GPT-6 Astra

gpt-6-astra by OpenAI Released September 5, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$10 / 1M
Output from
$50 / 1M
Cached input from
$1 / 1M
Context window
1.05M
Endpoints
7
from 4 providers
Regions
Monde, Europe, États-Unis

About GPT-6 Astra

GPT-6 Astra est le modèle phare d'OpenAI destiné aux tâches exigeantes de bout en bout.

GPT-6 Astra est un modèle conversationnel développé par OpenAI, disponible sur Eden AI via 7 endpoints chez 4 fournisseurs, à partir de 10 $ par million de tokens en entrée et 50 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

7 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 : 20 $ en entrée / 75 $ en sortie par 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Databricks (Europe)Official−%databricks/databricks-gpt-6-astra@eu
Europe
$10$10
$50
$1
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-gpt-6-astra
Monde
$10$10
$50
$1
ReasoningToolsJSONCacheVisionWeb
Microsoft AzureOfficial−%azure/gpt-6-astra
Monde
922K
$10$10
$50
$1
ReasoningToolsJSONCacheVisionWeb
OpenAI (États-Unis)Official−%openai/gpt-6-astra
États-Unis
1.05M
$10$10
$50
$1
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/openai.gpt-6-astra
Monde
1.05M
$11$11
$55
$1.1
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/openai.gpt-6-astra@us
États-Unis
1.05M
$11$11
$55
$1.1
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (États-Unis)Official−%azure/gpt-6-astra@us
États-Unis
922K
$11$11
$55
$1.1
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.47 s
Microsoft Azure
Lowest latency
6.4 s
OpenAI (États-Unis)
Highest throughput
43.43 tok/s
Databricks (Europe)
Best availability
99.95%
Databricks
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Databricks (Europe)
3.83 s
7.24 s
40.27 s
43.43 tok/s
99.94%
76.09%
21.49%
8.82%
Databricks
3.64 s
7.33 s
39.99 s
42.79 tok/s
99.95%
76.92%
21.49%
11.11%
Microsoft Azure
0.47 s
8.6 s
66.06 s
41.49 tok/s
82.43%
87.88%
3.23%
32.26%
OpenAI (États-Unis)
3.43 s
6.4 s
43.09 s
31.91 tok/s
99.92%
85.5%
0.12%
0.19%
Amazon Web Services
s
s
s
tok/s
%
%
%
%
Amazon Web Services (États-Unis)
s
s
s
tok/s
%
%
%
%
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-6 Astra 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-6 Astra

On Eden AI, prices for this model start at $10 per million input tokens and $50 per million output tokens. Prices differ by endpoint; the providers table lists each one. Au-delà de 272K tokens : 20 $ en entrée / 75 $ en sortie par 1M.

Up to 1.05M tokens, depending on the endpoint.

7 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 0.47 s (Microsoft Azure) and the highest throughput was 43.43 tokens per second (Databricks (Europe)).