Home / Model Explorer / GPT 6.2 Astra

GPT 6.2 Astra API

OpenAIChat

Deep reasoning and complex tasks

Overview

About this model

GPT 6.2 Astra, for complex reasoning, programming, and multi-step tasks. Supports OpenAI-compatible APIs and streaming responses. When the input context exceeds 272K tokens, the input and cache rates for the entire request are doubled, and the output rate is 1.5 times the standard tier.

Capabilities

Capability matrix

TextSupported
Vision—
Audio—
Tools—
JSONSupported
Reasoning—

Pricing and groups

Routes and pricing

GPT Discounted route optimization0.06× official price (save 94%)Collecting data

Switch to another route when there are fluctuations

Input

$0.48 / 1M

Output

$2.4 / 1M

Cache read

$0.024 / 1M

Cache write

$0.6 / 1M

All pricing tiers and conditions

Pricing tier

Input length ≤ 272,000 tokens

Input

$0.48 / 1M

Output

$2.4 / 1M

Cache read

$0.024 / 1M

Cache write

$0.6 / 1M

Pricing tier

Input length > 272,000 tokens

Input

$0.96 / 1M

Output

$3.6 / 1M

Cache read

$0.048 / 1M

Cache write

$1.2 / 1M

Recent availabilityPast 24 hours · Active probes—
24h ago16h ago8h agoNow
GPT Plus route0.08× official price (save 92%)Collecting data

pro+plus Mixed account pool

Input

$0.64 / 1M

Output

$3.2 / 1M

Cache read

$0.032 / 1M

Cache write

$0.8 / 1M

All pricing tiers and conditions

Pricing tier

Input length ≤ 272,000 tokens

Input

$0.64 / 1M

Output

$3.2 / 1M

Cache read

$0.032 / 1M

Cache write

$0.8 / 1M

Pricing tier

Input length > 272,000 tokens

Input

$1.28 / 1M

Output

$4.8 / 1M

Cache read

$0.064 / 1M

Cache write

$1.6 / 1M

Recent availabilityPast 24 hours · Active probes—
24h ago16h ago8h agoNow
GPT Pro High-performance line0.1× official price (save 90%)Collecting data

Enterprise dedicated line Pro

Input

$0.8 / 1M

Output

$4 / 1M

Cache read

$0.04 / 1M

Cache write

$1 / 1M

All pricing tiers and conditions

Pricing tier

Input length ≤ 272,000 tokens

Input

$0.8 / 1M

Output

$4 / 1M

Cache read

$0.04 / 1M

Cache write

$1 / 1M

Pricing tier

Input length > 272,000 tokens

Input

$1.6 / 1M

Output

$6 / 1M

Cache read

$0.08 / 1M

Cache write

$2 / 1M

Recent availabilityPast 24 hours · Active probes—
24h ago16h ago8h agoNow

Prices are in USD per million tokens. This page shows a public price snapshot. Before sending a request, check the Model Explorer for current prices. The console shows account-specific routes and charges.

How to compare prices · How to interpret performance metrics

Snapshot: . Availability reflects active probes over the past 24 hours; performance reflects actual calls.

Compare

Group comparison

GroupInput/output priceSpeedStability
GPT Discounted route optimization$0.48 / $2.412.7 t/s—
GPT Plus route$0.64 / $3.237.2 t/s—
GPT Pro High-performance line$0.8 / $445 t/s—

API

Integration example

Use a Yomi API key that can access this model and route. Check the endpoint and request parameters when switching models or protocols.

Set the environment variable YOMI_API_KEY.

Quick start · Pricing and billing · Protocol reference · Chat Completions

Python · OpenAI SDK
# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.yomiapi.com/v1",
    api_key=os.environ["YOMI_API_KEY"],
)

resp = client.chat.completions.create(
    model="gpt-6.2-astra",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
curl · OpenAI compatible
curl 'https://api.yomiapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $YOMI_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gpt-6.2-astra",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

Connect to GPT 6.2 Astra now

Create an API key in the console and select an available route.

Get an API key