Tier: frontier
Context: 128K
Cheapest Host: OpenAI Direct
Deprecation Alert: 2026-10-23
GPT-4 Turbo (Legacy) Cloud Pricing, API Cost Calculator & Cheapest Providers
Live unit economics and multi-provider host arbitrage for GPT-4 Turbo (Legacy) (openai/gpt-4-turbo).
Input tokens cost $10.00/1M, output tokens cost
$30.00/1M, and prompt cache reads drop to
$5.00/1M.
Input / Output / Cache Read
$10.00 / $30.00
Per 1M tokens · Cache Read: $5.00/1M
10,000 DAU Monthly Bill
$212,400/mo
Drops to $165,150/mo at 75% prompt cache hit rate
Speed & Context Spec
48 tok/s
1. Cheapest Cloud Providers for GPT-4 Turbo (Legacy) (2026 Cloud Pricing & Latency Matrix)
Compare the cheapest cloud providers and GPU endpoints hosting GPT-4 Turbo (Legacy) anchored by input price, output price, cache read discount, Time-to-First-Token (TTFT < 400ms SLA), and throughput speed:
| Provider / Endpoint | Input / 1M | Output / 1M | Cache Read / 1M | TTFT Latency & SLA | Throughput | 10K DAU Monthly Bill | Action |
|---|---|---|---|---|---|---|---|
| OpenAI Direct #1 Recommended Router | $10.00 | $30.00 | $5.00 | 583ms Batch/Async | 48 tok/s | $212,400/mo | Deploy (Route with 0% Markup Fallback) → |
⚡ Live Provider Disparity Anchor: OpenAI Direct delivers GPT-4 Turbo (Legacy) at $10.00/1M input while maintaining a real-time <400ms TTFT SLA (48 tok/s peak).
2. Monthly SaaS Spend by DAU Scale & Prompt Cache Hit Rate
Exact monthly spend projections across 1,000 DAU, 10,000 DAU, and 50,000 DAU with 0%, 50%, 75%, and 90% prompt caching:
| Active Users (DAU) | Uncached (0% Hit) | 50% Cache Hit | 75% Cache Hit (RAG) | 90% Cache Hit (Agents) |
|---|---|---|---|---|
| 1,000 DAU (1.55B tok/mo) | $21,240/mo | $18,090/mo | $16,515/mo | $15,570/mo |
| 10,000 DAU (15.5B tok/mo) | $212,400/mo | $180,900/mo | $165,150/mo | $155,700/mo |
| 50,000 DAU (77.4B tok/mo) | $1,062,000/mo | $904,500/mo | $825,750/mo | $778,500/mo |
3. Frequently Asked Questions (GPT-4 Turbo (Legacy))
What are the cheapest cloud providers for GPT-4 Turbo (Legacy) in 2026?
For GPT-4 Turbo (Legacy) (openai/gpt-4-turbo), the cheapest cloud providers and GPU endpoints among 1 verified hosts are OpenAI Direct, starting at $10.00 per 1M input tokens, $30.00 per 1M output tokens, and $5.00 per 1M cached input reads (48 tok/s throughput). Teams can also claim $200 in free DigitalOcean GPU Droplet credits, $300 in Vultr Cloud GPU credits, or $5-$500 in RunPod Serverless vLLM bonus credits.
What is the GPT-4 Turbo (Legacy) cloud pricing per 1M tokens?
GPT-4 Turbo (Legacy) (OpenAI) cloud pricing is $10.00 per 1M input tokens, $30.00 per 1M output tokens, and $5.00 per 1M cached input tokens. Its context window is 128K (128,000 tokens) with 4,096 max output tokens.
How much does GPT-4 Turbo (Legacy) cost per month at 1,000, 10,000, and 50,000 DAU?
On a standard SaaS production workload (12 requests/user/day, 3,500 input + 800 output tokens), GPT-4 Turbo (Legacy) costs $21,240/month at 1,000 DAU, $212,400/month at 10,000 DAU, and $1,062,000/month at 50,000 DAU. Enabling 75% prompt caching reduces the 10,000 DAU bill to $165,150/month.
4. Compare GPT-4 Turbo (Legacy) Against Alternative Models
GPT-4 Turbo (Legacy) vs GPT-4.1 (1M Context Frontier)
Side-by-side DAU cost & cache savings →
Claude 3.7 Sonnet Pricing Calculator
$3.00/1M in · $15.00/1M out →
Claude 3.7 Sonnet (Extended Thinking) Pricing Calculator
$3.00/1M in · $15.00/1M out →
Claude 3.5 Sonnet (v2) Pricing Calculator
$3.00/1M in · $15.00/1M out →
Claude 3.5 Haiku Pricing Calculator
$0.80/1M in · $4.00/1M out →
Claude 3 Opus (Legacy High-Cost) Pricing Calculator
$15.00/1M in · $75.00/1M out →
GPT-4o Pricing Calculator
$2.50/1M in · $10.00/1M out →