gpt-4-turbo · OpenAI
Previous flagship GPT-4 generation with 128K context window and vision capabilities.
Last checked Aug 28, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Confirm the current rate at the official provider source.
Quick answer
At the published base rate, GPT-4 Turbo costs $10.00 per 1M input tokens and $30.00 per 1M output tokens. It supports a 128K context window and is currently marked legacy.
Method & trust
This rate card uses the provider's listed base input, output, and cached-input prices. Workload tables below apply those rates to explicit token counts, cache assumptions, and request volumes; verify provider-specific tiers before committing budget.
Input
$10.00
per 1M tokens
Output
$30.00
per 1M tokens
Cached input
$5.00
per 1M tokens
Context window
128K
max output 4.1K
GPT-4 Turbo cost calculator
What GPT-4 Turbo costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.0333 | $997.50 |
| RAG / search-augmented answers | 8,000 | 500 | $0.075 | $2,250.00 |
| AI coding assistant | 12,000 | 2,000 | $0.144 | $4,320.00 |
| Document summarization | 25,000 | 600 | $0.2555 | $7,665.00 |
| Agentic workflow | 40,000 | 1,500 | $0.315 | $9,450.00 |
| Content generation | 800 | 1,200 | $0.0428 | $1,284.00 |
| Data extraction & tagging | 2,000 | 250 | $0.0255 | $765.00 |
| Translation | 5,000 | 5,500 | $0.2113 | $6,337.50 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Benchmark scores
Third-party composite indices (0-100) via OpenRouter's model catalog, verified Aug 28, 2026. Coding per $$30.00 of output: 0.7.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| GPT-4 Turbo | $10.00 | $30.00 | 128K | $0.054 |
| GPT-3.5 Turbocompare | $0.50 | $1.50 | 16.4K | $0.0032 |
| GLM-4-32B-0414-128K (Z.ai)compare | $0.10 | $0.10 | 128K | $0.00048 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
GPT-4 Turbo costs $10.00 per 1M input tokens and $30.00 per 1M output tokens, with cached input at $5.00 per 1M tokens. Verified Aug 28, 2026 against https://openai.com/api/pricing.
GPT-4 Turbo supports a 128,000-token context window with up to 4,096 output tokens per request, tokenized with cl100k_base.
At $10.00/M input and $30.00/M output, GPT-4 Turbo sits above GPT-3.5 Turbo ($0.50/M in, $1.50/M out) — see the comparison table for full-workload differences.