tokevenGPT · Fast / Budget · 1,050K context window
GPT 5.6 Luna pricing for code generation
$0.005200 per call at 2,000 input / 4,000 output tokens.
Per call
$0.005200
10K calls/mo
$52
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 code generation spend. Prices verified daily against provider pricing pages.
Configure your usage
Estimated cost
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=4000,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.005200 per call at standard rates
# Input: $0.20/MTok
# Output: $1.20/MTokHow GPT 5.6 Luna compares on cost
Per-call cost for all models scoring 50+ on code generation benchmarks. Hover for details.
Cheapest viable option: Claude Sonnet 5 at $0.0440/call (-746% less, 93/100 quality).
What drives code generation cost
Cost here is dominated by output, not input: the model writes far more than you ask. A prompt with a short spec and a few reference files runs 2K input, but a complete module comes back at 4K output or more, so a model's output rate matters roughly twice as much as its input rate. The biggest saving is not a cheaper model: it is caching the system prompt and coding standards you resend on every call.
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 2,000/4,000 token split, output accounts for 92% of the $0.005200 per-call cost.
Complete GPT 5.6 Luna pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $0.20 | 2,000 |
| Output | $1.20 | 4,000 |
Prompt caching: 90% off input tokens
Caching drops input cost from $0.20 to $0.02/MTok. For repeated system prompts, that saves $0.000360 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 volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.005200 | $52 | $48.4 | $3.6 |
| 50,000 calls | $0.005200 | $260 | $242 | $18 |
| 100,000 calls | $0.005200 | $520 | $484 | $36 |
| 500,000 calls | $0.005200 | $2,600 | $2,420 | $180 |
| 1,000,000 calls | $0.005200 | $5,200 | $4,840 | $360 |
GPT 5.6 Luna quality benchmarks for code generation
Consider alternatives for code generation
Scores 70/100 (rank #6 of 20). Better options exist at similar price points for code generation.
Top-ranked: Claude Fable 5 (96/100) at $0.2200/call
Performance across all task types
GPT 5.6 Luna scores by task type. Code Generation highlighted.
| Task type | Confidence score | Rank out of 20 |
|---|---|---|
| Classification | 91/100 | #1 |
| Extraction | 89/100 | #2 |
| Q&A | 85/100 | #4 |
| Summarization | 84/100 | #4 |
| Code Generation(current page) | 70/100 | #6 |
| Code Review | 68/100 | #6 |
| Reasoning | 63/100 | #6 |
| Creative Writing | 58/100 | #7 |
Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.
Alternative models for code generation
9 models score 80+ on code generation benchmarks, sorted by input rate. Cheapest: Claude Sonnet 5 (-746% less, 93/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs GPT |
|---|---|---|---|---|---|---|
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 93/100 | $0.0440 | 746% more |
| GPT 5.6 Terra | GPT | $2.00 | $12.00 | 86/100 | $0.0520 | 900% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 86/100 | $0.0520 | 900% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 84/100 | $0.0650 | 1150% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 92/100 | $0.0660 | 1169% more |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 94/100 | $0.0880 | 1592% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 95/100 | $0.1100 | 2015% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 91/100 | $0.1300 | 2400% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 96/100 | $0.2200 | 4131% more |
About GPT 5.6 Luna
Provider
GPT
Tier
Fast / Budget
Context
1,050K tokens
Released
Jul 2026
Other models from GPT
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| GPT 5.5 | Flagship | $5.00 | $30.00 | 1,050K |
| GPT 5.4 | Mid-tier | $2.50 | $15.00 | 1,050K |
| GPT 5.6 Sol | Flagship | $4.00 | $20.00 | 1,050K |
| GPT 5.6 Terra | Mid-tier | $2.00 | $12.00 | 1,050K |
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.
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
PDF Summarization
$0.004800/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 code generation per API call?
A typical code generation call using GPT 5.6 Luna costs about $0.005200 per call. This estimate uses 2,000 input tokens and 4,000 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 code generation?
GPT 5.6 Luna scores 70 out of 100 on code generation benchmarks overall. It ranks #6 across all 20 models in our cross-provider registry. The highest-ranked model for this task is Claude Fable 5 from Claude. That model scores 96/100 on this task type. Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.
What is the cheapest model for code generation with good quality?
The most affordable model for code generation above 80/100 quality is Claude Sonnet 5. It comes from Claude at $2.00 per million input tokens. Output costs $10.00 per million tokens with a quality score of 93/100. Switching from GPT 5.6 Luna to Claude Sonnet 5 saves about -746% per API call.
How can I reduce my GPT 5.6 Luna costs for code generation?
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 $0.005200 to about $0.000260 per call.
How does GPT 5.6 Luna pricing compare to other GPT models?
GPT has 4 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). The right choice depends on whether your code generation workload prioritizes quality, cost, or speed.
What context window does GPT 5.6 Luna support?
GPT 5.6 Luna supports a context window of 1,050K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For code generation, typical calls use 2,000 input and 4,000 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.