geminiavailablesupports_computer_usesupports_function_callingsupports_max_reasoning_effortsupports_native_streamingsupports_parallel_function_callingsupports_pdf_inputsupports_prompt_cache_breakpointsupports_prompt_cachingsupports_reasoningsupports_response_schemasupports_system_messagessupports_tool_choicesupports_visionsupports_web_searchsupports_xhigh_reasoning_effort

Back to Model Explorer

GoogleAvailable on AvalAI

gpt-6-astra API on AvalAI

gpt-6-astra

gpt-6-astra is an AI model from Google that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$10.00 / 1M tokens

Output price$50.00 / 1M tokens

Context window922,000 tokens

Maximum output128,000 tokens

Use gpt-6-astra with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "gpt-6-astra", "input": "Give a concise, practical solution."}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.responses.create(
    model="gpt-6-astra",
    input="Give a concise, practical solution.",
)

print(response.output_text)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.responses.create({
  model: "gpt-6-astra",
  input: "Give a concise, practical solution.",
});

console.log(response.output_text);

Create an API keyRead the quickstart

Capabilities and endpoints

• Computer use
• Function calling
• Max reasoning effort
• Streaming
• Parallel function calling
• PDF input
• Prompt cache breakpoint
• Prompt caching
• Reasoning
• Structured output
• System messages
• Tool choice
• Vision
• Web search
• Xhigh reasoning effort

Endpoints

• /v1/chat/completions
• /v1/batch
• /v1/responses

gpt-6-astra rate limits

Tier	RPM	TPM
Tier 1	2	80,000
Tier 2	25	1,000,000
Tier 3	75	2,000,000
Tier 4	500	8,000,000
Tier 5	3,500	30,000,000

Related models

• Gemma 4 31B
• Gemma 4 26B A4B
• gemini-robotics-er-1.5-preview
• gemini-flash-lite-latest

Frequently asked questions

What is the gpt-6-astra API on AvalAI?

Create an AvalAI API key and send the model ID gpt-6-astra to one of the supported endpoints shown on this page.

How much does the gpt-6-astra API cost on AvalAI?

The gpt-6-astra API on AvalAI costs $10.00 per 1M input tokens and $50.00 per 1M output tokens.

What is the token cost for gpt-6-astra?

Current AvalAI pricing for gpt-6-astra is $10.00 / 1M tokens for input and $50.00 / 1M tokens for output.

What is the gpt-6-astra context window?

The recorded maximum input context for gpt-6-astra is 922,000 tokens.

What are the rate limits for gpt-6-astra on AvalAI?

On tier 5, gpt-6-astra on AvalAI supports up to 3,500 requests per minute and 30,000,000 tokens per minute.

What features does gpt-6-astra support on AvalAI?

gpt-6-astra on AvalAI supports Computer use, Function calling, Max reasoning effort, Streaming, Parallel function calling, PDF input, Prompt cache breakpoint, Prompt caching, Reasoning, Structured output, System messages, Tool choice, Vision, Web search, Xhigh reasoning effort.

What account tier is required to use gpt-6-astra on AvalAI?

Calling gpt-6-astra on AvalAI requires tier 1 or higher.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)