GPT-5.6 Luna

gpt-5.6-luna by OpenAI Released July 9, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.2 / 1M
Output from
$1.2 / 1M
Cached input from
$0.02 / 1M
Context window
1.05M
Endpoints
8
from 4 providers
Regions
Monde, Europe, États-Unis

About GPT-5.6 Luna

GPT-5.6 Luna est un modèle rapide et économique issu de la série GPT-5.6 d'OpenAI.

GPT-5.6 Luna est un modèle conversationnel développé par OpenAI, disponible sur Eden AI via 8 endpoints chez 4 fournisseurs, à partir de 0,2 $ par million de tokens en entrée et 1,2 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

8 endpoints from 4 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. Au-delà de 272K tokens : 0,4 $ en entrée / 1,8 $ en sortie par 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Microsoft AzureOfficial−%azure/gpt-5.6-luna
Monde
922K
$0.2$0.2
$1.2
$0.02
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-gpt-5-6-luna@eu
Europe
922K
$0.2$0.2
$1.2
$0.02
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-5-6-luna
Monde
922K
$0.2$0.2
$1.2
$0.02
ReasoningToolsJSONCacheVisionWeb
OpenAI (États-Unis)Official−%openai/gpt-5.6-luna
États-Unis
1.05M
$0.2$0.2
$1.2
$0.02
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/openai.gpt-5.6-luna
Monde
1.05M
$0.22$0.22
$1.32
$0.022
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/openai.gpt-5.6-luna@us
États-Unis
1.05M
$0.22$0.22
$1.32
$0.022
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/gpt-5.6-luna@eu
Europe
922K
$0.22$0.22
$1.32
$0.022
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (États-Unis)Official−%azure/gpt-5.6-luna@us
États-Unis
922K
$0.22$0.22
$1.32
$0.022
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
1.58 s
Microsoft Azure (Europe)
Lowest latency
1.34 s
Microsoft Azure (Europe)
Highest throughput
76.87 tok/s
Databricks (Europe)
Best availability
100%
Amazon Web Services
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
1.6 s
1.41 s
12.73 s
34.55 tok/s
99.96%
71.45%
0.34%
0.72%
Databricks (Europe)
1.81 s
3.46 s
12.69 s
76.87 tok/s
99.97%
44.76%
20.42%
17.4%
Databricks
2.24 s
3.48 s
12.64 s
76.17 tok/s
99.97%
48.41%
19.57%
17.47%
OpenAI (États-Unis)
2.14 s
2.64 s
10.89 s
68.39 tok/s
99.98%
84.41%
0.05%
0.68%
Amazon Web Services
4.51 s
5.13 s
8.55 s
11.92 tok/s
100%
95.88%
0.26%
66.67%
Amazon Web Services (États-Unis)
s
s
s
tok/s
%
%
%
%
Microsoft Azure (Europe)
1.58 s
1.34 s
12.96 s
34.09 tok/s
99.96%
71.43%
0.38%
0.64%
Microsoft Azure (États-Unis)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-5.6 Luna with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about GPT-5.6 Luna

On Eden AI, prices for this model start at $0.2 per million input tokens and $1.2 per million output tokens. Prices differ by endpoint; the providers table lists each one. Au-delà de 272K tokens : 0,4 $ en entrée / 1,8 $ en sortie par 1M.

Up to 1.05M tokens, depending on the endpoint.

8 endpoints from 4 providers, available in: Monde, Europe, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 1.58 s (Microsoft Azure (Europe)) and the highest throughput was 76.87 tokens per second (Databricks (Europe)).