OpenAI

OpenAI: GPT 6 Astra

openai/gpt-6-astra
Context

1.05M

Input

text, image, file

Output

text

Tool calling

Supported

About this model

GPT-6 Astra is OpenAI's flagship model, released 3 September 2026. It costs $10 per million input tokens and $50 per million output, with a 1,050,000-token context window and 128,000 max output tokens. It accepts text and images, and supports streaming, function calling and structured outputs.

Input modalities

text

Accepted as model input

image

Accepted as model input

file

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Available

Input tokens

$10.000 / 1M tokens

Output tokens

$50.000 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$10.000 / 1M tokens
Output tokens$50.000 / 1M tokens
Cached input tokens$1.000 / 1M tokens

Performance

Published evaluation results associated with this model.

Mathematics

FrontierMath Tier 4 (v2)97.6

Abstract Reasoning

ARC-AGI-399.9

Cybersecurity

ExploitBench100
ExploitGym42.4

Graduate Science

GPQA Diamond96

Computer Use

OSWorld 2.072.6

Agentic Terminal

Terminal-Bench 4.057.9

Agentic Coding

DeepSWE v1.174.1

DevOps and SRE

SRE-Bench (single attempt)88

Agentic General

Agents Last Exam59.3

Healthcare

HealthBench Professional63.4

Life Sciences

LifeSciBench60.3

Genomics

GeneBench Pro37.8

Engineering and CAD

BenchCAD95.9

Scientific Agentic

Terminal-Bench Science 0.164.6

Artificial Analysis Independent

Intelligence Index61
Coding Agent Index67

API Guide

Refer Documentation
  1. 1

    Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. 2

    Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. 3

    Check your credits

    If your balance is too low, before calling the model.

  4. 4

    Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl https://api.oneinfer.ai/v1/ula/chat/completions \
      -H "Authorization: Bearer $JWT_TOKEN" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "openai/gpt-6-astra",
        "messages": [
          { "role": "user", "content": "Hello!" }
        ]
      }'