CrossModel
GPT-6.1 Sol
openai/gpt-6.1-sol
Back to model catalog

OpenAI · Model guide

GPT-6.1 Sol

Compare
openai/gpt-6.1-solReleased Sep 29, 2026

An upgrade to GPT-6 Sol for complex coding, computer use, and professional work. It accepts text and images, supports a 1.05M-token context window, and always reasons, with effort adjustable from low to max.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 2.00in$ 10.00out
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.

VendorNear-Astra performance for complex coding, computer use, and professional work.source

Best for

  • Complex coding · Take on complex software-engineering tasks.(vendor claim)source

  • Computer use · Operate software and complete tasks through a computer interface.(vendor claim)source

  • Professional work · Handle demanding professional tasks end to end.(vendor claim)source

Neighbouring models
  • openai/gpt-6-astrastronger —Use Astra when the hardest tasks need the most capable GPT-6 model.
  • openai/gpt-6-lunacheaper —Use Luna for focused, high-volume tasks.
  • openai/gpt-6-solpredecessor —Use GPT-6 Sol when you need reasoning effort none, or to keep an established baseline.
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$ 2.00$ 4.00
Output$ 10.00$ 15.00
Cache read$ 0.10$ 0.20
Cache write$ 2.50$ 5.00
Estimate a request

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

$ 0.0400
Estimated cost per request
10.0K × $ 2.00
+ 2.0K × $ 10.00
≈ $ 40.00 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 work
  • AutomationBench v1.0.6
    score·OpenAI · 2026-09-29effort maxsetup not fully disclosed

    官方发布页交互图表（2026-10-02 核对）各推理档位最高成绩，明确记录对应 effort。使用 47 种工具的端到端业务工作流；具体工具集合未完整披露。完整复现设置未披露；研究/API 配置可能不同于生产。

    36.1%
Coding
  • DeepSWE 1.1
    resolved_rate·OpenAI · 2026-09-29effort highsetup not fully disclosed

    官方发布页交互图表（2026-10-02 核对）各推理档位最高成绩，明确记录对应 effort。真实代码库的长程软件工程任务。完整复现设置未披露；研究/API 配置可能不同于生产。

    75.2%
Computer use
  • OSWorld 2.0 (v2026.08.08 offline, partial score)
    score·OpenAI · 2026-09-29effort maxsetup not fully disclosed

    官方发布页交互图表（2026-10-02 核对）各推理档位最高成绩，明确记录对应 effort。v2026.08.08 离线集的 partial reward，不是 OSWorld-Verified 或全任务成功率。完整复现设置未披露；研究/API 配置可能不同于生产。

    71.4%
Cybersecurity
  • ExploitBench
    score·OpenAI · 2026-09-29effort maxsetup not fully disclosed

    System card 9.1.2.1 节的 Preparedness 网络安全评测。OpenAI 自述该成绩可能因历史漏洞的训练数据污染而虚高；同节 GPT-6 Sol 81.7%、GPT-6 Astra 100%。研究/API 配置可能不同于生产。

    99.7%
Knowledge work
  • GDP.pdf
    score·OpenAI · 2026-09-29effort highsetup not fully disclosed

    官方发布页交互图表（2026-10-02 核对）各推理档位最高成绩，明确记录对应 effort。复杂专业 PDF 文档问答。完整复现设置未披露；研究/API 配置可能不同于生产。

    32%
  • HealthBench Professional
    score·OpenAI · 2026-09-29setup not fully disclosed

    System card 5.1 节（Table 7）的 length-adjusted 分数；未做长度调整为 67.2，平均回答长度 3038 字符。同表 GPT-6 Astra 64.7、GPT-6 Sol 60.8。该节未披露推理档位；研究/API 配置可能不同于生产。

    64.2%
Scientific research
  • Terminal-Bench-Science 0.1
    accuracy·OpenAI · 2026-09-29effort maxsetup not fully disclosed

    官方发布页交互图表（2026-10-02 核对）各推理档位最高成绩，明确记录对应 effort。使用代码与终端工具完成科研工作流；不同于 Terminal-Bench 2.x。完整复现设置未披露；研究/API 配置可能不同于生产。目录沿用此基准既有 accuracy 指标名；基准官网称 resolution rate（任务解决比例）。

    57%

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-6.1 Sol?
GPT-6.1 Sol is available on CrossModel as openai/gpt-6.1-sol. It has a 1M-token context window and can return up to 128K tokens per request.
How much does GPT-6.1 Sol cost?
Currently $ 2.00 per 1M input tokens and $ 10.00 per 1M output tokens. Cached input is billed at $ 0.10 per 1M.
Does GPT-6.1 Sol 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.