GPT-6.2 Astra overview
GPT-6.2 Astra by OpenAI
OpenAI calls GPT-6.2 Astra its frontier model for demanding professional work. It scored 5.2 points higher than GPT-6 Astra on Agents' Last Exam.
GPT-6.2 Astra specs
- Model ID
openai/gpt-6.2-astra- Developer
- OpenAI
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What the gains mean in practice
OpenAI says GPT-6.2 Astra can build and revise software, use a computer and work with documents. The model has reasoning, parallel tool calls, structured output and file input, so one request can read a long source and return a result in a fixed shape.
OpenAI also reports that GPT-6.2 Astra is more concise and direct by default than earlier models. If your prompts were written for a chattier model, check whether answers now come back shorter than you expect.
Set reasoning effort first
Reasoning effort is the one request option that matters here. It accepts low, medium or high. Lower values give faster responses and use fewer tokens on reasoning, and higher values give the model more room to work through a hard task.
Start with medium on your own tasks. Move to high for multi-step coding and agent runs that fail on a first pass, and try low for simple extraction or classification where speed matters more.
Astra or Sol
GPT-6.2 Sol is the related model in the same release. Run the same set of prompts through both and compare answer quality, reasoning token use and response time before you commit to one.
Use cases
Build and revise software across a large repository passed in a single 1.05M-token context.
Run agent workflows that call several tools in parallel and return structured output.
Read long documents and attached files, then produce a summary or an extracted record.
Answer questions about screenshots, charts and other images together with text instructions.
Capabilities
- File input
- Reasoning
- Streaming
- Structured outputs
- Function calling
- Vision
GPT-6.2 Astra API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $8 | 1M tokens |
| Output | $40 | 1M tokens |
| Cached input | $0.4 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 17, 2026.
GPT-6.2 Astra vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $8 | $40 | |
| $1 | $5 | |
| $2 | $10 | |
| $2 | $10 | |
| $2.116 | $10.58 |
How to use the GPT-6.2 Astra API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-6.2-astra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "openai/gpt-6.2-astra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "openai/gpt-6.2-astra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Related articles
GPT-6.2 Astra FAQ
How much does GPT-6.2 Astra cost?
GPT-6.2 Astra costs $8 / 1M tokens for input and $40 / 1M tokens for output on AI/ML API. Cached input is billed at $0.4 / 1M tokens.
What inputs does GPT-6.2 Astra accept?
It accepts text and image input, and file input is listed among its capabilities. The output is text.
How do I control how much the model reasons?
Set the reasoning effort option to low, medium or high. Lower values give faster responses and use fewer reasoning tokens.
How long can a response be?
The maximum output is 128,000 tokens per response. Streaming is supported if you want to read the text as it is generated.
What changed against GPT-6 Astra?
OpenAI reports a gain of 5.2 points on Agents' Last Exam, and 81.85 percent of rubric credit on one evaluation against 78.05 percent for GPT-6 Astra. It also describes GPT-6.2 Astra as more concise and direct by default than earlier models.
What is the GPT-6.2 Astra model ID?
Use openai/gpt-6.2-astra as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of GPT-6.2 Astra?
GPT-6.2 Astra accepts up to 1,050,000 tokens of context and returns up to 128,000 output tokens.


