Start free

GPT · Fast / Budget · 922K context window

GPT 5.6 Luna pricing for pdf summarization

$0.004800 per call at 15,000 input / 1,500 output tokens.

Per call

$0.004800

10K calls/mo

$48

Cache savings

90% off input

Batch savings

50% off all

Calculate your GPT 5.6 Luna costs

Adjust token counts, volume, and discount toggles to model your pdf summarization spend. Prices verified daily against provider pricing pages.

Configure your usage

15,000
100100K
1,500
5050K
10,000
1001M

Estimated cost

Monthly cost
$48
10,000 calls/month
Cost per call$0.004800
Daily cost$2
Input rate$0.20/MTok
Output rate$1.20/MTok
Analyze your real spend

Quick start

Call GPT 5.6 Luna with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5.6-luna",
    max_tokens=1500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.004800 per call at standard rates
# Input:  $0.20/MTok
# Output: $1.20/MTok

How GPT 5.6 Luna compares on cost

Per-call cost for all models scoring 50+ on pdf summarization benchmarks. Hover for details.

GPT 6 Luna$0.002250GPT 5.6 Luna$0.004800GPT 5.4 Nano$0.004875Gemini 3.5 Flash-Lite$0.008250Gemini 3 Flash$0.0120Gemini 3.6 Flash$0.0169Gemini 3.7 Flash$0.0169Gemini 3.8 Flash$0.0169GPT 5.4 Mini$0.0180Grok Build 0.1$0.0180Claude Haiku 4.5$0.0225Grok 4.3$0.0225Gemini 3.5 Flash$0.0360Grok 4.6$0.0390Grok 4.5$0.0390Grok 4.7$0.0390Claude Sonnet 5$0.0450GPT 6 Sol$0.0450GPT 5.6 Terra$0.0480Gemini 3.1 Pro$0.0480GPT 5.4$0.0600Claude Sonnet 4.6$0.0675Claude Opus 5.5$0.0900GPT 5.6 Sol$0.0900Claude Opus 4.8$0.1125Claude Opus 5$0.1125Claude Opus 4.7$0.1125Claude Opus 4.6$0.1125GPT 5.5$0.1200Claude Fable 5.1$0.2250Claude Fable 5$0.2250GPT 6 Astra$0.2250

Highest-quality affordable option: Gemini 3 Flash at $0.0120/call (2.5x the cost, 83/100 quality). GPT 5.6 Luna is already the cheapest choice for pdf summarization.

What drives pdf summarization cost

PDFs are the worst case for input cost: extracted text carries page furniture, headers, and footnotes that inflate token counts well past what the content warrants. Cleaning the extraction before sending it often cuts more cost than changing models. Long PDFs also routinely cross long-context pricing thresholds, so chunking is both a quality and a cost decision.

For GPT 5.6 Luna specifically, that means output tokens cost 6.0x more than input, at $1.20 vs $0.20 per MTok. At this use case’s 15,000/1,500 token split, output accounts for 38% of the $0.004800 per-call cost.

Complete GPT 5.6 Luna pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$0.2015,000
Output$1.201,500

Prompt caching: 90% off input tokens

Caching drops input cost from $0.20 to $0.02/MTok. For repeated system prompts, that saves $0.002700 per call.

Batch API: 50% off all tokens

Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.

Monthly cost projections

Monthly volumeCost per callStandard monthlyCached monthlyYou save with caching
10,000 calls$0.004800$48$21$27
50,000 calls$0.004800$240$105$135
100,000 calls$0.004800$480$210$270
500,000 calls$0.004800$2,400$1,050$1,350
1,000,000 calls$0.004800$4,800$2,100$2,700

GPT 5.6 Luna quality benchmarks for pdf summarization

Consider alternatives for pdf summarization

Scores 57/100 (rank #29 of 88). Better options exist at similar price points for pdf summarization.

Top-ranked: Gemini 3 Flash (83/100) at $0.0120/call

Performance across all task types

GPT 5.6 Luna scores by task type. PDF Summarization highlighted.

Classification91Reasoning86Q&A85Extraction74Creative Writing69Code Review68Code Generation62Summarization *57
Task typeConfidence scoreRank out of 88
Classification91/100#1
Reasoning86/100#19
Q&A85/100#4
Extraction74/100#13
Creative Writing69/100#19
Code Review68/100#6
Code Generation62/100#17
Summarization(current page)57/100#29

Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

Alternative models for pdf summarization

10 models score 80+ on pdf summarization benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (150% more, 83/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs GPT
Gemini 3 FlashGemini$0.50$3.0083/100$0.0120150% more
Gemini 3.6 FlashGemini$0.75$3.7575/100$0.0169252% more
Gemini 3.7 FlashGemini$0.75$3.7579/100$0.0169252% more
Gemini 3.8 FlashGemini$0.75$3.7581/100$0.0169252% more
Claude Haiku 4.5Claude$1.00$5.0082/100$0.0225369% more
Gemini 3.5 FlashGemini$1.50$9.0076/100$0.0360650% more
Gemini 3.1 ProGemini$2.00$12.0080/100$0.0480900% more
Grok 4.7Grok$2.00$6.0075/100$0.0390712% more
Claude Fable 5Claude$10.00$50.0077/100$0.22504587% more
GPT 6 AstraGPT$10.00$50.0076/100$0.22504587% more

About GPT 5.6 Luna

Provider

GPT

Tier

Fast / Budget

Context

922K tokens

Released

Jul 2026

Other models from GPT

ModelTierInput $/MTokOutput $/MTokContext
GPT 5.5Flagship$5.00$30.001.1M
GPT 5.4Mid-tier$2.50$15.001.1M
GPT 5.6 SolFlagship$4.00$20.00922K
GPT 5.6 TerraMid-tier$2.00$12.00922K
GPT 3.5 TurboFast / Budget$0.50$1.5016K
GPT 3.5 Turbo (0125)Fast / Budget$0.50$1.5016K
GPT 4 (0613)Flagship$30.00$60.008K
GPT 4 Turbo (2024-04-09)Flagship$10.00$30.00128K
GPT 4Flagship$30.00$60.008K
GPT 4 TurboFlagship$10.00$30.00128K
GPT 4.1Mid-tier$2.00$8.001.0M
GPT 4.1 MiniFast / Budget$0.40$1.601.0M
GPT 4.1 NanoFast / Budget$0.10$0.401.0M
GPT 4oMid-tier$2.50$10.00128K
GPT 4o (2024-05-13)Flagship$5.00$15.00128K
GPT 4o MiniFast / Budget$0.15$0.60128K
GPT 5Mid-tier$1.25$10.00272K
GPT 5 MiniFast / Budget$0.25$2.00272K
GPT 5 NanoFast / Budget$0.05$0.40272K
GPT 5 ProFlagship$15.00$120.00400K
GPT 5.1Mid-tier$1.25$10.00272K
GPT 5.2Mid-tier$1.75$14.00272K
GPT 5.2 ProFlagship$21.00$168.00272K
GPT 5.4 MiniFast / Budget$0.75$4.50272K
GPT 5.4 NanoFast / Budget$0.20$1.25272K
GPT 5.4 ProFlagship$30.00$180.001.1M
GPT 5.5 ProFlagship$30.00$180.001.1M
GPT 6 AstraFlagship$10.00$50.00922K
GPT 6 LunaFast / Budget$0.10$0.50922K
GPT 6 SolFlagship$2.00$10.00922K
o1Flagship$15.00$60.00200K
o1 ProFlagship$150.00$600.00200K
o3Mid-tier$2.00$8.00200K
o3 MiniFast / Budget$1.10$4.40200K
o3 ProFlagship$20.00$80.00200K
o4 MiniFast / Budget$1.10$4.40200K
GPT 6.1 SolFlagship$2.00$10.00922K

You can compare GPT 5.6 Luna head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

GPT 5.6 Luna pricing for other use cases

See how GPT 5.6 Luna costs change across different workload types.

Code Generation

$0.005200/call

Unit Test Generation

$0.006600/call

SQL Generation

$0.001500/call

API Generation

$0.007800/call

Code Refactoring

$0.005600/call

Code Review

$0.003400/call

PR Review

$0.005200/call

Security Review

$0.004200/call

Bug Detection

$0.003400/call

Document Summarization

$0.003200/call

Meeting Notes

$0.004000/call

Email Summarization

$0.001200/call

Chatbot

$0.001600/call

RAG Pipeline

$0.003000/call

Customer Support Bot

$0.001800/call

FAQ Bot

$0.001260/call

Data Extraction

$0.002000/call

JSON Extraction

$0.001560/call

Invoice Parsing

$0.001120/call

Resume Parsing

$0.001460/call

Chain of Thought

$0.006600/call

Legal Analysis

$0.006800/call

Math Reasoning

$0.003900/call

Financial Analysis

$0.006400/call

Content Moderation

$0.000220/call

Sentiment Analysis

$0.000220/call

Categorization

$0.000340/call

Intent Detection

$0.000180/call

Copywriting

$0.002500/call

Blog Writing

$0.009800/call

Marketing Copy

$0.003760/call

Product Descriptions

$0.001900/call

Related pages

Frequently asked questions

How much does GPT 5.6 Luna cost for pdf summarization per API call?

A typical pdf summarization call using GPT 5.6 Luna costs about $0.004800 per call. This estimate uses 15,000 input tokens and 1,500 output tokens at standard rates. Standard rates are $0.20 per million input tokens and $1.20 per million output tokens.

Is GPT 5.6 Luna the best model for pdf summarization?

GPT 5.6 Luna scores 57 out of 100 on pdf summarization benchmarks overall. It ranks #29 across all 88 models in our cross-provider registry. The highest-ranked model for this task is Gemini 3 Flash from Gemini. That model scores 83/100 on this task type. Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

What is the cheapest model for pdf summarization with good quality?

The most affordable model for pdf summarization above 80/100 quality is Gemini 3 Flash. It comes from Gemini at $0.50 per million input tokens. Output costs $3.00 per million tokens with a quality score of 83/100. Gemini 3 Flash costs more per call than GPT 5.6 Luna but scores higher on quality benchmarks for this task type.

How can I reduce my GPT 5.6 Luna costs for pdf summarization?

Three strategies lower GPT 5.6 Luna costs for this task type effectively. Prompt caching gives a 90% discount on input tokens when reusing system prompts. The batch API gives 50% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.004800 to about $0.000240 per call.

How does GPT 5.6 Luna pricing compare to other GPT models?

GPT has 37 other models alongside GPT 5.6 Luna today: GPT 5.5 at $5.00/$30.00 per million tokens (flagship), GPT 5.4 at $2.50/$15.00 per million tokens (mid-tier), GPT 5.6 Sol at $4.00/$20.00 per million tokens (flagship), GPT 5.6 Terra at $2.00/$12.00 per million tokens (mid-tier), GPT 3.5 Turbo at $0.50/$1.50 per million tokens (fast / budget), GPT 3.5 Turbo (0125) at $0.50/$1.50 per million tokens (fast / budget), GPT 4 (0613) at $30.00/$60.00 per million tokens (flagship), GPT 4 Turbo (2024-04-09) at $10.00/$30.00 per million tokens (flagship), GPT 4 at $30.00/$60.00 per million tokens (flagship), GPT 4 Turbo at $10.00/$30.00 per million tokens (flagship), GPT 4.1 at $2.00/$8.00 per million tokens (mid-tier), GPT 4.1 Mini at $0.40/$1.60 per million tokens (fast / budget), GPT 4.1 Nano at $0.10/$0.40 per million tokens (fast / budget), GPT 4o at $2.50/$10.00 per million tokens (mid-tier), GPT 4o (2024-05-13) at $5.00/$15.00 per million tokens (flagship), GPT 4o Mini at $0.15/$0.60 per million tokens (fast / budget), GPT 5 at $1.25/$10.00 per million tokens (mid-tier), GPT 5 Mini at $0.25/$2.00 per million tokens (fast / budget), GPT 5 Nano at $0.05/$0.40 per million tokens (fast / budget), GPT 5 Pro at $15.00/$120.00 per million tokens (flagship), GPT 5.1 at $1.25/$10.00 per million tokens (mid-tier), GPT 5.2 at $1.75/$14.00 per million tokens (mid-tier), GPT 5.2 Pro at $21.00/$168.00 per million tokens (flagship), GPT 5.4 Mini at $0.75/$4.50 per million tokens (fast / budget), GPT 5.4 Nano at $0.20/$1.25 per million tokens (fast / budget), GPT 5.4 Pro at $30.00/$180.00 per million tokens (flagship), GPT 5.5 Pro at $30.00/$180.00 per million tokens (flagship), GPT 6 Astra at $10.00/$50.00 per million tokens (flagship), GPT 6 Luna at $0.10/$0.50 per million tokens (fast / budget), GPT 6 Sol at $2.00/$10.00 per million tokens (flagship), o1 at $15.00/$60.00 per million tokens (flagship), o1 Pro at $150.00/$600.00 per million tokens (flagship), o3 at $2.00/$8.00 per million tokens (mid-tier), o3 Mini at $1.10/$4.40 per million tokens (fast / budget), o3 Pro at $20.00/$80.00 per million tokens (flagship), o4 Mini at $1.10/$4.40 per million tokens (fast / budget), GPT 6.1 Sol at $2.00/$10.00 per million tokens (flagship). The right choice depends on whether your pdf summarization workload prioritizes quality, cost, or speed.

What context window does GPT 5.6 Luna support?

GPT 5.6 Luna supports a context window of 922K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For pdf summarization, typical calls use 15,000 input and 1,500 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.

Track what you spend on AI

This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.

Free spend teardownStart free dashboard