GPT-5 Cost Calculator: OpenAI reasoning model API pricing
Estimate cost for GPT-5 — OpenAI's flagship reasoning model. Input $0.625/1M, output $5/1M (as of 2026). 400K context window, reasoning tokens billed at the output rate.
GPT-5 pricing (per 1M tokens)
OpenAI's flagship — 400K context, top-tier reasoning. Output is 8× more expensive than input.
| Model | Input | Output | Context |
|---|---|---|---|
| GPT-5 | $0.625 | $5.00 | 400K |
What you'll use this for
Forecasting AI spend is the difference between a sustainable feature and an unexpected invoice. Pre-flight every prompt.
Budget planning
Forecast monthly and annual costs based on expected call volume and prompt size.
Model selection
Compare model size variants side-by-side to pick the right cost/quality tradeoff.
Cost optimization
See how prompt caching, shorter outputs, and smaller models slash bills.
Pricing transparency
All rates visible up front — no surprises after the invoice arrives.
How to estimate GPT costs
Paste your prompt
Drop a representative prompt into the left editor. Tokens are estimated at ~4 chars/token.
Set expected output tokens
How long do you expect the response to be? Default 500 covers a paragraph or two.
Set calls per day
How often does this prompt run? 100 = trial-scale, 10000+ = production-scale.
Read the forecast
Per-call, per-day, per-month, per-year totals update live as you tweak inputs.
Frequently asked questions
We use ~4 chars/token, accurate to about ±20%. For exact counts use the model-specific token counter such as the OpenAI token counter.
OpenAI's public pricing pages as of 2026. Subject to change — always confirm at openai.com/pricing before signing contracts.
Yes. Completely free, no signup, runs entirely in your browser.
Toggle "Cached input" to apply the model's published cached rate. OpenAI's prompt caching kicks in for repeated prefixes ≥ 1024 tokens and the discount is per-model (typically 50–87%). DeepSeek and Anthropic offer ~90% off cached input.
Provider tokenizers can differ slightly from our estimate; system prompts and tool definitions also count toward input; rates change over time. Treat this as a planning tool, not a billing replica.
About GPT-5 API pricing
GPT-5 is OpenAI's flagship: 400K context, deep reasoning, multimodal. At $0.625/1M input and $5/1M output (refreshed 2026-05) it is dramatically cheaper than the 2025 launch pricing — but for complex agents, long-document synthesis, and hard reasoning it earns it.
When GPT-5 is worth the spend
- Multi-step agentic workflows with tool use.
- Long-document analysis up to 400K tokens.
- Hard reasoning: math, code synthesis, planning.
- Cases where one good call beats five mediocre ones.
How to control spend
- Bound output tokens — output is 5x input.
- Cache system prompts (~90% discount).
- Route simpler subtasks to GPT-4o or 4o mini.
- Use Batch API where realtime isn't required (~50% off).