OpenAI · Pricing & cost calculator
Legacy 8K-context model — kept only for API compatibility. Retire this workload.
Input tokens
$0.03000
per 1,000 tokens
Output tokens
$0.06000
per 1,000 tokens
Context window
8,192
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
$0.075000
at 1,500/500 tokens
Monthly spend
$750
10,000 requests × $0.075000
Could save ~88% with a similar-quality alternative
Same workload at 1,500/500 tokens × 10,000 req/month: $750 → $88. 12× cheaper on input, 128K context.
TrackCost's gateway auto-detects which requests are safe to route to the cheaper model and flags the ones that need GPT-4's full capability. You stay in control — we surface the opportunity.
GPT-4 costs $0.03000 per 1,000 input tokens and $0.06000 per 1,000 output tokens as of the current OpenAI API pricing.
GPT-4o is significantly cheaper than GPT-4 (12× cheaper on input, 128K context) and often works fine for tasks that don't need GPT-4'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 supports up to 8,192 tokens of context. For comparison with other models, use the TrackCost savings calculator.