GPT-6.2 Astra

gpt-6.2-astra by OpenAI Released November 18, 2026
New · Reasoning · Function calling · Structured output · Prompt caching · Web search · Computer use · Image input · File input · EU hosting
Input from
$8 / 1M
Output from
$40 / 1M
Cached input from
$0.4 / 1M
Context window
1.05M
Endpoints
4
from 2 providers
Regions
Global, Europe, United States

About GPT-6.2 Astra

GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.

GPT-6.2 Astra is a chat model by OpenAI, available on Eden AI through 4 endpoints from 2 providers, from $8 per million input tokens and $40 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

4 endpoints from 2 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. Above 272K tokens: $16 input / $60 output per 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Microsoft Azureazure/gpt-6.2-astra
Global
1.05M
$8
$40
$0.4
Reasoning · Tools · JSON · Cache · Vision · Web
OpenAI (United States)openai/gpt-6.2-astra
United States
1.05M
$8
$40
$0.4
Official · Reasoning · Tools · JSON · Cache · Vision · Web
Microsoft Azure (United States)azure/gpt-6.2-astra@us
United States
1.05M
$8.8
$44
$0.44
Reasoning · Tools · JSON · Cache · Vision · Web
Microsoft Azure (Europe)azure/gpt-6.2-astra@eu
Europe
1.05M
$9.6
$48
$0.48
Reasoning · Tools · JSON · Cache · Vision · Web

Performance

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

Fastest first token
0.99 s
Microsoft Azure (Europe)
Lowest latency
1.17 s
Microsoft Azure (Europe)
Highest throughput
16.4 tok/s
OpenAI (United States)
Best availability
100%
Microsoft Azure (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
1.12 s
1.37 s
5.4 s
4.36 tok/s
100%
51.24%
0%
0%
OpenAI (United States)
2.38 s
4.97 s
22.13 s
16.4 tok/s
97.83%
58.07%
8.33%
0%
Microsoft Azure (Europe)
0.99 s
1.17 s
4.33 s
2.91 tok/s
100%
70.15%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GPT-6.2 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": "gpt-6.2-astra",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about GPT-6.2 Astra

On Eden AI, prices for this model start at $8 per million input tokens and $40 per million output tokens. Prices differ by endpoint; the providers table lists each one. Above 272K tokens: $16 input / $60 output per 1M.

Up to 1.05M tokens, depending on the endpoint.

4 endpoints from 2 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Can I run GPT-6.2 Astra in the EU? 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. ‖ How fast is GPT-6.2 Astra? Over the last 30 days, the fastest first token was 0.99 s (Microsoft Azure (Europe)) and the highest throughput was 16.4 tokens per second (OpenAI (United States)).