CrossModel
GPT-6 Astra
openai/gpt-6-astra
Back to model catalog

OpenAI · Model guide

GPT-6 Astra

Compare
openai/gpt-6-astraReleased Sep 3, 2026

A general-purpose reasoning model for complex software engineering, research, and document creation. It accepts text and images and supports extended workflows with tools.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 10.00in$ 50.00out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorBuilt for demanding end-to-end work.source

Best for

  • Software engineering · Build, debug and test software.(vendor claim)source

  • Professional deliverables · Create documents, spreadsheets and presentations.(vendor claim)source

  • Research with computer use · Browse, inspect evidence and synthesize findings.(vendor claim)source

  • Scientific reasoning · Explore mathematical and scientific problems.(vendor claim)source

Neighbouring models
  • openai/gpt-5.6-terracheaper —Use Terra when a lower price materially improves throughput.
  • openai/gpt-5.6-solpredecessor —Use GPT-5.6 Sol only when preserving an established evaluation baseline matters.
Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input sizeInput < 272.0KInput ≥ 272.0K
Input$ 10.00$ 20.00
Output$ 50.00$ 75.00
Cache read$ 1.00$ 2.00
Cache write$ 12.50$ 25.00
Estimate a request

At this input size you are on the Input < 272.0K tier.

$ 0.2000
Estimated cost per request
10.0K × $ 10.00
+ 2.0K × $ 50.00
≈ $ 200.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.1M tokens
Max output
128.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Reasoning effort
low · medium · high · xhigh · max
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsdevelopers.openai.com 1developers.openai.com 2Capabilitiesdevelopers.openai.com 1developers.openai.com 2
Conditional limitsDisclosed by the vendor. These do not make the capability unavailable — they say when it is not.
  • Tool calling is available only when source

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 4.0
    pass_rate·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    57.9%
Agentic search
  • BrowseComp (with tools)
    accuracy·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    91.5%
Agentic work
  • Agents' Last Exam
    score·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    59.3%
Coding
  • DeepSWE 1.1
    resolved_rate·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    74.1%
Computer use
  • OSWorld 2.0 (v2026.08.08 offline, partial score)
    score·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    72.6%
Long context
  • OpenAI MRCR v2 8-needle 512K–1M
    accuracy·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    96.3%
Math reasoning
  • FrontierMath Tier 4 (v2)
    score·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    97.6%
Scientific reasoning
  • GPQA Diamond
    accuracy·OpenAI · 2026-09-03setup not fully disclosed

    各推理档位最高成绩；研究/API 配置可能不同于生产。

    96%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is GPT-6 Astra?
GPT-6 Astra is available on CrossModel as openai/gpt-6-astra. It has a 1M-token context window and can return up to 128K tokens per request.
How much does GPT-6 Astra cost?
Currently $ 10.00 per 1M input tokens and $ 50.00 per 1M output tokens. Cached input is billed at $ 1.00 per 1M.
Does GPT-6 Astra support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.