OpenAI's cheapest 5.6 tier. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
Modalities
Text+Image → Text
Below release
Not established
Weights
Not published
Where it sits in the catalogue Kyma measures
Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.
$0.2944
output $1.767 · cached $0.027
median $1.013 · best $0.0435
$1.767
per 1M tokens generated
median $3.528 · best $0.1886
96.53%
1,470 observations since 2026-08-01
median 99.5% · best 100.0%
61 tok/s
from traffic, 7d — real prompts, not a probe
median 44.9 tok/s · best 160.1 tok/s
4.30 s
from traffic, 7d — real prompts, not a probe
median 1.34 s · best 0.46 s
1.05M
max output 128,000
published by OpenAI, not measured here
Tick above each rail is this model, below it the other 83. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.
Usage
How much this model is actually called here.
Rank
#14
of 113 active models
Tokens served
81.6M
all-time
Platform share
1.1%
of all tokens
How it behaves under real clients
The same model answering different prompt shapes — measured, not benchmarked.
| Client | Requests | Tokens | Throughput | To first token | p95 total | Completed |
|---|---|---|---|---|---|---|
| Lua/OpenResty | 345 | 1.4M | 50 tok/s | 4.81 s | 19 s | 97.7% |
| Node.js App | 244 | 19.4M | 66 tok/s | 2.82 s | 34 s | 83.6% |
| Java/Kotlin App | 120 | 132.1K | 71 tok/s | 3.68 s | 17 s | 100% |
Grouped by the client that sent the request. Not a benchmark: the same model on different prompt shapes. Throughput and time-to-first-token are medians; p95 is the slowest response in twenty. 5 clients under 100 requests not shown.
Pricing
Pay per token. Cached input bills at this model’s own cached rate, listed below.
+ Estimate your workload− Estimate your workload
Estimated monthly cost
$39.36
$1.31 / day on GPT-5.6 Luna
Same workload on:
Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.
How it compares
Against the peers people actually weigh it against.
| Spec | GPT-5.6 Luna | GPT-5.6 Sol Pro | GPT-5.6 Sol |
|---|---|---|---|
| Input /1M | $0.2944 | $2.70 | $3.151 |
| Output /1M | $1.767 | $13.50 | $15.753 |
| Context | 1M | 1M | 1M |
| Tools | Yes | Yes | Yes |
| Reasoning | Yes | Yes | Yes |
| Throughput | 61 tok/s | 32 tok/s |
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers GPT-5.6 Luna. No card required.
Get API key → - 2
Make your first request
Drop in your key and send a chat completion — fully OpenAI-compatible.
curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.6-luna", "messages": [ {"role": "user", "content": "Explain prompt caching in one paragraph."} ] }' - 3
Stream responses
Add
"stream": trueto receive tokens as they arrive.curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.6-luna", "stream": true, "messages": [{"role": "user", "content": "Hello!"}] }'
FAQ
Common questions about this model.
What is the context window of GPT-5.6 Luna?
How much does the GPT-5.6 Luna API cost?
Does GPT-5.6 Luna support function calling?
Are the weights for GPT-5.6 Luna publicly available?
Is GPT-5.6 Luna ever served below the precision its creator released it at?
How do I use GPT-5.6 Luna?
More models by OpenAI
See all 15 →| Model | Context | Input | Output |
|---|---|---|---|
GPT-6.1 Sol | 1M | $2.70 | $13.50 |
GPT-6 Luna | 1M | $0.1639 | $0.8195 |
GPT Image 2.5 Flare | — | $0.019 / image | |
GPT-6 Astra | 1M | $13.50 | $67.50 |
GPT Transcribe | — | $0.006075 / min | |
GPT-5.6 Terra | 1M | $2.70 | $16.20 |
GPT-5.6 Luna Pro | 1M | $0.2703 | $1.621 |
GPT-5.6 Terra Pro | 1M | $2.70 | $16.20 |
