GPT-6 Astra

OpenAIMCP Tool CallReasoning

openai/gpt-6-astraClosed API

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Benchmark Pricing$10.00 / 1M in$50.00 / 1M out$1.00 cache read

Context: 1,050,000 tokens•Max Output: 128,000 tokens•Knowledge: 2026-04-30•Released: 2026-09-04

TECHNICAL SPECIFICATIONS

Context Window1,050,0001.1M tokens

Max Output128,000128K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVisionPDF

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT-6 Astra natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,050,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

Agents' Last ExamUnit not reported

59.3

OSWorldpartial score

72.6

ScreenSpot-Proaccuracy

92.7

AutomationBenchsuccess rate

41.4

BenchCADgeometric overlap

95.9

BrowseCompaccuracy

91.5

Terminal-Benchsuccess rate

57.9

DeepSWEresolve rate

74.1

FrontierCodescore

64.5

Terminal-Bench Sciencesuccess rate

64.6

FrontierMathaccuracy

97.6

GPQA Diamondaccuracy

Humanity's Last Examaccuracy

57.2

ExploitBenchsuccess rate

100

SRE-Benchsuccess rate

ARC-AGI-3RHAE

99.9

Artificial Analysis Intelligence Indexindex score

Artificial Analysis Coding Agent Indexindex score

API CALL INVOCATION EXAMPLE

// Example: Calling GPT-6 Astra via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/gpt-6-astra",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);