ai-cost-estimate Edge Function — Ai

ai-cost-estimate — Calculate LLM API request cost

Computes the cost of an LLM API call given a model, prompt token count, and completion token count — supports USD, EUR, and GBP with no external API calls.

---

Supported Models

Model	Prompt (per 1M)	Completion (per 1M)
gpt-4o	$2.50	$10.00
gpt-4o-mini	$0.15	$0.60
gpt-4-turbo	$10.00	$30.00
gpt-3.5-turbo	$0.50	$1.50
claude-3-5-sonnet	$3.00	$15.00
claude-3-5-haiku	$0.80	$4.00
claude-3-opus	$15.00	$75.00
claude-sonnet-4-6	$3.00	$15.00
gemini-1.5-pro	$1.25	$5.00
gemini-1.5-flash	$0.075	$0.30

---

API

POST /api/ai-cost-estimate

Request body

Field	Type	Required	Default	Description
model	string	✅	—	Model identifier
promptTokens	number	✅	—	Number of prompt/input tokens
completionTokens	number	❌	0	Number of completion/output tokens
currency	"USD" | "EUR" | "GBP"	❌	"USD"	Output currency

Success response (200)

{
  "success": true,
  "data": {
    "promptCost": 0.0025,
    "completionCost": 0.01,
    "totalCost": 0.0125,
    "currency": "USD",
    "model": "gpt-4o",
    "pricePerMillion": { "prompt": 2.5, "completion": 10.0 }
  }
}

Error responses

Code	HTTP	When
INVALID_INPUT	400	Missing or invalid field
INTERNAL_ERROR	500	Unknown model

---

Usage

cURL

curl -X POST "$FUNCTION_URL" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o", "promptTokens": 1500, "completionTokens": 800, "currency": "EUR"}'

TypeScript / JavaScript (HTTP)

const response = await fetch(FUNCTION_URL, {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ model: 'claude-3-5-sonnet', promptTokens: 2000, completionTokens: 500 }),
});
const { data } = await response.json();
console.log(`Total cost: $${data.totalCost}`);

Direct import (Node / Bun / Deno)

import { aiCostEstimate } from '@aerostack/functions/ai-cost-estimate';

const { totalCost } = aiCostEstimate({ model: 'gpt-4o-mini', promptTokens: 5000, completionTokens: 1000 });

---

Use Cases

• Displaying real-time cost estimates to users in an AI product before they submit a request.
• Tracking per-request LLM spend in an application analytics dashboard.
• Comparing cost across models to choose the most cost-effective option for a given task.

---

Notes

• Prices are approximate as of early 2026 and may change — update MODEL_PRICING in core.ts as needed.
• EUR rate: 0.92, GBP rate: 0.79 relative to USD.
• Unknown models throw a clear error listing all supported model names.