Felo API PlatformFelo API Platform
Back to models
OpenAIresponses

GPT-6.2 Astra API

OpenAI GPT-6.2 Astra is a frontier model for complex professional work, multilingual vision tasks, coding, research, and bounded agentic workflows.

OpenAI GPT-6.2 Astra is described as OpenAI's most capable and aligned model, designed for the hardest professional work. It supports text input, image input, and text output, with multilingual capabilities and vision. Its default tone is concise and direct, and it can be tuned for different applications.

The model is designed for sustained reasoning across code, applications, and complex documents. It can produce slides, spreadsheets, and documents that follow templates and field specifications, making it suitable for advanced data analysis, scientific research, complex software engineering, and enterprise knowledge work. It also supports agentic workflows within defined boundaries and is available through the Responses API and OpenAI's Client SDKs.

GPT-6.2 Astra is positioned as the successor to GPT-6 Astra, with described gains in computer use, coding, scientific reasoning, and cybersecurity. The available Artificial Analysis Intelligence Index results are reported at different reasoning efforts, including62 at max reasoning effort,62 at xhigh reasoning effort, and60 at high reasoning effort.

Updated:

MODEL ID

gpt-6.2-astra
Context
1.05M
Max output
128K
Recommended API
responses
Input
file / image / text
Output
text
GPT-6.2 Astra: a pelican riding a bicycle

See this model’s pelican

See what GPT-6.2 Astra created from the same prompt.

Highlights

  • Multilingual vision support
  • Template-following document creation
  • Concise, tunable default tone
  • Bounded agentic workflows
  • Sustained complex reasoning

Providers

Best price
6 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details
Uptime
$8$40$0.4
$8$1.6$40$8$0.4$0.08
$8$4.8$40$24$0.4$0.24
$8$40$0.4
$8$40$0.4
$16$80$0.8

What $10 buys

Input
1.3M tokens
Output
250K tokens

Estimated from current input and output prices, before discounts.

Benchmarks

  • Artificial Analysis Intelligence Index

    Score at maximum reasoning effort.

    62
  • Artificial Analysis Intelligence Index

    Score at xhigh reasoning effort.

    62
  • Artificial Analysis Intelligence Index

    Score at high reasoning effort.

    60

Scores as published by the model provider.

Reasoning

Default effort
medium
Enabled by default
Yes
Always enabled
Yes
Available effort levels
max / xhigh / high / medium / low

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

1

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"
2

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

gpt-6.2-astra

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/responses", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "gpt-6.2-astra",
  "input": "Hello"
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

3

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/responses \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.2-astra",
  "input": "Hello",
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Responses

Responses-compatible agent and workflow requests.

POST

https://openapi.felo.ai/api/v1/responses

Parameters

NameTypeDefaultDescription
modelstringgpt-6.2-astraPublic model ID to call.
inputstring | array——
seed———
toolsarray—Tool calling definitions following compatible schema.
reasoning———
verbosity———
max_tokensinteger—Maximum generated tokens.
tool_choicestring or object—Controls whether a tool should be called.
response_formatobject—Request structured output when supported.
reasoning_effort———
include_reasoning———
structured_outputs———
max_completion_tokens———

Frequently asked questions

What is GPT-6.2 Astra?

OpenAI GPT-6.2 Astra is described as OpenAI's most capable and aligned model, designed for the hardest professional work. It supports text input, image input, and text output, with multilingual capabilities and vision. Its default tone is concise and direct, and it can be tuned for different applications. The model is designed for sustained reasoning across code, applications, and complex documents. It can produce slides, spreadsheets, and documents that follow templates and field specifications, making it suitable for advanced data analysis, scientific research, complex software engineering, and enterprise knowledge work. It also supports agentic workflows within defined boundaries and is available through the Responses API and OpenAI's Client SDKs. GPT-6.2 Astra is positioned as the successor to GPT-6 Astra, with described gains in computer use, coding, scientific reasoning, and cybersecurity. The available Artificial Analysis Intelligence Index results are reported at different reasoning efforts, including62 at max reasoning effort,62 at xhigh reasoning effort, and60 at high reasoning effort.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

What inputs and outputs does GPT-6.2 Astra support?

It supports text input, image input, and text output. It also supports multilingual capabilities and vision.

What kinds of tasks is GPT-6.2 Astra suited for?

It is suited for complex software engineering, scientific research and reasoning, advanced data analysis, professional work, and enterprise knowledge work.

Can it create structured business documents?

Yes. It can produce slides, spreadsheets, and documents that follow templates and field specifications.

Does it support agentic workflows?

Yes. It supports agentic workflows within defined boundaries.

How is it different from GPT-6 Astra?

GPT-6.2 Astra is described as the successor to GPT-6 Astra, with described gains in computer use, coding, scientific reasoning, and cybersecurity.

How can developers access it?

It is available through the Responses API and OpenAI's Client SDKs.

Related models

GPT-6.2 Astra Pro

OpenAIgpt-6.2-astra-pro

GPT-6.2 Astra Pro is OpenAI’s flagship frontier model for complex reasoning, coding, professional work, and scientific applications.

Complex codebase changesPractical web applicationsSlide design workflows3D engineering development

Context

1.05M

Max output

128K

Input tokens · Base rate

$8 / 1M tokens

Output tokens · Base rate

$40 / 1M tokens

GPT-6.2 Sol Pro

OpenAIgpt-6.2-sol-pro

GPT-6.2 Sol Pro is an efficient, versatile model for coding, writing, multi-step work, and interactive browser experiences.

Everyday coding tasksPull request reviewProject brief creationInteractive browser experiences

Context

1.05M

Max output

128K

Input tokens · Base rate

$2 / 1M tokens

Output tokens · Base rate

$10 / 1M tokens

GPT-6.2 Sol

OpenAIgpt-6.2-sol

GPT-6.2 Sol is an efficient multilingual and vision-capable model for coding, automation, reports, and multi-step agent work.

Daily code editingReport draftingProject planningAutomation tasks

Context

1.05M

Max output

128K

Input tokens · Base rate

$2 / 1M tokens

Output tokens · Base rate

$10 / 1M tokens

GPT-6.1 Terra Pro

OpenAIgpt-6.1-terra-pro

GPT-6.1 Terra Pro is OpenAI's mid-tier reasoning model that runs GPT-6.1 Terra with reasoning.mode set to pro for higher accuracy on hard, high-stakes tasks.

High-stakes accuracy-critical problemsComplex multi-step problem solvingAdvanced document analysisComplex code debugging

Context

1.05M

Max output

128K

Input tokens · Base rate

$1 / 1M tokens

Output tokens · Base rate

$5 / 1M tokens

GPT-6.1 Terra

OpenAIgpt-6.1-terra

GPT-6.1 Terra is OpenAI's balanced mid-tier model in the GPT-6.1 series, combining visual reasoning with fast, accurate computer operation.

Drafting proposalsInterpreting technical drawingsMatching product photos to catalogsAgentic codebase investigation

Context

1.05M

Max output

128K

Input tokens · Base rate

$1 / 1M tokens

Output tokens · Base rate

$5 / 1M tokens

GPT-6.1 Sol

OpenAIgpt-6.1-sol

GPT-6.1 Sol is OpenAI's near-flagship model for agentic coding, computer use, and document-heavy professional work, with a 1,050,000 token context and tiered reasoning controls.

Agentic coding and debuggingRepository analysis and code reviewComputer use and supervised agentsDocument-heavy professional work

Context

1.05M

Max output

128K

Input tokens · Base rate

$2 / 1M tokens

Output tokens · Base rate

$10 / 1M tokens