GPT-5.6 Luna (batch)
by OpenAI · openai/gpt-5.6-luna:batch · #93 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.10
per 1M tokens
Output
$0.60
per 1M tokens
Blended (3:1)
$0.225
3 input : 1 output
Cache read
$0.01
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-5.6 Luna (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.225 | $0.0108 | — |
| 50% | $0.191 | $0.0063 | −42% |
| 90% | $0.164 | $0.0027 | −75% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00023 | $0.23 |
| Document summary | 8,000 | 1,000 | $0.0014 | $1.40 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0042 | $4.20 |
| Long-context analysis | 150,000 | 5,000 | $0.018 | $18.00 |
Performance
Intelligence Index
37.3
AA composite quality
Coding Index
71.4
Math Index
—
Agentic Index
42.7
Output speed
133 tok/s
median
Time to first token
92.18s
median
Time to first answer
92.18s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 91.1% |
| Humanity's Last Exam | 39.5% |
| SciCode | 53.6% |
| AA-LCR (Long Context Reasoning) | 83.7% |
| Terminal-Bench 2.1 | 80.9% |
| τ³-Bench Banking | 31.1% |
Specs
Context window
1.05M
tokens
Max output
128K
tokens
Input modalities
file, image, text
Tokenizer
GPT