Verified 2026-10-07 · sourced from OpenAI
100K GPT-6 Luna Tokens — Cost Breakdown
Use this guide to benchmark budgets for 100,000 tokens. Standard pricing is $0.10 per million input tokens and $0.50 per million output tokens. Cached input, when available, reduces costs significantly for repeated contexts.
Reference rates: Standard · ≤272K input · global
USD per million text tokens. Verified 2026-10-07 · Official source
| Mode / prompt size | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤272,000 input | $0.1 | $0.01 | $0.125 | $0.5 |
| Standard >272,000 input | $0.2 | $0.02 | $0.25 | $0.75 |
| Batch ≤272,000 input | $0.05 | $0.005 | $0.0625 | $0.25 |
| Batch >272,000 input | $0.1 | $0.01 | $0.125 | $0.375 |
| Flex ≤272,000 input | $0.05 | $0.005 | $0.0625 | $0.25 |
| Flex >272,000 input | $0.1 | $0.01 | $0.125 | $0.375 |
| Fast mode ≤272,000 input | $0.2 | $0.02 | $0.25 | $1 |
| Fast mode >272,000 input | $0.4 | $0.04 | $0.5 | $1.5 |
1,050,000 context tokens · max output 128,000. Local token counts are estimates; use the provider’s usage counts for an invoice estimate.
Text-only estimate. Local token counts are approximate; use provider-reported usage for billing. Tool, image, audio and video charges are excluded.
Above 272,000 input tokens, the full request uses 2× input/cache rates and 1.5× output rates. Batch/Flex and Fast/Ultrafast are separate processing options, not stackable discounts.
Global endpoint rates shown. Regional processing adds 10% where available and is excluded from this estimate.
Billed output includes reasoning/thinking tokens that cannot be inferred from pasted final text; use API-reported output usage for accurate billing.
Scenario breakdown
Cost estimates for different input/output distributions using 100K total tokens.
| Scenario | Tokens in | Tokens out | Standard cost | Cached cost |
|---|---|---|---|---|
Balanced conversation 50% input · 50% output | 50,000 | 50,000 | $0.0300 | $0.0255 |
Input-heavy workflow 80% input · 20% output | 80,000 | 20,000 | $0.0180 | $0.0108 |
Generation heavy 30% input · 70% output | 30,000 | 70,000 | $0.0380 | $0.0353 |
Cached system prompt 90% cached input · 10% fresh output | 90,000 | 10,000 | $0.0140 | $0.0059 |
Workload multipliers
Convert 100K tokens into daily and monthly run-rate budgets.
| Profile | Runs/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Single workload | 1 | 100,000 | $0.0300 | $0.900 | $0.0059 | $0.177 |
| Daily batch (10 runs) | 10 | 1,000,000 | $0.475 | $14.25 | $0.0930 | $2.79 |
| Team workload (100 runs) | 100 | 10,000,000 | $4.75 | $142.50 | $0.930 | $27.90 |
Frequently asked questions
What is the standard cost of 100K GPT-6 Luna tokens?
100K tokens in a 50/50 conversation mix cost roughly $0.0300 at the published OpenAI rates.
What happens if cached input is enabled?
With cached contexts, the same 100K tokens drop to $0.0255 because input costs fall to $0.010 per million tokens.
How many requests does 100K tokens cover?
If your prompts average around 3,000 tokens per call, 100K total tokens cover about 33 requests.
How fresh is the pricing information?
Prices are taken from https://developers.openai.com/api/docs/models/gpt-6-luna and were last verified on 2026-10-07. models.json keeps this guide in sync with upstream changes.