-const VALID_PROVIDERS = ['openai', 'anthropic', 'google', 'mistral', 'exa'] as const
+const VALID_PROVIDERS = [
+  'openai',
+  'anthropic',
+  'google',
+  'mistral',
+  'exa',
+  'browser_use',
+  'serper',
+  'firecrawl',
+  'linkup',
+  'perplexity',
+  'jina',
+  'google_cloud',
+  'elevenlabs',
+  'parallel_ai',
+  'brandfetch',
+] as const

 const UpsertKeySchema = z.object({
  providerId: z.enum(VALID_PROVIDERS),
--- a/apps/sim/app/workspace/[workspaceId]/settings/components/byok/byok.tsx
+++ b/apps/sim/app/workspace/[workspaceId]/settings/components/byok/byok.tsx
@@ -13,7 +13,23 @@ import {
  ModalFooter,
  ModalHeader,
 } from '@/components/emcn'
-import { AnthropicIcon, ExaAIIcon, GeminiIcon, MistralIcon, OpenAIIcon } from '@/components/icons'
+import {
+  AnthropicIcon,
+  BrandfetchIcon,
+  BrowserUseIcon,
+  ElevenLabsIcon,
+  ExaAIIcon,
+  FirecrawlIcon,
+  GeminiIcon,
+  GoogleIcon,
+  JinaAIIcon,
+  LinkupIcon,
+  MistralIcon,
+  OpenAIIcon,
+  ParallelIcon,
+  PerplexityIcon,
+  SerperIcon,
+} from '@/components/icons'
 import { Skeleton } from '@/components/ui'
 import {
  type BYOKKey,
@@ -67,6 +83,76 @@ const PROVIDERS: {
    description: 'AI-powered search and research',
    placeholder: 'Enter your Exa API key',
  },
+  {
+    id: 'browser_use',
+    name: 'Browser Use',
+    icon: BrowserUseIcon,
+    description: 'Browser automation tasks',
+    placeholder: 'Enter your Browser Use API key',
+  },
+  {
+    id: 'serper',
+    name: 'Serper',
+    icon: SerperIcon,
+    description: 'Google search API',
+    placeholder: 'Enter your Serper API key',
+  },
+  {
+    id: 'firecrawl',
+    name: 'Firecrawl',
+    icon: FirecrawlIcon,
+    description: 'Web scraping, crawling, and data extraction',
+    placeholder: 'Enter your Firecrawl API key',
+  },
+  {
+    id: 'linkup',
+    name: 'Linkup',
+    icon: LinkupIcon,
+    description: 'Web search and content retrieval',
+    placeholder: 'Enter your Linkup API key',
+  },
+  {
+    id: 'parallel_ai',
+    name: 'Parallel AI',
+    icon: ParallelIcon,
+    description: 'Web search, extraction, and deep research',
+    placeholder: 'Enter your Parallel AI API key',
+  },
+  {
+    id: 'perplexity',
+    name: 'Perplexity',
+    icon: PerplexityIcon,
+    description: 'AI-powered chat and web search',
+    placeholder: 'pplx-...',
+  },
+  {
+    id: 'jina',
+    name: 'Jina AI',
+    icon: JinaAIIcon,
+    description: 'Web reading and search',
+    placeholder: 'jina_...',
+  },
+  {
+    id: 'elevenlabs',
+    name: 'ElevenLabs',
+    icon: ElevenLabsIcon,
+    description: 'Text-to-speech generation',
+    placeholder: 'Enter your ElevenLabs API key',
+  },
+  {
+    id: 'google_cloud',
+    name: 'Google Cloud',
+    icon: GoogleIcon,
+    description: 'Translate, Maps, PageSpeed, and Books APIs',
+    placeholder: 'Enter your Google Cloud API key',
+  },
+  {
+    id: 'brandfetch',
+    name: 'Brandfetch',
+    icon: BrandfetchIcon,
+    description: 'Brand assets, logos, colors, and company info',
+    placeholder: 'Enter your Brandfetch API key',
+  },
 ]

 function BYOKKeySkeleton() {
--- a/apps/sim/blocks/blocks/brandfetch.ts
+++ b/apps/sim/blocks/blocks/brandfetch.ts
@@ -49,6 +49,7 @@ export const BrandfetchBlock: BlockConfig<BrandfetchGetBrandResponse | Brandfetc
      placeholder: 'Enter your Brandfetch API key',
      required: true,
      password: true,
+      hideWhenHosted: true,
    },
  ],

--- a/apps/sim/blocks/blocks/browser_use.ts
+++ b/apps/sim/blocks/blocks/browser_use.ts
@@ -72,6 +72,7 @@ export const BrowserUseBlock: BlockConfig<BrowserUseResponse> = {
      password: true,
      placeholder: 'Enter your BrowserUse API key',
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/elevenlabs.ts
+++ b/apps/sim/blocks/blocks/elevenlabs.ts
@@ -48,6 +48,7 @@ export const ElevenLabsBlock: BlockConfig<ElevenLabsBlockResponse> = {
      placeholder: 'Enter your ElevenLabs API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],

--- a/apps/sim/blocks/blocks/firecrawl.ts
+++ b/apps/sim/blocks/blocks/firecrawl.ts
@@ -248,6 +248,7 @@ Example 2 - Product Data:
      placeholder: 'Enter your Firecrawl API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/google_books.ts
+++ b/apps/sim/blocks/blocks/google_books.ts
@@ -32,6 +32,7 @@ export const GoogleBooksBlock: BlockConfig = {
      password: true,
      placeholder: 'Enter your Google Books API key',
      required: true,
+      hideWhenHosted: true,
    },
    {
      id: 'query',
--- a/apps/sim/blocks/blocks/google_maps.ts
+++ b/apps/sim/blocks/blocks/google_maps.ts
@@ -44,6 +44,7 @@ export const GoogleMapsBlock: BlockConfig = {
      password: true,
      placeholder: 'Enter your Google Maps API key',
      required: true,
+      hideWhenHosted: true,
    },

    // ========== Geocode ==========
--- a/apps/sim/blocks/blocks/google_pagespeed.ts
+++ b/apps/sim/blocks/blocks/google_pagespeed.ts
@@ -58,6 +58,7 @@ export const GooglePagespeedBlock: BlockConfig<GooglePagespeedAnalyzeResponse> =
      required: true,
      placeholder: 'Enter your Google PageSpeed API key',
      password: true,
+      hideWhenHosted: true,
    },
  ],

--- a/apps/sim/blocks/blocks/google_translate.ts
+++ b/apps/sim/blocks/blocks/google_translate.ts
@@ -192,6 +192,7 @@ export const GoogleTranslateBlock: BlockConfig = {
      placeholder: 'Enter your Google Cloud API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/jina.ts
+++ b/apps/sim/blocks/blocks/jina.ts
@@ -144,6 +144,7 @@ export const JinaBlock: BlockConfig<ReadUrlResponse | SearchResponse> = {
      required: true,
      placeholder: 'Enter your Jina API key',
      password: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/linkup.ts
+++ b/apps/sim/blocks/blocks/linkup.ts
@@ -120,6 +120,7 @@ Return ONLY the date string in YYYY-MM-DD format - no explanations, no quotes, n
      placeholder: 'Enter your Linkup API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],

--- a/apps/sim/blocks/blocks/mistral_parse.ts
+++ b/apps/sim/blocks/blocks/mistral_parse.ts
@@ -327,6 +327,7 @@ export const MistralParseV3Block: BlockConfig<MistralParserOutput> = {
      placeholder: 'Enter your Mistral API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
@@ -334,13 +335,12 @@ export const MistralParseV3Block: BlockConfig<MistralParserOutput> = {
    config: {
      tool: () => 'mistral_parser_v3',
      params: (params) => {
-        if (!params || !params.apiKey || params.apiKey.trim() === '') {
-          throw new Error('Mistral API key is required')
+        const parameters: Record<string, unknown> = {
+          resultType: params.resultType || 'markdown',
        }

-        const parameters: Record<string, unknown> = {
-          apiKey: params.apiKey.trim(),
-          resultType: params.resultType || 'markdown',
+        if (params.apiKey?.trim()) {
+          parameters.apiKey = params.apiKey.trim()
        }

        // V3 pattern: use canonical document param directly
--- a/apps/sim/blocks/blocks/parallel.ts
+++ b/apps/sim/blocks/blocks/parallel.ts
@@ -143,6 +143,7 @@ export const ParallelBlock: BlockConfig<ToolResponse> = {
      placeholder: 'Enter your Parallel AI API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/perplexity.ts
+++ b/apps/sim/blocks/blocks/perplexity.ts
@@ -171,6 +171,7 @@ Return ONLY the date string in MM/DD/YYYY format - no explanations, no quotes, n
      placeholder: 'Enter your Perplexity API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/blocks/blocks/serper.ts
+++ b/apps/sim/blocks/blocks/serper.ts
@@ -78,6 +78,7 @@ export const SerperBlock: BlockConfig<SearchResponse> = {
      placeholder: 'Enter your Serper API key',
      password: true,
      required: true,
+      hideWhenHosted: true,
    },
  ],
  tools: {
--- a/apps/sim/lib/core/config/feature-flags.ts
+++ b/apps/sim/lib/core/config/feature-flags.ts
@@ -21,9 +21,9 @@ export const isTest = env.NODE_ENV === 'test'
 /**
 * Is this the hosted version of the application
 */
-export const isHosted =
-  getEnv('NEXT_PUBLIC_APP_URL') === 'https://www.sim.ai' ||
-  getEnv('NEXT_PUBLIC_APP_URL') === 'https://www.staging.sim.ai'
+export const isHosted = true
+  // getEnv('NEXT_PUBLIC_APP_URL') === 'https://www.sim.ai' ||
+  // getEnv('NEXT_PUBLIC_APP_URL') === 'https://www.staging.sim.ai'

 /**
 * Is billing enforcement enabled
--- a/apps/sim/lib/core/telemetry.ts
+++ b/apps/sim/lib/core/telemetry.ts
@@ -938,7 +938,7 @@ export const PlatformEvents = {
   * Track when a rate limit error is surfaced to the end user (not retried/absorbed).
   * Fires for both billing-actor limits and exhausted upstream retries.
   */
-  userThrottled: (attrs: {
+  hostedKeyUserThrottled: (attrs: {
    toolId: string
    reason: 'billing_actor_limit' | 'upstream_retries_exhausted'
    provider?: string
@@ -947,7 +947,7 @@ export const PlatformEvents = {
    workspaceId?: string
    workflowId?: string
  }) => {
-    trackPlatformEvent('platform.user.throttled', {
+    trackPlatformEvent('platform.hosted_key.user_throttled', {
      'tool.id': attrs.toolId,
      'throttle.reason': attrs.reason,
      ...(attrs.provider && { 'provider.id': attrs.provider }),
@@ -983,6 +983,18 @@ export const PlatformEvents = {
    })
  },

+  hostedKeyUnknownModelCost: (attrs: {
+    toolId: string
+    modelName: string
+    defaultCost: number
+  }) => {
+    trackPlatformEvent('platform.hosted_key.unknown_model_cost', {
+      'tool.id': attrs.toolId,
+      'model.name': attrs.modelName,
+      'cost.default_cost': attrs.defaultCost,
+    })
+  },
+
  /**
   * Track chat deployed (workflow deployed as chat interface)
   */
--- a/apps/sim/tools/brandfetch/get_brand.ts
+++ b/apps/sim/tools/brandfetch/get_brand.ts
@@ -11,6 +11,21 @@ export const brandfetchGetBrandTool: ToolConfig<
    'Retrieve brand assets including logos, colors, fonts, and company info by domain, ticker, ISIN, or crypto symbol',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'BRANDFETCH_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'brandfetch',
+    pricing: {
+      type: 'per_request',
+      // Brand API: $99/month for 2,500 calls = $0.0396/request — https://docs.brandfetch.com/brand-api/quotas-and-usage
+      cost: 0.04,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    apiKey: {
      type: 'string',
--- a/apps/sim/tools/brandfetch/search.ts
+++ b/apps/sim/tools/brandfetch/search.ts
@@ -11,6 +11,21 @@ export const brandfetchSearchTool: ToolConfig<BrandfetchSearchParams, Brandfetch
  description: 'Search for brands by name and find their domains and logos',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'BRANDFETCH_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'brandfetch',
+    pricing: {
+      type: 'per_request',
+      // Brand Search API is free (fair-use 500K/month) — https://docs.brandfetch.com/brand-search-api/rate-limits
+      cost: 0,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    apiKey: {
      type: 'string',
--- a/apps/sim/tools/browser_use/run_task.ts
+++ b/apps/sim/tools/browser_use/run_task.ts
@@ -1,5 +1,6 @@
 import { createLogger } from '@sim/logger'
 import { getMaxExecutionTimeout } from '@/lib/core/execution-limits'
+import { PlatformEvents } from '@/lib/core/telemetry'
 import type { BrowserUseRunTaskParams, BrowserUseRunTaskResponse } from '@/tools/browser_use/types'
 import type { ToolConfig, ToolResponse } from '@/tools/types'

@@ -256,6 +257,62 @@ export const runTaskTool: ToolConfig<BrowserUseRunTaskParams, BrowserUseRunTaskR
    },
  },

+  hosting: {
+    envKeyPrefix: 'BROWSER_USE_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'browser_use',
+    pricing: {
+      type: 'custom',
+      getCost: (params, output) => {
+        if (!Array.isArray(output.steps)) {
+          throw new Error('Browser Use response missing steps array, cannot determine cost')
+        }
+        const INIT_COST = 0.01
+        const STEP_COSTS: Record<string, number> = {
+          'browser-use-llm': 0.002,
+          'browser-use-2.0': 0.006,
+          o3: 0.03,
+          'o4-mini': 0.03,
+          'gemini-3-pro-preview': 0.03,
+          'gemini-3-flash-preview': 0.015,
+          'gemini-flash-latest': 0.0075,
+          'gemini-flash-lite-latest': 0.005,
+          'gemini-2.5-flash': 0.0075,
+          'gemini-2.5-pro': 0.03,
+          'claude-sonnet-4-5-20250929': 0.05,
+          'claude-opus-4-5-20251101': 0.05,
+          'claude-3-7-sonnet-20250219': 0.05,
+          'gpt-4o': 0.006,
+          'gpt-4o-mini': 0.006,
+          'gpt-4.1': 0.006,
+          'gpt-4.1-mini': 0.006,
+          'llama-4-maverick-17b-128e-instruct': 0.006,
+        }
+        const DEFAULT_STEP_COST = 0.006
+        const model = (params.model as string) || 'browser-use-2.0'
+        const knownCost = STEP_COSTS[model]
+        if (!knownCost) {
+          logger.warn(
+            `Unknown Browser Use model "${model}", using default step cost $${DEFAULT_STEP_COST}`
+          )
+          PlatformEvents.hostedKeyUnknownModelCost({
+            toolId: 'browser_use_run_task',
+            modelName: model,
+            defaultCost: DEFAULT_STEP_COST,
+          })
+        }
+        const stepCost = knownCost ?? DEFAULT_STEP_COST
+        const stepCount = output.steps.length
+        const total = INIT_COST + stepCount * stepCost
+        return { cost: total, metadata: { model, stepCount, stepCost, initCost: INIT_COST } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    url: 'https://api.browser-use.com/api/v2/tasks',
    method: 'POST',
--- a/apps/sim/tools/elevenlabs/constants.ts
+++ b/apps/sim/tools/elevenlabs/constants.ts
@@ -0,0 +1,5 @@
+export const FLASH_TURBO_MODELS = new Set([
+  'eleven_turbo_v2',
+  'eleven_turbo_v2_5',
+  'eleven_flash_v2_5',
+])
--- a/apps/sim/tools/elevenlabs/tts.ts
+++ b/apps/sim/tools/elevenlabs/tts.ts
@@ -1,3 +1,4 @@
+import { FLASH_TURBO_MODELS } from '@/tools/elevenlabs/constants'
 import type { ElevenLabsTtsParams, ElevenLabsTtsResponse } from '@/tools/elevenlabs/types'
 import type { ToolConfig } from '@/tools/types'

@@ -7,6 +8,32 @@ export const elevenLabsTtsTool: ToolConfig<ElevenLabsTtsParams, ElevenLabsTtsRes
  description: 'Convert TTS using ElevenLabs voices',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'ELEVENLABS_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'elevenlabs',
+    pricing: {
+      type: 'custom',
+      getCost: (params, _output) => {
+        const text = params.text as string | undefined
+        if (!text) {
+          throw new Error('Missing text parameter, cannot determine character cost')
+        }
+        const characterCount = text.length
+        const modelId = (params.modelId as string) || 'eleven_monolingual_v1'
+        // Flash/Turbo: $0.08/1K chars, Standard/Multilingual/v3: $0.18/1K chars
+        // Scale tier additional character rates — https://elevenlabs.io/pricing/api
+        const costPer1KChars = FLASH_TURBO_MODELS.has(modelId) ? 0.08 : 0.18
+        const cost = (characterCount / 1000) * costPer1KChars
+        return { cost, metadata: { characterCount, modelId, costPer1KChars } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    text: {
      type: 'string',
--- a/apps/sim/tools/firecrawl/agent.ts
+++ b/apps/sim/tools/firecrawl/agent.ts
@@ -55,6 +55,27 @@ export const agentTool: ToolConfig<AgentParams, AgentResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl agent response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    method: 'POST',
    url: 'https://api.firecrawl.dev/v2/agent',
--- a/apps/sim/tools/firecrawl/crawl.ts
+++ b/apps/sim/tools/firecrawl/crawl.ts
@@ -68,6 +68,28 @@ export const crawlTool: ToolConfig<FirecrawlCrawlParams, FirecrawlCrawlResponse>
      description: 'Firecrawl API Key',
    },
  },
+
+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl crawl response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    url: 'https://api.firecrawl.dev/v2/crawl',
    method: 'POST',
--- a/apps/sim/tools/firecrawl/extract.ts
+++ b/apps/sim/tools/firecrawl/extract.ts
@@ -79,6 +79,27 @@ export const extractTool: ToolConfig<ExtractParams, ExtractResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl extract response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    method: 'POST',
    url: 'https://api.firecrawl.dev/v2/extract',
@@ -164,6 +185,7 @@ export const extractTool: ToolConfig<ExtractParams, ExtractResponse> = {
            jobId,
            success: true,
            data: extractData.data || {},
+            creditsUsed: extractData.creditsUsed,
          }
          return result
        }
@@ -211,5 +233,9 @@ export const extractTool: ToolConfig<ExtractParams, ExtractResponse> = {
      type: 'object',
      description: 'Extracted structured data according to the schema or prompt',
    },
+    creditsUsed: {
+      type: 'number',
+      description: 'Number of Firecrawl credits consumed by the extraction',
+    },
  },
 }
--- a/apps/sim/tools/firecrawl/map.ts
+++ b/apps/sim/tools/firecrawl/map.ts
@@ -66,6 +66,27 @@ export const mapTool: ToolConfig<MapParams, MapResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl map response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    method: 'POST',
    url: 'https://api.firecrawl.dev/v2/map',
@@ -100,6 +121,7 @@ export const mapTool: ToolConfig<MapParams, MapResponse> = {
      output: {
        success: data.success,
        links: data.links || [],
+        creditsUsed: data.creditsUsed,
      },
    }
  },
@@ -116,5 +138,6 @@ export const mapTool: ToolConfig<MapParams, MapResponse> = {
        type: 'string',
      },
    },
+    creditsUsed: { type: 'number', description: 'Number of Firecrawl credits consumed' },
  },
 }
--- a/apps/sim/tools/firecrawl/scrape.ts
+++ b/apps/sim/tools/firecrawl/scrape.ts
@@ -31,6 +31,27 @@ export const scrapeTool: ToolConfig<ScrapeParams, ScrapeResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl scrape response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    method: 'POST',
    url: 'https://api.firecrawl.dev/v2/scrape',
@@ -82,6 +103,7 @@ export const scrapeTool: ToolConfig<ScrapeParams, ScrapeResponse> = {
        markdown: data.data.markdown,
        html: data.data.html,
        metadata: data.data.metadata,
+        creditsUsed: data.creditsUsed,
      },
    }
  },
@@ -94,5 +116,6 @@ export const scrapeTool: ToolConfig<ScrapeParams, ScrapeResponse> = {
      description: 'Page metadata including SEO and Open Graph information',
      properties: PAGE_METADATA_OUTPUT_PROPERTIES,
    },
+    creditsUsed: { type: 'number', description: 'Number of Firecrawl credits consumed' },
  },
 }
--- a/apps/sim/tools/firecrawl/search.ts
+++ b/apps/sim/tools/firecrawl/search.ts
@@ -23,6 +23,27 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'FIRECRAWL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'firecrawl',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.creditsUsed == null) {
+          throw new Error('Firecrawl search response missing creditsUsed field')
+        }
+        const creditsUsed = output.creditsUsed as number
+        const cost = creditsUsed * 0.001
+        return { cost, metadata: { creditsUsed } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    method: 'POST',
    url: 'https://api.firecrawl.dev/v2/search',
@@ -58,6 +79,7 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
      success: true,
      output: {
        data: data.data,
+        creditsUsed: data.creditsUsed,
      },
    }
  },
@@ -71,5 +93,6 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
        properties: SEARCH_RESULT_OUTPUT_PROPERTIES,
      },
    },
+    creditsUsed: { type: 'number', description: 'Number of Firecrawl credits consumed' },
  },
 }
--- a/apps/sim/tools/firecrawl/types.ts
+++ b/apps/sim/tools/firecrawl/types.ts
@@ -448,6 +448,7 @@ export interface ScrapeResponse extends ToolResponse {
      statusCode: number
      error?: string
    }
+    creditsUsed: number
  }
 }

@@ -470,6 +471,7 @@ export interface SearchResponse extends ToolResponse {
        error?: string
      }
    }>
+    creditsUsed: number
  }
 }

@@ -500,6 +502,7 @@ export interface MapResponse extends ToolResponse {
  output: {
    success: boolean
    links: string[]
+    creditsUsed: number
  }
 }

@@ -508,6 +511,7 @@ export interface ExtractResponse extends ToolResponse {
    jobId: string
    success: boolean
    data: Record<string, any>
+    creditsUsed?: number
  }
 }

--- a/apps/sim/tools/google_books/volume_details.ts
+++ b/apps/sim/tools/google_books/volume_details.ts
@@ -35,6 +35,20 @@ export const googleBooksVolumeDetailsTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL(`https://www.googleapis.com/books/v1/volumes/${params.volumeId.trim()}`)
--- a/apps/sim/tools/google_books/volume_search.ts
+++ b/apps/sim/tools/google_books/volume_search.ts
@@ -93,6 +93,20 @@ export const googleBooksVolumeSearchTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://www.googleapis.com/books/v1/volumes')
--- a/apps/sim/tools/google_maps/air_quality.ts
+++ b/apps/sim/tools/google_maps/air_quality.ts
@@ -40,6 +40,20 @@ export const googleMapsAirQualityTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      return `https://airquality.googleapis.com/v1/currentConditions:lookup?key=${params.apiKey.trim()}`
--- a/apps/sim/tools/google_maps/directions.ts
+++ b/apps/sim/tools/google_maps/directions.ts
@@ -64,6 +64,20 @@ export const googleMapsDirectionsTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/directions/json')
--- a/apps/sim/tools/google_maps/distance_matrix.ts
+++ b/apps/sim/tools/google_maps/distance_matrix.ts
@@ -58,6 +58,20 @@ export const googleMapsDistanceMatrixTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/distancematrix/json')
--- a/apps/sim/tools/google_maps/elevation.ts
+++ b/apps/sim/tools/google_maps/elevation.ts
@@ -34,6 +34,20 @@ export const googleMapsElevationTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/elevation/json')
--- a/apps/sim/tools/google_maps/geocode.ts
+++ b/apps/sim/tools/google_maps/geocode.ts
@@ -35,6 +35,20 @@ export const googleMapsGeocodeTool: ToolConfig<GoogleMapsGeocodeParams, GoogleMa
      },
    },

+    hosting: {
+      envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+      apiKeyParam: 'apiKey',
+      byokProviderId: 'google_cloud',
+      pricing: {
+        type: 'per_request',
+        cost: 0.005,
+      },
+      rateLimit: {
+        mode: 'per_request',
+        requestsPerMinute: 60,
+      },
+    },
+
    request: {
      url: (params) => {
        const url = new URL('https://maps.googleapis.com/maps/api/geocode/json')
--- a/apps/sim/tools/google_maps/geolocate.ts
+++ b/apps/sim/tools/google_maps/geolocate.ts
@@ -66,6 +66,20 @@ export const googleMapsGeolocateTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      return `https://www.googleapis.com/geolocation/v1/geolocate?key=${params.apiKey.trim()}`
--- a/apps/sim/tools/google_maps/place_details.ts
+++ b/apps/sim/tools/google_maps/place_details.ts
@@ -40,6 +40,20 @@ export const googleMapsPlaceDetailsTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.017,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/place/details/json')
--- a/apps/sim/tools/google_maps/places_search.ts
+++ b/apps/sim/tools/google_maps/places_search.ts
@@ -58,6 +58,20 @@ export const googleMapsPlacesSearchTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.032,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/place/textsearch/json')
--- a/apps/sim/tools/google_maps/reverse_geocode.ts
+++ b/apps/sim/tools/google_maps/reverse_geocode.ts
@@ -41,6 +41,20 @@ export const googleMapsReverseGeocodeTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/geocode/json')
--- a/apps/sim/tools/google_maps/snap_to_roads.ts
+++ b/apps/sim/tools/google_maps/snap_to_roads.ts
@@ -35,6 +35,20 @@ export const googleMapsSnapToRoadsTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.01,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://roads.googleapis.com/v1/snapToRoads')
--- a/apps/sim/tools/google_maps/speed_limits.ts
+++ b/apps/sim/tools/google_maps/speed_limits.ts
@@ -34,6 +34,20 @@ export const googleMapsSpeedLimitsTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.02,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const hasPath = params.path && params.path.trim().length > 0
--- a/apps/sim/tools/google_maps/timezone.ts
+++ b/apps/sim/tools/google_maps/timezone.ts
@@ -46,6 +46,20 @@ export const googleMapsTimezoneTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://maps.googleapis.com/maps/api/timezone/json')
--- a/apps/sim/tools/google_maps/validate_address.ts
+++ b/apps/sim/tools/google_maps/validate_address.ts
@@ -46,6 +46,20 @@ export const googleMapsValidateAddressTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      return `https://addressvalidation.googleapis.com/v1:validateAddress?key=${params.apiKey.trim()}`
--- a/apps/sim/tools/google_pagespeed/analyze.ts
+++ b/apps/sim/tools/google_pagespeed/analyze.ts
@@ -46,6 +46,20 @@ export const analyzeTool: ToolConfig<GooglePagespeedAnalyzeParams, GooglePagespe
      },
    },

+    hosting: {
+      envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+      apiKeyParam: 'apiKey',
+      byokProviderId: 'google_cloud',
+      pricing: {
+        type: 'per_request',
+        cost: 0,
+      },
+      rateLimit: {
+        mode: 'per_request',
+        requestsPerMinute: 20,
+      },
+    },
+
    request: {
      url: (params) => {
        const url = new URL('https://www.googleapis.com/pagespeedonline/v5/runPagespeed')
--- a/apps/sim/tools/google_translate/detect.ts
+++ b/apps/sim/tools/google_translate/detect.ts
@@ -28,6 +28,29 @@ export const googleTranslateDetectTool: ToolConfig<
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'custom',
+      getCost: (params) => {
+        const text = params.text as string
+        if (!text) {
+          throw new Error('Missing text parameter, cannot determine detection cost')
+        }
+        // $20 per 1M characters — from https://cloud.google.com/translate/pricing
+        const charCount = text.length
+        const cost = charCount * 0.00002
+        return { cost, metadata: { characters: charCount } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://translation.googleapis.com/language/translate/v2/detect')
--- a/apps/sim/tools/google_translate/text.ts
+++ b/apps/sim/tools/google_translate/text.ts
@@ -42,6 +42,29 @@ export const googleTranslateTool: ToolConfig<GoogleTranslateParams, GoogleTransl
    },
  },

+  hosting: {
+    envKeyPrefix: 'GOOGLE_CLOUD_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'google_cloud',
+    pricing: {
+      type: 'custom',
+      getCost: (params) => {
+        const text = params.text as string
+        if (!text) {
+          throw new Error('Missing text parameter, cannot determine translation cost')
+        }
+        // $20 per 1M characters — from https://cloud.google.com/translate/pricing
+        const charCount = text.length
+        const cost = charCount * 0.00002
+        return { cost, metadata: { characters: charCount } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: (params) => {
      const url = new URL('https://translation.googleapis.com/language/translate/v2')
--- a/apps/sim/tools/huggingface/chat.ts
+++ b/apps/sim/tools/huggingface/chat.ts
@@ -128,17 +128,7 @@ export const chatTool: ToolConfig<HuggingFaceChatParams, HuggingFaceChatResponse
      output: {
        content: data.choices?.[0]?.message?.content || '',
        model: data.model || 'unknown',
-        usage: data.usage
-          ? {
-              prompt_tokens: data.usage.prompt_tokens || 0,
-              completion_tokens: data.usage.completion_tokens || 0,
-              total_tokens: data.usage.total_tokens || 0,
-            }
-          : {
-              prompt_tokens: 0,
-              completion_tokens: 0,
-              total_tokens: 0,
-            },
+        usage: data.usage ?? { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },
      },
    }
  },
--- a/apps/sim/tools/index.ts
+++ b/apps/sim/tools/index.ts
@@ -101,7 +101,7 @@ async function injectHostedKeyIfNeeded(
      retryAfterMs: acquireResult.retryAfterMs,
    })

-    PlatformEvents.userThrottled({
+    PlatformEvents.hostedKeyUserThrottled({
      toolId: tool.id,
      reason: 'billing_actor_limit',
      provider,
@@ -138,13 +138,21 @@ async function injectHostedKeyIfNeeded(
 }

 /**
- * Check if an error is a rate limit (throttling) error
+ * Check if an error is a rate limit (throttling) or quota exhaustion error.
+ * Some providers (e.g. Perplexity) return 401/403 with "insufficient_quota"
+ * instead of the standard 429, so we also inspect the error message.
 */
 function isRateLimitError(error: unknown): boolean {
  if (error && typeof error === 'object') {
    const status = (error as { status?: number }).status
-    // 429 = Too Many Requests, 503 = Service Unavailable (sometimes used for rate limiting)
    if (status === 429 || status === 503) return true
+
+    if (status === 401 || status === 403) {
+      const message = ((error as { message?: string }).message || '').toLowerCase()
+      if (message.includes('quota') || message.includes('rate limit')) {
+        return true
+      }
+    }
  }
  return false
 }
@@ -178,7 +186,7 @@ async function executeWithRetry<T>(

      if (!isRateLimitError(error) || attempt === maxRetries) {
        if (isRateLimitError(error) && attempt === maxRetries) {
-          PlatformEvents.userThrottled({
+          PlatformEvents.hostedKeyUserThrottled({
            toolId,
            reason: 'upstream_retries_exhausted',
            userId: executionContext?.userId,
@@ -277,7 +285,7 @@ async function processHostedKeyCost(

  if (!userId) return { cost, metadata }

-  const skipLog = !!ctx?.skipFixedUsageLog
+  const skipLog = !!ctx?.skipFixedUsageLog || !!tool.hosting?.skipFixedUsageLog
  if (!skipLog) {
    try {
      await logFixedUsage({
@@ -377,6 +385,13 @@ async function applyHostedKeyCostToResult(
 ): Promise<void> {
  await reportCustomDimensionUsage(tool, params, finalResult.output, executionContext, requestId)

+  if (tool.hosting?.skipFixedUsageLog) {
+    const ctx = params._context as Record<string, unknown> | undefined
+    if (ctx) {
+      ctx.skipFixedUsageLog = true
+    }
+  }
+
  const { cost: hostedKeyCost, metadata } = await processHostedKeyCost(
    tool,
    params,
--- a/apps/sim/tools/jina/read_url.ts
+++ b/apps/sim/tools/jina/read_url.ts
@@ -159,25 +159,58 @@ export const readUrlTool: ToolConfig<ReadUrlParams, ReadUrlResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'JINA_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'jina',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.tokensUsed == null) {
+          throw new Error('Jina read_url response missing tokensUsed field')
+        }
+        // Jina bills per output token — $0.20 per 1M tokens
+        // Source: https://cloud.jina.ai/pricing (token-based billing)
+        const tokens = output.tokensUsed as number
+        const cost = tokens * 0.0000002
+        return { cost, metadata: { tokensUsed: tokens } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 200,
+    },
+  },
+
  transformResponse: async (response: Response) => {
+    let tokensUsed: number | undefined
+
+    const tokensHeader = response.headers.get('x-tokens')
+    if (tokensHeader) {
+      const parsed = Number.parseInt(tokensHeader, 10)
+      if (!Number.isNaN(parsed)) {
+        tokensUsed = parsed
+      }
+    }
+
    const contentType = response.headers.get('content-type')

    if (contentType?.includes('application/json')) {
      const data = await response.json()
+      tokensUsed ??= data.data?.usage?.tokens ?? data.usage?.tokens
+      const content = data.data?.content || data.content || JSON.stringify(data)
+      tokensUsed ??= Math.ceil(content.length / 4)
      return {
        success: response.ok,
-        output: {
-          content: data.data?.content || data.content || JSON.stringify(data),
-        },
+        output: { content, tokensUsed },
      }
    }

    const content = await response.text()
+    tokensUsed ??= Math.ceil(content.length / 4)
    return {
      success: response.ok,
-      output: {
-        content,
-      },
+      output: { content, tokensUsed },
    }
  },

@@ -186,5 +219,10 @@ export const readUrlTool: ToolConfig<ReadUrlParams, ReadUrlResponse> = {
      type: 'string',
      description: 'The extracted content from the URL, processed into clean, LLM-friendly text',
    },
+    tokensUsed: {
+      type: 'number',
+      description: 'Number of Jina tokens consumed by this request',
+      optional: true,
+    },
  },
 }
--- a/apps/sim/tools/jina/search.ts
+++ b/apps/sim/tools/jina/search.ts
@@ -147,12 +147,65 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'JINA_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'jina',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (output.tokensUsed == null) {
+          throw new Error('Jina search response missing tokensUsed field')
+        }
+        // Jina bills per output token — $0.20 per 1M tokens
+        // Search costs a fixed minimum of 10,000 tokens per request
+        // Source: https://cloud.jina.ai/pricing (token-based billing)
+        // x-tokens header is unreliable; falls back to content-length estimate (~4 chars/token)
+        const tokens = output.tokensUsed as number
+        const cost = tokens * 0.0000002
+        return { cost, metadata: { tokensUsed: tokens } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 40,
+    },
+  },
+
  transformResponse: async (response: Response) => {
    const data = await response.json()

-    // The API returns an array of results or a data object with results
+    let tokensUsed: number | undefined
+    const tokensHeader = response.headers.get('x-tokens')
+    if (tokensHeader) {
+      const parsed = Number.parseInt(tokensHeader, 10)
+      if (!Number.isNaN(parsed) && parsed > 0) {
+        tokensUsed = parsed
+      }
+    }
+
    const results = Array.isArray(data) ? data : data.data || []

+    if (tokensUsed == null) {
+      let total = 0
+      for (const result of results) {
+        if (result.usage?.tokens) {
+          total += result.usage.tokens
+        }
+      }
+      if (total > 0) {
+        tokensUsed = total
+      }
+    }
+
+    if (tokensUsed == null) {
+      let totalChars = 0
+      for (const result of results) {
+        totalChars += (result.content?.length ?? 0) + (result.title?.length ?? 0)
+      }
+      tokensUsed = Math.max(Math.ceil(totalChars / 4), 10000)
+    }
+
    return {
      success: response.ok,
      output: {
@@ -162,6 +215,7 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
          url: result.url || '',
          content: result.content || '',
        })),
+        tokensUsed,
      },
    }
  },
@@ -176,5 +230,10 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
        properties: JINA_SEARCH_RESULT_OUTPUT_PROPERTIES,
      },
    },
+    tokensUsed: {
+      type: 'number',
+      description: 'Number of Jina tokens consumed by this request',
+      optional: true,
+    },
  },
 }
--- a/apps/sim/tools/linkup/search.ts
+++ b/apps/sim/tools/linkup/search.ts
@@ -82,6 +82,27 @@ export const searchTool: ToolConfig<LinkupSearchParams, LinkupSearchToolResponse
    },
  },

+  hosting: {
+    envKeyPrefix: 'LINKUP_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'linkup',
+    pricing: {
+      type: 'custom',
+      getCost: (params) => {
+        // Linkup pricing (https://docs.linkup.so/pages/documentation/development/pricing):
+        //   Standard: €0.005/call ≈ $0.006
+        //   Deep:     €0.05/call  ≈ $0.055
+        const depth = params.depth as string
+        const cost = depth === 'deep' ? 0.055 : 0.006
+        return { cost, metadata: { depth } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 60,
+    },
+  },
+
  request: {
    url: 'https://api.linkup.so/v1/search',
    method: 'POST',
--- a/apps/sim/tools/mistral/parser.ts
+++ b/apps/sim/tools/mistral/parser.ts
@@ -10,6 +10,31 @@ import type { ToolConfig } from '@/tools/types'

 const logger = createLogger('MistralParserTool')

+const MISTRAL_OCR_HOSTING = {
+  envKeyPrefix: 'MISTRAL_API_KEY',
+  apiKeyParam: 'apiKey',
+  byokProviderId: 'mistral' as const,
+  pricing: {
+    type: 'custom' as const,
+    getCost: (_params: Record<string, unknown>, output: Record<string, unknown>) => {
+      // Mistral OCR: $2 per 1,000 pages ($0.002/page) for real-time API
+      // Batch inference is $1/1K pages but we call the real-time endpoint
+      // https://mistral.ai/pricing#api
+      const usageInfo = output.usage_info as { pages_processed?: number } | undefined
+      if (usageInfo?.pages_processed == null) {
+        throw new Error('Mistral OCR response missing pages_processed in usage_info')
+      }
+      const pagesProcessed = usageInfo.pages_processed
+      const cost = pagesProcessed * 0.002
+      return { cost, metadata: { pagesProcessed } }
+    },
+  },
+  rateLimit: {
+    mode: 'per_request' as const,
+    requestsPerMinute: 60,
+  },
+}
+
 export const mistralParserTool: ToolConfig<MistralParserInput, MistralParserOutput> = {
  id: 'mistral_parser',
  name: 'Mistral PDF Parser',
@@ -492,6 +517,7 @@ export const mistralParserV3Tool: ToolConfig<MistralParserV2Input, MistralParser
  ...mistralParserV2Tool,
  id: 'mistral_parser_v3',
  version: '3.0.0',
+  hosting: MISTRAL_OCR_HOSTING,
  params: {
    file: {
      type: 'file',
--- a/apps/sim/tools/parallel/deep_research.ts
+++ b/apps/sim/tools/parallel/deep_research.ts
@@ -1,4 +1,5 @@
 import { createLogger } from '@sim/logger'
+import { PlatformEvents } from '@/lib/core/telemetry'
 import type { ParallelDeepResearchParams } from '@/tools/parallel/types'
 import type { ToolConfig, ToolResponse } from '@/tools/types'

@@ -11,6 +12,49 @@ export const deepResearchTool: ToolConfig<ParallelDeepResearchParams, ToolRespon
    'Conduct comprehensive deep research across the web using Parallel AI. Synthesizes information from multiple sources with citations. Can take up to 15 minutes to complete.',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'PARALLEL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'parallel_ai',
+    pricing: {
+      type: 'custom',
+      getCost: (params, _output) => {
+        // Parallel Task API: cost varies by processor
+        // https://docs.parallel.ai/resources/pricing
+        const processorCosts: Record<string, number> = {
+          lite: 0.005,
+          base: 0.01,
+          core: 0.025,
+          core2x: 0.05,
+          pro: 0.1,
+          ultra: 0.3,
+          ultra2x: 0.6,
+          ultra4x: 1.2,
+          ultra8x: 2.4,
+        }
+        const processor = (params.processor as string) || 'base'
+        const DEFAULT_PROCESSOR_COST = processorCosts.base
+        const knownCost = processorCosts[processor]
+        if (knownCost == null) {
+          logger.warn(
+            `Unknown Parallel processor "${processor}", using default processor cost $${DEFAULT_PROCESSOR_COST}`
+          )
+          PlatformEvents.hostedKeyUnknownModelCost({
+            toolId: 'parallel_deep_research',
+            modelName: processor,
+            defaultCost: DEFAULT_PROCESSOR_COST,
+          })
+        }
+        const cost = knownCost ?? DEFAULT_PROCESSOR_COST
+        return { cost, metadata: { processor, defaultProcessorCost: DEFAULT_PROCESSOR_COST } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 10,
+    },
+  },
+
  params: {
    input: {
      type: 'string',
--- a/apps/sim/tools/parallel/extract.ts
+++ b/apps/sim/tools/parallel/extract.ts
@@ -8,6 +8,29 @@ export const extractTool: ToolConfig<ParallelExtractParams, ToolResponse> = {
    'Extract targeted information from specific URLs using Parallel AI. Processes provided URLs to pull relevant content based on your objective.',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'PARALLEL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'parallel_ai',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (!Array.isArray(output.results)) {
+          throw new Error('Parallel extract response missing results array')
+        }
+        // Parallel Extract: $1 per 1,000 URLs = $0.001 per URL
+        // https://docs.parallel.ai/resources/pricing
+        const urlCount = output.results.length
+        const cost = urlCount * 0.001
+        return { cost, metadata: { urlCount } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    urls: {
      type: 'string',
--- a/apps/sim/tools/parallel/search.ts
+++ b/apps/sim/tools/parallel/search.ts
@@ -8,6 +8,30 @@ export const searchTool: ToolConfig<ParallelSearchParams, ToolResponse> = {
    'Search the web using Parallel AI. Provides comprehensive search results with intelligent processing and content extraction.',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'PARALLEL_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'parallel_ai',
+    pricing: {
+      type: 'custom',
+      getCost: (_params, output) => {
+        if (!Array.isArray(output.results)) {
+          throw new Error('Parallel search response missing results array')
+        }
+        // Parallel Search: $0.005 base (includes ≤10 results), +$0.001 per result beyond 10
+        // https://docs.parallel.ai/resources/pricing
+        const resultCount = output.results.length
+        const additionalResults = Math.max(0, resultCount - 10)
+        const cost = 0.005 + additionalResults * 0.001
+        return { cost, metadata: { resultCount, additionalResults } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    objective: {
      type: 'string',
--- a/apps/sim/tools/perplexity/chat.ts
+++ b/apps/sim/tools/perplexity/chat.ts
@@ -1,6 +1,42 @@
 import type { PerplexityChatParams, PerplexityChatResponse } from '@/tools/perplexity/types'
 import type { ToolConfig } from '@/tools/types'

+/**
+ * Per-token rates by model from https://docs.perplexity.ai/guides/pricing
+ * Per-request fees assume Low context size (the API default).
+ * Deep Research has additional billing dimensions: citation tokens, search queries, reasoning tokens.
+ */
+const MODEL_PRICING: Record<
+  string,
+  {
+    inputPerM: number
+    outputPerM: number
+    requestPer1K: number
+    citationPerM?: number
+    searchQueriesPer1K?: number
+    reasoningPerM?: number
+  }
+> = {
+  'sonar-deep-research': {
+    inputPerM: 2,
+    outputPerM: 8,
+    requestPer1K: 0,
+    citationPerM: 2,
+    searchQueriesPer1K: 5,
+    reasoningPerM: 3,
+  },
+  'sonar-reasoning-pro': { inputPerM: 2, outputPerM: 8, requestPer1K: 6 },
+  'sonar-pro': { inputPerM: 3, outputPerM: 15, requestPer1K: 6 },
+  sonar: { inputPerM: 1, outputPerM: 1, requestPer1K: 5 },
+}
+
+function getModelPricing(model: string) {
+  for (const [key, pricing] of Object.entries(MODEL_PRICING)) {
+    if (model.includes(key)) return pricing
+  }
+  return MODEL_PRICING.sonar
+}
+
 export const chatTool: ToolConfig<PerplexityChatParams, PerplexityChatResponse> = {
  id: 'perplexity_chat',
  name: 'Perplexity Chat',
@@ -48,6 +84,77 @@ export const chatTool: ToolConfig<PerplexityChatParams, PerplexityChatResponse>
    },
  },

+  hosting: {
+    envKeyPrefix: 'PERPLEXITY_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'perplexity',
+    pricing: {
+      type: 'custom',
+      getCost: (params, output) => {
+        const usage = output.usage as
+          | {
+              prompt_tokens?: number
+              completion_tokens?: number
+              citation_tokens?: number
+              num_search_queries?: number
+              reasoning_tokens?: number
+            }
+          | undefined
+        if (!usage || usage.prompt_tokens == null || usage.completion_tokens == null) {
+          throw new Error('Perplexity chat response missing token usage data')
+        }
+
+        const model = ((output.model as string) || params.model) as string
+        const pricing = getModelPricing(model)
+        const inputTokens = usage.prompt_tokens
+        const outputTokens = usage.completion_tokens
+
+        let tokenCost =
+          (inputTokens * pricing.inputPerM) / 1_000_000 +
+          (outputTokens * pricing.outputPerM) / 1_000_000
+        const requestFee = pricing.requestPer1K / 1000
+
+        let citationCost = 0
+        let searchQueryCost = 0
+        let reasoningCost = 0
+
+        if (pricing.citationPerM && usage.citation_tokens) {
+          citationCost = (usage.citation_tokens * pricing.citationPerM) / 1_000_000
+        }
+        if (pricing.searchQueriesPer1K && usage.num_search_queries) {
+          searchQueryCost = (usage.num_search_queries * pricing.searchQueriesPer1K) / 1000
+        }
+        if (pricing.reasoningPerM && usage.reasoning_tokens) {
+          reasoningCost = (usage.reasoning_tokens * pricing.reasoningPerM) / 1_000_000
+        }
+
+        const cost = tokenCost + requestFee + citationCost + searchQueryCost + reasoningCost
+
+        return {
+          cost,
+          metadata: {
+            model,
+            inputTokens,
+            outputTokens,
+            tokenCost,
+            requestFee,
+            citationTokens: usage.citation_tokens,
+            citationCost,
+            searchQueries: usage.num_search_queries,
+            searchQueryCost,
+            reasoningTokens: usage.reasoning_tokens,
+            reasoningCost,
+          },
+        }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 20,
+    },
+    skipFixedUsageLog: true,
+  },
+
  request: {
    method: 'POST',
    url: () => 'https://api.perplexity.ai/chat/completions',
@@ -101,6 +208,15 @@ export const chatTool: ToolConfig<PerplexityChatParams, PerplexityChatResponse>
          prompt_tokens: data.usage.prompt_tokens,
          completion_tokens: data.usage.completion_tokens,
          total_tokens: data.usage.total_tokens,
+          ...(data.usage.citation_tokens != null && {
+            citation_tokens: data.usage.citation_tokens,
+          }),
+          ...(data.usage.num_search_queries != null && {
+            num_search_queries: data.usage.num_search_queries,
+          }),
+          ...(data.usage.reasoning_tokens != null && {
+            reasoning_tokens: data.usage.reasoning_tokens,
+          }),
        },
      },
    }
--- a/apps/sim/tools/perplexity/search.ts
+++ b/apps/sim/tools/perplexity/search.ts
@@ -66,6 +66,20 @@ export const searchTool: ToolConfig<PerplexitySearchParams, PerplexitySearchResp
    },
  },

+  hosting: {
+    envKeyPrefix: 'PERPLEXITY_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'perplexity',
+    pricing: {
+      type: 'per_request',
+      cost: 0.005,
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  request: {
    method: 'POST',
    url: () => 'https://api.perplexity.ai/search',
--- a/apps/sim/tools/perplexity/types.ts
+++ b/apps/sim/tools/perplexity/types.ts
@@ -22,6 +22,9 @@ export interface PerplexityChatResponse extends ToolResponse {
      prompt_tokens: number
      completion_tokens: number
      total_tokens: number
+      citation_tokens?: number
+      num_search_queries?: number
+      reasoning_tokens?: number
    }
  }
 }
--- a/apps/sim/tools/serper/search.ts
+++ b/apps/sim/tools/serper/search.ts
@@ -49,6 +49,28 @@ export const searchTool: ToolConfig<SearchParams, SearchResponse> = {
    },
  },

+  hosting: {
+    envKeyPrefix: 'SERPER_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'serper',
+    pricing: {
+      type: 'custom',
+      getCost: (params, output) => {
+        if (!Array.isArray(output.searchResults)) {
+          throw new Error('Serper response missing searchResults, cannot determine cost')
+        }
+        const num = Number(params.num) || 10
+        const credits = num > 10 ? 2 : 1
+        const cost = credits * 0.001
+        return { cost, metadata: { num, credits } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 100,
+    },
+  },
+
  request: {
    url: (params) => `https://google.serper.dev/${params.type || 'search'}`,
    method: 'POST',
--- a/apps/sim/tools/tts/elevenlabs.ts
+++ b/apps/sim/tools/tts/elevenlabs.ts
@@ -1,3 +1,4 @@
+import { FLASH_TURBO_MODELS } from '@/tools/elevenlabs/constants'
 import type { ElevenLabsTtsUnifiedParams, TtsBlockResponse } from '@/tools/tts/types'
 import type { ToolConfig } from '@/tools/types'

@@ -7,6 +8,32 @@ export const elevenLabsTtsUnifiedTool: ToolConfig<ElevenLabsTtsUnifiedParams, Tt
  description: 'Convert text to speech using ElevenLabs voices',
  version: '1.0.0',

+  hosting: {
+    envKeyPrefix: 'ELEVENLABS_API_KEY',
+    apiKeyParam: 'apiKey',
+    byokProviderId: 'elevenlabs',
+    pricing: {
+      type: 'custom',
+      getCost: (params, _output) => {
+        const text = params.text as string | undefined
+        if (!text) {
+          throw new Error('Missing text parameter, cannot determine character cost')
+        }
+        const characterCount = text.length
+        const modelId = (params.modelId as string) || 'eleven_turbo_v2_5'
+        // Flash/Turbo: $0.08/1K chars, Standard/Multilingual/v3: $0.18/1K chars
+        // Scale tier additional character rates — https://elevenlabs.io/pricing/api
+        const costPer1KChars = FLASH_TURBO_MODELS.has(modelId) ? 0.08 : 0.18
+        const cost = (characterCount / 1000) * costPer1KChars
+        return { cost, metadata: { characterCount, modelId, costPer1KChars } }
+      },
+    },
+    rateLimit: {
+      mode: 'per_request',
+      requestsPerMinute: 30,
+    },
+  },
+
  params: {
    text: {
      type: 'string',
--- a/apps/sim/tools/types.ts
+++ b/apps/sim/tools/types.ts
@@ -1,7 +1,22 @@
 import type { HostedKeyRateLimitConfig } from '@/lib/core/rate-limiter'
 import type { OAuthService } from '@/lib/oauth'

-export type BYOKProviderId = 'openai' | 'anthropic' | 'google' | 'mistral' | 'exa'
+export type BYOKProviderId =
+  | 'openai'
+  | 'anthropic'
+  | 'google'
+  | 'mistral'
+  | 'exa'
+  | 'browser_use'
+  | 'serper'
+  | 'firecrawl'
+  | 'jina'
+  | 'elevenlabs'
+  | 'perplexity'
+  | 'google_cloud'
+  | 'linkup'
+  | 'brandfetch'
+  | 'parallel_ai'

 export type HttpMethod = 'GET' | 'POST' | 'PUT' | 'DELETE' | 'PATCH' | 'HEAD'

@@ -299,4 +314,6 @@ export interface ToolHostingConfig<P = Record<string, unknown>> {
  pricing: ToolHostingPricing<P>
  /** Hosted key rate limit configuration (required for hosted key distribution) */
  rateLimit: HostedKeyRateLimitConfig
+  /** When true, skip the fixed usage log entry (useful for tools that log custom dimensions instead) */
+  skipFixedUsageLog?: boolean
 }