跳转到内容
Alpha
  • 模型
  • 排行榜
  • Ori
联系销售

页脚

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

产品

  • 聊天
  • 排行榜
  • 基准测试
  • 应用
  • 发现
  • 模型
  • Ori
  • 合集
  • 提供商
  • 工具
  • 定价
  • Business
  • Enterprise
  • 实验室

公司

  • 关于
  • 博客
  • 客户
  • 招聘
    招聘
  • 隐私
  • 服务条款
  • 信任中心
  • 支持
  • 兼容 OR
  • 数据
  • 品牌

开发者

  • 文档
  • API 参考
  • 开发者平台
  • 状态
  • AI 站点地图

连接

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
openai 的网站图标

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

模型权重
比较

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

模态
输入 / 输出价格
US$0.03 / US$0.15每 1M
上下文
131K
发布时间
2025年8月5日
知识截止日期
2024年6月
比较
提供商定价性能正常运行时间基准测试应用活动常见问题探索

提供商

不同公司托管同一个模型。OpenRouter 会根据您选择的路由模式，将您的请求路由到其中一家公司：Balanced（价格 + 速度）、Nitro（最快）或 Floor（最便宜）。

定价

客户为此模型实际支付的平均价格，与提供商公布的价格并列展示。由于缓存和折扣，实际支付的价格往往远低于标价。

性能

吞吐量是模型生成内容的速度（每秒 token 数，越高越好）。延迟是完整的往返时间（越低越好）。TTFT 是首个 token 的响应时间，即您看到内容出现前需要等待的时间（越低越好）。

正常运行时间

正常运行时间是指过去 3 天中至少有一家提供商响应请求的时间百分比。可用性是指成功提供推理服务的时间百分比。OpenRouter 会持续监控，并在某家提供商返回错误时使用次优提供商。

基准测试

标准化评测得分，以及此模型针对共用基准测试提示词的实际输出。百分比越高越好，每项排名显示此模型在该来源所评测的模型中的位置。

基准测试得分摘要： OpenAI: gpt-oss-120b （Artificial Analysis、Design Arena 和 Vals AI）
来源基准测试得分
Artificial Analysisgpt-oss-120b (High) Coding Index30.4
Artificial Analysisgpt-oss-120b (High) Agentic Index3.7
Artificial Analysisgpt-oss-120b (High) GPQA Diamond78.2%
Artificial Analysisgpt-oss-120b (High) HLE19.6%
Artificial Analysisgpt-oss-120b (High) IFBench69.0%
Artificial Analysisgpt-oss-120b (High) τ²-Bench Telecom65.8%
Artificial Analysisgpt-oss-120b (High) AA-LCR52.0%
Artificial Analysisgpt-oss-120b (High) τ-Bench Banking12.8%
Artificial Analysisgpt-oss-120b (High) GDPval-AA5.8%
Artificial Analysisgpt-oss-120b (High) CritPt1.1%
Artificial Analysisgpt-oss-120b (High) LiveCodeBench87.8%
Artificial Analysisgpt-oss-120b (High) SciCode34.0%
Artificial Analysisgpt-oss-120b (High) Terminal-Bench Hard23.5%
Artificial Analysisgpt-oss-120b (High) Terminal-Bench 4.00.0%
Artificial Analysisgpt-oss-120b (High) Terminal-Bench 2.126.2%
Artificial Analysisgpt-oss-120b (High) MMLU-Pro80.8%
Artificial Analysisgpt-oss-120b (High) AIME 202593.4%
Artificial Analysisgpt-oss-120b (Low) Coding Index21.2
Artificial Analysisgpt-oss-120b (Low) GPQA Diamond67.2%
Artificial Analysisgpt-oss-120b (Low) HLE5.9%
Artificial Analysisgpt-oss-120b (Low) IFBench58.3%
Artificial Analysisgpt-oss-120b (Low) τ²-Bench Telecom45.0%
Artificial Analysisgpt-oss-120b (Low) AA-LCR46.0%
Artificial Analysisgpt-oss-120b (Low) τ-Bench Banking2.9%
Artificial Analysisgpt-oss-120b (Low) GDPval-AA0.0%
Artificial Analysisgpt-oss-120b (Low) CritPt0.0%
Artificial Analysisgpt-oss-120b (Low) LiveCodeBench70.7%
Artificial Analysisgpt-oss-120b (Low) Terminal-Bench Hard5.3%
Artificial Analysisgpt-oss-120b (Low) Terminal-Bench 2.113.9%
Artificial Analysisgpt-oss-120b (Low) MMLU-Pro77.5%
Artificial Analysisgpt-oss-120b (Low) AIME 202566.7%
Design ArenaGPT OSS 120B Models Arena 3D Elo898
Design ArenaGPT OSS 120B Models Arena Code Categories Elo961
Design ArenaGPT OSS 120B Models Arena Data Visualization Elo987
Design ArenaGPT OSS 120B Models Arena Game Development Elo992
Design ArenaGPT OSS 120B Models Arena UI Component Elo921
Design ArenaGPT OSS 120B Models Arena Website Elo966
Vals AIGPT OSS 120B AIME92.6%
Vals AIGPT OSS 120B CaseLaw v248.8%
Vals AIGPT OSS 120B CorpFin v258.2%
Vals AIGPT OSS 120B Finance Agent v1.121.5%
Vals AIGPT OSS 120B GPQA Diamond78.5%
Vals AIGPT OSS 120B LiveCodeBench83.2%
Vals AIGPT OSS 120B LegalBench75.9%
Vals AIGPT OSS 120B MATH 50094.8%
Vals AIGPT OSS 120B MedQA91.4%
Vals AIGPT OSS 120B MGSM92.0%
Vals AIGPT OSS 120B MMLU Pro79.2%
Vals AIGPT OSS 120B SWE-bench33.6%
Vals AIGPT OSS 120B TaxEval v271.6%
Vals AIGPT OSS 120B Terminal-Bench 2.019.1%

应用

向此模型发送最多流量的公开应用。这能很好地反映实际生产工作负载的情况，也能提示此模型最适合哪些用例。

活动

此模型的 token 用量和请求流量随时间的变化。

API

可直接用于调用此模型的代码。OpenRouter 的 API 与 OpenAI 兼容——大多数 SDK 只需替换基础 URL 即可使用。切换模型时，唯一需要更改的是下方的模型标识符。

可通过欧盟区域内路由使用

OpenAI: gpt-oss-120b 可通过欧盟区域内路由使用。发送至 eu.openrouter.ai 的请求会在欧盟境内解密，并且仅路由至欧洲（欧盟/欧洲经济区、英国和瑞士）的共享提供商端点。

欧洲的提供商
Amazon Bedrock
欧洲价格
  • Amazon Bedrock：输入 US$0.15/M tokens，输出 US$0.60/M tokens
基础 URL
https://eu.openrouter.ai/api/v1
套餐
需要 Business 或 Enterprise 套餐。Business 支持自助使用：无需合同，无每月最低消费。 用于欧盟区域内路由的 OpenRouter Business

故障时关闭：如果欧洲没有可用的共享提供商端点，请求将报错，而不会离开该区域。使用您自己的 BYOK 密钥处理的请求会发送至您部署所在的区域，该区域由您控制。 区域内路由文档

探索更多模型

AI 模型排行榜排名
延迟 / 吞吐量
US$0.030US$0.150US$0.0150.66s54 tps
100.00%
US$0.030US$0.150US$0.0300.69s47 tps
99.11%
US$0.030US$0.170US$0.0300.31s120 tps
99.91%
US$0.030US$0.180US$0.0300.42s88 tps
100.00%
US$0.030US$0.187US$0.0300.31s116 tps
100.00%
US$0.032US$0.120US$0.0290.66s72 tps
99.21%
US$0.037US$0.170--0.49s30 tps
99.67%
US$0.050US$0.250US$0.0500.23s239 tps
100.00%
US$0.050US$0.250--0.68s167 tps
99.60%
US$0.055US$0.250--0.86s46 tps
99.86%
US$0.060US$0.400US$0.0300.56s115 tps
100.00%
US$0.060US$0.420US$0.0120.66s51 tps
100.00%
US$0.100US$0.500US$0.1000.16s190 tps
98.48%
US$0.100US$0.500US$0.1000.21s190 tps
99.28%
US$0.100US$0.750US$0.0550.39s137 tps
100.00%
US$0.140US$0.950--0.63s377 tps
99.56%
US$0.150US$0.600US$0.1000.29s280 tps
99.74%
US$0.150US$0.600--0.54s333 tps
100.00%
US$0.150US$0.600US$0.0751.16s30 tps
91.01%
US$0.150US$0.600--0.89s157 tps
99.43%
US$0.150US$0.600US$0.0750.18s327 tps
99.70%
US$0.150US$0.750--0.82s184 tps
96.33%
US$0.350US$0.750US$0.3500.16s852 tps
100.00%
US$0.150US$0.600--0.25s144 tps
98.45%
US$0.200US$0.950--1.54s59 tps
84.31%
US$0.090US$0.360--0.38s36 tps
2.18%
不用于 Standard 路由：未使用这些端点的原因
US$0.150US$0.600--0.43s172 tps
100.00%
吞吐量
852token/秒

P50，所有提供商中最佳

延迟
0.16秒

P50，最佳提供商

AutoExacto 基准测试
GPQA DiamondTAU-BenchAmazon Bedrock76.8%--Amazon Bedrock (EU)76.8%--Google Vertex72.6%--AkashML77.4%66.5%Sail Research77.0%66.7%NEAR AI76.6%66.8%
+20 家其他提供商
正常运行时间（3 天）模型可访问。请求已路由至提供商。
100.00%
可用性（3 天）模型通过任意提供商返回了推理结果。错误和空响应均计为失败。
99.63%

过去 3 天的可用性

最近 72 小时
可用性 99.63%
3 天前2 天前昨天现在

过去 24 小时的可用性

OpenRouter Availability
99.72%
Without Routing
90.89%

当上游提供商发生错误时，如果您的请求筛选条件允许，我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据： 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。

1.
https://convosight.com/ 的网站图标
cvi-magic-tasks-ai-tagging
新增
45.6Btoken
2.
https://mira.tg/ 的网站图标
Mira is the leading AI agent inside Telegram
Mira is a Telegram-native AI assistant.
35.9Btoken
3.
https://op.gg/ 的网站图标
OP.GG
新增
27Btoken
4.
https://apollo.halan.io/ 的网站图标
LibreChat
新增
15.9Btoken
5.
https://craftrpgs.com/?utm_source=openrouter 的网站图标
Craft
Build and play AI RPGs
12.2Btoken

常见问题

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization.

gpt-oss-120b 的费用为 US$0.03/百万输入 token 和 US$0.15/百万输出 token，Cache Read，价格为 US$0.015/M tokens 单独计费。

gpt-oss-120b 的上下文窗口为 131,072 个 token。它最多支持 131,072 个补全 token。

支持。在提供 gpt-oss-120b 的 24 家提供商中，有 20 家支持该模型通过 tools 和 tool_choice 进行函数调用，包含工具的请求会被路由到这些提供商。 它还支持通过 response_format 中的 JSON schema 实现结构化输出。

gpt-oss-120b 在 OpenRouter 上由 24 家提供商提供服务：NEAR AI, Venice, CoreWeave, DekaLLM, AkashML, Prime Intellect, DeepInfra (fp8), Crusoe 及另外 16 个。请求会路由至当前可用的最佳提供商，并在故障时自动切换至其他提供商，您也可以通过提供商路由固定或排除提供商。

gpt-oss-120b 于 2025年8月5日 发布。其知识截止日期为 2024年6月30日。

更多模型，来自 OpenAI

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$1 / US$5
GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$0.50 / US$2.50
GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

文本1.1M 上下文US$1 / US$5
GPT-6.1 Terra (batch)

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

文本1.1M 上下文US$0.50 / US$2.50
GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

决策US$0.10 / US$0
GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$2 / US$10
GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$1 / US$5
GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

文本1.1M 上下文US$2 / US$10
GPT-6.1 Sol (batch)

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

文本1.1M 上下文US$1 / US$5
GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$0.10 / US$0.50
GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$0.05 / US$0.25
GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

文本1.1M 上下文US$0.10 / US$0.50
GPT-6 Luna (batch)

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

文本1.1M 上下文US$0.05 / US$0.25
GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$2 / US$10
GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

文本1.1M 上下文US$1 / US$5
GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

文本1.1M 上下文US$2 / US$10
GPT-6 Sol (batch)

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

文本1.1M 上下文US$1 / US$5
GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

文本1.1M 上下文
GPT Sol Latest

This model always redirects to the latest model in the GPT Sol family.

文本1.1M 上下文
GPT Terra Latest

This model always redirects to the latest model in the GPT Terra family.

文本1.1M 上下文