OpenAI · Pricing & cost calculator
Legacy flagship — GPT-4o is usually better AND cheaper. Most teams should switch.
Input tokens
$0.01000
per 1,000 tokens
Output tokens
$0.03000
per 1,000 tokens
Context window
128,000
tokens max
Prices sourced from OpenAI's public API rate card. Last reviewed April 2026.
Drag the sliders. The math runs in your browser.
Per request
$0.030000
at 1,500/500 tokens
Monthly spend
$300
10,000 requests × $0.030000
Could save ~71% with a similar-quality alternative
Same workload at 1,500/500 tokens × 10,000 req/month: $300 → $88. 4× cheaper on input, similar quality.
TrackCost's gateway auto-detects which requests are safe to route to the cheaper model and flags the ones that need GPT-4 Turbo's full capability. You stay in control — we surface the opportunity.
GPT-4 Turbo costs $0.01000 per 1,000 input tokens and $0.03000 per 1,000 output tokens as of the current OpenAI API pricing.
GPT-4o is significantly cheaper than GPT-4 Turbo (4× cheaper on input, similar quality) and often works fine for tasks that don't need GPT-4 Turbo's full capability. TrackCost automatically suggests model downgrades where safe.
The three highest-leverage ways: (1) route requests to a cheaper model where possible, (2) cache identical requests so you don't pay twice for the same response, (3) set hard monthly budgets that block requests when exceeded. TrackCost automates all three at the gateway layer.
GPT-4 Turbo supports up to 128,000 tokens of context. For comparison with other models, use the TrackCost savings calculator.